Search

Typhoon waves possess significant destructive potential, and their numerical simulation relies on accurate sea surface wind fields. An evaluation of different combinations of the radial air pressure distribution coefficient B and the radius of maximum wind speed (R max) in the Holland wind field (HWF) model was conducted to determine the optimal configuration. The HWF and the ERA5 wind field (EWF) were used as input wind fields to drive the typhoon wave model for China's coastal waters. Validation results indicated that neither wind field accurately reflected real conditions; therefore, a hybrid wind field (HBWF) was created by combining HWF and EWF using weighting coefficients that vary with the radius of wind speed to enhance accuracy. Simulation results showed that the HBWF improved the accuracy of significant wave heights (SWHs), with a mean relative error of 25.29%, compared to 32.48% for HWF and 27.94% for EWF. Additionally, HBWF also demonstrated the best performance in terms of root mean square error (RMSE) and consistency index. Overall, the HBWF enhances the simulation accuracy of typhoon waves in China's coastal waters. [ABSTRACT FROM AUTHOR]

In recent years, tourism and leisure districts have become a pivotal aspect of China's tourism development. Analyzing their spatial distribution characteristics and driving factors is essential for fostering comprehensive district tourism and promoting sustainable development, while also facilitating the profound integration of culture and tourism. This study undertakes a thorough investigation of the spatiotemporal patterns of national-level tourism and leisure districts in China, employing GIS spatial statistical analysis techniques, including the Average Nearest-Neighbor Index, Kernel Density Analysis, and Standard Deviation Ellipse. Additionally, this research identifies the principal driving factors affecting the spatial distribution of these districts through overlay analysis, buffer analysis, and geographic detectors. The findings reveal that (1) tourism and leisure districts exhibit a notable spatial clustering pattern, characterized by a predominance in the eastern regions and scarcity in the west, alongside a higher concentration in the south compared to the north, with a gradual decline in spatial density. (2) High-density tourism and leisure districts are predominantly located in the Yangtze River Delta and the Beijing–Tianjin–Hebei urban agglomerations, while regions of elevated density are situated in the southwest (notably in Sichuan, Chongqing, Guizhou, and Yunnan provinces). The centroids of the first to third batches of tourism and leisure districts have transitioned from southern to northern locations. (3) The population density factor exhibits the most substantial explanatory power regarding the distribution of tourism and leisure districts (q: 0.80528), followed by the added value of the tertiary industry (q: 0.53285), whereas the slope factor shows minimal influence (q: 0.00876). Furthermore, the distance to rivers of grade three and above, in conjunction with population density, constitutes the primary factor combination influencing the spatial configuration of tourism and leisure districts (q: 0.9101). [ABSTRACT FROM AUTHOR]

RCTs in primary schools in rural China show frequent personalized teacher feedback improves exam scores for Grade 3 (age 9), including those ‘left behind’ by migrating parents. Two terms of biweekly feedback increase math and language scores by 0.15 standard deviations, with an RCT texting results to parents giving 0.26 sd extra math improvement for the left-behind. Some math improvements maintain even 30 months later. Direct costs are under $5/student. Yet identical feedback produces nothing for Grade 5. Information feedback interventions thus have excellent potential, but their fall in impact with age suggests efforts must begin early. [ABSTRACT FROM AUTHOR]

The purpose of this research is to apply and compare the performance of the three machine learning algorithms-Naive Bayes (NB), kernel logistic regression (KLR), and alternation decision tree (ADT) to come up with landslide susceptibility maps for Pengyang County, a landslide-prone area in Ningxia Hui Autonomous Region, China. In the first phase, we constructed a landslide inventory map consisting of 972 landslides and the same quantity of non-landslides based on digital elevation model analysis, survey data and satellite images, then combined the two databases and classified into training and validating subsets randomly at the ratio of 70:30. Secondly, 13 conditional factors were prepared, and feature selection was performed using average merit. Subsequently, we used the area under the receiver operating characteristic curve (AUC), root mean square error, mean squared error, and frequency ratio precision to test the validity and prediction ability of the models. This outcome demonstrated that three models are all predictive and can generate adequate results in the study scope, and the ADT model is entitled with the best performance, whose AUC values are 0.844 for the training dataset and 0.838 for the validation dataset. The next is KLR (0.811 for the training dataset, 0.814 for the validation dataset) and then NB (0.808 for the training dataset, 0.797 for the validation dataset) models. Meanwhile, the frequency ratio precision of ADT model is 0.971, which is higher than KLR (0.844) and NB (0.810). The suggested landslide susceptibility map and corresponding method enable researchers and local authorities in future decision-making for geological disaster prevention and mitigation. [ABSTRACT FROM AUTHOR]

Net radiation (Rn), a critical component in land surface energy cycling, is calculated as the difference between net shortwave radiation and longwave radiation at the Earth's surface and holds significant importance in crop models for precision agriculture management. In this study, we examined the performance of four machine learning models, including extreme learning machine (ELM), hybrid artificial neural networks with genetic algorithm models (GANN), generalized regression neural networks (GRNN), and random forests (RF), in estimating daily Rn at four representative sites across different climatic zones of China. The input variables included common meteorological factors such as minimum and maximum temperature, relative humidity, sunshine duration, and shortwave solar radiation. Model performance was assessed and compared using statistical parameters such as the correlation coefficient (R2), root mean square errors (RMSE), mean absolute errors (MAE), and Nash–Sutcliffe coefficient (NS). The results indicated that all models slightly underestimated actual Rn, with linear regression slopes ranging from 0.810 to 0.870 across different zones. The estimated Rn was found to be comparable to observed values in terms of data distribution characteristics. Among the models, the ELM and GANN demonstrated higher consistency with observed values, exhibiting R2 values ranging from 0.838 to 0.963 and 0.836 to 0.963, respectively, across varying climatic zones. These values surpassed those of the RF (0.809–0.959) and GRNN (0.812–0.949) models. Additionally, the ELM and GANN models showed smaller simulation errors in terms of RMSE, MAE, and NS across the four climatic zones compared to the RF and GRNN models. Overall, the ELM and GANN models outperformed the RF and GRNN models. Notably, the ELM model's faster computational speed makes it a strong recommendation for Rn estimates across different climatic zones of China. [ABSTRACT FROM AUTHOR]

The stable hydrogen isotope in precipitation is an effective environmental tracer for climatic and hydrologic studies. However, accurate and high-precision precipitation hydrogen isoscapes are currently unavailable in China. In this study, a data fusion method based on Convolutional Neural Networks (CNN) is used to fuse the hydrogen isotopic composition (δ2Hp) of observations and isotope-equipped general circulation model (iGCM) simulations. A precipitation hydrogen isoscape with a temporal resolution of monthly and a spatial resolution of 50–60 km is established for East China for the 1969–2017 period. Prior to building the isoscape, the performance of three data fusion methods (DFMs) and two bias correction methods (BCMs) is compared. The results indicate that the CNN fusion method performs the best with a correlation coefficient larger than 0.90 and root mean square error smaller than 10.5‰when using observation as a benchmark. The fusion methods based on back propagation and long short-term memory neural network perform similarly, while slightly outperforming the bias correction methods. Thus, the CNN method is used to generate the hydrogen isoscape, and the temporal and spatial distribution characteristics of the hydrogen isotope in precipitation are analyzed based on this dataset. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ2Hp is consistent with the temperature effect in northern China, and consistent with the precipitation amount effect in southern China. The trend of the δ2Hp time series is consistent with that of observed precipitation and temperature. Overall, the generated isoscape effectively reproduces the observations, and has the characteristics of time continuity and relative spatial regularity, which can provide valuable data support for tracking atmospheric and hydrological processes. [ABSTRACT FROM AUTHOR]

Background: Influenza is an acute respiratory infectious disease with a significant global disease burden. Additionally, the coronavirus disease 2019 pandemic and its related nonpharmaceutical interventions (NPIs) have introduced uncertainty to the spread of influenza. However, comparative studies on the performance of innovative models and approaches used for influenza prediction are limited. Therefore, this study aimed to predict the trend of influenza-like illness (ILI) in settings with diverse climate characteristics in China based on sentinel surveillance data using three approaches and evaluate and compare their predictive performance. Methods: The generalized additive model (GAM), deep learning hybrid model based on Gate Recurrent Unit (GRU), and autoregressive moving average-generalized autoregressive conditional heteroscedasticity (ARMA--GARCH) model were established to predict the trends of ILI 1-, 2-, 3-, and 4-week-ahead in Beijing, Tianjin, Shanxi, Hubei, Chongqing, Guangdong, Hainan, and the Hong Kong Special Administrative Region in China, based on sentinel surveillance data from 2011 to 2019. Three relevant metrics, namely, Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and R squared, were calculated to evaluate and compare the goodness of fit and robustness of the three models. Results: Considering the MAPE, RMSE, and R squared values, the ARMA--GARCH model performed best, while the GRU-based deep learning hybrid model exhibited moderate performance and GAM made predictions with the least accuracy in the eight settings in China. Additionally, the models' predictive performance declined as the weeks ahead increased. Furthermore, blocked cross-validation indicated that all models were robust to changes in data and had low risks of overfitting. Conclusions: Our study suggested that the ARMA--GARCH model exhibited the best accuracy in predicting ILI trends in China compared to the GAM and GRU-based deep learning hybrid model. Therefore, in the future, the ARMA--GARCH model may be used to predict ILI trends in public health practice across diverse climatic zones, thereby contributing to influenza control and prevention efforts. [ABSTRACT FROM AUTHOR]

Purpose: Depression is a growing public health concern around the world. For adolescents, depression not only impedes healthy development, but is negatively associated with academic performance. The purpose of this paper is to examine the prevalence of adolescent depressive symptoms in a sample of rural primary and junior high school students. Additionally, we examine various factors to identify subgroups within the sample that may be more vulnerable to depression. Finally, we explore the extent to which depression correlates with academic performance and conduct a series of heterogeneity analyses. Patients and Methods: We utilize cross-sectional data derived from 30 schools in underdeveloped regions of rural China encompassing primary and junior high school students (n = 1,609). Results: We find a high prevalence of depression, with 23% and 9% of students experiencing general depression (depression score ≥ 14) and severe depression (depression score ≥ 21), respectively. Female gender, elevated stress and anxiety levels, boarding at school, exposure to bullying, and having depressed caregiver(s) are positively correlated with depressive symptoms, while high social support exhibits a negative association. Importantly, our analyses consistently show a significantly negative link between depression and academic performance, which is measured using standardized math tests. For instance, transitioning from a non-depressed state to a state of general depression (depression score ≥ 14) is linked to a decline of 0.348– 0.406 standard deviations in math scores (p < 0.01). Heterogeneity analyses reveal that this adverse relationship is more pronounced for male students, boarding students, those with lower social support, individuals with more educated mothers, and those with lower family assets. Conclusion: Our findings underscore the high prevalence of depression in rural schools and the detrimental impact on academic performance. We advocate for the implementation of policies aimed at reducing student depression, particularly within vulnerable populations and subgroups. [ABSTRACT FROM AUTHOR]

Considering the nonlinear and non-stationary characteristics of sea-level-change time series, this study focuses on enhancing the predictive accuracy of sea level change. The adjacent seas of China are selected as the research area, and the study integrates singular spectrum analysis (SSA) with long short-term memory (LSTM) neural networks to establish an SSA-LSTM hybrid model for predicting sea level change based on sea level anomaly datasets from 1993 to 2021. Comparative analyses are conducted between the SSA-LSTM hybrid model and singular LSTM neural network model, as well as (empirical mode decomposition) EMD-LSTM and (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) CEEMDAN-LSTM hybrid models. Evaluation metrics, including the root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2), are employed for the accuracy assessment. The results demonstrate a significant improvement in prediction accuracy using the SSA-LSTM hybrid model, with an RMSE of 5.26 mm, MAE of 4.27 mm, and R2 of 0.98, all surpassing those of the other models. Therefore, it is reasonable to conclude that the SSA-LSTM hybrid model can more accurately predict sea level change. [ABSTRACT FROM AUTHOR]

Objectives: We investigate the impact of wildfire disasters on cognitive health (i.e., thinking and language skills) in individuals aged 10 years and older using 2014 and 2018 wildfire and cognitive ability survey data from China. Methods: We distinguished wildfires in each county at different wind directions each day by exogenous wind direction changes, and analyzed the effects of wildfires on cognitive abilities through upwind and non-upwind wildfires. Results: Our analysis shows that for every 10-unit increase in upwind wildfires compared to non-upwind wildfires, respondents' scores on word and math tests decrease by 0.235 and 0.236 standard deviations, respectively. Furthermore, we find that the impact of wildfire on cognitive ability is more pronounced in younger individuals, and those with lower defensive expenditures experience more severe impacts. Additionally, wildfires negatively affect individuals' cognitive abilities by generating air pollution. Conclusion: Wildfires significantly reduce individuals' cognitive abilities. Two recommendations are as follows: 1) governments should follow the principle of green development, introduce relevant regulations, and increase investment in adaptive technologies. 2) Individuals should raise awareness of climate hazards preparedness and strengthen defensive protection. [ABSTRACT FROM AUTHOR]

Accurate prediction of regional terrestrial water storage change (TWSA) is of great significance for water resources planning and management, and early warning of extreme climate disasters. Aiming at the problem that the conventional methods on prediction of TWSA time series are difficult to be accurate, the six typical regions are selected in China as examples, including the upper reaches of the Yangtze River (UYR), the southwest region (SWR), the Liaohe River Basin (LRB), the North China Plain (NCP), the Qinghai-Tibet Plateau (QTP), and the Pearl River Basin (PRB). The mascon product from GRACE/GRACE-FO provided by CSR is used to extract TWSA time series in six typical areas. The improved Back Propagation (BP) neural network, Long Short-Term Memory (LSTM) neural network and the latest Bidirectional LSTM (BiLSTM-attention) neural network model based on attention mechanism are proposed to predict and analyze the regional TWSA. In the experiment, the selection of the optimal model parameters such as the number of hidden layer nodes and the number of hidden units of the neural network model is tested and analyzed in detail. Meanwhile, the model prediction results are compared with the traditional least squares method and random forest (RF) prediction method. The root mean square error (RMSE), determination coefficient (R2), Nash–Sutcliffe efficiency coefficient (NSE) and mean absolute percentage error (MAPE) were used to evaluate the accuracy of the predicted results. The results show that the improved BP, LSTM and Bi-LSTM-attention neural network models all achieve higher prediction accuracy in UYR and SWR areas. RMSE is less than 2.641 cm, R2 is as high as 0.8 or more, NSE is above 0.6, and MAPE is within 0.1. Compared with the least square method, the RMSE of the predicted results from three neural network decreased by 0.998 cm, 0.700 cm and 0.7563 on average, and the R2 increased by 81.75%, 69.89% and 72% on average. Compared with RFML method, the RMSE from three neural network is reduced by 0.601 cm, 0.316 cm and 0.360, and R2 is increased by 38.20%, 24.60% and 27.06% on average. NSE and RMSE are improved to varying degrees in the above regions. It shows that the improved BP, LSTM and BiLSTM-attention model used can effectively predict TWSA. The research methods and results in this paper can provide important reference for the rational utilization of regional water resources and disaster risk assessment. [ABSTRACT FROM AUTHOR]

Predicting soil heavy metal (HM) content is crucial for monitoring soil quality and ensuring ecological health. However, existing methods often neglect the spatial dependency of data. To address this gap, our study introduces a novel graph neural network (GNN) model, Multi-Scale Attention-based Graph Neural Network for Heavy Metal Prediction (MSA-GNN-HMP). The model integrates multi-scale graph convolutional network (MS-GCN) and attention-based GNN (AGNN) to capture spatial relationships. Using surface soil samples from the Pearl River Basin, we evaluate the MSA-GNN-HMP model against four other models. The experimental results show that the MSA-GNN-HMP model has the best predictive performance for Cd and Pb, with a coefficient of determination (R2) of 0.841 for Cd and 0.886 for Pb, and the lowest mean absolute error (MAE) of 0.403 mg kg−1 for Cd and 0.670 mg kg−1 for Pb, as well as the lowest root mean square error (RMSE) of 0.563 mg kg−1for Cd and 0.898 mg kg−1 for Pb. In feature importance analysis, latitude and longitude emerged as key factors influencing the heavy metal content. The spatial distribution prediction trend of heavy metal elements by different prediction methods is basically consistent, with the high-value areas of Cd and Pb respectively distributed in the northwest and northeast of the basin center. However, the MSA-GNN-HMP model demonstrates superior detail representation in spatial prediction. MSA-GNN-HMP model has excellent spatial information representation capabilities and can more accurately predict heavy metal content and spatial distribution, providing a new theoretical basis for monitoring, assessing, and managing soil pollution. [ABSTRACT FROM AUTHOR]

The investigation into the impact of gravel on water infiltration process and hydraulic parameters in stony soil could offer a theoretical basis to enhance water availability in rocky mountain area. A one-dimensional vertical infiltration experiment was used in this study. Six groups of gravel content of 0% (CK), 10% (W1), 20% (W2), 30% (W3), 40% (W4) and 50% (W5) were established to explore the changes in the wetting front, cumulative infiltration volume and infiltration rate. Then the accuracy of four infiltration models in simulating soil water infiltration processes was evaluated. Finally, Hydrus-1D was used to perform numerical inversion of the soil water content after infiltration. The findings revealed that: (1) When the infiltration time reached 300 min, the wetting front of the W1, W2, W3, W4 and W5 treatments was 11.00%, 17.00%, 32.25%, 38.75% and 54.50% lower than CK, the cumulative infiltration volume was 29.80%, 38.97%, 45.62%, 54.74% and 73.17% lower than CK, and the stable infiltration rate was 50.98%, 52.94%, 66.67%, 68.63% and 86.27% lower than CK. (2) The soil–water infiltration processes were accurately described by the Horton model, the coefficient of determination (R2) > 0.935. (3) The simulation results of Hydrus-1D showed that with the increase of gravel content, the values of the retention water content (θr), saturated water content (θs), shape coefficient (n) and saturated hydraulic conductivity (Ks) were decreased, the values of the reciprocal of air-entry (α) were increased. The value of R2 was more than 0.894, the root mean square error (RMSE) and mean absolute error (MAE) were less than 2%, which demonstrated that the Hydrus-1D model exhibited superior capability in simulating the changes of water content in stony soil in rocky mountain area. The findings of this study demonstrated that gravel could decrease the water infiltration process and affect the water availability. It could provide data support for the water movement process of stony soil and rational utilization of limited water resources in mountainous area. [ABSTRACT FROM AUTHOR]

Diffuse solar radiation (DSR) plays a critical role in renewable energy utilization and efficient agricultural production. However, there is a scarcity of high-precision, long-term, and spatially continuous datasets for DSR in the world, and particularly in China. To address this gap, a 41-year (1982–2022) daily diffuse solar radiation dataset (CHDSR) is constructed with a spatial resolution of 10 km, based on a new ensemble model that combines the clear-sky irradiance estimated by the REST2 model and a machine-learning technique using precise cloud information derived from reanalysis data. Validation against ground-based measurements indicates strong performance of the new hybrid model, with a correlation coefficient, root mean square error and mean bias error (MBE) of 0.94, 13.9 W m−2 and −0.49 W m−2, respectively. The CHDSR dataset shows good spatial and temporal continuity over the time horizon from 1982 to 2022, with a multi-year mean value of 74.51 W m−2. This dataset is now freely available on figshare to the potential benefit of any analytical work in solar energy, agriculture, climate change, etc (https://doi.org/10.6084/m9.figshare.21763223.v3). [ABSTRACT FROM AUTHOR]

Aerosol research is important for the protection of the ecological environment, the improvement of air quality, and as a response to climate change. In this study, a random forest (RF) estimation model of aerosol optical depth (AOD) and extinction coefficient vertical profiles was, respectively, established using Orbiting Carbon Observatory-2 (OCO-2) oxygen-A band (O2 A-band) data from China and its surrounding areas in 2016, combined with geographical information (longitude, latitude, and elevation) and viewing angle data. To address the high number of OCO-2 O2 A-band channels, principal component analysis (PCA) was employed for dimensionality reduction. The model was then applied to estimate the aerosol extinction coefficients for the region in 2017, and its validity was verified by comparing the estimated values with the Cloud-Aerosol Lidar Infrared Pathfinder Satellite Observations (CALIPSO) Level 2 extinction coefficients. In the comprehensive analysis of overall performance, an AOD model was initially constructed using variables, achieving a correlation coefficient (R) of 0.676. Subsequently, predictions for aerosol extinction coefficients were generated, revealing a satisfactory agreement between the predicted and the actual values in the vertical direction, with an R of 0.535 and a root mean square error (RMSE) of 0.107 km−1. Of the four seasons of the year, the model performs best in autumn (R = 0.557), while its performance was relatively lower in summer (R = 0.442). Height had a significant effect on the model, with both R and RMSE decreasing as height increased. Furthermore, the accuracy of aerosol profile inversion shows a dependence on AOD, with a better accuracy when AOD is less than 0.3 and RMSE can be less than 0.06 km−1. [ABSTRACT FROM AUTHOR]

A non-periodic "step-like" variation in displacement is exhibited owing to the repeated instability of expansive soil landslides. The dynamic prediction of deformation for expansive soil landslides has become a challenge in actual engineering for disaster prevention and mitigation. Therefore, a support vector regression prediction (AMPSO-SVR) model based on adaptive mutation particle swarm optimization is proposed, which is suitable for small samples of data. The shallow displacement is decomposed into a trend component and fluctuating component by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and the trend displacement is predicted by cubic polynomial fitting. In this paper, the multiple disaster-inducing factors of expansive landslides and the time hysteresis effect between displacement and its influencing factors are fully considered, and the crucial influencing factors which eliminate the time lag effect and state factors are input into the model to predict the fluctuation displacement. Monitoring data in the Ningming area of China are employed for the model validation. The predicted results are compared with those of the traditional model. The model performance is evaluated through indicators such as the goodness of fit R2 and root mean square error RMSE. The results show that the prediction RMSE of the new model for three monitoring stations can reach 2.6 mm, 6.6 mm, and 2.5 mm, respectively. Compared with the common Grid search support vector regression (GS-SVR), the Particle Swarm Optimization Support Vector Regression (PSO-SVR) and Back Propagation Neural Network (BPNN) models have average improvements of 58.4%, 38.1%, and 25.2% respectively. The goodness of fit R2 is superior to 0.99 in the new method. The proposed model can effectively be deployed for the displacement prediction of non-periodic stepped expansive soil landslides driven by multiple influencing factors, providing a reference idea for the deformation prediction of expansive soil landslides. [ABSTRACT FROM AUTHOR]

The timely and accurate acquisition of information on the distribution of the crop planting structure in the Loess Plateau of eastern Gansu Province, one of the most important agricultural areas in Western China, is crucial for promoting fine management of agriculture and ensuring food security. This study uses multi-temporal high-resolution remote sensing images to determine optimal segmentation scales for various crops, employing the estimation of scale parameter 2 (ESP2) tool and the Ratio of Mean Absolute Deviation to Standard Deviation (RMAS) model. The Canny edge detection algorithm is then applied for multi-scale image segmentation. By incorporating crop phenological factors and using the L1-regularized logistic regression model, we optimized 39 spatial feature factors—including spectral, textural, geometric, and index features. Within a multi-level classification framework, the Random Forest (RF) classifier and Convolutional Neural Network (CNN) model are used to classify the cropping patterns in four test areas based on the multi-scale segmented images. The results indicate that integrating the Canny edge detection algorithm with the optimal segmentation scales calculated using the ESP2 tool and RMAS model produces crop parcels with more complete boundaries and better separability. Additionally, optimizing spatial features using the L1-regularized logistic regression model, combined with phenological information, enhances classification accuracy. Within the OBIC framework, the RF classifier achieves higher accuracy in classifying cropping patterns. The overall classification accuracies for the four test areas are 91.93%, 94.92%, 89.37%, and 90.68%, respectively. This paper introduced crop phenological factors, effectively improving the extraction precision of the shattered agricultural planting structure in the Loess Plateau of eastern Gansu Province. Its findings have important application value in crop monitoring, management, food security and other related fields. [ABSTRACT FROM AUTHOR]

Nonlinear deformation is a dynamically changing pattern of multiple surface deformations caused by groundwater overexploitation, underground coal mining, landslides, urban construction, etc., which are often accompanied by severe damage to surface structures or lead to major geological disasters; therefore, the high-precision monitoring and prediction of nonlinear surface deformation is significant. Traditional deep learning methods encounter challenges such as long-term dependencies or difficulty capturing complex spatiotemporal patterns when predicting nonlinear deformations. In this study, we developed a dual-attention-mechanism CNN-LSTM network model (DACLnet) to monitor and accurately predict nonlinear surface deformations precisely. Using advanced time series InSAR results as input, the DACLnet integrates the spatial feature extraction capability of a convolutional neural network (CNN), the advantages of the time series learning of a long short-term memory (LSTM) network, and the enhanced focusing effect of the dual-attention mechanism on crucial information, significantly improving the prediction accuracy of nonlinear surface deformations. The groundwater overexploitation area of the Turpan Basin, China, is selected to test the nonlinear deformation prediction effect of the proposed DACLnet. The results demonstrate that the DACLnet accurately captures developmental trends in historical surface deformations and effectively predicts surface deformations for the next two months in the study area. Compared to traditional LSTM and CNN-LSTM methods, the root mean square error (RMSE) of the DACLnet improved by 85.09% and 68.57%, respectively. These research results can provide crucial technical support for the early warning and prevention of geological disasters and can serve as an effective alternative tool for short-term ground subsidence prediction in areas lacking hydrogeological and other related data. [ABSTRACT FROM AUTHOR]

Scatterometers are highlighted in polar applications, such as sea ice extent retrieval. There are currently three types of spaceborne scatterometer in operation, among which the rotating pencil beam scatterometer and the rotating fan beam scatterometer have similar rotating observation geometry, but different beam sampling. However, it is difficult to objectively evaluate the performance of the two rotating beam scatterometers using the obtained data. This is because there are significant differences in their system parameters, which in turn affects the objectivity of the evaluation. Considering the high flexibility of the rotating fan beam scatterometer, this study proposes a dual-mode sea ice extent retrieval method for the rotating fan beam scatterometer. The dual modes refer to the rotating fan beam mode (or full incidence mode) and the equivalent rotating pencil beam mode (or single incidence mode). The two modes share the same system and spatiotemporal synchronous backscatter measurements provide the possibility of objectively comparing the rotating pencil beam and rotating fan beam scatterometers. The comparison, validation, and evaluation of the dual-mode sea ice extent of China France Oceanography Satellite Scatterometer (CSCAT) were performed. The results indicate that the sea ice extent retrieval of the equivalent rotating pencil beam mode of the rotating fan beam scatterometer is realizable, and compared to the existing rotating pencil beam scatterometers (such as the OceanSat Scatterometer on ScatSat-1, OSCAT, on ScatSat-1, and the Hai Yang 2B Scatterometer, HSCAT-B), the derived sea ice extent is closer to that of Advanced Microwave Scanning Radiometer 2 (AMSR2). For the two modes of CSCAT, when compared to AMSR2, the sea ice extent of the CSCAT full incidence mode has smaller values of root mean squared error (RMSE), error-of-ice (EI), and ice edge location distance (LD) than those of the CSCAT single incidence mode. These suggest that the rotating fan beam scatterometer shows better observation abilities for sea ice extent than the rotating pencil beam scatterometers. [ABSTRACT FROM AUTHOR]

Land surface temperature (LST) serves as a pivotal component within the surface energy cycle, offering fundamental insights for the investigation of agricultural water environment, urban thermal environment, and land planning. However, LST monitoring at a point scale entails substantial costs and poses implementation challenges. Moreover, the existing LST products are constrained by their low spatiotemporal resolution, limiting their broader applicability. The fusion of multi-source remote sensing data offers a viable solution to enhance spatiotemporal resolution. In this study, the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) was used to estimate time series LST utilizing multi-temporal Landsat 8 (L8) and MOD21A2 within the Haihe basin in 2021. Validation of ESTARFM LST was conducted against L8 LST and in situ LST. The results can be summarized as follows: (1) ESTARFM was found to be effective in heterogeneous regions within the Haihe basin, yielding LST with a spatiotemporal resolution of 30 m and 8 d while retaining clear texture information; (2) the comparison between ESTARFM LST and L8 LST shows a coefficient determination (R2) exceeding 0.59, a mean absolute error (MAE) lower than 2.43 K, and a root mean square error (RMSE) lower than 2.63 K for most dates; (3) comparison between ESTARFM LST and in situ LST showcased high validation accuracy, revealing a R2 of 0.87, a MAE of 2.27 K, and a RMSE of 4.12 K. The estimated time series LST exhibited notable reliability and robustness. This study introduced ESTARFM for LST estimation, achieving satisfactory outcomes. The findings offer a valuable reference for other regions to generate LST data with a spatiotemporal resolution of 8 d and 30 m, thereby enhancing the application of data products in agriculture and hydrology contexts. [ABSTRACT FROM AUTHOR]

High precision ionospheric Total Electron Content(TEC) prediction is of great significance for improving the accuracy of Global Navigation Satellite System(GNSS), preventing natural disasters, and ensuring wireless communication. Given the varying frequencies of TEC signals, a hybrid CEEMDAN-BiLSTM-PSO-LSSVM-FE model for predicting ionospheric TEC content is proposed in this paper. Firstly, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to decompose the extracted hourly TEC sequence and calculate the fuzzy entropy (FE) of the subsequences. Then, the signal is divided into high-frequency and low-frequency parts based on the fuzzy entropy value, for the high-frequency component, Bidirectional Long Short-Term Memory network (BiLSTM) is used for prediction; for the low-frequency component, Particle Swarm Optimization-based Least Squares Support Vector Machine (PSO-LSSVM) is used for prediction. The hourly TEC values collected from six evenly distributed GPS stations in China are used as the main input variable for the proposed model, with solar and geomagnetic activity data used as auxiliary data, using the TEC data from the previous 48 h to forecast the TEC content for the next hour. The performance of the model is evaluated by comparing it with other models under different geographical locations, seasons, solar and geomagnetic activity conditions. Experimental results show that the proposed hybrid model outperforms other models, with a correlation coefficient R2 and root mean square error (RMSE) of 0.99 and 0.20 TECU, respectively. The model effectively overcomes the problem of low TEC prediction accuracy and can provide more precise ionospheric delay correction services. [ABSTRACT FROM AUTHOR]

Remote sensing has become an effective way for regional soil organic matter (SOM) quantitative analysis. Topographic factors affect SOM content and distribution, also influence the accuracy of SOM remote sensing inversion. In large region with complex topographic conditions, characteristic topographic factors of SOM in different topographic regions are unknown, and the effect of combining characteristic topographic factors with spectral parameters on improving SOM inversion accuracy remains to be further studied. Three typical topographic regions of Shandong Province in China, namely Western plain region (WPR), Central and southern mountain region (CSMR), Eastern hilly region (EHR), were selected. Topographic factors, namely Elevation, Slope, Aspect and Relief Amplitude, were introduced. Respectively, the characteristic topographic factors and spectral parameters of SOM in each region were identified. The SOM inversion models were built separately for each region by integrating spectral parameters with topographic factors. The results revealed that as for the characteristic topographic factors of SOM, none was in the WPR, E, RA, and S were in the CSMR, E and RA were in the EHR. In combination with characteristic topographic factors, the accuracy of SOM spectral inversion models improved, the calibration R2 increased by 0.075-0.102, the RMSE (Root mean square error) decreased by 0.162-0.171 g/kg, the validation R² increased by 0.067-0.095, the RMSE decreased by 0.236-0.238 g/kg, and RPD (Relative prediction deviation) increased by 0.129-0.169. The most significant improvement was observed in the CSMR with the calibration R² of 0.725, the validation R2 of 0.713 and the RPD of 1.852, followed by the EHR. This study not only contributes to the advancement of soil quantitative remote sensing theory but also offers more precise data support for the development of green, low-carbon, and precision agriculture. [ABSTRACT FROM AUTHOR]

In order to optimize the Chinese medical and health system and improve people's health level, the SFA Malmquist model, the spatial econometric model, and the standard deviation ellipse method were used to measure the efficiency of medical and health services in China's 31 provinces between 2010 and 2020. Study results indicated that the average efficiency value of the 31 provinces generally exceeded 0.8. Specifically, the average efficiency values in the eastern and central regions increased from 0.852 to 0.875 and from 0.858 to 0.88, respectively. In the western and northeastern regions, these values rose from 0.804 to 0.835 and from 0.827 to 0.854, respectively. From the perspective of spatial distribution, there were high-high and low-low clusters in most provinces with significant spatial dependence among them. This analysis reveals that medical and health services efficiency in China demonstrates a spatial pattern extending from northeast to southwest. [ABSTRACT FROM AUTHOR]

Geostationary satellite data enable frequent observations of the Earth's surface, facilitating the rapid monitoring of land covers and changes. However, optical signals over vegetation, represented by the vegetation index (VI), exhibit an anisotropic effect due to the diurnal variation in the solar angle during data acquisition by geostationary satellites. This effect, typically characterized by the bi-directional reflectance distribution function (BRDF), can introduce uncertainties in vegetation monitoring and the estimation of phenological transition dates (PTDs). To address this, we investigated the diurnal variation in the normalized difference vegetation index (NDVI) with solar angles obtained from geostationary satellites since the image had fixed observation angles. By establishing a temporal conversion relationship between instantaneous NDVI and daily NDVI at the local solar noon (LSNVI), we successfully converted NDVIs obtained at any time during the day to LSNVI, increasing cloud-free observations of NDVI by 34%. Using different statistics of the time series vegetation index, including LSNVI, daily averaged NDVI (DAVI), and angular corrected NDVI (ACVI), we extracted PTD at five typical sites in China. The results showed a difference of up to 41.5 days in PTD estimation, with the highest accuracy achieved using LSNVI. The use of the proposed conversion approach, utilizing time series LSNVI, reduced the root mean square error (RMSE) of PTD estimation by 9 days compared with the use of actual LSNVI. In conclusion, this study highlights the importance of eliminating BRDF effects in geostationary satellite observations and demonstrates that the proposed angular normalization method can enhance the accuracy of time series NDVI in vegetation monitoring. [ABSTRACT FROM AUTHOR]

Dicranopteris dichotoma is a pioneer herbaceous plant species that is tolerant to barrenness and drought. Mapping its biomass spatial distribution is valuable for understanding its important role in reducing soil erosion and restoring ecosystems. This research selected Luodihe watershed in Changting County, Fujian Province, China, where soil erosion has been a severe problem for a long time, as a case study to explore the method to estimate biomass, including total and aboveground biomass, through the integration of field measurements, handheld laser scanning (HLS), and airborne laser scanning (ALS) data. A stepwise regression model and an allometric equation form model were used to develop biomass estimation models based on Lidar-derived variables at typical areas and at a regional scale. The results indicate that at typical areas, both total and aboveground biomass were best estimated using an allometric equation form model when HLS-derived height and density variables were extracted from a window size of 6 m × 6 m, with the coefficients of determination (R2) of 0.64 and 0.58 and relative root mean square error (rRMSE) of 28.2% and 35.8%, respectively. When connecting HLS-estimated biomass with ALS-derived variables at a regional scale, total and aboveground biomass were effectively predicted with rRMSE values of 17.68% and 17.91%, respectively. The HLS data played an important role in linking field measurements and ALS data. This research provides a valuable method to map Dicranopteris biomass distribution using ALS data when other remotely sensed data cannot effectively estimate the understory vegetation biomass. The estimated biomass spatial pattern will be helpful to understand the role of Dicranopteris in reducing soil erosion and improving the degraded ecosystem. [ABSTRACT FROM AUTHOR]

In recent years, with the deepening of exploration and development theories for tight oil reservoirs and the continuous breakthroughs in key engineering technologies, positive progress has been made in the development of onshore tight oil in China, it has become an important supplement to the growth of petroleum reserves and production. Therefore, identifying the main controlling factors of tight oil reservoir productivity and predicting this productivity are crucial for the development of petroleum resources. The article employs a comprehensive data preprocessing method to address field data, minimizing data errors to the greatest extent possible. In the study of controlling factors and prediction of productivity, various methods such as Pearson correlation coefficient, Random Forest, XGBoost, etc., are compared to enhance the reliability of the results. In addition, root mean square error, mean absolute error, and coefficient of determination are also introduced to evaluate the prediction results of each model, providing an overview of the overall framework of machine learning application in productivity. The study shows that compared with mutual information coefficient, the results of production capacity analysis using Random Forest are more consistent with Pearson correlation coefficient method. The fracturing engineering factors are dominant in the initial production capacity and first-year cumulative production; the initial production capacity is mainly controlled by the soaking time, the stable water cut, the volume of fracturing liquid volume and the formation thickness; the first-year cumulative oil production is mainly dependent on the stable water cut. The XGBoost method yielded the best performance across all three evaluation metrics, indicating that its prediction results are more reliable. In conclusion, machine learning methods can provide significant technical support for the exploration and development of tight oil reservoirs. • Utilize machine learning to discern geological and engineering factors impacting oil production. • Employ Random Forest and Pearson correlation coefficient for production analysis. • Achieve superior accuracy in oil production prediction with XGBoost. [ABSTRACT FROM AUTHOR]

Improving the accuracy of zenith tropospheric delay (ZTD) models is an important task. However, the existing ZTD models still have limitations, such as a lack of appropriate vertical adjustment function and being unsuitable for China, which has a complex climate and great undulating terrain. A new approach that considers the time-varying vertical adjustment and delicate diurnal variations of ZTD was introduced to develop a new grid ZTD model (NGZTD). The NGZTD model employed the Gaussian function and considered the seasonal variations of Gaussian coefficients to express the vertical variations of ZTD. The effectiveness of vertical interpolation for the vertical adjustment model (NGZTD-H) was validated. The root mean squared errors (RMSE) of the NGZTD-H model improved by 58% and 22% compared to the global pressure and temperature 3 (GPT3) model using ERA5 and radiosonde data, respectively. The NGZTD model's effectiveness for directly estimating the ZTD was validated. The NGZTD model improved by 22% and 31% compared to the GPT3 model using GNSS-derived ZTD and layered ZTD at radiosonde stations, respectively. Seasonal variations in Gaussian coefficients need to be considered. Using constant Gaussian coefficients will generate large errors. The NGZTD model exhibited outstanding advantages in capturing diurnal variations and adapting to undulating terrain. We analyzed and discussed the main error sources of the NGZTD model using validation of spatial interpolation accuracy. This new ZTD model has potential applications in enhancing the reliability of navigation, positioning, and interferometric synthetic aperture radar (InSAR) measurements and is recommended to promote the development of space geodesy techniques. [ABSTRACT FROM AUTHOR]

As the urgency of PM2.5 prediction becomes increasingly ingrained in public awareness, deep-learning methods have been widely used in forecasting concentration trends of PM2.5 and other atmospheric pollutants. Traditional time-series forecasting models, like long short-term memory (LSTM) and temporal convolutional network (TCN), were found to be efficient in atmospheric pollutant estimation, but either the model accuracy was not high enough or the models encountered certain challenges due to their own structure or some specific application scenarios. This study proposed a high-accuracy, hourly PM2.5 forecasting model, poly-dimensional local-LSTM Transformer, namely PD-LL-Transformer, by deep-learning methods, based on air pollutant data and meteorological data, and aerosol optical depth (AOD) data retrieved from the Himawari-8 satellite. This research was based on the Yangtze River Delta Urban Agglomeration (YRDUA), China for 2020–2022. The PD-LL-Transformer had three parts: a poly-dimensional embedding layer, which integrated the advantages of allocating and embedding multi-variate features in a more refined manner and combined the superiority of different temporal processing methods; a local-LSTM block, which combined the advantages of LSTM and TCN; and a Transformer encoder block. Over the test set (the whole year of 2022), the model's R2 was 0.8929, mean absolute error (MAE) was 4.4523 µg/m3, and root mean squared error (RMSE) was 7.2683 µg/m3, showing great accuracy for PM2.5 prediction. The model surpassed other existing models upon the same tasks and similar datasets, with the help of which a PM2.5 forecasting tool with better performance and applicability could be established. [ABSTRACT FROM AUTHOR]

Satellite precipitation products can help improve precipitation estimates where ground-based observations are lacking; however, their relative accuracy and applicability in data-scarce areas remain unclear. Here, we evaluated the accuracy of different satellite precipitation datasets for the Lancang River Basin, Western China, including the Tropical Rainfall Measuring Mission (TRMM) 3B42RT, the Global Precipitation Measurement Integrated Multi-satellitE Retrievals (GPM IMERG), and Fengyun 2G (FY-2G) datasets. The results showed that GPM IMERG and FY-2G are superior to TRMM 3B42RT for meeting local research needs. A subsequent bias correction on these two datasets significantly increased the correlation coefficient and probability of detection of the products and reduced error indices such as the root mean square error and mean absolute error. To further improve data quality, we proposed a novel correction–fusion method based on window sliding data correction and Bayesian data fusion. Specifically, the corrected FY-2G dataset was merged with GPM IMERG Early, Late, and Final Runs. The resulting FY-Early, FY-Late, and FY-Final fusion datasets showed high correlation coefficients, strong detection performances, and few observation errors, thereby effectively extending local precipitation data sources. The results of this study provide a scientific basis for the rational use of satellite precipitation products in data-scarce areas, as well as reliable data support for precipitation forecasting and water resource management in the Lancang River Basin. [ABSTRACT FROM AUTHOR]

Crop yield predictions are important for crop monitoring and agronomic management. The traditional methods for yield predictions are complicated and resource consuming. With the availability of affordable handheld imaging and computing devices, the image processing-based yield prediction methods are gaining popularity. In this work, RGB images of rice panicles are captured using DSLR camera with simple background and processed to determine the panicle area in terms of number of pixels. A machine learning-based model is developed to make predictions for rice yield. The model is trained to make predictions on unseen data. Various machine learning-based regression algorithms including decision tree, random forest, support vector machine, and convolution neural network are tested. The experiments are performed on a publically available dataset from China as well as on a self-acquired dataset in India. The results have shown that image processing and machine learning-based methods can make yield predictions satisfactorily as evident from the coefficient of determination ( R 2 ) that ranges 0.80–0.97 for different cultivars. The prediction error is determined in terms of root mean square error (RMSE) and mean absolute error (MAE). RMSE for different methods lies between 0.14 and 0.40, whereas MAE varies from 0.11 to 0.30. Among the tested algorithms, linear regression achieved the best precision with R 2 = 0.97, RMSE = 0.14, and MAE = 0.11. [ABSTRACT FROM AUTHOR]

Root zone soil moisture (RZSM) is critical for water resource management, drought monitoring and sub-seasonal flood climate prediction. While RZSM is not directly observable from space, several RZSM products are available and widely used at global and continental scales. This study conducts a comprehensive and quantitative evaluation of eight RZSM products using observations from 58 in situ soil moisture stations over the Huai River basin (HRB) in China. Attention is drawn to the potential factors that contribute to the uncertainties of model-based RZSM, including the errors in atmospheric forcing, vegetation parameterizations, soil properties and spatial scale mismatch. The results show that the Global Land Data Assimilation System Catchment Land Surface Model (GLDAS_CLSM) outperforms the other RZSM products with the highest correlation coefficient (R= 0.69) and the lowest unbiased root mean square error (ubRMSE = 0.018 m 3 m -3), while SMOS Level 4 (L4) RZSM shows the worst performance among eight RZSM products. The RZSM products based on land surface models generally perform better in the wet season than in the dry season due to the enhanced ability to capture of the temporal dynamics of in situ observations in the wet season and the inertia of remaining high soil moisture values even in the dry season, while the SMOS L4 RZSM product, derived from SMOS L3 surface moisture (SSM) combined with an exponential filter method, performs better in the dry season due to the attenuated ground microwave radiation signal caused by the increased water vapour absorption and scattering in the wet season. The underestimated SMOS L3 SSM triggers the underestimation of RZSM in SMOS L4. The overestimated RZSM products based on land surface models could be associated with the overestimated precipitation amounts and frequency, the underestimated air temperature, and the underestimated ratio of transpiration to the total terrestrial evapotranspiration. In addition, the biased soil properties and flawed vegetation parameterizations affect the hydrothermal transport processes represented in different land surface models (LSMs) and lead to inaccurate soil moisture simulation. The scale mismatch between point and footprint also introduces representative errors. The comparison of frequency of normalized soil moisture between RZSM products and in situ observations indicates that the LSMs should focus on reducing the frequency of wet soil moisture, increasing the frequency of dry soil moisture and the ability to capture the frequency peak of soil moisture. The study provides some insights into how to improve the ability of land surface models to simulate the land surface states and fluxes by taking into account the issues mentioned above. Finally, these results can be extrapolated to other regions located in similar climate zones, as they share similar precipitation patterns that dominate the terrestrial water cycle. [ABSTRACT FROM AUTHOR]

Precise prediction of irrigation volumes is crucial in modern agriculture. This study proposes an optimized long short-term memory (LSTM) model-based irrigation prediction method that combines bidirectional LSTM networks. The model provides farmers with more precise irrigation management decisions, facilitating optimal utilization of water resources and effective crop production management. This proposed model aims to fully exploit spatio-temporal features and sequence dependencies to enhance prediction accuracy and reliability. We aim to fully leverage crop irrigation volumes’ spatio-temporal features and sequence dependencies to improve prediction accuracy and reliability. First, this study adopts a bidirectional LSTM (BiLSTM) model to simulate the temporal features of irrigation volumes and learn the sequential dependencies of crop growth data from historical records. Then, this study passes the irrigation volume data through a convolutional neural network (CNN) model to extract spatial features and capture correlations among various features such as temperature, precipitation, and wind speed. Our prediction performance significantly improved after incorporating an attention mechanism that involves weighting features and enhancing focus on crucial aspects. The proposed BiLSTM-CNN-Attention approach is used to predict irrigation volume for spring corn in significant irrigation areas in Jilin Province, China. The results demonstrate that the proposed method surpasses recurrent neural network (RNN), CNN, LSTM, BiLSTM, and BiLSTM-CNN methods in terms of mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) (0.000004, 0.005968, 0.004599), and R² (0.9749), making a superior solution for predicting the volume of crop irrigation. [ABSTRACT FROM AUTHOR]

A simple, low-cost, and highly sensitive method using a modified QuECHERS procedure based on a liquid chromatography-tandem mass spectrometer (LC-MS/MS) was established to simultaneously quantify lufenuron and chlorfenapyr and the corresponding metabolite tralopyril in cabbage for the first time. On the basis of this method, terminal residue and dietary risk of lufenuron and chlorfenapyr in cabbage were investigated. The recoveries of lufenuron, chlorfenapyr, and tralopyril ranged from 88 to 110%, with relative standard deviation of less than 12.4%. The field trial results showed that at the pre-harvest interval (PHI) of 21 days, the terminal residues of lufenuron, chlorfenapyr, and tralopyril in the supervised trials were not higher than 0.02 mg/kg, and the highest detected residue levels of lufenuron, chlorfenapyr, and tralopyril were 0.047, 0.055, and <0.02 mg·kg-1 at 14-day pre-harvest respectively, which were lower than the maximum residue limits (MRLs) for cabbage established in China. For the dietary risk assessment, the national estimated daily intakes (NEDIs) as proportion of acceptable daily intakes (ADIs) were 80.4% and 29.9% for chlorfenapyr and lufenuron respectively indicating an acceptable dietary risk to Chinese population. [ABSTRACT FROM AUTHOR]

With the continuous advancement of China's "peak carbon dioxide emissions and Carbon Neutrality" process, the proportion of wind power is increasing. In the current research, aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data, a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine (IL-Bagging-DHKELM) error affinity propagation cluster analysis is proposed. The algorithm effectively combines deep hybrid kernel extreme learning machine (DHKELM) with incremental learning (IL). Firstly, an initial wind power prediction model is trained using the Bagging-DHKELM model. Secondly, Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model. Finally, the correlation between wind power prediction errors and Numerical Weather Prediction (NWP) data is introduced as incremental updates to the initial wind power prediction model. During the incremental learning process, multiple error performance indicators are used to measure the overall model performance, thereby enabling incremental updates of wind power models. Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points, indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate. The accuracy and precision of wind power generation prediction are effectively improved through the method. [ABSTRACT FROM AUTHOR]

Inhalable particulate matter (PM10) is a major air pollutant that has significant impacts on environmental climate and human health. Land-cover change is also a key factor influencing changes in atmospheric pollution. Changes in land-cover types can lead to changes in the sources and sinks of air pollutants, thus affecting the spatial distribution of PM10, which poses a threat to human health. Therefore, exploring the relationship between PM10 concentration change and land-cover change is of great significance. In this study, we constructed an extreme randomized trees model (ET) based on ground PM10 monitoring data, satellite-based aerosol optical depth (AOD) data, and auxiliary data including meteorological, vegetation, and population data to retrieve ground-level PM10 concentrations across China. The coefficient of determination (R2), the mean absolute error (MAE), and the root mean square error (RMSE) of the model were 0.878, 5.742 μg/m3, and 8.826 μg/m3, respectively. Based on this, we analyzed the spatio-temporal distribution of PM10 concentrations in China from 2015 to 2021. High PM10 values were mainly observed in the desert areas of northwestern China and the Beijing–Tianjin–Hebei urban agglomeration. The majority of China showed a significant decrease in PM10 concentrations. Additionally, we also analyzed the nonlinear response mechanism of the PM10 concentration change to land-cover change. The PM10 concentration is sensitive to forest and barren land change. Therefore, strengthening the protection of forests and desertification control can significantly reduce air pollution. Attention should also be paid to emission management in agricultural activities and urbanization processes. [ABSTRACT FROM AUTHOR]

Accurate forecasts of water demand are a crucial factor in the strategic planning and judicious use of finite water resources within a region, underpinning sustainable socio-economic development. This study aims to compare the applicability of various artificial intelligence models for long-term water demand forecasting across different water use sectors. We utilized the Tuojiang River basin in Sichuan Province as our case study, comparing the performance of five artificial intelligence models: Genetic Algorithm optimized Back Propagation Neural Network (GA-BP), Extreme Learning Machine (ELM), Gaussian Process Regression (GPR), Support Vector Regression (SVR), and Random Forest (RF). These models were employed to predict water demand in the agricultural, industrial, domestic, and ecological sectors using actual water demand data and relevant influential factors from 2005 to 2020. Model performance was evaluated based on the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), with the most effective model used for 2025 water demand projections for each sector within the study area. Our findings reveal that the GPR model demonstrated superior results in predicting water demand for the agricultural, domestic, and ecological sectors, attaining R2 values of 0.9811, 0.9338, and 0.9142 for the respective test sets. Also, the GA-BP model performed optimally in predicting industrial water demand, with an R2 of 0.8580. The identified optimal prediction model provides a useful tool for future long-term water demand forecasting, promoting sustainable water resource management. [ABSTRACT FROM AUTHOR]

Long-term, daily, and gap-free Normalized Difference Vegetation Index (NDVI) is of great significance for a better Earth system observation. However, gaps and contamination are quite severe in current daily NDVI datasets. This study developed a daily 0.05° gap-free NDVI dataset from 1981–2023 in China by combining valid data identification and spatiotemporal sequence gap-filling techniques based on the National Oceanic and Atmospheric Administration daily NDVI dataset. The generated NDVI in more than 99.91% of the study area showed an absolute percent bias (|PB|) smaller than 1% compared with the original valid data, with an overall R2 and root mean square error (RMSE) of 0.79 and 0.05, respectively. PB and RMSE between our dataset and the MODIS daily gap-filled NDVI dataset (MCD19A3CMG) during 2000 to 2023 are 7.54% and 0.1, respectively. PB between our dataset and three monthly NDVI datasets (i.e., GIMMS3g, MODIS MOD13C2, and SPOT/PROBA) are only −5.79%, 4.82%, and 2.66%, respectively. To the best of our knowledge, this is the first long-term daily gap-free NDVI in China by far. [ABSTRACT FROM AUTHOR]

Ultraviolet (UV) radiation is closely related to health, but limited measurements hindered further investigation of its health effects in China. Machine learning algorithm has been widely used in predicting environmental factors with high accuracy, but limited studies have done for UV radiation. This study aimed to develop UV radiation prediction model based on random forest method, and predict UV radiation at daily level and 10 km resolution in mainland China in 2005–2020. A random forest model was employed to predict UV radiation by integrating ground UV radiation measurements from monitoring stations and multiple predictors, such as UV radiation data from satellite. Missing data of satellite-based UV radiation was filled by three-day moving average method. The model's performance was evaluated through multiple cross-validation (CV) methods. The overall R2 (root mean square error, RMSE) between measured and predicted UV radiation from model development and model 10-fold CV was 0.97 (15.64 W m-2) and 0.83 (37.44 W m-2) at daily level, respectively. The model with OMI EDD performed higher predicting accuracy than the one without it. Based on predictions of UV radiation at daily level and 10 km spatial resolution and nearly 100 % spatiotemporal coverage, we found UV radiation increased by 4.20 % while PM2.5 levels decreased by 48.51 % and O3 levels rose by 22.70 % in 2013–2020, suggesting a potential correlation among these environmental factors. Uneven spatial distribution of UV radiation was found to be associated with factors such as latitude, elevation, meteorological factors and seasons. The eastern areas of China posed higher risk with both high population density and UV radiation intensity. Based on machine learning algorithm, this study generated a gridded dataset characterized by relatively high precision and extensive spatiotemporal coverage of UV radiation, which demonstrates the spatiotemporal variability of UV radiation levels in China and can facilitate health-related research in the future. This dataset is currently freely available at https://doi.org/10.5281/zenodo.10884591 (Jiang et al., 2024). [ABSTRACT FROM AUTHOR]

Tropospheric delay constitutes a primary source of error in Global Navigation Satellite System (GNSS) navigation positioning. Existing machine learning zenith wet delay (ZWD) models have limitations in their feature extraction capabilities. To address these limitations, we propose a ZWD (CNN_ZWD) model which is built upon observation data collected from 88 radiosonde (RS) stations in China from 2015 to 2017, employing the one-dimensional convolutional neural network (1D-CNN) deep learning method. The accuracy of the CNN_ZWD model is validated using the 2018 RS data and is compared with other models. The results reveal that the root mean square error (RMSE) of the 1D-CNN-based empirical model CNN_ZWD-A is 4.29 cm. This marks a 0.17 cm (3.81 %) improvement over the machine learning empirical models based on the random forest (RF) and back propagation neural network (BPNN) and a 0.70 cm (14.03 %) enhancement over the GPT3 empirical model. Moreover, when meteorological data is available at the station, the meteorological parameterized CNN_ZWD-B model has an RMSE of 2.69 cm. Its precision closely matches that of the RF_ZWD-D model and slightly exceeds the BP_ZWD-F model (RMSE: 2.85 cm). Remarkably, compared to the conventional Saastamoinen (Saa_ZWD) model, our proposed model demonstrates a 32.24 % increase in accuracy. This underscores that incorporating surface meteorological parameters into the functional formulation can significantly enhance the accuracy of regional ZWD prediction in China. Furthermore, compared with the empirical model, the predictive accuracy of the meteorological parameterized ZWD model based on the 1D-CNN exhibits significant improvement, particularly in China's monsoon climate region. [ABSTRACT FROM AUTHOR]

Surface ozone is an important air pollutant detrimental to human health and vegetation productivity, particularly in China. However, high resolution surface ozone concentration data is still lacking, largely hindering accurate assessment of associated environmental impacts. Here, we collected hourly ground ozone observations (over 6 million records), remote sensing products, meteorological data, and social-economic information, and applied recurrent neural networks to map hourly surface ozone data (HrSOD) at a 0.1° × 0.1° resolution across China during 2015–2020. The coefficient of determination (R2) values in sample-based, site-based, and by-year cross-validations were 0.72, 0.65 and 0.71, respectively, with the root mean square error (RMSE) values being 11.71 ppb (mean = 30.89 ppb), 12.81 ppb (mean = 30.96 ppb) and 11.14 ppb (mean = 31.26 ppb). Moreover, it exhibits high spatiotemporal consistency with ground-level observations at different time scales (diurnal, seasonal, annual), and at various spatial levels (individual sites and regional scales). Meanwhile, the HrSOD provides critical information for fine-resolution assessment of surface ozone impacts on environmental and human benefits. [ABSTRACT FROM AUTHOR]

Traditionally, the assessment of heavy metal concentrations using remote sensing technology is sample-intensive, with expensive model development. Using a mining area case study of Daxigou, China, we propose a cross-time-domain transfer learning model to monitor heavy metal pollution using samples collected from different time domains. Specifically, spectral indices derived from Landsat 8 multispectral images, terrain, and other auxiliary data correlative to soil heavy metals were prepared. A cross time-domain sample transfer learning model proposed in the paper based on the TrAdaBoost algorithm was used for the Cu content mapping in the topsoil by selective use of soil samples acquired in 2017 and 2019. We found that the proposed model accurately estimated the concentration of Cu in the topsoil of the mining area in 2019 and performed better than the traditional TrAdaBoost algorithms. The goodness of fit (R2) of the test set increased from 0.55 to 0.66; the relative prediction deviation (RPD) increased from 1.37 to 1.76; and finally, the root-mean-square deviation (RMSE), decreased from 8.33 to 7.24 mg·kg−1. The proposed model is potentially applicable to more accurate and inexpensive monitoring of heavy metals, facilitating remediation-related efforts. [ABSTRACT FROM AUTHOR]

Tropical cyclones (TCs) are characterized by robust vortical motion and intense thermodynamic processes, often causing damage in coastal cities as they result in landfall. Accurately estimating the ensemble mean of TC precipitation is critical for forecasting and remains a foremost global challenge. In this study, we develop an ensemble algorithm based on the feature-oriented mean (FM) suitable for spatially discrete variables in precipitation ensembles. This method can adjust the locations of ensemble precipitation fields to reduce the location-related deviations among ensemble members, ultimately enhancing the ensemble mean forecast skill for TC precipitation. To evaluate the feasibility of the FM in TC precipitation ensemble forecasting, 18 landing TC cases in China from 2019 to 2021 were selected for validation. For precipitation forecasts of the landing TCs with a varying leading time, we conducted a comprehensive quantitative evaluation and comparison of the precipitation forecast skills of the FM and arithmetic mean (AM) algorithms. The results indicate that the field adjustment algorithm in the FM can effectively align with the TC precipitation structure and the location of the ensemble mean, reducing the spatial divergence among precipitation fields. The FM method demonstrates superior performance in the equitable threat score, probability of detection, and false alarm ratio compared with the AM, exhibiting an overall improvement of around 10%. Furthermore, the FM ensemble mean shows a higher pattern of the correlation coefficient with observations and has a smaller root mean square error than the AM ensemble mean, signifying that the FM method can better preserve the characteristics of the precipitation structure. Additionally, an object-based diagnostic evaluation method was used to verify forecast results, and the results suggest that the attribute distribution of FM forecast objects more closely resembles that of observed precipitation objects (including the area, longitudinal and latitudinal centroid locations, axis angle, and aspect ratio). [ABSTRACT FROM AUTHOR]

Deformation along a subway rail network is related to the safe operation of the subway and the stability of construction facilities on the surface, making long-term deformation monitoring imperative. Long-term monitoring of surface deformation along the subway network and statistical analysis of the overall deformation situation are lacking in China. Therefore, targeting 35 Chinese cities whose subway mileage exceeds 50 km, we extracted their surface deformation along subway networks between 2018 and 2022, using spaceborne synthetic aperture radar (SAR) interferometry (InSAR) technology and Sentinel-1 satellite data. We verified the results with the continuous global navigation satellite system (GNSS) stations' data and found that the root mean square error (RMSE) of the InSAR results was 3.75 mm/year. Statistical analysis showed that ground subsidence along the subways was more prominent in Beijing, Tianjin, and other areas in the North China Plain, namely Kunming (which is dominated by karst landforms), as well as Shanghai, Guangzhou, Qingdao, and other coastal cities. In addition, an analysis revealed that the severity of surface subsidence correlated positively with a city's gross domestic product (GDP) with a Pearson correlation of 0.787, since the higher the GDP, the more frequent the construction and maintenance of subway, and the more commuters there are, which in turn exacerbates the disturbance to the surface. Additionally, the type of land cover also affects the ground deformation. Our findings provide a reference for constructing, operating, and maintaining the urban subway systems in China. [ABSTRACT FROM AUTHOR]

Satellite precipitation products (SPPs) are of great significance for water resource management and utilization in China; however, they suffer from considerable uncertainty. While numerous researchers have evaluated the accuracy of various SPPs, further investigation is needed to assess their performance across China's nine major water resource regions. This study used the latest precipitation dataset of the China Meteorological Administration's Land Surface Data Assimilation System (CLDAS-V2.0) as the benchmark and evaluated the performance of six SPPs—GSMaP, PERSIANN, CMORPH, CHIRPS, GPM IMERG, and TRMM—using six indices: correlation coefficient (CC), root mean square error (RMSE), mean absolute error (MAE), probability of detection (POD), false alarm rate (FAR), and critical success index (CSI), at both daily and hourly scales across China's nine water resource regions. The conclusions of this study are as follows: (1) The performance of the six SPPs was generally weaker in the west than in the east, with the Continental Basin (CB) exhibiting the poorest performance, followed by the Southwest Basin (SB). (2) At the hourly scale, the performance of the six SPPs was weaker compared to the daily scale, particularly in the high-altitude CB and the high-latitude Songhua and Liaohe River Basin (SLRB), where observing light precipitation and snowfall presents significant challenges. (3) GSMaP, CMORPH, and GPM IMERG demonstrated superior overall performance compared to CHIRPS, PERISANN, and TRMM. (4) CMORPH was found to be better suited for application in drought-prone areas, showcasing optimal performance in the CB and SB. GSMaP excelled in humid regions, displaying the best overall performance in the remaining seven basins. GPM IMERG serves as a complementary precipitation data source for the first two. [ABSTRACT FROM AUTHOR]

The Long-term Gap-free High-resolution Air Pollutants (LGHAP) concentration dataset generated in our previous study has provided spatially contiguous daily aerosol optical depth (AOD) and fine particulate matter (PM 2.5) concentrations at a 1 km grid resolution in China since 2000. This advancement empowered unprecedented assessments of regional aerosol variations and their influence on the environment, health, and climate over the past 20 years. However, there is a need to enhance such a high-quality AOD and PM 2.5 concentration dataset with new robust features and extended spatial coverage. In this study, we present version 2 of a global-scale LGHAP dataset (LGHAP v2), which was generated using improved big Earth data analytics via a seamless integration of versatile data science, pattern recognition, and machine learning methods. Specifically, multimodal AODs and air quality measurements acquired from relevant satellites, ground monitoring stations, and numerical models were harmonized by harnessing the capability of random-forest-based data-driven models. Subsequently, an improved tensor-flow-based AOD reconstruction algorithm was developed to weave the harmonized multisource AOD products together for filling data gaps in Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD retrievals from Terra. The results of the ablation experiments demonstrated better performance of the improved tensor-flow-based gap-filling method in terms of both convergence speed and data accuracy. Ground-based validation results indicated good data accuracy of this global gap-free AOD dataset, with a correlation coefficient (R) of 0.85 and a root mean square error (RMSE) of 0.14 compared to the worldwide AOD observations from the AErosol RObotic NETwork (AERONET), outperforming the purely reconstructed AODs (R = 0.83, RMSE = 0.15), but they were slightly worse than raw MAIAC AOD retrievals (R = 0.88, RMSE = 0.11). For PM 2.5 concentration mapping, a novel deep-learning approach, termed the SCene-Aware ensemble learning Graph ATtention network (SCAGAT), was hereby applied. While accounting for the scene representativeness of data-driven models across regions, the SCAGAT algorithm performed better during spatial extrapolation, largely reducing modeling biases over regions with limited and/or even absent in situ PM 2.5 concentration measurements. The validation results indicated that the gap-free PM 2.5 concentration estimates exhibit higher prediction accuracies, with an R of 0.95 and an RMSE of 5.7 µg m -3 , compared to PM 2.5 concentration measurements obtained from former holdout sites worldwide. Overall, while leveraging state-of-the-art methods in data science and artificial intelligence, a quality-enhanced LGHAP v2 dataset was generated through big Earth data analytics by cohesively weaving together multimodal AODs and air quality measurements from diverse sources. The gap-free, high-resolution, and global coverage merits render the LGHAP v2 dataset an invaluable database for advancing aerosol- and haze-related studies as well as triggering multidisciplinary applications for environmental management, health-risk assessment, and climate change attribution. All gap-free AOD and PM 2.5 concentration grids in the LGHAP v2 dataset, as well as the data user guide and relevant visualization codes, are publicly accessible at https://zenodo.org/communities/ecnu%5flghap (last access: 3 April 2024, Bai and Li, 2023a). [ABSTRACT FROM AUTHOR]

Simple Summary: In recent years, the damage inflicted upon vegetation by the fall webworm (FWW), Hyphantria cunea (Drury) (Lepidoptera: Erebidae: Arctiidae), has escalated globally. The black-headed fall webworm has extensively invaded regions in Europe and Asia. In China, scholars have conducted extensive research on the fall webworm. However, there has been limited research on the dynamics of invasion by the black-headed form of the fall webworm and the comprehensive interplay of various factors affecting its spread. Therefore, this study focuses on the dynamics of invasion by the black-headed form of the fall webworm and the combined influence of various factors affecting its spread. The plan is to map the invasion road map of Autumn Dictyophora melanocephala since its introduction into China and summarize the effects of terrain, vegetation, and human factors on the temporal and spatial changes of the species. The fall webworm (FWW), H. cunea (Drury) (Lepidoptera: Erebidae: Arctiidae), is an extremely high-risk globally invasive pest. Understanding the invasion dynamics of invasive pests and identifying the critical factors that promote their spread is essential for devising practical and efficient strategies for their control and management. The invasion dynamics of the FWW and its influencing factors were analyzed using standard deviation ellipse and spatial autocorrelation methods. The analysis was based on statistical data on the occurrence of the FWW in China. The dissemination pattern of the FWW between 1979 and 2022 followed a sequence of "invasion-occurrence-transmission-outbreak", spreading progressively from coastal to inland regions. Furthermore, areas with high nighttime light values, abundant ports, and non-forested areas with low vegetation cover at altitudes below 500 m were more likely to be inhabited by the black-headed FWW. The dynamic invasion pattern and the driving factors associated with the fall webworm (FWW) provide critical insights for future FWW management strategies. These strategies serve not only to regulate the dissemination of insects and diminish migratory tendencies but also to guarantee the implementation of efficient early detection systems and prompt response measures. [ABSTRACT FROM AUTHOR]

To solve the problems of large prediction error, slow convergence speed, and poor generalisation ability of traditional models in predicting surface deformation of open-pit mine slopes, this paper proposes a new intelligent prediction model based on the Mayfly algorithm-optimised support vector machine (MA-SVM). In this method, the MA is used to optimise the SVM parameters to reduce the uncertainty of the model and avoid time-consuming parameter adjustment. To evaluate the proposed prediction model, real-world deformation data of the north slope of the Anjialing open-pit mine in Pingshuo city, China, are collected using the microdeformation monitoring radar and used to investigate the deformation prediction performance of the proposed method. The results of the analysis demonstrate that the proposed method is able to accurately predict the deformation of the surface of the mine slope and outperforms three existing popular methods, including SVM, genetic algorithm (GA)-SVM, and particle swarm optimisation (PSO)-SVM). The mean absolute error (MAE) of the proposed MA⁃SVM is 2.52 % while 6.56 %, 4.95 %, and 5.16 % for the SVM, GA-SVM, and PSO-SVM, respectively; the root mean square error (RMSE) of the proposed MA⁃SVM is 10.21 % while 30.79 %, 17.38 %, and 22.54 % for the other three methods. Because the proposed MA⁃SVM model is able to predict slope deformation using actual monitoring data, it is of practical importance in real-world applications for early warning on landslides of mine slopes. [ABSTRACT FROM AUTHOR]

In the pivotal water resource region of the Yellow River Basin in China, precise prediction of water resources is essential for their effective and rational management. This study introduces a novel approach to water resource prediction by employing the Harris Hawks Optimization-Long Short-Term Memory (HHO-LSTM) model. This method overcomes the constraints faced by traditional techniques in processing time series data and various variable factors. It encompasses a comprehensive description of the multi-source hydrological data collection process within the Yellow River Basin, followed by meticulous data preprocessing. The data set for this study includes estimates of four critical water quality parameters, and the efficacy of the model is gauged through the mean squared error (MSE) and root mean squared error (RMSE) metrics. This facilitates the projection of future water quality trends in specific areas by leveraging historical water quality data. The HHO-LSTM model has demonstrated outstanding accuracy and robustness in predicting water quality across diverse temporal scales and water resource variables, marking a significant advancement in water resource management within the Yellow River Basin. This approach not only enhances current management strategies but also contributes valuable insights for ongoing water resource research and decision-making processes. [ABSTRACT FROM AUTHOR]

Due to its effectiveness as a risk-hedging trading strategy in financial markets, futures arbitrage is highly sought after by investors in turbulent market conditions. The essence of futures arbitrage lies in formulating strategies based on predictions of future futures price differentials. However, contemporary research predominantly focuses on projections of single indicators for the subsequent temporal juncture, and devising efficacious arbitrage strategies often necessitates the examination of multiple indicators across timeframes. To tackle the aforementioned challenge, our methodology leverages a PSO Deep-ConvLSTM network, which, through particle swarm optimization (PSO), refines hyperparameters, including layer architectures and learning rates, culminating in superior predictive performance. By analyzing temporal-spatial data within financial markets through ConvLSTM, the model captures intricate market patterns, performing better in forecasting than traditional models. Multistep forward simulation experiments and extensive ablation studies using future data from the Shanghai Futures Exchange in China validate the effectiveness of the integrated model. Compared with the gate recurrent unit (GRU), long short-term memory (LSTM), Transformer, and FEDformer, this model exhibits an average reduction of 39.8% in root mean squared error (RMSE), 42.5% in mean absolute error (MAE), 45.6% in mean absolute percentage error (MAPE), and an average increase of 1.96% in coefficient of determination (R2) values. [ABSTRACT FROM AUTHOR]

Estimating and monitoring chlorophyll content is a critical step in crop spectral image analysis. The quick, non-destructive assessment of chlorophyll content in rice leaves can optimize nitrogen fertilization, benefit the environment and economy, and improve rice production management and quality. In this research, spectral analysis of rice leaves is performed using hyperspectral and fluorescence spectroscopy for the detection of chlorophyll content in rice leaves. This study generated ninety experimental spectral datasets by collecting rice leaf samples from a farm in Sichuan Province, China. By implementing a feature extraction algorithm, this study compresses redundant spectral bands and subsequently constructs machine learning models to reveal latent correlations among the extracted features. The prediction capabilities of six feature extraction methods and four machine learning algorithms in two types of spectral data are examined, and an accurate method of predicting chlorophyll concentration in rice leaves was devised. The IVSO-IVISSA (Iteratively Variable Subset Optimization–Interval Variable Iterative Space Shrinkage Approach) quadratic feature combination approach, based on fluorescence spectrum data, has the best prediction performance among the CNN+LSTM (Convolutional Neural Network Long Short-Term Memory) algorithms, with corresponding RMSE-Train (Root Mean Squared Error), RMSE-Test, and RPD (Ratio of standard deviation of the validation set to standard error of prediction) indexes of 0.26, 0.29, and 2.64, respectively. We demonstrated in this study that hyperspectral and fluorescence spectroscopy, when analyzed with feature extraction and machine learning methods, provide a new avenue for rapid and non-destructive crop health monitoring, which is critical to the advancement of smart and precision agriculture. [ABSTRACT FROM AUTHOR]