Search

Soil salinization has become one of the major environmental problems threatening food security. The identification and knowledge of the spatial distributions of soil salinization are key in addressing this problem. This study assumes that a good saline land identification effect can be obtained with the help of deep learning methods. Therefore, this study used the OLI sensor data from the Landsat-8, based on the U2-Network, and proposes a method to extract saline land from remote sensing images. The study also adds different salinity indices (SI, SI1, and SI2) to explore its impact on classification accuracy. Through our method, accurate saline soil distribution information were obtained, and several verification indicators (the Intersection-over-Union (IoU), recall, precision, and F1-score) were all measured above 0.8. In addition, compared with the multi-spectral training results, the classification accuracy increased after adding a specific salinity index, and most of the accuracy indices increased by about 2% (the IoU increased by 3.70%, recall increased by 1.50%, precision increased by 2.81%, and F1-score increased by 2.13%). In addition, we also included a case study based on our methodology to analyze the distribution characteristics and changes of saline soil in the Zhenlai area of Northeast China from 2016 to 2020. We found that the area of saline land in the Zhenlai area has reduced, which shows that the extraction method proposed in this study is feasible. Overall, this paper indicates that deep learning-based methods can efficiently extract the salinity of soil and enhance the mapping of its spatial distribution. The study has the broad impact of supplementing satellite imagery for salinity modeling and helping to guide agricultural land management practices for northeastern China and other salinized regions. [ABSTRACT FROM AUTHOR]

Extraterrestrial solar radiation (ESR) is the essential basic background for solar radiation, which determines the occurrence of the weather and atmospheric phenomena. Since the influence of ESR variation on actual rugged terrain is a diverse, complex, and dynamic process, simulating ESR over a large spatial-temporal span, especially with a high-resolution digital elevation model (DEM), is a significant challenge. In this paper, we developed a new scheme for simulating ESR over the entirety of China using a DEM with a resolution of 30 m. To fully consider regional terrain status, the feature variables used were elevation, slope, and aspects of the located grid and the surrounding four grids to reveal the topography. In addition, latitude was used as a feature variable to consider the geographical location, and the month number was used to consider the duration. On the basis of different geographical locations, the training dataset was established from 20,000 grids. With the feature variable composition and training dataset, a backpropagation artificial neural network (BP ANN) was found to have the best performance compared with the other three machine learning methods in simulating ESR for a DEM. In terms of the proposed scheme and BP ANN, we drew an ESR map of China with a resolution of 30 m. The determination coefficient of the simulation result achieved 0.99 and the root-mean-square error was less than 50 MJ/m2 in all sample areas, confirming its remarkable accuracy. In terms of efficiency, the time consumption of ESR simulated using the proposed scheme shrinks over 150 times in all sample areas compared to that simulated via the theoretical model. Simultaneously, the developed scheme was also used to simulate an ESR for a DEM with a resolution of 90 m to verify the universality and robustness of the developed scheme. In addition, we used the proposed scheme to derive the direct solar radiation and global solar radiation, thereby further proving the reliability and applicability of our study. Overall, our work convincingly proved that the proposed scheme is a potential and effective approach for quickly simulating ESR with high accuracy. This study provides the basis for different solar radiation inversions of long time series and large spatial scales, offering additional insights for simulating ESR on a large spatial-temporal span. [ABSTRACT FROM AUTHOR]

The extraction and evaluation of crop production units are important foundations for agricultural production and management in modern smallholder regions, which are very significant to the regulation and sustainable development of agriculture. Crop areas have been recognized efficiently and accurately via remote sensing (RS) and machine learning (ML), especially deep learning (DL), which are too rough for modern smallholder production. In this paper, a delimitation-grading method for actual crop production units (ACPUs) based on RS images was explored using a combination of a mask region-based convolutional neural network (Mask R-CNN), spatial analysis, comprehensive index evaluation, and cluster analysis. Da'an City, Jilin province, China, was chosen as the study region to satisfy the agro-production demands in modern smallholder areas. Firstly, the ACPUs were interpreted from perspectives such as production mode, spatial form, and actual productivity. Secondly, cultivated land plots (C-plots) were extracted by Mask R-CNN with high-resolution RS images, which were used to delineate contiguous cultivated land plots (CC-plots) on the basis of auxiliary data correction. Then, the refined delimitation-grading results of the ACPUs were obtained through comprehensive evaluation of spatial characteristics and real productivity clustering. For the conclusion, the effectiveness of the Mask R-CNN model in C-plot recognition (loss = 0.16, mean average precision (mAP) = 82.29%) and a reasonable distance threshold (20 m) for CC-plot delimiting were verified. The spatial features were evaluated with the scale-shape dimensions of nine specific indicators. Real productivities were clustered by the incorporation of two-step cluster and K-Means cluster. Furthermore, most of the ACPUs in the study area were of a reasonable scale and an appropriate shape, holding real productivities at a medium level or above. The proposed method in this paper can be adjusted according to the changes of the study area with flexibility to assist agro-supervision in many modern smallholder regions. [ABSTRACT FROM AUTHOR]

Cloud recognition is a basic task in ground meteorological observation. It is of great significance to accurately identify cloud types from long-time-series satellite cloud images for improving the reliability and accuracy of weather forecasting. However, different from ground-based cloud images with a small observation range and easy operation, satellite cloud images have a wider cloud coverage area and contain more surface features. Hence, it is difficult to effectively extract the structural shape, area size, contour shape, hue, shadow and texture of clouds through traditional deep learning methods. In order to analyze the regional cloud type characteristics effectively, we construct a China region meteorological satellite cloud image dataset named CRMSCD, which consists of nine cloud types and the clear sky (cloudless). In this paper, we propose a novel neural network model, UATNet, which can realize the pixel-level classification of meteorological satellite cloud images. Our model efficiently integrates the spatial and multi-channel information of clouds. Specifically, several transformer blocks with modified self-attention computation (swin transformer blocks) and patch merging operations are used to build a hierarchical transformer, and spatial displacement is introduced to construct long-distance cross-window connections. In addition, we introduce a Channel Cross fusion with Transformer (CCT) to guide the multi-scale channel fusion, and design an Attention-based Squeeze and Excitation (ASE) to effectively connect the fused multi-scale channel information to the decoder features. The experimental results demonstrate that the proposed model achieved 82.33% PA, 67.79% MPA, 54.51% MIoU and 70.96% FWIoU on CRMSCD. Compared with the existing models, our method produces more precise segmentation performance, which demonstrates its superiority on meteorological satellite cloud recognition tasks. [ABSTRACT FROM AUTHOR]

It is an objective demand for sustainable agricultural development to realize fast and accurate cultivated land quality assessment. In this paper, Tengzhou city (county-scale hilly area: scale A), Shanghe county (county-scale plain area: scale B), and Huang-Huai-Hai region (including large-scale hilly and plain area: scale C and D) were taken as research areas. Through the conversion of evaluation systems, the inversion models at the county-scale were constructed. Then, the image scale conversion was carried out based on the numerical regression method, and the upscaling inversion was realized. The results showed that: (1) the conversion models of evaluation systems (CMES) are Y = 1.021x − 4.989 (CMESA−B), Y = 0.801x + 16.925 (CMESA−C), and Y = 0.959x + 3.458 (CMESC−D); (2) the booting stage is the best inversion phase; (3) the back propagation neural network model based on the combination index group (CI-BPNN) is the best inversion model, with the R2 are 0.723 (modeling set) and 0.722 (verification set). CI-BPNN and CI-BPNN-CMESA−B models are suitable for the hilly and plain areas at the county-scale, and the level area ratio difference is less than 4.87%. Furthermore, (4) the reflectance conversion model of short-wave infrared 2 is cubic, and the rest are quadratic. CI-BPNN-CMESA−C and CI-BPNN-CMESA−C-CMESC−D models realized upscaling inversion in the hilly and plain areas, with the maximum level area ratio difference being 1.60%. Additionally, (5) the wheat field quality has improved steadily since 2001 in the Huang-Huai-Hai region. This study proposes an upscaling inversion method of wheat field quality, which provides a scientific basis for cultivated land management and agricultural production in large areas. [ABSTRACT FROM AUTHOR]

Landslides pose a constant threat to the lives and property of mountain people and may also cause geomorphological destruction such as soil and water loss, vegetation destruction, and land cover change. Landslide susceptibility assessment (LSA) is a key component of landslide risk evaluation. There are many related studies, but few analyses and comparisons of models for optimization. This paper aims to introduce the Tree-structured Parzen Estimator (TPE) algorithm for hyperparameter optimization of three typical neural network models for LSA in Shuicheng County, China, as an example, and to compare the differences of predictive ability among the models in order to achieve higher application performance. First, 17 influencing factors of landslide multiple data sources were selected for spatial prediction, hybrid ensemble oversampling and undersampling techniques were used to address the imbalanced sample and small sample size problem, and the samples were randomly divided into a training set and validation set. Second, deep neural network (DNN), recurrent neural network (RNN), and convolutional neural network (CNN) models were adopted to predict the regional landslides susceptibility, and the TPE algorithm was used to optimize the hyperparameters respectively to improve the assessment capacity. Finally, to compare the differences and optimization effects of these models, several objective measures were applied for validation. The results show that the high-susceptibility regions mostly distributed in bands along fault zones, where the lithology is mostly claystone, sandstone, and basalt. The DNN, RNN, and CNN models all perform well in LSA, especially the RNN model. The TPE optimization significantly improves the accuracy of the DNN and CNN (3.92% and 1.52%, respectively), but does not improve the performance of the RNN. In summary, our proposed RNN model and TPE-optimized DNN and CNN model have robust predictive capability for landslide susceptibility in the study area and can also be applied to other areas containing similar geological conditions. [ABSTRACT FROM AUTHOR]

As one of the most devastating disasters to pine forests, pine wilt disease (PWD) has caused tremendous ecological and economic losses in China. An effective way to prevent large-scale PWD outbreaks is to detect and remove the damaged pine trees at the early stage of PWD infection. However, early infected pine trees do not show obvious changes in morphology or color in the visible wavelength range, making early detection of PWD tricky. Unmanned aerial vehicle (UAV)-based hyperspectral imagery (HI) has great potential for early detection of PWD. However, the commonly used methods, such as the two-dimensional convolutional neural network (2D-CNN), fail to simultaneously extract and fully utilize the spatial and spectral information, whereas the three-dimensional convolutional neural network (3D-CNN) is able to collect this information from raw hyperspectral data. In this paper, we applied the residual block to 3D-CNN and constructed a 3D-Res CNN model, the performance of which was then compared with that of 3D-CNN, 2D-CNN, and 2D-Res CNN in identifying PWD-infected pine trees from the hyperspectral images. The 3D-Res CNN model outperformed the other models, achieving an overall accuracy (OA) of 88.11% and an accuracy of 72.86% for detecting early infected pine trees (EIPs). Using only 20% of the training samples, the OA and EIP accuracy of 3D-Res CNN can still achieve 81.06% and 51.97%, which is superior to the state-of-the-art method in the early detection of PWD based on hyperspectral images. Collectively, 3D-Res CNN was more accurate and effective in early detection of PWD. In conclusion, 3D-Res CNN is proposed for early detection of PWD in this paper, making the prediction and control of PWD more accurate and effective. This model can also be applied to detect pine trees damaged by other diseases or insect pests in the forest. [ABSTRACT FROM AUTHOR]

In this paper, a deep learning long-short-term memory (LSTM) method is applied to the forecasting of the critical frequency of the ionosphere F2 layer (foF2). Hourly values of foF2 from 10 ionospheric stations in China and Australia (based on availability) from 2006 to 2019 are used for training and verifying. While 2015 and 2019 are exclusive for verifying the forecasting accuracy. The inputs of the LSTM model are sequential data for the previous values, which include local time (LT), day number, solar zenith angle, the sunspot number (SSN), the daily F10.7 solar flux, geomagnetic the Ap and Kp indices, geographic coordinates, neutral winds, and the observed value of foF2 at the previous moment. To evaluate the forecasting ability of the deep learning LSTM model, two different neural network forecasting models: a back-propagation neural network (BPNN) and a genetic algorithm optimized backpropagation neural network (GABP) were established for comparative analysis. The foF2 parameters were forecasted under geomagnetic quiet and geomagnetic disturbed conditions during solar activity maximum (2015) and minimum (2019), respectively. The forecasting results of these models are compared with those of the international reference ionosphere model (IRI2016) and the measurements. The diurnal and seasonal variations of foF2 for the 4 models were compared and analyzed from 8 selected verification stations. The forecasting results reveal that the deep learning LSTM model presents the optimal performance of all models in forecasting the time series of foF2, while the IRI2016 model has the poorest forecasting performance, and the BPNN model and GABP model are between two of them. [ABSTRACT FROM AUTHOR]

The accurate and timely estimation of regional crop biomass at different growth stages is of great importance in guiding crop management decision making. The recent availability of long time series of remote sensing data offers opportunities for crop monitoring. In this paper, four machine learning models, namely random forest (RF), support vector machine (SVM), artificial neural network (ANN), and extreme gradient boosting (XGBoost) were adopted to estimate the seasonal corn biomass based on field observation data and moderate resolution imaging spectroradiometer (MODIS) reflectance data from 2012 to 2019 in the middle reaches of the Heihe River basin, China. Nine variables were selected with the forward feature selection approach from among twenty-seven variables potentially influencing corn biomass: soil-adjusted total vegetation index (SATVI), green ratio vegetation index (GRVI), Nadir_B7 (2105–2155 nm), Nadir_B6 (1628–1652 nm), land surface water index (LSWI), normalized difference vegetation index (NDVI), Nadir_B4 (545–565 nm), and Nadir_B3 (459–479 nm). The results indicated that the corn biomass was suitably estimated (the coefficient of determination (R2) was between 0.72 and 0.78) with the four machine learning models. The XGBoost model performed better than the other three models (R2 = 0.78, root mean squared error (RMSE) = 2.86 t/ha and mean absolute error (MAE) = 1.86 t/ha). Moreover, the RF model was an effective method (R2 = 0.77, RMSE = 2.91 t/ha and MAE = 1.91 t/ha), with a performance comparable to that of the XGBoost model. This study provides a reference for estimating crop biomass from MOD43A4 datasets. In addition, the research demonstrates the potential of machine learning techniques to achieve a relatively accurate estimation of daily corn biomass at a large scale. [ABSTRACT FROM AUTHOR]

How to acquire landslide disaster information quickly and accurately has become the focus and difficulty of disaster prevention and relief by remote sensing. Landslide disasters are generally featured by sudden occurrence, proposing high demand for emergency data acquisition. The low-altitude Unmanned Aerial Vehicle (UAV) remote sensing technology is widely applied to acquire landslide disaster data, due to its convenience, high efficiency, and ability to fly at low altitude under cloud. However, the spectrum information of UAV images is generally deficient and manual interpretation is difficult for meeting the need of quick acquisition of emergency data. Based on this, UAV images of high-occurrence areas of landslide disaster in Wenchuan County and Baoxing County in Sichuan Province, China were selected for research in the paper. Firstly, the acquired UAV images were pre-processed to generate orthoimages. Subsequently, multi-resolution segmentation was carried out to obtain image objects, and the barycenter of each object was calculated to generate a landslide sample database (including positive and negative samples) for deep learning. Next, four landslide feature models of deep learning and transfer learning, namely Histograms of Oriented Gradients (HOG), Bag of Visual Word (BOVW), Convolutional Neural Network (CNN), and Transfer Learning (TL) were compared, and it was found that the TL model possesses the best feature extraction effect, so a landslide extraction method based on the TL model and object-oriented image analysis (TLOEL) was proposed; finally, the TLOEL method was compared with the object-oriented nearest neighbor classification (NNC) method. The research results show that the accuracy of the TLOEL method is higher than the NNC method, which can not only achieve the edge extraction of large landslides, but also detect and extract middle and small landslides accurately that are scatteredly distributed. [ABSTRACT FROM AUTHOR]

Strawberry growers in Florida suffer from a lack of efficient and accurate yield forecasts for strawberries, which would allow them to allocate optimal labor and equipment, as well as other resources for harvesting, transportation, and marketing. Accurate estimation of the number of strawberry flowers and their distribution in a strawberry field is, therefore, imperative for predicting the coming strawberry yield. Usually, the number of flowers and their distribution are estimated manually, which is time-consuming, labor-intensive, and subjective. In this paper, we develop an automatic strawberry flower detection system for yield prediction with minimal labor and time costs. The system used a small unmanned aerial vehicle (UAV) (DJI Technology Co., Ltd., Shenzhen, China) equipped with an RGB (red, green, blue) camera to capture near-ground images of two varieties (Sensation and Radiance) at two different heights (2 m and 3 m) and built orthoimages of a 402 m2 strawberry field. The orthoimages were automatically processed using the Pix4D software and split into sequential pieces for deep learning detection. A faster region-based convolutional neural network (R-CNN), a state-of-the-art deep neural network model, was chosen for the detection and counting of the number of flowers, mature strawberries, and immature strawberries. The mean average precision (mAP) was 0.83 for all detected objects at 2 m heights and 0.72 for all detected objects at 3 m heights. We adopted this model to count strawberry flowers in November and December from 2 m aerial images and compared the results with a manual count. The average deep learning counting accuracy was 84.1% with average occlusion of 13.5%. Using this system could provide accurate counts of strawberry flowers, which can be used to forecast future yields and build distribution maps to help farmers observe the growth cycle of strawberry fields. [ABSTRACT FROM AUTHOR]

Due to the advantage of geostationary satellites, Himawari-8/AHI can provide near-real-time air quality monitoring over China with a high temporal resolution. Satellite-based aerosol optical depth (AOD) retrieval over land is a challenge because of the large surface contribution to the top of atmosphere (TOA) signal and the uncertainty of aerosol modes. Here, by combining satellite TOA reflectance, sun-sensor geometries, meteorological factors and vegetation information, we propose a data-driven AOD detection algorithm based on a deep neural network (DNN) model for Himawari-8/AHI. It is trained by sample data of 2018 and 2019 and is applied to derive hourly AODs over China in 2020. By comparison with ground-based AERONET measurements, R2 for DNN-estimated AOD is up to 0.8702, which is much higher than that for the AHI AOD product with R2 = 0.4869. The hourly AOD results indicate that the DNN model has a good potential in improving the performance of AOD retrieval in the early morning and in the late afternoon, and the spatial distribution is reliable for capturing the variation of aerosol pollution on the regional scale. By analyzing different DNN modeling strategies, it is found that seasonal modeling can hardly increase the accuracy of AOD retrieval to a certain extent, and R2 increases from 0.7394 to 0.8168 when meteorological features, especially air pressure, are involved in the model training. [ABSTRACT FROM AUTHOR]

Snow depth estimation with passive microwave (PM) remote sensing is challenged by spatial variations in the Earth's surface, e.g., snow metamorphism, land cover types, and topography. Thus, traditional static snow depth retrieval algorithms cannot capture snow thickness well. In this study, we present a new operational retrieval algorithm, hereafter referred to as the pixel-based method (0.25° × 0.25° grid-level), to provide more accurate and nearly real-time snow depth estimates. First, the reference snow depth was retrieved using a previously proposed model in which a microwave snow emission model was coupled with a machine learning (ML) approach. In this process, an effective grain size (effGS) value was optimized by utilizing the snow microwave emission model, and then the nonlinear relationship between snow depth and multiple predictive variables, e.g., effGS, longitude, elevation, and brightness temperature (Tb) gradients, was established with the ML technique to retrieve reference snow depth data. To select a robust and well-performing ML approach, we compared the performance of widely used support vector regression (SVR), artificial neural network (ANN) and random forest (RF) algorithms over China. The results show that the three ML models performed similarly in snow depth estimation, which was attributed to the inclusion of effGS in the training samples. In this study, the RF model was used to retrieve the snow depth reference dataset due to its slightly stronger robustness according to our comparison of results. Second, the pixel-based algorithm was built based on the retrieved reference snow depth dataset and satellite Tb observations (18.7 GHz and 36.5 GHz) from Advanced Microwave Scanning Radiometer 2 (AMSR2) during the 2012–2020 period. For the pixel-based algorithm, the fitting coefficients were achieved dynamically pixel by pixel, making it superior to the traditional static methods. Third, the built pixel-based algorithm was verified using ground-based observations and was compared to the AMSR2, GlobSnow-v3.0, and ERA5-land products during the 2012–2020 period. The pixel-based algorithm exhibited an overall unbiased root mean square error (unRMSE) and R2 of 5.8 cm and 0.65, respectively, outperforming GlobSnow-v3.0, with unRMSE and R2 values of 9.2 cm and 0.22, AMSR2, with unRMSE and R2 values of 18.5 cm and 0.13, and ERA5-land, with unRMSE and R2 values of 10.5 cm and 0.33, respectively. However, the pixel-based algorithm estimates were still challenged by the complex terrain, e.g., the unRMSE was up to 17.4 cm near the Tien Shan Mountains. The proposed pixel-based algorithm in this study is a simple and operational method that can retrieve accurate snow depths based solely on spaceborne PM data in comparatively flat areas. [ABSTRACT FROM AUTHOR]

As a result of the influence of plate movement, the upper reaches of Jinsha River have strong geological tectonic activities, large topographic fluctuations, and complex climate characteristics, which result in the frequent occurrence of landslide disasters. Hence, there is the need to carry out landslide susceptibility mapping in the upper reaches of Jinsha River to ensure the safety of local people's property and the safe exploitation of hydraulic resources. In this study, InSAR technology and a field geological survey were used to map the landslides. Then, the curvature watershed method was used to divide the slope units. A conditioning factor system was established, which can reflect the characteristics of the rapid uplift and vertical distribution of rainfall in the special geological environment of the study area. Finally, logistic regression, random forest, and artificial neural network models were used to establish the landslide susceptibility model. The results show that the random forest model is optimal for the landslide susceptibility mapping in this area. Additionally, the area percentages of the very low, low, moderate, high, and very high susceptibility classes were 40.13%, 20.06%, 13.39%, 12.55%, and 13.87%, respectively. Based on the analysis of the landslide susceptibility map, we suggest that the landslide geological hazards resulting from the rapid uplift of the Tibetan Plateau and the significant decrease in sea level during a glacial period in the upper reaches of Jinsha River are controlled by the double disaster effect of the geodynamic system. Consequently, this study can guide local prevention and mitigation. [ABSTRACT FROM AUTHOR]

Pine wood nematode (PWN), Bursaphelenchus xyophilus, originating from North America, has caused great ecological and economic hazards to pine trees worldwide, especially affecting the coniferous forests and mixed forests of masson pine in subtropical regions of China. In order to prevent PWN disease expansion, the risk level and susceptivity of PWN outbreaks need to be predicted in advance. For this purpose, we established a prediction model to estimate the susceptibility and risk level of PWN with vegetation condition variables, anthropogenic activity variables, and topographic feature variables across a large-scale district. The study was conducted in Dangyang City, Hubei Province in China, which was located in a subtropical zone. Based on the location of PWN points derived from airborne imagery and ground survey in 2018, the predictor variables were conducted with remote sensing and geographical information system (GIS) data, which contained vegetation indices including normalized difference vegetation index (NDVI), normalized difference moisture index (NDMI), normalized burn ratio (NBR), and normalized red edge index (NDRE) from Sentinel-2 imagery in the previous year (2107), the distance to different level roads which indicated anthropogenic activity, topographic variables in including elevation, slope, and aspect. We compared the fitting effects of different machine learning algorithms such as random forest (RF), K-neighborhood (KNN), support vector machines (SVM), and artificial neural networks (ANN) and predicted the probability of the presence of PWN disease in the region. In addition, we classified PWN points to different risk levels based on the density distribution of PWN sites and built a PWN risk level model to predict the risk levels of PWN outbreaks in the region. The results showed that: (1) the best model for the predictive probability of PWN presence is the RF classification algorithm. For the presence prediction of the dead trees caused by PWN, the detection rate (DR) was 96.42%, the false alarm rate (FAR) was 27.65%, the false detection rate (FDR) was 4.16%, and the area under the receiver operating characteristic curve (AUC) was equal to 0.96; (2) anthropogenic activity variables had the greatest effect on PWN occurrence, while the effects of slope and aspect were relatively weak, and the maximum, minimum, and median values of remote sensing indices were more correlated with PWN occurrence; (3) modeling analysis of different risk levels of PWN outbreak indicated that high-risk level areas were the easiest to monitor and identify, while lower incidence areas were identified with relatively low accuracy. The overall accuracy of the risk level of the PWN outbreak was identified with an AUC value of 0.94. From the research findings, remote sensing data combined with GIS data can accurately predict the probability distribution of the occurrence of PWN disease. The accuracy of identification of high-risk areas is higher than other risk levels, and the results of the study may improve control of PWN disease spread. [ABSTRACT FROM AUTHOR]

Remote sensing technologies can accurately capture environmental characteristics, and together with environmental modeling approaches, help to predict climate-sensitive infectious disease outbreaks. Brucellosis remains rampant worldwide in both domesticated animals and humans. This study used human brucellosis (HB) as a test case to identify important environmental determinants of the disease and predict its outbreaks. A novel artificial neural network (ANN) model was developed, using annual county-level numbers of HB cases and data on 37 environmental variables, potentially associated with HB in Inner Mongolia, China. Data from 2006 to 2008 were used to train, validate and test the model, while data for 2009–2010 were used to assess the model’s performance. The Enhanced Vegetation Index was identified as the most important predictor of HB incidence, followed by land surface temperature and other temperature- and precipitation-related variables. The suitable ecological niche of HB was modeled based on these predictors. Model estimates were found to be in good agreement with reported numbers of HB cases in both the model development and assessment phases. The study suggests that HB outbreaks may be predicted, with a reasonable degree of accuracy, using the ANN model and environmental variables obtained from satellite data. The study deepened the understanding of environmental determinants of HB and advanced the methodology for prediction of climate-sensitive infectious disease outbreaks. [ABSTRACT FROM AUTHOR]

Guangzhou has experienced a rapid urbanization since 1978 when China initiated the economic reform, resulting in significant land use/cover changes (LUC). To produce a time series of accurate LUC dataset that can be used to study urbanization and its impacts, Landsat imagery was used to map LUC changes in Guangzhou from 1987 to 2015 at a three-year interval using a multiple classifier system (MCS). The system was based on a weighted vector to combine base classifiers of different classification algorithms, and was improved using the AdaBoost technique. The new classification method used support vector machines (SVM), C4.5 decision tree, and neural networks (ANN) as the training algorithms of the base classifiers, and produced higher overall classification accuracy (88.12%) and Kappa coefficient (0.87) than each base classifier did. The results of the experiment showed that, based on the accuracy improvement of each class, the overall accuracy was improved effectively, which combined advantages from each base classifier. The new method is of high robustness and low risk of overfitting, and is reliable and accurate, and could be used for analyzing urbanization processes and its impacts. [ABSTRACT FROM AUTHOR]

Enhanced methods are required for mapping the forest aboveground biomass (AGB) over a large area in Chinese forests. This study attempted to develop an improved approach to retrieving biomass by combining PALSAR (Phased Array type L-band Synthetic Aperture Radar) and WorldView-2 data. A total of 33 variables with potential correlations with forest biomass were extracted from the above data. However, these parameters had poor fits to the observed biomass. Accordingly, the synergies of several variables were explored to identify improved relationships with the AGB. Using principal component analysis and multivariate linear regression (MLR), the accuracies of the biomass estimates obtained using PALSAR and WorldView-2 data were improved to approximately 65% to 71%. In addition, using the additional dataset developed from the fusion of FBD (fine beam dual-polarization) and WorldView-2 data improved the performance to 79% with an RMSE (root mean square error) of 35.13 Mg/ha when using the MLR method. Moreover, a further improvement (R2 = 0.89, relative RMSE = 17.08%) was obtained by combining all the variables mentioned above. For the purpose of comparison with MLR, a neural network approach was also used to estimate the biomass. However, this approach did not produce significant improvements in the AGB estimates. Consequently, the final MLR model was recommended to map the AGB of the study area. Finally, analyses of estimated error in distinguishing forest types and vertical structures suggested that the RMSE decreases gradually from broad-leaved to coniferous to mixed forest. In terms of different vertical structures (VS), VS3 has a high error because the forest lacks undergrowth trees, while VS4 forest, which has approximately the same amounts of stems in each of the three DBH (diameter at breast height) classes (DBH > 20, 10 ≤ DBH ≤ 20, and DBH < 10 cm), has the lowest RMSE. This study demonstrates that the combination of PALSAR and WorldView-2 data is a promising approach to improve biomass estimation. [ABSTRACT FROM AUTHOR]

Ionospheric delay is a critical error source in Global Navigation Satellite Systems (GNSSs) and a principal aspect of Satellite Based Augmentation System (SBAS) corrections. Grid Ionospheric Vertical Delays (GIVDs) are derived from the delays on Ionosphere Pierce Points (IPPs), which are observed by SBAS reference stations. SBAS master stations calculate ionospheric delay corrections by several methods, such as planar fit or Kriging. However, when there are not enough IPPs around an Ionosphere Grid Point (IGP) or the IPPs are unevenly distributed, the fitting accuracy of planar fit or Kriging is unsatisfactory. Moreover, the integrity bounds of Grid Ionospheric Vertical Errors (GIVEs) are overly conservative. Since Artificial Neural Networks (ANNs) are widely used in ionospheric research due to their self-adaptation, parallelism, non-linearity, robustness, and learnability, the ANN method for GIVD and GIVE derivation is proposed in this article. Networks are separately trained for IGPs, and five years of historical data are applied on network training. Principal Component Analysis (PCA) is applied for dimensionality reduction of geomagnetic and solar indices, which is employed as a network input feature. Furthermore, the GIVE algorithm of the ANN method is derived based on the distribution of the residual random variable. Finally, experiments are conducted on 12 IGPs over the East China region. Under normal ionospheric conditions, compared with the planar fit and Kriging methods, the residual reduction of the ANN method is approximately 15%. The ANN method fits the ionospheric delay residual error better. The percentage of GIVE availability under 2.7 m increases at least 25 points in comparison to Kriging. Under disturbed conditions, due to a lack of training samples, the ANN method is incompetent compared with planar fit or Kriging. [ABSTRACT FROM AUTHOR]

Soil moisture is a key parameter for land-atmosphere interaction system; however, fewer existing spatial-temporally continuous and high-quality observation records impose great limitations on the application of soil moisture on long term climate change monitoring and predicting. Therefore, this study selected the Qinghai–Tibet Plateau (QTP) of China as research region, and explored the feasibility of using Artificial Neural Network (ANN) to reconstruct soil moisture product based on AMSR-2/AMSR-E brightness temperature and SMAP satellite data by introducing auxiliary variables, specifically considering the sensitivity of different combination of input variables, number of neurons in hidden layer, sample ratio, and precipitation threshold in model building. The results showed that the ANN model had the highest accuracy when all variables were used as inputs, it had a network containing 12 neurons in a hidden layer, it had a sample ratio 80%-10%-10% (training-validation-testing), and had a precipitation threshold of 8.75 mm, respectively. Furthermore, validation of the reconstructed soil moisture product (named ANN-SM) in other period were conducted by comparing with SMAP (April 2019 to July 2021) for all grid cells and in situ soil moisture sites (August 2010 to March 2015) of QTP, which achieved an ideal accuracy. In general, the proposed method is capable of rebuilding soil moisture products by adopting different satellite data and our soil moisture product is promising for serving the studies of long-term global and regional dynamics in water cycle and climate. [ABSTRACT FROM AUTHOR]

The Qaidam Basin is a unique and complex ecosystem, wherein elevation gradients lead to high spatial heterogeneity in vegetation dynamics and responses to environmental factors. Based on the remote sensing data of Moderate Resolution Imaging Spectroradiometer (MODIS), Tropical Rainfall Measuring Mission (TRMM) and Global Land Data Assimilation System (GLDAS), we analyzed the spatiotemporal variations of vegetation dynamics and responses to precipitation, accumulative temperature (AT) and soil moisture (SM) in the Qaidam Basin from 2001 to 2016. Moreover, the contribution of those factors to vegetation dynamics at different altitudes was analyzed via an artificial neural network (ANN) model. The results indicated that the Normalized Difference Vegetation Index (NDVI) values in the growing season showed an overall upward trend, with an increased rate of 0.001/year. The values of NDVI in low-altitude areas were higher than that in high-altitude areas, and the peak values of NDVI appeared along the elevation gradient at 4400–4600 m. Thanks to the use of ANN, we were able to detect the relative contribution of various environmental factors; the relative contribution rate of AT to the NDVI dynamic was the most significant (35.17%) in the low-elevation region (<2900 m). In the mid-elevation area (2900–3900 m), precipitation contributed 44.76% of the NDVI dynamics. When the altitude was higher than 3900 m, the relative contribution rates of AT (39.50%) and SM (38.53%) had no significant difference but were significantly higher than that of precipitation (21.97%). The results highlight that the different environmental factors have various contributions to vegetation dynamics at different altitudes, which has important theoretical and practical significance for regulating ecological processes. [ABSTRACT FROM AUTHOR]

Wheat yellow rust has a severe impact on wheat production and threatens food security in China; as such, an effective monitoring method is necessary at the regional scale. We propose a model for yellow rust monitoring based on Sentinel-2 multispectral images and a series of two-stage vegetation indices and meteorological data. Sensitive spectral vegetation indices (single- and two-stage indices) and meteorological features for wheat yellow rust discrimination were selected using the random forest method. Wheat yellow rust monitoring models were established using three different classification methods: linear discriminant analysis (LDA), support vector machine (SVM), and artificial neural network (ANN). The results show that models based on two-stage indices (i.e., those calculated using images from two different days) significantly outperform single-stage index models (i.e., those calculated using an image from a single day), the overall accuracy improved from 63.2% to 78.9%. The classification accuracies of models combining a vegetation index with meteorological feature are higher than those of pure vegetation index models. Among them, the model based on two-stage vegetation indices and meteorological features performs best, with a classification accuracy exceeding 73.7%. The SVM algorithm performed best for wheat yellow rust monitoring among the three algorithms; its classification accuracy (84.2%) was ~10.5% and 5.3% greater than those of LDA and ANN, respectively. Combined with crop growth and environmental information, our model has great potential for monitoring wheat yellow rust at a regional scale. Future work will focus on regional-scale monitoring and forecasting of crop disease. [ABSTRACT FROM AUTHOR]

Forest canopy height is an indispensable forest vertical structure parameter for understanding the carbon cycle and forest ecosystem services. A variety of studies based on spaceborne Lidar, such as ICESat, ICESat-2 and airborne Lidar, were conducted to estimate forest canopy height at multiple scales. However, while a few studies have been conducted based on ICESat-2 simulated data from airborne Lidar data, few studies have analyzed ATL08 and ATL03 products derived from the ATLAS sensor onboard ICESat-2 for regional vegetation canopy height mapping. It is necessary and promising to explore how data obtained by ICESat-2 can be applied to estimate forest canopy height. This study proposes a new means to estimate forest canopy height, defined as the mean height of trees within a given forest area, using a combination of ICESat-2 ATL08 and ATL03 data and ZY-3 satellite stereo images. Five procedures were used to estimate the forest canopy height of the city of Nanning in China: (1) Processing ground photons in a 30 m × 30 m grid; (2) Extracting a digital surface model (DSM) using ZY-3 stereo images; (3) Calculating a discontinuous canopy height model (CHM) dataset; (4) Validating the DSM and ground photon height using GEDI data; (5) Estimating the regional wall-to-wall forest canopy height product based on the backpropagation artificial neural network (BP-ANN) model and Landsat 8 vegetation indices and independent accuracy assessments with field measured plots. The validation shows a root mean square error (RMSE) of 3.34 m to 3.47 m and a coefficient of determination R2 = 0.51. The new method shows promise and can be used for large-scale forest canopy height mapping at various resolutions or in combination with other data, such as SAR images. Finally, this study analyzes resolutions and how to filter effective data when ATL08 data are directly used to generate regional or global vegetation height products, which will be the focus of future research. [ABSTRACT FROM AUTHOR]

Spaceborne Global Navigation Satellite System Reflectometry (GNSS-R) provides a new opportunity for land observation. This study is the first to compare and evaluate the performance of the only two spaceborne GNSS-R satellite missions whose data are publicly available, i.e., the UK's TechdemoSat-1 (TDS-1) and the US's Cyclone Global Navigation Satellite System (CYGNSS), for sensitivity analysis with SMAP SM on a daily basis and soil moisture (SM) estimates on a monthly basis over Mainland China. For daily sensitivity analysis, the two data were matched up and compared for the period (i.e., May 2017 through April 2018) when they coexisted (R = 0.561 vs. R = 0.613). For monthly SM estimates, a back-propagation artificial neural network (BP-ANN) was used to construct a model using data from more than two years. The model was subsequently used to derive long-term and continuous SM maps over Mainland China. The results showed that TDS-1 and CYGNSS agree and correlate very well with the SMAP SM in Mainland China (R = 0.676, MAE = 0.052 m3m−3, and ubRMSE = 0.060 m3m−3 for TDS-1; R = 0.798, MAE = 0.040 m3m−3, and ubRMSE = 0.062 m3m−3 for CYGNSS). The retrieved results were further validated using monthly in situ SM data from dense sites across Mainland China. It was found that the SM derived from the TDS-1/CYGNSS also correlated well with in situ SM (R = 0.687, MAE = 0.066 m3m−3, and ubRMSE = 0.056 m3m−3 for TDS-1; R = 0.724, MAE = 0.052 m3m−3, and ubRMSE = 0.053 m3m−3 for CYGNSS). The results in this study suggested that TDS-1/CYGNSS and the upcoming spaceborne GNSS-R mission could be new and powerful data sources to produce SM data set at a large scale and with relatively high precision. [ABSTRACT FROM AUTHOR]

Improving the accuracy of edge pixel classification is crucial for extracting the winter wheat spatial distribution from remote sensing imagery using convolutional neural networks (CNNs). In this study, we proposed an approach using a partly connected conditional random field model (PCCRF) to refine the classification results of RefineNet, named RefineNet-PCCRF. First, we used an improved RefineNet model to initially segment remote sensing images, followed by obtaining the category probability vectors for each pixel and initial pixel-by-pixel classification result. Second, using manual labels as references, we performed a statistical analysis on the results to select pixels that required optimization. Third, based on prior knowledge, we redefined the pairwise potential energy, used a linear model to connect different levels of potential energies, and used only pixel pairs associated with the selected pixels to build the PCCRF. The trained PCCRF was then used to refine the initial pixel-by-pixel classification result. We used 37 Gaofen-2 images obtained from 2018 to 2019 of a representative Chinese winter wheat region (Tai'an City, China) to create the dataset, employed SegNet and RefineNet as the standard CNNs, and a fully connected conditional random field as the refinement methods to conduct comparison experiments. The RefineNet-PCCRF's accuracy (94.51%), precision (92.39%), recall (90.98%), and F1-Score (91.68%) were clearly superior than the methods used for comparison. The results also show that the RefineNet-PCCRF improved the accuracy of large-scale winter wheat extraction results using remote sensing imagery. [ABSTRACT FROM AUTHOR]

Optimizing nitrogen (N) management in rice is crucial for China's food security and sustainable agricultural development. Nondestructive crop growth monitoring based on remote sensing technologies can accurately assess crop N status, which may be used to guide the in-season site-specific N recommendations. The fixed-wing unmanned aerial vehicle (UAV)-based remote sensing is a low-cost, easy-to-operate technology for collecting spectral reflectance imagery, an important data source for precision N management. The relationships between many vegetation indices (VIs) derived from spectral reflectance data and crop parameters are known to be nonlinear. As a result, nonlinear machine learning methods have the potential to improve the estimation accuracy. The objective of this study was to evaluate five different approaches for estimating rice (Oryza sativa L.) aboveground biomass (AGB), plant N uptake (PNU), and N nutrition index (NNI) at stem elongation (SE) and heading (HD) stages in Northeast China: (1) single VI (SVI); (2) stepwise multiple linear regression (SMLR); (3) random forest (RF); (4) support vector machine (SVM); and (5) artificial neural networks (ANN) regression. The results indicated that machine learning methods improved the NNI estimation compared to VI-SLR and SMLR methods. The RF algorithm performed the best for estimating NNI (R2 = 0.94 (SE) and 0.96 (HD) for calibration and 0.61 (SE) and 0.79 (HD) for validation). The root mean square errors (RMSEs) were 0.09, and the relative errors were <10% in all the models. It is concluded that the RF machine learning regression can significantly improve the estimation of rice N status using UAV remote sensing. The application machine learning methods offers a new opportunity to better use remote sensing data for monitoring crop growth conditions and guiding precision crop management. More studies are needed to further improve these machine learning-based models by combining both remote sensing data and other related soil, weather, and management information for applications in precision N and crop management. [ABSTRACT FROM AUTHOR]

Two back-propagation artificial neural network retrieval models have been developed for obtaining the dust aerosol optical depth (AOD) and dust-top height (DTH), respectively, from Atmospheric InfraRed Sounder (AIRS) brightness temperature (BT) measurements over Taklimakan Desert area. China Aerosol Remote Sensing Network (CARSNET) measurements at Tazhong station were used for dust AOD validation. Results show that the correlation coefficient of dust AODs between AIRS and CARSNET reaches 0.88 with a deviation of −0.21, which is the same correlation coefficient as the AIRS dust AOD and the Moderate-Resolution Imaging Spectroradiometer (MODIS) aerosol optical depth (AOD) product. In the AIRS DTH retrieval model, there is an option to include the collocated MODIS deep blue (DB) AOD as additional input for daytime retrieval; the independent dust heights from Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) are used for AIRS DTH validation, and results show that the DTHs derived from the combined AIRS BT measurements and MODIS DB AOD product have better accuracy than those from AIRS BT measurements alone. The correlation coefficient of DTHs between AIRS and independent CALIOP dust heights is 0.79 with a standard deviation of 0.41 km when MODIS DB AOD product is included in the retrieval model. A series of case studies from different seasons were examined to demonstrate the feasibility of retrieving dust parameters from AIRS and potential applications. The method and approaches can be applied to process measurements from advanced infrared (IR) sounder and high-resolution imager onboard the same platform. [ABSTRACT FROM AUTHOR]

Timely and accurate estimation of the area and distribution of crops is vital for food security. Optical remote sensing has been a key technique for acquiring crop area and conditions on regional to global scales, but great challenges arise due to frequent cloudy days in southern China. This makes optical remote sensing images usually unavailable. Synthetic aperture radar (SAR) could bridge this gap since it is less affected by clouds. The recent availability of Sentinel-1A (S1A) SAR imagery with a 12-day revisit period at a high spatial resolution of about 10 m makes it possible to fully utilize phenological information to improve early crop classification. In deep learning methods, one-dimensional convolutional neural networks (1D CNNs), long short-term memory recurrent neural networks (LSTM RNNs), and gated recurrent unit RNNs (GRU RNNs) have been shown to efficiently extract temporal features for classification tasks. However, due to the complexity of training, these three deep learning methods have been less used in early crop classification. In this work, we attempted to combine them with an incremental classification method to avoid the need for training optimal architectures and hyper-parameters for data from each time series. First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images' time series to attain three classifiers with optimal architectures and hyper-parameters. Then, starting at the first time point, we performed an incremental classification process to train each classifier using all of the previous data, and obtained a classification network with all parameter values (including the hyper-parameters) at each time point. Finally, test accuracies of each time point were assessed for each crop type to determine the optimal time series length. A case study was conducted in Suixi and Leizhou counties of Zhanjiang City, China. To verify the effectiveness of this method, we also implemented the classic random forest (RF) approach. The results were as follows: (i) 1D CNNs achieved the highest Kappa coefficient (0.942) of the four classifiers, and the highest value (0.934) in the GRU RNNs time series was attained earlier than with other classifiers; (ii) all three deep learning methods and the RF achieved F measures above 0.900 before the end of growth seasons of banana, eucalyptus, second-season paddy rice, and sugarcane; while, the 1D CNN classifier was the only one that could obtain an F-measure above 0.900 for pineapple before harvest. All results indicated the effectiveness of the solution combining the deep learning models with the incremental classification approach for early crop classification. This method is expected to provide new perspectives for early mapping of croplands in cloudy areas. [ABSTRACT FROM AUTHOR]

Grape is an economic crop of great importance and is widely cultivated in China. With the development of remote sensing, abundant data sources strongly guarantee that researchers can identify crop types and map their spatial distributions. However, to date, only a few studies have been conducted to identify vineyards using satellite image data. In this study, a vineyard is identified using satellite images, and a new approach is proposed that integrates the continuous wavelet transform (CWT) and a convolutional neural network (CNN). Specifically, the original time series of the normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), and green chlorophyll vegetation index (GCVI) are reconstructed by applying an iterated Savitzky-Golay (S-G) method to form a daily time series for a full year; then, the CWT is applied to three reconstructed time series to generate corresponding scalograms; and finally, CNN technology is used to identify vineyards based on the stacked scalograms. In addition to our approach, a traditional and common approach that uses a random forest (RF) to identify crop types based on multi-temporal images is selected as the control group. The experimental results demonstrated the following: (i) the proposed approach was comprehensively superior to the RF approach; it improved the overall accuracy by 9.87% (up to 89.66%); (ii) the CWT had a stable and effective influence on the reconstructed time series, and the scalograms fully represented the unique time-related frequency pattern of each of the planting conditions; and (iii) the convolution and max pooling processing of the CNN captured the unique and subtle distribution patterns of the scalograms to distinguish vineyards from other crops. Additionally, the proposed approach is considered as able to be applied to other practical scenarios, such as using time series data to identify crop types, map landcover/land use, and is recommended to be tested in future practical applications. [ABSTRACT FROM AUTHOR]

Deep learning methods used for hyperspectral image (HSI) classification often achieve greater accuracy than traditional algorithms but require large numbers of training epochs. To simplify model structures and reduce their training epochs, an end-to-end deep learning framework incorporating a spectral-spatial cascaded 3D convolutional neural network (CNN) with a convolutional long short-term memory (CLSTM) network, called SSCC, is proposed herein for HSI classification. The SSCC framework employs cascaded 3D CNN to learn the spectral-spatial features of HSIs and uses the CLSTM network to extract sequence features. Residual connections are used in SSCC to accelerate model convergence, with the outputs of previous convolutional layers concatenated as inputs for subsequent layers. Moreover, the data augmentation, parametric rectified linear unit, dynamic learning rate, batch normalization, and regularization (including dropout and L2) methods are used to increase classification accuracy and prevent overfitting. These attributes allow the SSCC framework to achieve good performance for HSI classification within 20 epochs. Three well-known datasets including Indiana Pines, University of Pavia, and Pavia Center were employed to evaluate the classification performance of the proposed algorithm. The GF-5 dataset of Anxin County, obtained from China's recently launched spaceborne Advanced Hyperspectral Imager, was also used for classification experiments. The experimental results demonstrate that the proposed SSCC framework achieves state-of-the-art performance with better training efficiency than other deep learning methods. [ABSTRACT FROM AUTHOR]