Search

Temperature is a crucial indicator for studying climate, as well as the social and economic changes in a region. Temperature reanalysis products, such as ERA5-Land, have been widely used in studying temperature change. However, global-scale temperature reanalysis products have errors because they overlook the influence of multiple factors on temperature, and this issue is more obvious in smaller areas. During the cold months (January, February, March, November, and December) in the Yellow River Basin, ERA5-Land products exhibit significant errors compared to temperatures observed by meteorological stations, typically underestimating the temperature. This study proposes improving temperature reanalysis products using deep learning and multi-source remote sensing and geographic data fusion. Specifically, convolutional neural networks (CNN) and bidirectional long short-term memory networks (BiLSTM) capture the spatial and temporal relationships between temperature, DEM, land cover, and population density. A deep spatiotemporal model is established to enhance temperature reanalysis products, resulting in higher resolution and more accurate temperature data. A comparison with the measured temperatures at meteorological stations indicates that the accuracy of the improved ERA5-Land product has been significantly enhanced, with the mean absolute error (MAE) reduced by 28.7% and the root mean square error (RMSE) reduced by 25.8%. This method obtained a high-precision daily temperature dataset with a 0.05° resolution for cold months in the Yellow River Basin from 2015 to 2019. Based on this dataset, the annual trend of average temperature changes during the cold months in the Yellow River Basin was analyzed. This study provides a scientific basis for improving ERA5-Land temperature reanalysis products in the Yellow River Basin and offers theoretical support for climate change research in the region.

Typhoons are destructive weather events. News media reports contain large amounts of typhoon information. Transforming this information into useful knowledge to provide a basis for mining typhoon knowledge and supporting disaster prevention and relief is urgently required to solve this problem. Knowledge representation can be used to address this problem, although it presents several challenges. These challenges lie in expressing the static and dynamic characteristics of typhoons and formalizing the knowledge representation method and making it suitable for machine processing. Moreover, the general Chinese time and space representation method is overly cumbersome for use in ontologies. The present study proposes an ontology-based typhoon event representation method that solves the representation problems of the typhoon static concept and dynamic features. Furthermore, it summarizes the fixed patterns of time and space in Chinese news and designs a time and space model suitable for typhoon event ontologies. From the ontology population, typhoon event ontology instances are created, and the typhoon event ontology model is applied to the analysis of typhoon processes, verifying the effectiveness of the typhoon event ontology model.

The Yan River Basin of the Loess Plateau is a key region for ensuring the environmental protection and sustainable development of the Yellow River Basin. Therefore, it is essential to identify how vegetation cover has changed and determine the factors that have driven these changes. In this study, we applied a three-dimensional vegetation cover model to examine the spatiotemporal variation characteristics of vegetation cover at the watershed scale in the Yan River Basin from 2001 to 2020 and forecast future trends. Subsequently, the driving forces of fractional vegetation cover (FVC) change were quantified based on meteorological, surface, and anthropogenic factors to explore the common driving relationships among these factors. (1) The accuracy of 3DFVC is better than that of FVC in the Yanhe River Basin, where the terrain is complex. (2) The temporal change trends indicated that the vegetation cover in the Yan River Basin significantly recovered and the basin FVC increased rapidly from 2001 to 2013 (S = 0.0152/a, p < 0.01) and increased gradually from 2013 to 2020 (S = 0.0015/a). The main reason for the increase in vegetation cover was the enhanced growth of medium FVC. (3) The vegetation spatial distribution showed that the FVC values varied substantially from north to south, indicating spatial heterogeneity, and 83.9% of the area presented a trend of increasing vegetation. Furthermore, vegetation cover was predicted to improve in the future. (4) The spatial heterogeneity of FVC was mainly influenced by relative humidity and rainfall, and the spatial variations in FVC were mainly determined by climate factors. Land use and cover change variations, which are influenced by human activities, represent major factors underlying the observed spatial heterogeneity. Most interactions between driving factors showed two-way enhancement or non-linear enhancement, with relative humidity and land use patterns presenting the strongest explanatory power. This study provides a scientific basis for vegetation conservation in the Yan River Basin and contributes theoretical support for decision-making regarding ecological environmental protection in the Loess Plateau and sustainable development in the Yellow River Basin.

Land use simulations are critical in predicting the impact of land use change (LUC) on the Earth. Various assumptions and policies influence land use structure and are a key factor in decisions made by policymakers. Meanwhile, the spatial autocorrelation effect between land use types has rarely been considered in existing land use spatial simulation models, and the simulation accuracy needs to be further improved. Thus, in this study, the driving mechanisms of LUC are analyzed. The quantity demand and spatial distribution of land use are predicted under natural development (ND), economic development (ED), ecological protection (EP), and sustainability development (SD) scenarios in Zhengzhou based on the coupled Multi-Objective Programming (MOP) model and the Patch-generating Land Use Simulation model (PLUS) considering Spatial Autocorrelation (PLUS-SA). We conclude the following. (1) The land use type in Zhengzhou was mainly cultivated land, and 83.85% of the land for urban expansion was cultivated land from 2000 to 2020. The reduction in forest from 2010 to 2020 was less than that from 2000 to 2010 due to the implementation of the policy in which farmland is transformed back into forests. (2) The accuracy of PLUS-SA was better than that of the traditional PLUS and Future Land Use Simulation (FLUS) models, and its Kappa coefficient, overall accuracy, and FOM were 0.91, 0.95, and 0.29, respectively. (3) Natural factors (temperature, precipitation, and DEM) contributed significantly to the expansion of cultivated land, and the increase in forest, grass, and construction land was greatly affected by socioeconomic factors (population, GDP, and proximity to town). (4) The land use structure will be more in line with the current requirements for sustainable urban development in the SD scenario, and the economic and ecological benefits will increase by 0.75 × 104 billion CNY and 1.71 billion CNY, respectively, in 2035 compared with those in 2020. The PLUS-SA model we proposed had higher simulation accuracy in Zhengzhou Compared with the traditional PLUS and FLUS models, and our research framework can provide a basis for decision-makers to formulate sustainable land use development policies to achieve high-quality and sustainable urban development.

Blue–green space refers to blue space (rivers and lakes) and green space (lawns and trees), which have the cooling island effect and are increasingly acknowledged as a potential and effective way to help alleviate the urban heat island effect. Scientific and flexible blue–green space planning is required, especially for medium- and large-scale urban agglomerations in the face of climate change. However, the temporal evolution and spatial patterns of the cooling island effect in the blue–green space under different future scenarios of climate change have not been fully investigated. This would impede long-term urban strategies for climate change adaptation and resilience. Here we studied the relationship between future climate change and blue–green spatial layout with Weather Research and Forecasting (WRF), based on the numerical simulation data of 15 global climate models under different extreme Shared Socioeconomic Pathway (SSP) scenarios. As a result, future changes in urban cooling island (UCI) magnitudes were estimated between historical (2015–2020) and future timelines: 2030s (2021–2040), 2050s (2041–2060), 2070s (2061–2080), and 2090s (2081–2100). Our results showed different land use types in blue and green space across the study area were predicted to present various changes in the next 80 years, with forest, grassland, and arable land experiencing the most significant land use transfer. The future UCI intensity of cities under SPP5-8.5 (12) was found to be lower than that under SPP2-4.5 (15), indicating that cities may be expected to experience decreases in UCI magnitudes in the future under SSP5-8.5. When there is no expansion of urban development land, we found that the conversion of different land use types into blue and green space leads to little change in future UCI intensity. While the area growth of forests and water bodies is proportional to the increase in UCI, the increase of farmland was observed to have the most significant impact on reducing the amplitude of urban UCI. Given that Huai’an City, Yancheng City, and Yangzhou City have abundant blue–green space, the urban cooling island effect was projected to be more significant than that of other cities in the study area under different SSP scenarios. The simulation results of the WRF model indicate that optimizing the layout of urban blue–green space plays an important role in modulating the urban thermal environment.

The mitigation of the urban heat island effect is increasingly imperative in light of climate change. Blue–green space, integrating water bodies and green spaces, has been demonstrated to be an effective strategy for reducing the urban heat island effect and enhancing the urban environment. However, there is a lack of coupled analysis on the cooling island effect of blue–green space at the meso-micro scale, with previous studies predominantly focusing on the heat island effect. This study coupled the single urban canopy model (UCM) with the mesoscale Weather Research and Forecasting (WRF) numerical model to simulate the cooling island effect of blue–green space in the Eastern Sea-River-Stream-Lake Linkage Zone (ESLZ) within the northern subtropical zone. In particular, we comparatively investigated the cooling island effect of micro-scale blue–green space via three mitigation strategies of increasing vegetation, water bodies, and coupling blue–green space, using the temperature data at the block scale within 100 m square of the urban center on the hottest day in summer. Results showed that the longitudinally distributed lakes and rivers in the city had a significant cooling effect on the ambient air temperature (Ta) at the mesoscale, with the largest cooling range occurring during the daytime and ranging from 1.01 to 2.15 °C. In contrast, a 5~20% increase in vegetation coverage or 5~15% increase in water coverage at the micro-scale was observed to reduce day and night Ta by 0.71 °C. Additionally, the most significant decrease in physiologically equivalent temperature (PET) was found in the mid-rise building environment, with a reduction of 2.65–3.26 °C between 11:00 and 13:00 h, and an average decrease of 1.25°C during the day. This study aims to guide the optimization of blue–green space planning at the meso-micro scale for the fast-development and expansion of new urban agglomerations.

Transformer models have achieved great results in the field of computer vision over the past 2 years, drawing attention from within the field of remote sensing. However, there are still relatively few studies on this model in the field of remote sensing. Which method is more suitable for remote-sensing segmentation? In particular, how do different transformer models perform in the face of high-spatial resolution and the multispectral resolution of remote-sensing images? To explore these questions, this paper presents a comprehensive comparative analysis of three mainstream transformer models, including the segmentation transformer (SETRnet), SwinUnet, and TransUnet, by evaluating three aspects: a visual analysis of feature-segmentation results, accuracy, and training time. The experimental results show that the transformer structure has obvious advantages for the feature-extraction ability of large-scale remote-sensing data sets and ground objects, but the segmentation performance of different transfer structures in different scales of remote-sensing data sets is also very different. SwinUnet exhibits better global semantic interaction and pixel-level segmentation prediction on the large-scale Potsdam data set, and the SwinUnet model has the highest accuracy metrics for KAPPA, MIoU, and OA in the Potsdam data set, at 76.47%, 63.62%, and 85.01%, respectively. TransUnet has better segmentation results in the small-scale Vaihingen data set, and the three accuracy metrics of KAPPA, MIoU, and OA are the highest, at 80.54%, 56.25%, and 85.55%, respectively. TransUnet is better able to handle the edges and details of feature segmentation thanks to the network structure together built by its transformer and convolutional neural networks (CNNs). Therefore, TransUnet segmentation accuracy is higher when using a small-scale Vaihingen data set. Compared with SwinUnet and TransUnet, the segmentation performance of SETRnet in different scales of remote-sensing data sets is not ideal, so SETRnet is not suitable for the research task of remote-sensing image segmentation. In addition, this paper discusses the reasons for the performance differences between transformer models and discusses the differences between transformer models and CNN. This study further promotes the application of transformer models in remote-sensing image segmentation, improves the understanding of transformer models, and helps relevant researchers to select a more appropriate transformer model or model improvement method for remote-sensing image segmentation.

High-quality urban land-use maps are essential for grasping the dynamics and scale of urban land use, predicting future environmental trends and changes, and allocating national land resources. This paper proposes a multisample “voting mechanism” based on multisource data and random forests to achieve fine mapping of urban land use. First, Zhengzhou City was selected as the study area. Based on full integration of multisource features, random forests were used to perform the preliminary classification of multiple samples. Finally, the preliminary classification results were filtered according to the “voting mechanism” to achieve high-precision urban land-use classification mapping. The results showed that the overall classification accuracy of Level I features increased by 5.66% and 14.32% and that the overall classification accuracy of Level II features increased by 9.02% and 12.46%, respectively, compared with the classification results of other strategies. Therefore, this method can significantly reduce the influence of mixed distribution of land types and improve the accuracy of urban land-use classification at a fine scale.

The performance of deep neural networks depends on the accuracy of labeled samples, as they usually contain label noise. This study examines the semantic segmentation of remote sensing images that include label noise and proposes an anti-label-noise network framework, termed Labeled Noise Robust Network in Remote Sensing Image Semantic Segmentation (NRN-RSSEG), to combat label noise. The algorithm combines three main components: network, attention mechanism, and a noise-robust loss function. Three different noise rates (containing both symmetric and asymmetric noise) were simulated to test the noise resistance of the network. Validation was performed in the Vaihingen region of the ISPRS Vaihingen 2D semantic labeling dataset, and the performance of the network was evaluated by comparing the NRN-RSSEG with the original U-Net model. The results show that NRN-RSSEG maintains a high accuracy on both clean and noisy datasets. Specifically, NRN-RSSEG outperforms UNET in terms of PA, MPA, Kappa, Mean_F1, and FWIoU in the presence of noisy datasets, and as the noise rate increases, each performance of UNET shows a decreasing trend while the performance of NRN-RSSEG decreases slowly and some performances show an increasing trend. At a noise rate of 0.5, the PA (−6.14%), MPA (−4.27%) Kappa (−8.55%), Mean_F1 (−5.11%), and FWIOU (−9.75%) of UNET degrade faster; while the PA (−2.51%), Kappa (−3.33%), and FWIoU of NRN-RSSEG (−3.26) degraded more slowly, MPA (+1.41) and Mean_F1 (+2.69%) showed an increasing trend. Furthermore, comparing the proposed model with the baseline method, the results demonstrate that the proposed NRN-RSSEG anti-noise framework can effectively help the current segmentation model to overcome the adverse effects of noisy label training.

Frequent agricultural activities in farmland ecosystems bring challenges to crop information extraction from remote sensing (RS) imagery. The accurate spatiotemporal information of crops serves for regional decision support and ecological assessment, such as disaster monitoring and carbon sequestration. Most traditional machine learning algorithms are not appropriate for prediction classification due to the lack of historical ground samples and poor model transfer capabilities. Therefore, a transferable learning model including spatiotemporal capability was developed based on the UNet++ model by integrating feature fusion and upsampling of small samples for Sentinel-2A imagery. Classification experiments were conducted for 10 categories from 2019 to 2021 in Xinxiang City, Henan Province. The feature fusion and upsampling methods improved the performance of the UNet++ model, showing lower joint loss and higher mean intersection over union (mIoU) values. Compared with the UNet, DeepLab V3+, and the pyramid scene parsing network (PSPNet), the improved UNet++ model exhibits the best performance, with a joint loss of 0.432 and a mIoU of 0.871. Moreover, the overall accuracy and macro F1 values of prediction classification results based on the UNet++ model are higher than 83% and 58%, respectively. Based on the reclassification rules, about 3.48% of the farmland was damaged in 2021 due to continuous precipitation. The carbon sequestration of five crops (including corn, peanuts, soybean, rice, and other crops) is estimated, with a total carbon sequestration of 2460.56, 2549.16, and 1814.07 thousand tons in 2019, 2020, and 2021, respectively. The classification accuracy indicates that the improved model exhibits a better feature extraction and transferable learning capability in complex agricultural areas. This study provides a strategy for RS semantic segmentation and carbon sequestration estimation of crops based on a deep learning network.

Accurate urban boundary data can directly reflect the expansion of urban space, help us accurately grasp the scale and form of urban space, and play a vital role in urban land development and policy-making. However, the lack of reliable multiscale and high-precision urban boundary data products and relevant training datasets has become one of the major factors hindering their application. The purpose of this study is to combine Sentinel-2 remote-sensing images and supplementary geographic data to generate a reliable high-precision urban boundary dataset for Henan Province (called HNUB2018). First, this study puts forward a clear definition of “urban boundary”. Using this concept as its basis, it proposes a set of operable urban boundary delimitation rules and technical processes. Then, based on Sentinel-2 remote-sensing images and supplementary geographic data, the urban boundaries of Henan Province are delimited by a visual interpretation method. Finally, the applicability of the dataset is verified by using a classical semantic segmentation deep learning model. The results show that (1) HNUB2018 has clear and rich detailed features as well as a detailed spatial structure of urban boundaries. The overall accuracy of HNUB2018 is 92.82% and the kappa coefficient reaches 0.8553, which is better than GUB (Henan) in overall accuracy. (2) HNUB2018 is well suited for deep learning, with excellent reliability and scientific validity. The research results of this paper can provide data support for studies of urban sprawl monitoring and territorial spatial planning, and will support the development of reliable datasets for fields such as intelligent mapping of urban boundaries, showing prospects and possibilities for wide application in urban research.

Land use is used to reflect the expression of human activities in space, and land use classification is a way to obtain accurate land use information. Obtaining high-precision land use classification from remote sensing images remains a significant challenge. Traditional machine learning methods and image semantic segmentation models are unable to make full use of the spatial and contextual information of images. This results in land use classification that does not meet high-precision requirements. In order to improve the accuracy of land use classification, we propose a land use classification model, called DADNet-CRFs, that integrates an attention mechanism and conditional random fields (CRFs). The model is divided into two modules: the Dual Attention Dense Network (DADNet) and CRFs. First, the convolution method in the UNet network is modified to Dense Convolution, and the band-hole pyramid pooling module, spatial location attention mechanism module, and channel attention mechanism module are fused at appropriate locations in the network, which together form DADNet. Second, the DADNet segmentation results are used as a priori conditions to guide the training of CRFs. The model is tested with the GID dataset, and the results show that the overall accuracy of land use classification obtained with this model is 7.36% and 1.61% higher than FCN-8s and BiSeNet in classification accuracy, 11.95% and 1.81% higher in MIoU accuracy, and with a 9.35% and 2.07% higher kappa coefficient, respectively. The proposed DADNet-CRFs model can fully use the spatial and contextual semantic information of high-resolution remote sensing images, and it effectively improves the accuracy of land use classification. The model can serve as a highly accurate automatic classification tool for land use classification and mapping high-resolution images.

In order to resist bubble loading, anisotropic composite materials are the development direction of the future. The objective of this paper was to experimentally investigate the hydrodynamic performance of anisotropic laminate composite plates, with a focus on the effect of its anisotropic characteristics on single bubble migration. In these experiments, the bubble was generated in a transparent water tank filled with sufficiently degassed water by Joule heating at the connecting point of the electrodes through the discharge of a 6600 μF charge to 800 V, and a high-speed camera system with a recording speed of 40,000 frames per second was used to record the temporal evolution of bubble patterns and the dynamic responses of the laminated composite plates. The results are presented for two anisotropic cantilever composite beams with different ply angles, namely, 0° and 30°. Several variables, such as the shapes of the bubble, the curved trail of motion of the bubble center, bubble collapse time, and bubble initial standoff distances were extracted from the photographic images. The results showed that bubble migration near the 30° plate presents a curved bubble trail with an evident tilted angle during the collapse and rebound stages, which is very different from bubbles that all move vertically above the 0° plate. Furthermore, a characterization method for bubble migration was proposed to quantitatively describe the curved bubble trails and the deformation of the composite beams in temporal and spatial scales. This method shows that the curved bubble trails near the 30° plate are closely related to the dynamic response of composite beams, with a focus on the bending-twisting coupling effect.

The current study presents a detailed assessment of risk zones related to karst collapse in Wuhan by analytical hierarchy process (AHP) and logistic regression (LR) models. The results showed that the LR model was more accurate with an area under the receiver operating characteristic (ROC) curve of 0.911 compared to 0.812 derived from the AHP model. Both models performed well in identifying high-risk zones with only a 3% discrepancy in area. However, for the medium- and low-risk classes, although the spatial distribution of risk zoning results were similar between two approaches, the spatial extent of the risk areas varied between final models. The reliability of both methods were reduced significantly by excluding the InSAR-based ground subsidence map from the analysis, with the karst collapse presence falling into the high-risk zone being reduced by approximately 14%, and karst collapse absence falling into the karst area being increased by approximately 6.5% on the training samples. To evaluate the practicality of using only results from ground subsidence maps for the risk zonation, the results of AHP and LR are compared with a weighted angular distortion (WAD) method for karst risk zoning in Wuhan. We find that the areas with relatively large subsidence horizontal gradient values within the karst belts are generally spatially consistent with high-risk class areas identified by the AHP- and LR-based approaches. However, the WAD-based approach cannot be used alone as an ideal karst collapse risk assessment model as it does not include geological and natural factors into the risk zonation.

Accurate temporal land use mapping provides important and timely information for decision making for large-scale management of land and crop production. At present, temporal land cover and crop classifications within a study area have neglected the differences between subregions. In this paper, we propose a classification rule by integrating the terrain, time series characteristics, priority, and seasonality (TTPSR) with Sentinel-2 satellite imagery. Based on the time series of Normalized Difference Water Index (NDWI) and Vegetation Index (NDVI), a dynamic decision tree for forests, cultivation, urban, and water was created in Google Earth Engine (GEE) for each subregion to extract cultivated land. Then, with or without this cultivated land mask data, the original classification results for each subregion were completed based on composite image acquisition with five vegetation indices using Random Forest. During the post-reclassification process, a 4-bit coding rule based on terrain, type, seasonal rhythm, and priority was generated by analyzing the characteristics of the original results. Finally, statistical results and temporal mapping were processed. The results showed that feature importance was dominated by B2, NDWI, RENDVI, B11, and B12 over winter, and B11, B12, NDBI, B2, and B8A over summer. Meanwhile, the cultivated land mask improved the overall accuracy for multicategories (seven to eight and nine to 13 during winter and summer, respectively) in each subregion, with average ranges in the overall accuracy for winter and summer of 0.857–0.935 and 0.873–0.963, respectively, and kappa coefficients of 0.803–0.902 and 0.835–0.950, respectively. The analysis of the above results and the comparison with resampling plots identified various sources of error for classification accuracy, including spectral differences, degree of field fragmentation, and planting complexity. The results demonstrated the capability of the TTPSR rule in temporal land use mapping, especially with regard to complex crops classification and automated post-processing, thereby providing a viable option for large-scale land use mapping.

The study of the temporal and spatial evolution of wetland landscapes and its driving factors is an important reference for wetland ecological restoration and protection. This article utilized seven periods of land use data in Henan Province from 1980 to 2015 to extract the spatial distribution characteristics of wetlands and analyze the temporal and spatial changes of wetlands in Henan Province. Transfer matrix, landscape metrics, correlation analysis, and redundancy analysis were applied to calculate and analyze the transformation types and area of wetland resources between all consecutive periods, and then the main driving factors of wetland expansion/contraction were explored. First, the total wetland area in Henan Province increased by 28% from 1980 to 2015, and the increased wetland area was mainly constructed wetlands, including paddy field, reservoir and pond, and canal. Natural wetlands such as marsh, lake, and floodplain decreased by 74%. Marsh area declined the most during 1990–1995, and was mainly transformed into floodplain and “Others” because of agricultural reclamation, low precipitation, and low Yellow River runoff. The floodplain area dropped the most from 2005 to 2010, mainly converted to canals and “Others” because of reclamation, exploitation of groundwater, the construction of the South–to–North Water Transfer Project, and recreational land development. Second, the results of correlation analysis and redundancy analysis indicated that economic factors were positively correlated with the area of some constructed wetlands and negatively correlated with the area of some natural wetlands. Socioeconomic development was the main driving factors for changes in wetland types. The proportion of wetland habitat in Henan Province in 2015 was only 0.3%, which is low compared to the Chinese average of 2.7%. The government should pay more attention to the restoration of natural wetlands in Henan Province.

Accurately identifying and delineating urban boundaries are the premise for and foundation of the control of disorderly urban sprawl, which is helpful for us to accurately grasp the scale and form of cities, optimize the internal spatial structure and pattern of cities, and guide the expansion of urban spaces in the future. At present, the concept and delineation of urban boundaries do not follow a unified method or standard. However, many scholars have made use of multi-source remote sensing images of various scales and social auxiliary data such as point of interest (POI) data to achieve large-scale, high-resolution, and high-precision land cover mapping and impermeable water surface mapping. The accuracy of small- and medium-scale urban boundary mapping has not been improved to an obvious extent. This study uses multi-temporal Sentinel-2 high-resolution images and POI data that can reflect detailed features of human activities to extract multi-dimensional features and use random forests and mathematical morphology to map the urban boundaries of the city of Zhengzhou. The research results show that: (1) the urban construction land extraction model established with multi-dimensional features has a great improvement in accuracy; (2) when the training sample accounts for 65% of the sample data set, the urban construction land extraction model has the highest accuracy, reaching 96.25%, and the Kappa coefficient is 0.93; (3) the optimized boundary of structural elements with a size of 13 × 13 is selected, which is in good agreement in terms of scope and location with the boundary of FROM-GLC10 (Zhengzhou) and visual interpretations. The results from the urban boundary delineation in this paper can be used as an important database for detailed basic land use mapping within cities. Moreover, the method in this paper has some reference value for other cities in terms of delineating urban boundaries.

As tea is an important economic crop in many regions, efficient and accurate methods for remotely identifying tea plantations are essential for the implementation of sustainable tea practices and for periodic monitoring. In this study, we developed and tested a method for tea plantation identification based on multi-temporal Sentinel-2 images and a multi-feature Random Forest (RF) algorithm. We used phenological patterns of tea cultivation in China’s Shihe District (such as the multiple annual growing, harvest, and pruning stages) to extracted multi-temporal Sentinel-2 MSI bands, their derived first spectral derivative, NDVI and textures, and topographic features. We then assessed feature importance using RF analysis; the optimal combination of features was used as the input variable for RF classification to extract tea plantations in the study area. A comparison of our results with those achieved using the Support Vector Machine method and statistical data from local government departments showed that our method had a higher producer’s accuracy (96.57%) and user’s accuracy (96.02%). These results demonstrate that: (1) multi-temporal and multi-feature classification can improve the accuracy of tea plantation recognition, (2) RF classification feature importance analysis can effectively reduce feature dimensions and improve classification efficiency, and (3) the combination of multi-temporal Sentinel-2 images and the RF algorithm improves our ability to identify and monitor tea plantations.

A soil erosion model is used to evaluate the conditions of soil erosion and guide agricultural production. Recently, high spatial resolution data have been collected in new ways, such as three-dimensional laser scanning, providing the foundation for refined soil erosion modelling. However, serial computing cannot fully meet the computational requirements of massive data sets. Therefore, it is necessary to perform soil erosion modelling under a parallel computing framework. This paper focuses on a parallel computing framework for soil erosion modelling based on the Hadoop platform. The framework includes three layers: the methodology, algorithm, and application layers. In the methodology layer, two types of parallel strategies for data splitting are defined as row-oriented and sub-basin-oriented methods. The algorithms for six parallel calculation operators for local, focal and zonal computing tasks are designed in detail. These operators can be called to calculate the model factors and perform model calculations. We defined the key-value data structure of GeoCSV format for vector, row-based and cell-based rasters as the inputs for the algorithms. A geoprocessing toolbox is developed and integrated with the geographic information system (GIS) platform in the application layer. The performance of the framework is examined by taking the Gushanchuan basin as an example. The results show that the framework can perform calculations involving large data sets with high computational efficiency and GIS integration. This approach is easy to extend and use and provides essential support for applying high-precision data to refine soil erosion modelling.

The Yellow River Basin has been affected by global climate change. Studying the spatial⁻temporal variability of the hydrothermal climate conditions in the Yellow River Basin is of vital importance for the development of technologies and policies related to ecological, environmental, and agricultural adaptation in this region. This study selected temperature and precipitation data observed from 118 meteorological stations distributed in the Yellow River Basin over the period of 1957⁻2015, and used the Mann⁻Kendall, Pettitt, and Hurst indices to investigate the spatial⁻temporal variability of the hydrothermal climate conditions in this area. The results indicated: (1) the annual maximum, minimum, and average temperatures have increased. The seasonal maximum, minimum, and average temperatures for the spring, summer, autumn, and winter have also increased, and this trend is statistically significant (p < 0.01) between 1957⁻2015. The rate of increase in the minimum temperature exceeded that of the maximum temperature, and diurnal warming was asymmetric. Annual precipitation and the total spring, summer, and autumn precipitations declined, while the total winter precipitation increased, although the trend was non-significant (p > 0.05). (2) Based on the very restrictive assumption that future changes will be similar to past changes, according to the Hurst index experiment, the future trends of temperature and precipitation in the Yellow River Basin are expected to stay the same as in the past. There will be a long-term correlation between the two trends: the temperature will continue to rise, while the precipitation will continue to decline (except in the winter). However, over the late stage of the study period, the trends slowed down to some extent.

To develop an appropriate sampling strategy to assess the intrauterine exposure to dechlorane plus (DP), we investigated DP levels in sequential maternal blood samples collected in three trimesters of pregnancy, respectively, from women living in Taizhou. The median concentration of DPs (sum of syn-DP and anti-DP) in all samples was 30.5 pg g−1 wet-weight and 5.01 ng g−1 lipid-adjusted weight, respectively. The trimester-related DP concentrations were consistently strongly correlated (p < 0.01), indicating that a single measurement of DP levels could represent intrauterine exposure without sampling from the same female repeatedly; however, the wet-weight levels significantly increased across trimesters (p < 0.05), while the lipid-adjusted levels did not significantly vary. Notably, whether lipid-adjusted weight or wet-weight levels, the variation extent of DP across trimesters was found to be less than 41%, and those for other persistent organic pollutants (POPs) reported in the literature were also limited to 100%. The limitation in variation extents indicated that, regardless of the time of blood collection during pregnancy and how the levels were expressed, a single measurement could be extended to screen for exposure risk if necessary. Our study provides different strategies for sampling the maternal blood to serve the requirement for assessment of in utero exposure to DP.