The Loess Plateau of China suffers from severe erosion, which results in a great variety of economic and ecological problems. For scientific control of soil erosion, the key questions urgently to be addressed in this paper are: (1) Which are the driving factors under diverse geomorphological types? (2) Do these driving factors operate independently or by interacting? (3) Which zones under diverse geomorphological types suffer from severe erosion and need more attention? In this paper, the RUSLE model was applied here to demonstrate the spatio-temporal variations in soil erosion from 2010 to 2017 in Yan’an City, and the Geo-detector model proved to be a useful tool to solve the questions mentioned above. The results showed that the average erosion modulus in Yan’an City decreased by 1927.36 t/km²·a from 2010 to 2017. The intensity of soil erosion in the northern Baota District, central Ganquan County, Luochuan County, Ansai County, and Zhidan County decreased to varying degrees. The effect size of driving factors affecting soil erosion varied significantly in diverse geomorphological types. The effect size of interaction between land-use types and vegetation coverage, land-use types and slope, slope and precipitation was higher than that of a single factor. High-risk zones with severe erosion were closer to cultivated land and forest land with steep slopes (>25°) in the mid-elevation hills of Yan’an City. Additionally, based on the specificity of the study area, the Geo-detector model performed better in a relatively flat region, and factors with macroscopic spatial distributions weaken its explanatory power on soil erosion on a regional scale. Based on data selection, data of different accuracy sparked the issue of “data coupling”, which led to the enormous deviation of model results in mid-elevation plains. Results from our analysis provide insights for a more ecologically sound development of Yan’an City and provide references for the scientific use of the Geo-detector model.

Maize (Zea mays L.), one of the most important agricultural crops in the world, which can be devastated by lodging, which can strike maize during its growing season. Maize lodging affects not only the yield but also the quality of its kernels. The identification of lodging is helpful to evaluate losses due to natural disasters, to screen lodging-resistant crop varieties, and to optimize field-management strategies. The accurate detection of crop lodging is inseparable from the accurate determination of the degree of lodging, which helps improve field management in the crop-production process. An approach was developed that fuses supervised and object-oriented classifications on spectrum, texture, and canopy structure data to determine the degree of lodging with high precision. The results showed that, combined with the original image, the change of the digital surface model, and texture features, the overall accuracy of the object-oriented classification method using random forest classifier was the best, which was 86.96% (kappa coefficient was 0.79). The best pixel-level supervised classification of the degree of maize lodging was 78.26% (kappa coefficient was 0.6). Based on the spatial distribution of degree of lodging as a function of crop variety, sowing date, densities, and different nitrogen treatments, this work determines how feature factors affect the degree of lodging. These results allow us to rapidly determine the degree of lodging of field maize, determine the optimal sowing date, optimal density and optimal fertilization method in field production.

Deep-learning-based object detectors have substantially improved state-of-the-art object detection in remote sensing images in terms of precision and degree of automation. Nevertheless, the large variation of the object scales makes it difficult to achieve high-quality detection across multiresolution remote sensing images, where the quality is defined by the Intersection over Union (IoU) threshold used in training. In addition, the imbalance between the positive and negative samples across multiresolution images worsens the detection precision. Recently, it was found that a Cascade region-based convolutional neural network (R-CNN) can potentially achieve a higher quality of detection by introducing a cascaded three-stage structure using progressively improved IoU thresholds. However, the performance of Cascade R-CNN degraded when the fourth stage was added. We investigated the cause and found that the mismatch between the ROI features and the classifier could be responsible for the degradation of performance. Herein, we propose a Cascade R-CNN++ structure to address this issue and extend the three-stage architecture to multiple stages for general use. Specifically, for cascaded classification, we propose a new ensemble strategy for the classifier and region of interest (RoI) features to improve classification accuracy at inference. In localization, we modified the loss function of the bounding box regressor to obtain higher sensitivity around zero. Experiments on the DOTA dataset demonstrated that Cascade R-CNN++ outperforms Cascade R-CNN in terms of precision and detection quality. We conducted further analysis on multiresolution remote sensing images to verify model transferability across different object scales.

The exploitation of coal resources has caused problems such as ground deformation, affecting the ecological environment. Spatiotemporal varying characteristics between land subsidence and ecological environmental quality (EEQ) are an important research hotspot. Using the SBAS-InSAR method, 64 Sentinel-1 images were utilized to monitor land subsidence in the Shenfu mining area, one of China’s largest coal source regions. And the remote sensing ecological index (RSEI) was used to monitor and evaluate EEQ of the Shenfu mining area. Global and local spatial autocorrelation methods were used to assess the spatial aggregation degree and change patterns over time. Spatial Econometric Models were employed to explore the impacts of land subsidence on EEQ. The results showed the following: (1) The average RSEI values in the Shenfu mining area were 0.531, 0.488, and 0.523 in 2016, 2018, and 2020, respectively; there was a slight downward trend in EEQ. The permanent scatter (PS) point deformation rate ranged from −353.40 mm/year to +246.24 mm/year, with average deformation rates of 0.1642, 0.2181, and 0.2490 mm/year, respectively. (2) There was a significant correlation and spatial agglomeration effect between land surface subsidence and EEQ. Low–high, high–low, and low–low clusters were the main types of relationships, indicating that land subsidence primarily has a negative spatial impact on the ecological environment. (3) The relationship between land subsidence and EEQ varied spatially in the Shenfu mining area at 500 × 500 grid units. This research can provide scientific guidance for disaster prevention and sustainable development in mining areas by considering long-term differences in ecological environmental quality and its correlation with land subsidence.

As a major component of water cycle, the accuracy quantification of different precipitation products is critical for evaluating climate change and ecosystem functions. However, a lack of evidence is available to choose a precise precipitation product in relative applications. Here, to solve this limit, we analyze the spatiotemporal pattern and accuracy of four precipitation products, including CHIRPS V2.0, PERSIANN-CDR, ECMWF ERA5-Land, and GLDAS_NOAH025_3H, over China during the period of 1981–2020, based on the five precipitation traits (i.e., spatial pattern of multi-year average, annual trend, seasonality, frequency, and intensity), and meteorological gauge observations are taken as the benchmark. Our results show that, compared to other products, CHIRPS data has the strongest ability to present spatial pattern of multi-year average precipitation, especially in most parts of northeastern and southern China, and ERA5 has the weakest ability to simulate the multi-year average precipitation. All four precipitation products can accurately depict the spatial pattern of seasonality, among which CHIRPS and ERA5 have the highest and lowest fitting ability, respectively, but four products poorly describe the spatial pattern of precipitation intensity and frequency at a daily scale. These products only correctly predict the interannual precipitation trend in some local areas. Our findings provide evidences to select high-quality precipitation data, and could help to improve the accuracy of relative geophysical models.