In this paper, landscape ecological risk in Qinling Mountain was studied. Using the remote sensing images of Landsat TM and DEM data in 1984, 2000, 2005, and 2014, an ecological risk assessment model was constructed, and landscape ecological risk indexes were calculated for four time periods 1984, 2004, 2005 and 2014. The spatial distribution of ecological risk was obtained with ArcGIS and geostatistics, and changes in the landscape patterns and spatiotemporal characteristics of ecological risk were analysed. As shown in the results; (a) from 1984 to 2014, the landscape pattern index of Qinling forest area was relatively stable; fragmentation and segregation decreased, and dominance and area increased. The fragmentation and separation of cultivated land increased over time, and the geographical distribution of cultivated land diversified, while its dominance decreased. (b) The areas of extremely low and extremely high ecological risk level in the study area is gradually reduced. But the area of high ecological risk level increased obviously. The extremely high ecological risk area was mainly distributed in the middle and south‐eastern regions. The extremely low and low risk areas were mainly distributed in the low hilly areas of northern Qinling.
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.
The arid region in the northern part of China is a bridge between China and neighbouring countries in the Silk Road Economic Belt, and the severe desertification in this region restricts its sustainable development. In this paper, MODIS data, including albedo, reflectance, normalized vegetation index, and land surface temperature, were selected in 2000, 2005, 2010, and 2015 to construct a decision tree to extract spatio‐temporal information of the desertified land in the arid area. The trend in desertification and transfer directions was analysed by the GIS method, and the dynamic characteristics of the desertification at different units (provincial administrative unit and typical sandy land) and with different topographic factors (slope and aspect) are discussed. Our conclusions include (a) desertification in the arid region in the northern part of China showed improvement overall and local deterioration. The deteriorating areas were located primarily in the western region of the Hunshandake Sandy Land, the tectonic zone of the Taklimakan Desert, and the Qaidam Basin; (b) the degree of desertification transfer occurred primarily at adjacent levels; (c) the desertified area in each province showed a different trend in fluctuation, and Maowusu Sandy Land recovered better among the 4 large sands; and (d) the desertified area was distributed primarily along 0o–3o slopes and showed a rapid decline at increased slopes. The change in the degree of desertification in each aspect largely was a general reversal, and the area of the north aspect was larger than that of other areas of aspects. This study provides some theoretical support for the control of desertification in the Silk Road Economic Belt.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.