No abstract

Understanding the response of vegetation to drought is of great significance to the biodiversity protection of terrestrial ecosystem. Based on the MOD13A2 NDVI, GOSIF, and SPEI data of the Yellow River Basin from 2001 to 2020, this paper used the methods of Theil–Sen median trend analysis, Mann–Kendall significance test, and Pearson correlation analysis to analyze whether the vegetation change trends monitored by MODIS and GOSIF are consistent and their sensitivity to meteorological drought. The results showed that NDVI and SIF increased significantly (p < 0.001) at the rate of 0.496 × 10−2 and 0.345 × 10−2, respectively. The significant improvement area of SIF (66.49%, p < 0.05) is higher than NDVI (50.7%, p < 0.05), and the spatial distribution trend of vegetation growth monitored by NDVI and SIF is consistent. The negative value of SPEI-12 accounts for 65.83%, with obvious periodic changes. The significant positive correlation areas of SIF-SPEI in spring, summer, and autumn (R > 0, p < 0.05) were 7.00%, 28.49%, and 2.28% respectively, which were higher than the significant positive correlation areas of NDVI-SPEI (spring: 1.79%; summer: 20.72%; autumn: 1.13%). SIF responded more strongly to SPEI in summer, and farmland SIF was significantly correlated with SPEI (0.3424, p < 0.01). The results indicate that SIF is more responsive to drought than NDVI. Analyzing the response of vegetation to meteorological drought can provide constructive reference for ecological protection.

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.