Understanding the impacts and extent of both climate change and human activities on ecosystems is crucial to sustainable development. With low anti-interference ability, arid and semi-arid ecosystems are particularly sensitive to disturbances from both climate change and human activities. We investigated how and to what extent climate variation and human activities influenced major indicators that are related to ecosystem functions and conditions in the past decades in Xinjiang, a typical arid and semi-arid region in China. We analyzed the changing trends of evapotranspiration (ET), gross primary productivity (GPP) and leaf area index (LAI) derived from the Moderate-Resolution Imaging Spectroradiometer (MODIS) satellite product and the Breathing Earth System Simulator (BESS) model in Xinjiang for different climate zones. We separated and quantified the contributions of climate forcing and human activities on the trends of the studied ecosystem indicators using the residual analysis method for different climate zones in Xinjiang. The results show that GPP and LAI increased and ET decreased from 2001 to 2015 in Xinjiang. Factors that dominate the changes in ecosystem indicators vary considerably across different climate zones. Precipitation plays a positive role in impacting vegetation indicators in arid and hyper-arid zones and temperature has a negative correlation with both GPP and LAI in hyper-arid zones in Xinjiang. Results based on residual analysis indicate that human activities could account for over 72% of variation in the changes in each ecosystem indicator. Human activities have large impacts on each vegetation indicator change in hyper-arid and arid zones and their relative contribution has a mean value of 79%. This study quantifies the roles of climate forcing and human activities in the changes in ecosystem indicators across different climate zones, suggesting that human activities largely influence ecosystem processes in the arid and semi-arid regions of Xinjiang in China.

Understanding the spatial distribution of irrigated croplands is crucial for food security and water use. To map land cover classes with high-spatial-resolution images, it is necessary to analyze the semantic information of target objects in addition to the spectral or spatial–spectral information of local pixels. Deep convolutional neural networks (DCNNs) can characterize the semantic features of objects adaptively. This study uses DCNNs to extract irrigated croplands from Sentinel-2 images in the states of Washington and California in the United States. We integrated the DCNNs of 101 layers, discarded pooling layers, and employed dilation convolution to preserve location information; these are models which were used based on fully convolutional network (FCN) architectures. The findings indicated that irrigated croplands may be effectively detected at various phases of crop growth in the fields. A quantitative analysis of the trained models revealed that the three models in the two states had the lowest values of Intersection over Union (IoU) and Kappa, i.e., 0.88 and 0.91, respectively. The deep models’ temporal portability across different years was acceptable. The lowest values of recall and OA (overall accuracy) from 2018 to 2021 were 0.91 and 0.87, respectively. In Washington, the lowest OA value from 10 to 300 m resolution was 0.76. This study demonstrates the potential of FCNs + DCNNs approaches for mapping irrigated croplands across large regions, providing a solution for irrigation mapping. The spatial resolution portability of deep models could be improved further by designing model architectures.

High- and very high-resolution (HR, VHR) remote sensing (RS) images can provide comprehensive and intricate spatial information for land cover classification, which is particularly crucial when analyzing complex built-up environments. However, the application of HR and VHR images to large-scale and detailed land cover mapping is always constrained by the intricacy of land cover classification models, the exorbitant cost of collecting training samples, and geographical changes or acquisition conditions. To overcome this limitation, we propose an unsupervised domain adaptation (UDA) with contrastive learning-based discriminative feature augmentation (CLDFA) for RS image classification. In detail, our method first utilizes contrastive learning (CL) through a memory bank in order to memorize sample features and improve model performance, where the approach employs an end-to-end Siamese network and incorporates dynamic pseudo-label assignment and class-balancing strategies for adaptive domain joint learning. By transferring classification models trained on a source domain (SD) to an unlabeled target domain (TD), our proposed UDA method enables large-scale land cover mapping. We conducted experiments using a massive five billion-pixels dataset as the SD and tested the HR and VHR RS images of five typical Chinese cities as the TD and applied the method on the completely unlabeled world view 3 (WV3) image of Urumqi city. The experimental results demonstrate that our method excels in large-scale HR and VHR RS image classification tasks, highlighting the advantages of semantic segmentation based on end-to-end deep convolutional neural networks (DCNNs).

Invasive plants (IPs) pose a significant threat to local ecosystems. Recent advances in remote sensing (RS) and deep learning (DL) significantly improved the accuracy of IP detection. However, mainstream DL methods often require large, high-quality labeled data, leading to resource inefficiencies. In this study, a deep learning framework called adversarial positive-unlabeled learning (APUL) was proposed to achieve high-precision IP detection using a limited number of target plant samples. APUL employs a dual-branch discriminator to constrain the class prior-free classifier, effectively harnessing information from positive-unlabeled data through the adversarial process and enhancing the accuracy of IP detection. The framework was tested on very high-resolution Jilin-1 and Sentinel-2 imagery of Bayinbuluke grasslands in Xinjiang, where the invasion of Pedicularis kansuensis has caused serious ecological and livestock damage. Results indicate that the adversarial structure can significantly improve the performance of positive-unlabeled learning (PUL) methods, and the class prior-free approach outperforms traditional PUL methods in IP detection. APUL achieved an overall accuracy of 92.2% and an F1-score of 0.80, revealing that Pedicularis kansuensis has invaded 4.43% of the local plant population in the Bayinbuluke grasslands, underscoring the urgent need for timely control measures.