With the development of deep learning algorithms, more and more deep learning algorithms are being applied to remote sensing image classification, detection, and semantic segmentation. The landslide semantic segmentation of a remote sensing image based on deep learning mainly uses supervised learning, the accuracy of which depends on a large number of training data and high-quality data annotation. At this stage, high-quality data annotation often requires the investment of significant human effort. Therefore, the high cost of remote sensing landslide image data annotation greatly restricts the development of a landslide semantic segmentation algorithm. Aiming to resolve the problem of the high labeling cost of landslide semantic segmentation with a supervised learning method, we proposed a remote sensing landslide semantic segmentation with weakly supervised learning method combing class activation maps (CAMs) and cycle generative adversarial network (cycleGAN). In this method, we used the image level annotation data to replace pixel level annotation data as the training data. Firstly, the CAM method was used to determine the approximate position of the landslide area. Then, the cycleGAN method was used to generate the fake image without a landslide, and to make the difference with the real image to obtain the accurate segmentation of the landslide area. Finally, the pixel-level segmentation of the landslide area on remote sensing image was realized. We used mean intersection-over-union (mIOU) to evaluate the proposed method, and compared it with the method based on CAM, whose mIOU was 0.157, and we obtain better result with mIOU 0.237 on the same test dataset. Furthermore, we made a comparative experiment using the supervised learning method of a u-net network, and the mIOU result was 0.408. The experimental results show that it is feasible to realize landslide semantic segmentation in a remote sensing image by using weakly supervised learning. This method can greatly reduce the workload of data annotation.

Identifying the distribution dynamics of invasive alien species can help in the early detection of and rapid response to these invasive species in newly invaded sites. Ageratina adenophora, a worldwide invasive plant, has spread rapidly since its invasion in China in the 1940s, causing serious damage to the local socioeconomic and ecological environment. To better control the spread of this invasive plant, we used the MaxEnt model and ArcGIS based on field survey data and online databases to simulate and predict the spatial and temporal distribution patterns and risk areas for the spread of this species in China, and thus examined the key factors responsible for this weed’s spread. The results showed that the risk areas for the invasion of A. adenophora in the current period were 18.394° N–33.653° N and 91.099° E–121.756° E, mainly in the tropical and subtropical regions of China, and densely distributed along rivers and well-developed roads. The high-risk areas are mainly located in the basins of the Lancang, Jinsha, Yalong, and Anning Rivers. With global climate change, the trend of continued invasion of A. adenophora is more evident, with further expansion of the dispersal zone towards the northeast and coastal areas in all climatic scenarios, and a slight contraction in the Yunnan–Guizhou plateau. Temperature, precipitation, altitude, and human activity are key factors in shaping the distribution pattern of A. adenophora. This weed prefers to grow in warm and precipitation-rich environments such as plains, hills, and mountains; in addition, increasing human activities provide more opportunities for its invasion, and well-developed water systems and roads can facilitate its spread. Measures should be taken to prevent its spread into these risk areas.

Species distribution models (SDMs) are critical in conservation decision-making and ecological or biogeographical inference. Accurately predicting species distribution can facilitate resource monitoring and management for sustainable regional development. Currently, species distribution models usually use a single source of information as input for the model. To determine a solution to the lack of accuracy of the species distribution model with a single information source, we propose a multimodal species distribution model that can input multiple information sources simultaneously. We used ResNet50 and Transformer network structures as the backbone for multimodal data modeling. The model’s accuracy was tested using the GEOLIFE2020 dataset, and our model’s accuracy is state-of-the-art (SOTA). We found that the prediction accuracy of the multimodal species distribution model with multiple data sources of remote sensing images, environmental variables, and latitude and longitude information as inputs (29.56%) was higher than that of the model with only remote sensing images or environmental variables as inputs (25.72% and 21.68%, respectively). We also found that using a Transformer network structure to fuse data from multiple sources can significantly improve the accuracy of multimodal models. We present a novel multimodal model that fuses multiple sources of information as input for species distribution prediction to advance the research progress of multimodal models in the field of ecology.