Landslide susceptibility mapping (LSM) is an important element of landslide risk assessment, but the process often needs to span multiple platforms and the operation process is complex. This paper develops an efficient user-friendly toolbox including the whole process of LSM, known as the SVM-LSM toolbox. The toolbox realizes landslide susceptibility mapping based on a support vector machine (SVM), which can be integrated into the ArcGIS or ArcGIS Pro platform. The toolbox includes three sub-toolboxes, namely: (1) influence factor production, (2) factor selection and dataset production, and (3) model training and prediction. Influence factor production provides automatic calculation of DEM-related topographic factors, converts line vector data to continuous raster factors, and performs rainfall data processing. Factor selection uses the Pearson correlation coefficient (PCC) to calculate the correlations between factors, and the information gain ratio (IGR) to calculate the contributions of different factors to landslide occurrence. Dataset sample production includes the automatic generation of non-landslide data, data sample production and dataset split. The accuracy, precision, recall, F1 value, receiver operating characteristic (ROC) and area under curve (AUC) are used to evaluate the prediction ability of the model. In addition, two methods—single processing and multiprocessing—are used to generate LSM. The prediction efficiency of multiprocessing is much higher than that of the single process. In order to verify the performance and accuracy of the toolbox, Wuqi County, Yan’an City, Shaanxi Province was selected as the test area to generate LSM. The results show that the AUC value of the model is 0.8107. At the same time, the multiprocessing prediction tool improves the efficiency of the susceptibility prediction process by about 60%. The experimental results confirm the accuracy and practicability of the proposed toolbox in LSM.

The rapid mapping of co-seismic landslides is essential for emergency management and loss assessment. Deep learning algorithms generally follow a supervised learning workflow, where the trained model is used to predict landslides in surrounding areas, achieving landslide mapping with high accuracy. For a new study area landslide extraction task, the performance of the model trained on a specific dataset will be greatly reduced due to the varying data distribution of co-seismic landslides. Considering urgent need for large large-scale co-seismic landslide mapping, we developed a generalized deep learning-based landslide identification method. Firstly, a new model – ResU-SENet is developed to generate semantic segmentation maps of landslides. The proposed model adaptively emphasizes the channel-wise weights of the input data. Three multi-domain models are then designed by combining annotated landslide samples from two different domains to improve the model generalization ability. Lastly, the trained models are applied directly to completely unknown domains to test model generalizability. Experiments in Iburi and Jiuzhaigou showed that the proposed model yielded the recall values of 5.93% and 7.51% higher than ResU-Net. The adoption of multi-domain models effectively reduced the number of new training samples required by 50% and maintained a similar identification performance as if trained entirely with new samples. Applying the models trained by Jiuzhaigou and Iburi samples directly to Palu, the F1-score under the ResU-SENet model reached 0.6875. Moreover, the connections of model generalization and data distribution was demonstrated. This work could provide a fast response for future large-scale co-seismic landslide mapping.

On 22 July 2020, an Mw 6.3 earthquake occurred in Nima County, central Qinghai-Tibet Plateau, China. We used the synthetic aperture radar interferometry (InSAR) technique with Sentinel-1 images to retrieve the line of sight (LOS) coseismic deformation fields which indicate that the maximum surface displacement reached ~30 cm. We then processed a series of interferograms spanning one year after the Nima earthquake with the Small Baseline Subset Interferometric SAR (SBAS-InSAR) technique. The maximum cumulative postseismic LOS surface displacement reached ~8 cm and approximately followed a logarithmic function over time. The inversion of the fault geometry and co- and afterslip distribution shows that the epicenter location was (33.18°N, 86.88°E) at a depth of 7.4 km, and the causative fault had an N29.1°E strike and 50.2° dip. The most coseismic slip was concentrated at depths between 3 to 12 km with a peak value of 2.0 m at 7.4 km, whilst most afterslips were concentrated at depths between 0 to 12 km with a peak value of 0.2 m at 5 km. The postseismic moment energy was about 5.04 × 10¹⁷ N∙m 308 days after the event, which was approximately 13.8% of the coseismic moment energy. By analyzing the contribution of afterslip and poroelastic rebound to postseismic deformation, it was concluded that afterslip was the main early postseismic deformation mechanism. Future attention should be paid to the northern segment of the West Yibug Caka fault and East Yibug Caka fault.

Rapid and accurate acquisition of landslide inventories is essential for effective disaster relief. Deep learning-based pixel-wise semantic segmentation of remote sensing imagery has greatly advanced in landslide mapping. However, the heavy dependance on extensive annotated labels and sensitivity to domain shifts severely constrain the model performance in unseen domains, leading to poor generalization. To address these limitations, we propose LandsDANet, an innovative unsupervised domain adaptation framework for cross-domain landslide identification. Firstly, adversarial learning is employed to reduce the data distribution discrepancies between the source and target domains, thereby achieving output space alignment. The improved SegFormer serves as the segmentation network, incorporating hierarchical Transformer blocks and an attention mechanism to enhance feature representation capabilities. Secondly, to alleviate inter-domain radiometric discrepancies and attain image-level alignment, a Wallis filter is utilized to perform image style transformation. Considering the class imbalance present in the landslide dataset, a Rare Class Sampling strategy is introduced to mitigate bias towards common classes and strengthen the learning of the rare landslide class. Finally, a contrastive loss is adopted to further optimize and enhance the model’s ability to delineate fine-grained class boundaries. The proposed model is validated on the Potsdam and Vaihingen benchmark datasets, followed by validation in two landslide scenarios induced by earthquakes and rainfall to evaluate its adaptability across different disaster domains. Compared to the source-only model, LandsDANet achieved improvements in IoU of 27.04% and 35.73% in two cross-domain landslide disaster recognition tasks, respectively. This performance not only showcases its outstanding capabilities but also underscores its robust potential to meet the demands for rapid response.

This paper focuses on the problem of mapping odour sources using a mobile robot in a time-variant airflow environment, and provides a localization method which uses the Dempster-Shafer (D-S) theory to reason the possible locations of odour sources. In the proposed method, the robot carries out the D-S inference and iteratively updates a grid map, using the successive measurements from a gas sensor and an anemometer when the robot is cruising in the given search area. Simulations are carried out and the results in a time-variant airflow environment show that the locations of the multiple odour sources can be estimated online with the proposed method.

Remote sensing image semantic segmentation (RSISS) aims to assign a correct class label to each pixel in remote sensing images and has wide applications. With the development of artificial intelligence, RSISS based on deep learning has made significant progress. However, existing methods remain more focused on predefined semantic classes and require costly retraining when confronted with new classes. To address this limitation, we propose the hierarchical guidance open-vocabulary semantic segmentation framework for remote sensing images (named HG-RSOVSSeg), enabling flexible segmentation of arbitrary semantic classes without model retraining. Our framework leverages pretrained text-embedding models to provide class common knowledge and aligns multimodal features through a dual-stream architecture. Specifically, we propose a multimodal feature aggregation module for pixel-level alignment and a hierarchical visual feature decoder guided by text feature alignment, which progressively refines visual features using language priors, preserving semantic coherence during high-resolution decoding. Extensive experiments were conducted on six representative public datasets, and the results showed that our method has the highest mean mIoU value, establishing state-of-the-art performance in the field of open-vocabulary semantic segmentation of remote sensing images.