The wide application and rapid development of satellite remote sensing technology have put higher requirements on remote sensing image segmentation methods. Because of its characteristics of large image size, large data volume, and complex segmentation background, not only are the traditional image segmentation methods difficult to apply effectively, but the image segmentation methods based on deep learning are faced with the problem of extremely unbalanced data between categories. In order to solve this problem, first of all, according to the existing effective sample theory, the effective sample calculation method in the context of semantic segmentation is firstly proposed in the highly unbalanced dataset. Then, a dynamic weighting method based on the effective sample concept is proposed, which can be applied to the semantic segmentation of remote sensing images. Finally, the applicability of this method to different loss functions and different network structures is verified on the self-built Landsat8-OLI remote sensing image-based tri-classified forest fire burning area dataset and the LoveDA dataset, which is for land-cover semantic segmentation. It has been concluded that this weighting algorithm can enhance the minimal-class segmentation accuracy while ensuring that the overall segmentation performance in multi-class segmentation tasks is verified in two different semantic segmentation tasks, including the land use and land cover (LULC) and the forest fire burning area segmentation In addition, this proposed method significantly improves the recall of forest fire burning area segmentation by as much as about 30%, which is of great reference value for forest fire research based on remote sensing images.

Forest fires have become a significant global threat, with many negative impacts on human habitats and forest ecosystems. This study proposed a forest fire identification method by fusing visual and infrared images, addressing the high false alarm and missed alarm rates of forest fire monitoring using single spectral imagery. A dataset suitable for image fusion was created using UAV aerial photography. An improved image fusion network model, the FF-Net, incorporating an attention mechanism, was proposed. The YOLOv5 network was used for target detection, and the results showed that using fused images achieved a higher accuracy, with a false alarm rate of 0.49% and a missed alarm rate of 0.21%. As such, using fused images has greater significance for the early warning of forest fires.

In recent years, the investigation of fire disturbance of microbial communities has gained growing attention. However, how the bacterial community varies in response to different severities of fire at different soil depths is largely unknown. We utilized Illumina MiSeq sequencing to illustrate the changing patterns of the soil bacterial community following low-, moderate- and high-severity wildfire in the topsoil (0–10 cm) and subsoil (10–20 cm), 6 months after the fire. Acidobacteria, Proteobacteria, Actinobacteria, Verrucomicrobia and Chloroflexi were the dominant phyla among all samples. Bacterial alpha diversity (i.e. Shannon and Simpson indices) in the topsoil was significantly higher than that in the subsoil after a high-severity wildfire. Non-metric multidimensional scaling (NMDS) analysis and permutational multivariate analysis of variance (PERMANOVA) revealed significant differences in the bacterial community structure between the two soil layers. Soil pH, ammonium nitrogen (NH₄⁺-N) and total nitrogen were the main factors in shaping the bacterial community structure, of which soil pH was the most robust in both soil layers. Our study reveals that wildfire results in short-term changes in soil bacterial community. However, a long-term monitoring of microbial variation after burning is also essential.

Forest fires, as severe natural disasters, pose significant threats to ecosystems and human societies, and their spread is characterized by constant evolution over time and space. This complexity presents an immense challenge in predicting the course of forest fire spread. Traditional methods of forest fire spread prediction are constrained by their ability to process multidimensional fire-related data, particularly in the integration of spatiotemporal information. To address these limitations and enhance the accuracy of forest fire spread prediction, we proposed the AutoST-Net model. This innovative encoder–decoder architecture combines a three-dimensional Convolutional Neural Network (3DCNN) with a transformer to effectively capture the dynamic local and global spatiotemporal features of forest fire spread. The model also features a specially designed attention mechanism that works to increase predictive precision. Additionally, to effectively guide the firefighting work in the southwestern forest regions of China, we constructed a forest fire spread dataset, including forest fire status, weather conditions, terrain features, and vegetation status based on Google Earth Engine (GEE) and Himawari-8 satellite. On this dataset, compared to the CNN-LSTM combined model, AutoST-Net exhibits performance improvements of 5.06% in MIou and 6.29% in F1-score. These results demonstrate the superior performance of AutoST-Net in the task of forest fire spread prediction from remote sensing images.

In recent years, the increasingly significant impacts of climate change and human activities on the environment have led to more frequent occurrences of extreme events such as forest fires. The recurrent wildfires pose severe threats to ecological environments and human life safety. Consequently, forest fire prediction has become a current research hotspot, where accurate forecasting technologies are crucial for reducing ecological and economic losses, improving forest fire management efficiency, and ensuring personnel safety and property security. To enhance comprehensive understanding of wildfire prediction research, this paper systematically reviews studies since 2015, focusing on two key aspects: datasets with related tools and prediction algorithms. We categorized the literature into three categories: statistical analysis and physical models, traditional machine learning methods, and deep learning approaches. Additionally, this review summarizes the data types and open-source datasets used in the selected literature. The paper further outlines current challenges and future directions, including exploring wildfire risk data management and multimodal deep learning, investigating self-supervised learning models, improving model interpretability and developing explainable models, integrating physics-informed models with machine learning, and constructing digital twin technology for real-time wildfire simulation and fire scenario analysis. This study aims to provide valuable support for forest natural resource management and enhanced environmental protection through the application of remote sensing technologies and artificial intelligence algorithms.

Forest fires are significant disturbances to ecosystems, necessitating accurate mapping of burned areas and assessment of burn severity. Firstly, we reconstruct a dataset whose label uses a more flexible classification method from Landsat imagery and establish auxiliary environmental datasets for fire-affected regions. Leveraging vegetation change pre-fire and post-fire, we propose a transformer-based change detection model that integrates remote sensing and environmental information effectively. We introduce a multi-level feature fusion mechanism to address spatial resolution degradation in burn severity estimation. Experimental results show our model closely approximates evaluation dataset labels. For burned area segmentation, our method achieves the highest F1 (0.897) and mIoU of 0.781. For burn severity estimation, our method also achieves the highest mIoU (0.851). Incorporating auxiliary features improves performance by nearly 30%, while the multi-level feature fusion mechanism reduces resolution degradation by 9.6%.