Liu Lizhi, Guo Ying, Chen Erxue, Li Zengyuan, Li Yu, Liu Yang, Zhang Qiang, Wang Bing
College of Horticulture and Forestry, Tarim University, Alar, Xinjiang, 843300, China.
Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, BeiJing, 100091, China.
Sci Rep. 2025 May 7;15(1):15969. doi: 10.1038/s41598-024-66060-7.
Complete and accurate burned area map data are needed to document spatial and temporal patterns of fires, to quantify their drivers, and to assess the impacts on human and natural systems. To achieve the the purpose of identifying burned area accurately and efficiency from remote sensing images, a lightweight deep learning model is proposed based on Deeplab V3 + , which employs the combination of attention mechanism and deep transitive transfer learning (DTTL) strategy. The lightweight MobileNet V2 network integrated with Convolutional Block Attention Module (CBAM) is designed as the backbone network to replace the traditional time-consuming Xception of Deeplab V3 +. The attention mechanism is introduced to enhance the recognition ability of the proposed deep learning model, and the deep transitive transfer learning strategy is adopted to solve the problem of incorrect identification of the burned area and discontinuous edge details caused by insufficient sample size during the extraction process. For the process of DTTL, the improved Deeplab V3 + network was first pre-trained on ImageNet. Sequentially, WorldView-2 and the Sentinel-2 dataset were employed to train the proposed network based on the ImageNet pre-trained weights. Experiments were conducted to extract burned area from remote sensing images based on the trained model, and the results show that the proposed methodology can improve extraction accuracy with OA of 92.97% and Kappa of 0.819, which is higher than the comparative methods, and it can reduce the training time at the same time. We applied this methodology to identify the burned area in Western Attica region of Greece, and a satisfactory result was achieved with. OA of 93.58% and Kappa of 0.8265. This study demonstrates the effectiveness of the improved Deeplab V3 +in identifying forest burned area. which can provide valuable information for forest protection and monitoring.
需要完整准确的火烧面积地图数据来记录火灾的时空模式、量化其驱动因素，并评估对人类和自然系统的影响。为了实现从遥感图像中准确高效地识别火烧面积的目的，提出了一种基于Deeplab V3+的轻量级深度学习模型，该模型采用了注意力机制和深度传递迁移学习（DTTL）策略的组合。将集成了卷积块注意力模块（CBAM）的轻量级MobileNet V2网络设计为主干网络，以取代传统的耗时的Deeplab V3+的Xception网络。引入注意力机制以增强所提出的深度学习模型的识别能力，并采用深度传递迁移学习策略来解决提取过程中由于样本量不足导致的火烧面积识别错误和边缘细节不连续的问题。对于DTTL过程，改进的Deeplab V3+网络首先在ImageNet上进行预训练。随后，基于ImageNet预训练权重，使用WorldView-2和哨兵-2数据集来训练所提出的网络。基于训练好的模型对遥感图像进行火烧面积提取实验，结果表明，所提出的方法可以提高提取精度，总体精度（OA）为92.97%，卡帕系数（Kappa）为0.819，高于对比方法，同时还能减少训练时间。我们将该方法应用于识别希腊西部阿提卡地区的火烧面积，取得了令人满意的结果，总体精度为93.58%，卡帕系数为0.8265。本研究证明了改进的Deeplab V3+在识别森林火烧面积方面的有效性，可为森林保护和监测提供有价值的信息。
