Dynamic detection of forest change is the fundamental method of monitoring forest resources and an essential means of preserving the accuracy and timeliness of forest land resource data. This study focuses on a deep learning-based method for dynamic forest change detection using Sentinel-2 satellite data, especially within mountainous areas. First, the performance of various deep learning models (U-Net++, U-Net, LinkNet, DeepLabV3+, and STANet) and various loss functions (CrossEntropyLoss(CELoss), DiceLoss, FocalLoss, and their combinations) are compared on a self-made dataset. Next, the best model and loss function is used to predict the annual forest change in Hunan Province from 2017 to 2021, and the detection results are evaluated in 12 sample areas. Finally, forest changes are detected in Sentinel-2 images for each quarter of 2017–2021. In addition, a dynamic detection map of forest change in Hunan Province from 2017 to 2021 is drawn. The results reveal that the U-Net++ model and the CELoss performed the best on the self-made dataset, with a Precision of 0.795, a Recall of 0.748, and an F1-score of 0.771. The results of annual and quarterly forest change detection were consistent with the changes in the Sentinel-2 images with accurate boundaries. This result demonstrates the high practicality and generalizability of the method used in this paper. This paper achieves a rapid and accurate extraction of multi-temporal Sentinel-2 image forest change areas based on the U-Net++ model, which can be used as a benchmark for future large territorial areas monitoring and management of forest resources.

The use of remote sensing images to detect forest changes is of great significance for forest resource management. With the development and implementation of deep learning algorithms in change detection, a large number of models have been designed to detect changes in multi-phase remote sensing images. Although synthetic aperture radar (SAR) data have strong potential for application in forest change detection tasks, most existing deep learning-based models have been designed for optical imagery. Therefore, to effectively combine optical and SAR data in forest change detection, this paper proposes a double Siamese branch-based change detection network called DSNUNet. DSNUNet uses two sets of feature branches to extract features from dual-phase optical and SAR images and employs shared weights to combine features into groups. In the proposed DSNUNet, different feature extraction branch widths were used to compensate for a difference in the amount of information between optical and SAR images. The proposed DSNUNet was validated by experiments on the manually annotated forest change detection dataset. According to the obtained results, the proposed method outperformed other change detection methods, achieving an F1-score of 76.40%. In addition, different combinations of width between feature extraction branches were analyzed in this study. The results revealed an optimal performance of the model at initial channel numbers of the optical imaging branch and SAR image branch of 32 and 8, respectively. The prediction results demonstrated the effectiveness of the proposed method in accurately predicting forest changes and suppressing cloud interferences to some extent.

The situation of rocky desertification in the southwestern part of China is very serious and has been included as one of three major ecological problems. In this study, using Landsat images as the data sources, we estimated the fractional vegetation coverage (FVC) in the Mengdong River Basin in the Hunan Province over the past 40 years, analyzed its spatio-temporal variation characteristics, and explored the driving mechanism (climate and anthropogenic) using the Mann–Kendall, Hurst index, and partial correlation methods. Specifically, the impact of ecological engineering on the recovery of vegetation cover in rocky desertification areas was analyzed and discussed in this study. The results demonstrate the following: (1) The changes in FVC in the study area before and after the rocky desertification management ecological project differed significantly, with a very small change in the rate of change in the mean value of FVC between 1987 and 1999 (0.9%). (2) The Hurst index of FVC ranged from −0.233 to 2.476, with an average value of 0.864. The area with an H value greater than 0.75 accounted for 80.12%, indicating that the future trend in the vast majority of regions will develop in accordance with the current change trend. (3) The average partial correlation coefficients between FVC and precipitation and between FVC and temperature were −0.02 and 0.27, respectively, showing that FVC is more sensitive to temperature than precipitation. The combination of climate change and human activities is the main cause of FVC change. The contributions of climate change (precipitation and temperature) and human activities to FVC variation are about 30% and 70%, respectively. Ecological restoration projects have a significant positive effect on the recovery of vegetation in rocky desertification areas. The results of this study are intended to provide a scientific basis for analyzing the characteristics of vegetation restoration in existing rocky desertification areas and ecological management in future rocky desertification areas.