Code for the single U-Net model (Model 11).

Land cover and plant species identification using satellite images and deep learning approaches have recently been a widely addressed area of research. However, mangroves, a specific species that have significantly declined in quantity and quality worldwide despite their numerous benefits, have not been the subject of attention. The novelty of this research is to deal with this species based on an advanced deep learning solution (a proposed ensemble U-Net model) and a high-resolution Planet satellite imagery (5 m x 5 m) in a case study of Ngoc Hien district, Ca Mau province, Vietnam. Twelve single U-Net backbone models were trained, and three quantitative metrics (Intersection over Union, F1-score, and Overall Accuracy) were used to evaluate. The findings indicate that three out of twelve models (MobileNet, SEResNeXt-101 and Efficientnet-B7) experienced the most efficient assessment results for identifying all classes, in which the MobileNet model was the best. These models were applied for the ensemble model’s development. The ensemble model’s quantitative assessment metrics increased considerably by about 3–10% compared to the single-component models. The IoU, F1-score, and OA values of this model were 80.08%, 95.82%, and 95.90%, respectively. Three classes of mangrove species (Avicennia alba, Rhizophora apiculate, and mixed mangroves) in the ensemble model had more uniform assessment results. In conclusion, to achieve optimal classification outcomes, a land-cover map comprising mangrove species is possibly established using the proposed ensemble model, while a distribution map of mangrove species enables to be developed using the MobileNet model.

近年来，利用卫星影像与深度学习方法开展土地覆盖及植物物种识别的研究已成为广受关注的热点研究领域。然而，红树林虽具备多重生态价值，却在全球范围内出现了数量与质量的双重显著下降，目前尚未得到足够的研究关注。本研究的创新点在于，以越南金瓯省玉贤县为研究案例区，结合先进深度学习方案（所提出的集成U-Net模型）与5米×5米分辨率的高分辨率Planet卫星影像，针对红树林物种开展研究。研究共训练了12个单一U-Net骨干模型，并采用交并比（Intersection over Union, IoU）、F1分数（F1-score）与总体精度（Overall Accuracy, OA）三项定量指标开展模型评估。评估结果显示，12个单一模型中，MobileNet、SEResNeXt-101与Efficientnet-B7这3个模型在全类别识别任务中表现最优，其中MobileNet模型的综合性能最佳。上述表现优异的模型被用于构建集成U-Net模型。与单一骨干模型相比，集成U-Net模型的各项定量评估指标均获得显著提升，增幅约为3%~10%。该集成模型的交并比、F1分数与总体精度分别为80.08%、95.82%与95.90%。集成U-Net模型对三类红树林物种——白骨壤（Avicennia alba）、尖瓣海莲（Rhizophora apiculate）与混生红树林——的评估结果更为均匀一致。综上，利用本研究提出的集成U-Net模型可构建包含红树林物种信息的高精度土地覆盖图，以实现最优分类效果；而利用MobileNet模型则可生成红树林物种分布地图。