Mapping Forested Wetland Inundation in the Delmarva Peninsula, USA Using Deep Convolutional Neural Networks

Remote Sensing

Chengquan Huang¹  Zhenhua Zou¹  Xia Li²  Sangchul Lee²  GregoryW. McCarty²  Ling Du²  Xin Zhang³  MeganW. Lang⁴  MelanieK. Vanderhoof⁵ 

[1] Department of Geographical Sciences, University of Maryland, College Park, MD 20742, USA;Hydrology and Remote Sensing Laboratory, USDA-ARS, Beltsville, MD 20705, USA;School of Computing, Mathematics and Digital Technology, Manchester Metropolitan University, Manchester M1 5GD, UK;U.S. Fish and Wildlife Service National Wetlands Inventory, Falls Church, VA 22041, USA;U.S. Geological Survey, Geosciences and Environmental Change Science Center, P.O. Box 25046, DFC, MS980, Denver, CO 80225, USA;

关键词: forested wetland;    inundation;    deep learning;    lidar;    worldview-3;    dem;    topographic wetness index;   

DOI  :  10.3390/rs12040644

来源: DOAJ

【 摘 要 】

The Delmarva Peninsula in the eastern United States is partially characterized by thousands of small, forested, depressional wetlands that are highly sensitive to weather variability and climate change, but provide critical ecosystem services. Due to the relatively small size of these depressional wetlands and their occurrence under forest canopy cover, it is very challenging to map their inundation status based on existing remote sensing data and traditional classification approaches. In this study, we applied a state-of-the-art U-Net semantic segmentation network to map forested wetland inundation in the Delmarva area by integrating leaf-off WorldView-3 (WV3) multispectral data with fine spatial resolution light detection and ranging (lidar) intensity and topographic data, including a digital elevation model (DEM) and topographic wetness index (TWI). Wetland inundation labels generated from lidar intensity were used for model training and validation. The wetland inundation map results were also validated using field data, and compared to the U.S. Fish and Wildlife Service National Wetlands Inventory (NWI) geospatial dataset and a random forest output from a previous study. Our results demonstrate that our deep learning model can accurately determine inundation status with an overall accuracy of 95% (Kappa = 0.90) compared to field data and high overlap (IoU = 70%) with lidar intensity-derived inundation labels. The integration of topographic metrics in deep learning models can improve the classification accuracy for depressional wetlands. This study highlights the great potential of deep learning models to improve the accuracy of wetland inundation maps through use of high-resolution optical and lidar remote sensing datasets.

【 授权许可】

Unknown