A new satellite-derived dataset for marine aquaculture areas in China's coastal region

Abstract

China has witnessed extensive development of the marine aquaculture industry over recent years. However, such rapid and disordered expansion posed risks to coastal environment, economic development, and biodiversity protection. This study aimed to produce an accurate national-scale marine aquaculture map at a spatial resolution of 16 m, using a proposed model based on deep convolution neural networks (CNNs) and applied it to satellite data from China's GF-1 sensor in an end-To-end way. The analyses used homogeneous CNNs to extract high-dimensional features from the input imagery and preserve information at full resolution. Then, a hierarchical cascade architecture was followed to capture multi-scale features and contextual information. This hierarchical cascade homogeneous neural network (HCHNet) was found to achieve better classification performance than current state-of-The-Art models (FCN-32s, Deeplab V2, U-Net, and HCNet). The resulting marine aquaculture area map has an overall classification accuracy span classCombining double low line"inline-formula"&/span 95 % (95.2 %-96.4, 95 % confidence interval). And marine aquaculture was found to cover a total area of span classCombining double low line"inline-formula"g1/4/span 1100 kmspan classCombining double low line"inline-formula"2/span (1096.8-1110.6 kmspan classCombining double low line"inline-formula"2/span, 95 % confidence interval) in China, of which more than 85 % is marine plant culture areas, with 87 % found in the Fujian, Shandong, Liaoning, and Jiangsu provinces. The results confirm the applicability and effectiveness of HCHNet when applied to GF-1 data, identifying notable spatial distributions of different marine aquaculture areas and supporting the sustainable management and ecological assessments of coastal resources at a national scale. The national-scale marine aquaculture map at 16 m spatial resolution is published in the Google Maps kmz file format with georeferencing information at a hrefCombining double low line"https://doi.org/10.5281/zenodo.3881612"https://doi.org/10.5281/zenodo.3881612/a (Fu et al., 2020)./p.