Mapping national-scale aquaculture ponds based on the Google Earth Engine in the Chinese coastal zone

Aquaculture plays a key role in addressing global food security and nutrition issues. However, the rapid expansion of the aquaculture industry has imposed tremendous pressure on coastal environments in some developing countries. The aquaculture industry in China is the largest worldwide. However, to date, we know little about the spatial distribution of aquaculture ponds. This study proposed an efficient method for mapping aquaculture ponds on a national scale using Landsat 8 images based on the Google Earth Engine (GEE) platform. We integrated spectral, spatial characteristics and morphological operations to construct a decision tree classifier that was successfully used to extract the aquaculture pond regions in the Chinese coastal zone in 2017, with an overall accuracy of 0.96 (0.94–0.97, 95% confidence interval) and kappa coefficient of 0.82. When compared with the results of visual interpretation and other relevant studies, our method exhibited good consistency. The results provided a detailed spatial distribution of the aquaculture ponds in the Chinese coastal zone and revealed that the total area of aquaculture ponds is approximately 15632.64 km2 (14386.98 km2–17924.95 km2, 95% confidence interval), which is mainly concentrated in the Bohai Rim, Jiangsu Coastal Plain, and Guangdong coastal region. This work demonstrated that this method can generate high-quality datasets of the spatial distribution of aquaculture ponds and could map the global aquaculture ponds distribution. •The first national-scale application to extract aquaculture ponds using satellite images based on Google Earth Engine.•We propose a decision tree classifier by integrating spectral, spatial characteristics and morphological operations.•The method can generate high-quality datasets of the spatial distribution of aquaculture ponds in a large scale.