Improving Satellite Retrieval of Coastal Aquaculture Pond by Adding Water Quality Parameters

Abstract

Coastal aquaculture is an important supply of animal proteins for human consumption, which is expanding globally. Meanwhile, extensive aquaculture may increase nutrient loadings and environmental concerns along the coast. Accurate information on aquaculture pond location is essential for coastal management. Traditional methods use morphological parameters to characterize the geometry of surface waters to differentiate artificially constructed conventional aquaculture ponds from other water bodies. However, there are other water bodies with similar morphology (e.g., saltworks, rice fields, and small reservoirs) that are difficult to distinguish from aquaculture ponds, causing a lot of omission/commissioning errors in areas with complex land-use types. Here, we develop an extraction method with shape and water quality parameters to map aquaculture ponds, including three steps: (1) Sharpen normalized difference water index to detect and binarize water pixels by the Otsu method; (2) Connect independent water pixels into water objects through the four-neighbor connectivity algorithm; and (3) Calculate the shape features and water quality features of water objects and input them into the classifier for supervised classification. We selected eight sites along the coast of China to evaluate the accuracy and generalization of our method in an environment with heterogeneous pond morphology and landscape. The results showed that six transfer characteristics including water quality characteristics improved the accuracy of distinguishing aquaculture ponds from salt pans, rice fields, and wetland parks, which typically had F1 scores > 85%. Our method significantly improved extraction efficiency on average, especially when aquaculture ponds are mixed with other morphological similar water bodies. Our identified area was in agreement with statistics data of 12 coastal provinces in China. In addition, our approach can effectively improve water objects when high-resolution remote sensing images are unavailable. This work was applied to open-source remote sensing imagery and has the potential to extract long-term series and large-scale aquaculture ponds globally.