Visibility Characteristics over the South China Sea during 1980–2018 Based on Gridded Data Generated by Artificial Neural Network

This paper generated gridded visibility (Vis) data from 1980 to 2018 over the South China Sea (SCS) based on artificial neural network (ANN), and the accuracy of the generated data was tested. Then, temporal and spatial characteristics of Vis in the area were analyzed based on the generated Vis data. The results showed that Vis in the southern SCS was generally better than that in the northern SCS. In the past 39 years, Vis in both spring and winter has improved, especially in winter at a significant increased speed of 0.37 km decade⁻¹. However, Vis in both summer and autumn has decreased, especially in summer with an obvious reduction of 0.84 km decade⁻¹. Overall, Vis is best in summer and worst in winter, averaging 31.89 km in summer and 20.96 km in winter, which may be related to the difference of climatic conditions and wind speed in different seasons. At the same time, probability of low Vis in spring is significantly higher than that in other seasons, especially in the northwest of Hainan Island and the northwest of Malaysia.