Remote Sensing Data-Driven Carbon Sink Prediction for Algae and Shellfish Aquaculture

Carbon emissions exacerbate global warming and climate change, resulting in air pollution and increased Carbon dioxide (CO
2
) concentrations, bringing global climate change problems. Algae and shellfish aquaculture in the ocean make an important contribution to CO
2
uptake and fixation. The traditional estimation method of removable carbon sink relies too much on field survey year data, which leads to poor scientific and predictive carbon sink estimation. The development of satellite remote sensing provides convenient access to marine environmental data. In order to solve the above problems, this paper proposed a prediction model of carbon sinks in algae and shellfish aquaculture driven by remote sensing data. Linear regression models are used to evaluate the correlation between monthly marine elements and algae/shellfish prediction from 2013 to 2020, including cultivation area, sea surface temperature (SST), chlorophyll-a concentration (Chl-a), and the months with the highest correlation are chosen. By comparing linear, logarithmic, and quadratic models for different environmental factors, it is concluded that the quadratic model is the most reliable for explaining aquaculture prediction with a single covariate. Therefore, in multiple regression, the quadratic model is chosen