ANN-Based Estimation of Low-Latitude Monthly Ocean Latent Heat Flux by Ensemble Satellite and Reanalysis Products

Ocean latent heat flux (LHF) is an essential variable for air-sea interactions, which establishes the link between energy balance, water and carbon cycle. The low-latitude ocean is the main heat source of the global ocean and has a great influence on global climate change and energy transmission. Thus, an accuracy estimation of high-resolution oceanLHFover low-latitude area is vital to the understanding of energy and water cycle, and it remains a challenge. To reduce the uncertainties of individualLHFproducts over low-latitude areas, four machine learning (ML) methods (Artificial Neutral Network (ANN), Random forest (RF), Bayesian Ridge regression and Random Sample Consensus (RANSAC) regression) were applied to estimate low-latitude monthly oceanLHFby using two satellite products (JOFURO-3 andGSSTF-3) and two reanalysis products (MERRA-2 andERA-I). We validated the estimated oceanLHFusing 115 widely distributed buoy sites from three buoy site arrays (TAO,PIRATAandRAMA). The validation results demonstrate that the performance ofLHFestimations derived from theMLmethods (includingANN,RF,BRandRANSAC) were significantly better than individualLHFproducts, indicated byR(2)increasing by 3.7-46.4%. Among them, theLHFestimation using theANNmethod increased theR(2)of the four-individual oceanLHFproducts (ranging from 0.56 to 0.79) to 0.88 and decreased the RMSE (ranging from 19.1 to 37.5) to 11 W m(-2). Compared to three otherMLmethods (RF,BRandRANSAC),ANNmethod exhibited the best performance according to the validation results. The results of relative uncertainty analysis using the triangle cornered hat(TCH)method show that the ensembleLHFproduct usingMLmethods has lower relative uncertainty than individualLHFproduct in most area. TheANNwas employed to implement the mapping of annual average oceanLHFover low-latitude at a spatial resolution of 0.25 degrees during 2003-2007. The oceanLHFfusion products estimated fromANNmethods were 10-30 W m(-2)lower than those of the four original ocean products (MERRA-2,JOFURO-3,ERA-IandGSSTF-3) and were more similar to observations.