Supplementaries of paper "Performance Comparison of Multi-Task and Single-Task Learning in Ocean Color Retrieval: A Case Study of Hong Kong Coastal Waters"

Read full text
Authors: Ma, Chunlei
Cited by: 0

Abstract

The uploaded package “MTL_example.rar” contains three components: (1) a sample model input file, “SNPP_VIIRS.20150413T054200.L2_OC_reprojected.nc”, which provides VIIRS remote-sensing data used to demonstrate the retrieval workflow; (2) the trained multi-task learning neural network file “MTL_net.mat”; and (3) an example MATLAB script “MTL_retrieval_example.m”, which illustrates how to load the sample data, apply the trained MTL model, and generate retrievals of Chl-a, TSS, and water clarity. The uploaded package "TSS_SVM_example.rar" contains three components: (1) the same sample model input file; (2) the trained Support Vector Machine model file “SVM_TSS_Model.mat”, which represents the optimal algorithm for retrieving TSS; and (3) an example MATLAB script “TSS_retrieval_example.m”, which illustrates how to load the input data, apply the trained SVM model, and generate retrievals of TSS.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
7 February 2026
Document type
Dataset