VIIRS-derived annual mean chlorophyll-a in China large lakes from 2012 to 2021

This dataset included annual mean Chl-a in China's large lakes (>50 km2) derived from VIIRS-SNPP imagery from 2012 to 2021. The dataset is stored as the Geo-Tiff data.

To generate this dataset, we develop a practical deep neural network (DNN) model .  The DNN model performed satisfactory performance on Chl-a retrievals (MR = 0.86, MAPE = 32%, Bias = 5%) over the three magnitudes (0.1–300 μg L−1) spanning clear/deep to turbid/shallow waters, with significant improvements compared with the existing algorithms and other machine learning approaches. 

The dataset is related to a under-review manuscript and we will release it when the paper is published.