Dr. Han Ma’s recent publication on Remote Sensing of Environment

The first gap-free 20 m 5-day LAI/FAPAR products over China (2018-2023) from integrated Landsat-8/9 and Sentinel-2 Analysis Ready Data

Congratulations to Dr. Han Ma and colleagues on publishing a research article on Remote Sensing of Environment (Vol. 331, 115048). The title of the article is “The first gap-free 20 m 5-day LAI/FAPAR products over China (2018-2023) from integrated Landsat-8/9 and Sentinel-2 Analysis Ready Data” and it is now available at https://doi.org/10.1016/j.rse.2025.115048. The product is available at www.glass.hku.hk.

This study presents a temporal deep learning model that generates the first gap-free, 20 m and 5-day Leaf Area Index (LAI) and Fraction of Absorbed Photosynthetically Active Radiation (FAPAR) products over China. These high-resolution variables are essential for environmental monitoring, but their production is often hindered by cloud cover. The proposed approach addresses this challenge by using a hybrid Bidirectional LSTM with an attention mechanism to leverage time-series information from integrated Landsat-8/9 and Sentinel-2 data. Unlike traditional pixel-based methods, this model effectively estimates values under varying cloud conditions, ensuring spatiotemporally continuous and physically consistent products. The new Hi-GLASS LS20 products were validated against 4,046 in-situ measurements, achieving high accuracy (LAI R²=0.79, FAPAR R²=0.86) and demonstrating superior continuity over existing datasets.

Flowchart of model development and 20 m/5-day Hi-GLASS LS20 LAI/FAPAR product generation.

Spatial comparison of the Hi-GLASS LS20 LAI product (b) with the GLASS LAI product (a) over China in March 2022. The Hi-GLASS product provides complete, gap-free coverage, in contrast to the corresponding 5-day composite NDVI map (m) which has large gaps (grey areas) due to cloud cover.

Reference: Ma, H., Wang, Q., Li, W., Chen, Y., Xu, J., Ma, Y., Huang, J., Liang, S., 2025. The first gap-free 20 m 5-day LAI/FAPAR products over China (2018–2023) from integrated Landsat-8/9 and Sentinel-2 Analysis Ready Data. Remote Sensing of Environment 331, 115048. https://doi.org/10.1016/j.rse.2025.115048

Keywords: LAI, FAPAR, Gap-free, High resolution, Deep learning, Data integration, Landsat-8/9, Sentinel-2