Publications

Zhang, GD; Yin, GF; Zhang, Y; Hu, JC; Li, ZY; Wang, CJ; Ma, DJ; Xie, JL (2025). An RTM-Driven Machine Learning Approach for Estimating High-Resolution FAPAR From LANDSAT 5/7/8/9 Surface Reflectance. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 18, 10225-10240.

Abstract
Fraction of absorbed photosynthetically active radiation (FAPAR) is an essential indicator of vegetation productivity and carbon uptake. Although coarse-resolution FAPAR products from moderate-resolution imaging spectroradiometer (MODIS) and visible infrared imaging radiometer suite (VIIRS) sensors have supported global vegetation monitoring, their limitations in characterizing heterogeneity at ecosystem scales necessitate Landsat-derived FAPAR at the 30-m resolution. This study developed a practical approach integrating radiative transfer (RT) modeling and machine learning to estimate 30-m FAPAR from Landsat surface reflectance. A coupled land-atmosphere RT model (RTM) and shuffled complex evolution optimization algorithm were first implemented at globally distributed VIIRS pixels for realistic simulation of land surface reflectance corresponding Landsat spectral bands and FAPAR under various conditions. The simulated dataset encompassing diverse canopy structural and atmospheric states is utilized to train a random forest model relating Landsat surface reflectance bands to FAPAR. The trained RF model was applied to estimate long-term FAPAR from Landsat 5/7/8/9 surface reflectance data and demonstrated reliable performance in capturing FAPAR dynamics across vegetation types. Comprehensive validation of the Landsat FAPAR was conducted using global field measurements from three observation networks, including the validation of land European remote sensing instruments, ImagineS, and Copernicus Ground-Based Observations for Validation projects, which involved shrubland, forest, grassland, and cropland; coarse-resolution FAPAR products were also used for comparison to evaluate our estimates. Validation results demonstrate good agreement of the estimated Landsat FAPAR with ground measurements, achieving R-2 of 0.876, RMSE of 0.108, and bias of 0.032. Consistent accuracy was attained across different Landsat sensors. The validation performance of the Landsat FAPAR over various land cover types was shrubland (R-2: 0.848; RMSE: 0.092), forest (R-2: 0.876; RMSE: 0.101), grassland (R-2: 0.739; RMSE: 0.118), and cropland (R-2: 0.839; RMSE: 0.125). Comparison against global land surface satellite/MODIS products shows improved accuracy over the existing FAPAR datasets, benefiting from the ability of Landsat to resolve within-pixel heterogeneity. This study synergized the strengths of RTM and machine learning algorithm while overcoming the limitations of RTM parameterization and generalization, providing an efficient and robust Landsat FAPAR estimation approach. The demonstrated approach creates opportunities to generate a long-term 30-m FAPAR record by leveraging the continuity of Landsat observations to advance vegetation productivity monitoring and carbon science.

DOI:
10.1109/JSTARS.2024.3428481

ISSN:
2151-1535