Improving the accuracy of canopy height mapping in rubber plantations based on stand age, multi-source satellite images, and random forest algorithm

Accurate canopy height mapping is crucial for estimating rubber plantation productivity, carbon storage, and biomass accurately. The prevailing method combines Global Ecosystem Dynamics Investigation (GEDI) data with spatially continuous variables. However, these models often overlook forest growth variables and face challenges with GEDI geolocation errors. This study introduces a novel GEDI filtering technique to screen for high-quality footprints and incorporates rubber plantation age as a key factor. Utilizing a comprehensive dataset from Landsat-8, Sentinel-2, and Phased Array type L -band Synthetic Aperture Radar (PALSAR-2), we established a model for the canopy height of rubber plantations. Our multifaceted approach yields significant improvements: 1) enhanced rubber canopy height estimation accuracy, evidenced by an R-squared value of 0.86 and reduced error metrics (RMSE = 1.68, MAE = 1.32); 2) The mean difference of -2.81 +/- 3.05 m compared with Potapov's study and -5.62 +/- 6.64 m compared with Liu's, indicating superior consistency and reduced underestimation; and 3) Accurately average canopy heights for rubber plantations aged between 3 and 30 years on Hainan Island at 15.67 +/- 1.87 m, spanning a height range of 5.02 to 18.59 m. The integration of stand age and the GEDI footprint filtering technique markedly enhances canopy height estimation accuracy, offering valuable insights for ecological monitoring and the advancement of sustainable forest management practices.