Uncovering the Potential of Multi-Temporally Integrated Satellite Imagery for Accurate Tree Species Classification

In this study, prior to the launch of compact advanced satellite 500 (CAS500-4), which is an agriculture and forestry satellite, nine major tree species were classified using multi-temporally integrated imageries based on a random forest model RapidEye Sentinel-2. Six scenarios devised considering composition input dataset, was used evaluate accuracy different datasets for each scenario. The highest accuracy, with values 84.5% (kappa value: 0.825), achieved by Sentinel-2 spectral wavelengths along gray-level co-occurrence matrix (GLCM) statistics (Scenario IV). variable importance analysis, short-wave infrared (SWIR) band GLCM found be sequentially higher. This study proposes optimal dataset classification variance error range establish window size calculation methodology. We also demonstrate effectiveness in improving model, achieving approximate improvement 20.5%. findings suggest that combining advantages platforms statistical methods can lead significant improvements contribute better resource assessments management strategies face climate change.