AUTHOR=Muhammad Bilal , Rehman Arif U. R. , Mumtaz Faisal , Qun Yin , Zhongkui Jia TITLE=Estimation of above-ground biomass in dry temperate forests using Sentinel-2 data and random forest: a case study of the Swat area of Pakistan JOURNAL=Frontiers in Environmental Science VOLUME=Volume 12 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2024.1448648 DOI=10.3389/fenvs.2024.1448648 ISSN=2296-665X ABSTRACT=Accurate mapping of above-ground biomass is essential for carbon stock quantification and climate change impact assessment, particularly in mountainous areas. This study applies a random forest regression model (RF) to predict the spatial distribution of above-ground biomass (AGB) in Usho (Site-A) and Utror (Site-B) forests located in the northern mountainous region of Pakistan. The predicted maps elucidate AGB variations across these sites, with nonforest areas excluded based on an NDVI threshold value of <0.4. Three different combinations of input datasets were used to predict the biomass, including spectral bands only (SB), vegetation indices (VI) only, and a combination of both spectral bands and vegetation indices (SBVI). Utilizing SB, the biomass ranges between 150 to 286 mg/ha in Site A and 99 to 376 mg/ha in Site B. Meanwhile, employing VI indicated 163 Mg/ha to 337 Mg/ha and 131 to 392 Mg/ha, respectively. The combination of spectral bands and vegetation indices yielded AGB values of 145 to 290 Mg/ha in Site-A and 116 to 389 Mg/ha in Site-B. Site-A's northern and western regions, characterized by higher altitudes and lower forest density, notably showed lower biomass values than other regions. Conversely, similar regions in Site-B, situated at lower latitudes, demonstrated different biomass ranges. The RF model exhibited robust accuracy, with R2 values of 0.74 and 0.83 for spectral bands and vegetation indices,respectively. However, with a combination of both, R2 of 0.79 was achieved. Furthermore, altitudinal gradients significantly influence the biomass distribution across both sites, with specific elevation ranges yielding optimal results. The AGB variation along the slope further corroborated these findings. In both sites, the western aspects showed the highest biomass across all combinations of input datasets. The variable importance analysis highlighted that ARVI8a, NDI45, Band12, Band11, TSAVI8, and ARVI8a are significant predictors in sites A and B, respectively. This comprehensive analysis enhances our understanding of AGB distribution in the mountainous forests of Pakistan, offering valuable insight for forest management and ecological studies.