Machine learning approach for Forest Biomass Modelling with In-Situ and Remote Sensing Data in Narmadapuram central India

The study estimation of forest Biomass using In-Situ and Remote Sensing data presents a comprehensive investigation into the estimation of forest biomass, a pivotal component of forest ecosystems and a key parameter in understanding carbon dynamics. This research merges in-situ field measurements with cutting-edge remote sensing technologies to develop robust and accurate models for predicting forest biomass. The research leverages data acquired from ground-based measurements, including tree diameter, height, and species composition, in tandem with remote sensing data obtained from satellite platforms. Various modelling techniques, including machine learning algorithms and statistical analyses, are applied to establish the relationship between these datasets and forest biomass. The study evaluates the performance of multiple methods, such as Exponential Regression, Linear Regression, Random Forest, and Support Vector Machines (SVM). The results indicate that Random Forest outperformed other methods with an RMSE of 1.61, MAE of 0.84, relRMSE of 0.1046609, and r² of 0.51. In comparison, Exponential Regression achieved an RMSE of 2.26, MAE of 0.97, relRMSE of 0.1471322, and r² of 0.04, Linear Regression produced an RMSE of 2.48, MAE of 1.34, relRMSE of 0.1616262, and r² of -0.16; while SVM recorded an RMSE of 2.00, MAE of 1.06, relRMSE of 0.1301456, and r² of 0.25. The outcomes of this study hold significant implications for forest management, climate change mitigation, and conservation efforts. Accurate forest biomass estimates are crucial for assessing carbon storage, understanding ecosystem health, and designing sustainable forestry practices. Moreover, by integrating in-situ and remote sensing data, this research contributes to the ongoing global efforts to monitor and protect the world's forests in an era of environmental challenges. The findings of this study provide valuable insights for policymakers, environmentalists, and researchers engaged in forestry, ecology, and climate change studies, facilitating more informed decisions and sustainable practices in forest management and conservation.