Forest Carbon

Forest carbon research focuses on accurately quantifying and mapping forest biomass and carbon stocks to understand their role in the global carbon cycle and inform climate change mitigation strategies. Current research emphasizes developing improved methods for estimating forest carbon using remote sensing data (e.g., LiDAR, satellite imagery) combined with advanced machine learning techniques, such as random forests, LightGBM, and deep learning architectures (including Minkowski convolutional neural networks), to create high-resolution maps. These advancements aim to replace less accurate methods and provide more precise data for carbon accounting, forest management, and the verification of carbon offset projects, ultimately enhancing the reliability of climate change mitigation efforts. The improved accuracy and spatial resolution of these models are crucial for effective policy and conservation decisions.