Forest Environment
Forest environment research focuses on understanding and monitoring forest ecosystems using diverse data sources, including satellite imagery (multispectral, hyperspectral, SAR), LiDAR, and ground-based measurements. Current research emphasizes the development and application of advanced machine learning models, such as deep learning architectures (U-Net, transformers, CNNs) and ensemble methods (random forests, LightGBM), for tasks like biomass estimation, canopy height mapping, tree species classification, and forest change detection. These advancements are crucial for improving forest management practices, carbon accounting, biodiversity conservation, and addressing the challenges of climate change.
Papers
Learning Decision Trees and Forests with Algorithmic Recourse
Kentaro Kanamori, Takuya Takagi, Ken Kobayashi, Yuichi Ike
Estimating Canopy Height at Scale
Jan Pauls, Max Zimmer, Una M. Kelly, Martin Schwartz, Sassan Saatchi, Philippe Ciais, Sebastian Pokutta, Martin Brandt, Fabian Gieseke
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
Weijun Li, Qiongkai Xu, Mark Dras
Planted: a dataset for planted forest identification from multi-satellite time series
Luis Miguel Pazos-Outón, Cristina Nader Vasconcelos, Anton Raichuk, Anurag Arnab, Dan Morris, Maxim Neumann
Comparing remote sensing-based forest biomass mapping approaches using new forest inventory plots in contrasting forests in northeastern and southwestern China
Wenquan Dong, Edward T. A. Mitchard, Yuwei Chen, Man Chen, Congfeng Cao, Peilun Hu, Cong Xu, Steven Hancock