A research team led by Associate Professor Yang Wentao from the School of Soil and Water Conservation has published a study in Ecological Informatics, a leading journal in environmental informatics. Their paper, titled "Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing", presents a significant advancement in rapidly assessing forest damage after natural disasters.

Timely mapping of damaged forests is critical for disaster assessment. However, remote sensing data immediately after natural hazards is always scarce and susceptible to cloud contamination, hindering holistic assessment of damaged forests in a timely manner. Herein, a novel method was proposed to map damaged forests obscured by clouds in post-hazard images by taking the September 2024 typhoon Yagi in Hainan Island, China as an example. Our approach uniquely integrates observed forest damage in cloud-free pixels with its influencing factors (the maximum wind speed and cumulative rainfall during the typhoon, terrain (elevation, slope and aspect), and canopy height) to interpolate the relationship into cloud-covered pixels by using three mainstream machine learning models (XGBoost, artificial neural networks and random forest). The research team found severe forest damage in the Northeast Hainan and the total area of the typhoon-damaged forests accounts for 12.8 %–15.5 % of the island's forest cover. This method can also be used for fast mapping of forest damage in partially available remote sensing images after other major natural hazards such as wildfires and landslides.

Wang Tianchu, a master's student from the School of Soil and Water Conservation, is the first author of the paper, with Yang Wentao as the corresponding author. Beijing Forestry University is the signature unitr of the first author. The research was also supported by researchers from the National Research Institute for Disaster Prevention and Control, the University of Leeds, UK, Beijing Normal University, and the National Center for Disaster Reduction and other institutions.

This research was funded by the National Natural Science Foundation of China (No. 42407257) and the National Key Research and Development Program of China (No. 2024YFC3012603–04)

Paper link: https://www.sciencedirect.com/science/article/pii/S1574954125002614

Written by Wang Tianchu
Translated and edited by Song He
Reviewed by Yu Yangyang