Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing

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, we propose a novel method to map...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianchu Wang, Wentao Yang, Ziteng Xu, Wenwen Qi, Liam Taylor, Ming Wang, Wei Wu
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Ecological Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1574954125002614
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233594261700608
author Tianchu Wang
Wentao Yang
Ziteng Xu
Wenwen Qi
Liam Taylor
Ming Wang
Wei Wu
author_facet Tianchu Wang
Wentao Yang
Ziteng Xu
Wenwen Qi
Liam Taylor
Ming Wang
Wei Wu
author_sort Tianchu Wang
collection DOAJ
description 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, we propose a novel method 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). We 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
format Article
id doaj-art-2d384195baf64f77a74f0814bd7d6ffd
institution Kabale University
issn 1574-9541
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Ecological Informatics
spelling doaj-art-2d384195baf64f77a74f0814bd7d6ffd2025-08-20T05:05:20ZengElsevierEcological Informatics1574-95412025-12-019010325210.1016/j.ecoinf.2025.103252Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensingTianchu Wang0Wentao Yang1Ziteng Xu2Wenwen Qi3Liam Taylor4Ming Wang5Wei Wu6Three-gorges reservoir area (Jinyun Mountain, Chongqing) Forest Ecosystem National Observation and Research Station, School of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, ChinaThree-gorges reservoir area (Jinyun Mountain, Chongqing) Forest Ecosystem National Observation and Research Station, School of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China; Academy of Plateau Science and Sustainability, People's Government of Qinghai Province and Beijing Normal University, Xining 810016, China; Corresponding author at: Three-gorges reservoir area (Jinyun Mountain, Chongqing) Forest Ecosystem National Observation and Research Station, School of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China.Three-gorges reservoir area (Jinyun Mountain, Chongqing) Forest Ecosystem National Observation and Research Station, School of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, ChinaNational Institute of Natural Hazards, Ministry of Emergency Management of China, Beijing 100085, ChinaSchool of Geography, University of Leeds, Leeds LS2 9JT, UKSchool of National Safety and Emergency Management, Beijing Normal University, Beijing 100875, China; Joint International Research Laboratory of Catastrophe Simulation and Systemic Risk Governance, Beijing Normal University at Zhuhai, Zhuhai 519087, ChinaNational Disaster Reduction Center, Ministry of Emergency Management of China, Beijing 100124, ChinaTimely 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, we propose a novel method 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). We 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 landslideshttp://www.sciencedirect.com/science/article/pii/S1574954125002614Post-hazard assessmentFast mappingMachine learningRemote sensing
spellingShingle Tianchu Wang
Wentao Yang
Ziteng Xu
Wenwen Qi
Liam Taylor
Ming Wang
Wei Wu
Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing
Ecological Informatics
Post-hazard assessment
Fast mapping
Machine learning
Remote sensing
title Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing
title_full Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing
title_fullStr Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing
title_full_unstemmed Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing
title_short Overcoming cloud obstruction: Fast forest-damage assessment in post-tropical cyclone optical remote sensing
title_sort overcoming cloud obstruction fast forest damage assessment in post tropical cyclone optical remote sensing
topic Post-hazard assessment
Fast mapping
Machine learning
Remote sensing
url http://www.sciencedirect.com/science/article/pii/S1574954125002614
work_keys_str_mv AT tianchuwang overcomingcloudobstructionfastforestdamageassessmentinposttropicalcycloneopticalremotesensing
AT wentaoyang overcomingcloudobstructionfastforestdamageassessmentinposttropicalcycloneopticalremotesensing
AT zitengxu overcomingcloudobstructionfastforestdamageassessmentinposttropicalcycloneopticalremotesensing
AT wenwenqi overcomingcloudobstructionfastforestdamageassessmentinposttropicalcycloneopticalremotesensing
AT liamtaylor overcomingcloudobstructionfastforestdamageassessmentinposttropicalcycloneopticalremotesensing
AT mingwang overcomingcloudobstructionfastforestdamageassessmentinposttropicalcycloneopticalremotesensing
AT weiwu overcomingcloudobstructionfastforestdamageassessmentinposttropicalcycloneopticalremotesensing