Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forest

Abstract In recent decades, the increasing frequency and severity of wildfires have been linked to climate change and human activities. Understanding the dynamics of post-fire vegetation recovery (PVR) is therefore critical for forest ecosystem restoration and management. The present study analysed...

Full description

Saved in:
Bibliographic Details
Main Authors: Loventa Anyango Otieno, Terry Amolo Otieno, Brian Rotich, Katharina Löhr, Harison Kiplagat Kipkulei
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Geoscience
Subjects:
Online Access:https://doi.org/10.1007/s44288-025-00196-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333372124397568
author Loventa Anyango Otieno
Terry Amolo Otieno
Brian Rotich
Katharina Löhr
Harison Kiplagat Kipkulei
author_facet Loventa Anyango Otieno
Terry Amolo Otieno
Brian Rotich
Katharina Löhr
Harison Kiplagat Kipkulei
author_sort Loventa Anyango Otieno
collection DOAJ
description Abstract In recent decades, the increasing frequency and severity of wildfires have been linked to climate change and human activities. Understanding the dynamics of post-fire vegetation recovery (PVR) is therefore critical for forest ecosystem restoration and management. The present study analysed burn severities and investigated the impact of environmental variables on post-fire recovery (PVR) in the Mount Kenya Forest Ecosystem (MKFE). The Random Forest (RF) regression model was employed to predict PVR and identify factors that significantly contribute to PVR in the Mount Kenya Forest ecosystem. Landsat satellite imageries from 2011 to 2021 were used to classify burn severity into seven classes based on the differenced Normalized Burn Ratio (dNBR) index. Climate data, soil organic carbon, and topographic variables were integrated into the RF model to predict trends in PVR. The RF model achieved excellent accuracy with a coefficient of determination (R²) of 0.9013 and a Root Mean Square Error (RMSE) of 0.0280 on the training dataset, and R² of 0.8753 and RMSE of 0.0406 on the validation set. The model further revealed a strong positive relationship between temperature and Land Surface Temperature (LST), as well as vegetation recovery. On the other hand, topographic variables demonstrated a strong negative relationship with vegetation recovery. The combined influence of topographic and temperature condition variables highlights the heterogeneous nature of recovery processes, hence the need for spatially targeted management strategies. These findings have significant implications for adaptive management strategies in tropical montane ecosystems facing increasing wildfire risks.
format Article
id doaj-art-df63b68e50de471bb8706f7207fd5643
institution Kabale University
issn 2948-1589
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Geoscience
spelling doaj-art-df63b68e50de471bb8706f7207fd56432025-08-20T03:45:52ZengSpringerDiscover Geoscience2948-15892025-07-013111810.1007/s44288-025-00196-5Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forestLoventa Anyango Otieno0Terry Amolo Otieno1Brian Rotich2Katharina Löhr3Harison Kiplagat Kipkulei4Department of Geomatic Engineering and Geospatial Information Systems, Jomo Kenyatta University of Agriculture and Technology (JKUAT)Department of Geomatic Engineering and Geospatial Information Systems, Jomo Kenyatta University of Agriculture and Technology (JKUAT)Faculty of Environmental Studies and Resources Development, Chuka UniversityFaculty of Forest and Environment, Eberswalde University for Sustainable Development (HNEE)Department of Geomatic Engineering and Geospatial Information Systems, Jomo Kenyatta University of Agriculture and Technology (JKUAT)Abstract In recent decades, the increasing frequency and severity of wildfires have been linked to climate change and human activities. Understanding the dynamics of post-fire vegetation recovery (PVR) is therefore critical for forest ecosystem restoration and management. The present study analysed burn severities and investigated the impact of environmental variables on post-fire recovery (PVR) in the Mount Kenya Forest Ecosystem (MKFE). The Random Forest (RF) regression model was employed to predict PVR and identify factors that significantly contribute to PVR in the Mount Kenya Forest ecosystem. Landsat satellite imageries from 2011 to 2021 were used to classify burn severity into seven classes based on the differenced Normalized Burn Ratio (dNBR) index. Climate data, soil organic carbon, and topographic variables were integrated into the RF model to predict trends in PVR. The RF model achieved excellent accuracy with a coefficient of determination (R²) of 0.9013 and a Root Mean Square Error (RMSE) of 0.0280 on the training dataset, and R² of 0.8753 and RMSE of 0.0406 on the validation set. The model further revealed a strong positive relationship between temperature and Land Surface Temperature (LST), as well as vegetation recovery. On the other hand, topographic variables demonstrated a strong negative relationship with vegetation recovery. The combined influence of topographic and temperature condition variables highlights the heterogeneous nature of recovery processes, hence the need for spatially targeted management strategies. These findings have significant implications for adaptive management strategies in tropical montane ecosystems facing increasing wildfire risks.https://doi.org/10.1007/s44288-025-00196-5Post-fire vegetation recovery (PVR)Land surface temperatureBurn severityRandom forest modelRemote sensingMount Kenya forest ecosystem
spellingShingle Loventa Anyango Otieno
Terry Amolo Otieno
Brian Rotich
Katharina Löhr
Harison Kiplagat Kipkulei
Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forest
Discover Geoscience
Post-fire vegetation recovery (PVR)
Land surface temperature
Burn severity
Random forest model
Remote sensing
Mount Kenya forest ecosystem
title Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forest
title_full Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forest
title_fullStr Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forest
title_full_unstemmed Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forest
title_short Integrating remote sensing and machine learning to evaluate environmental drivers of post-fire vegetation recovery in the Mount Kenya forest
title_sort integrating remote sensing and machine learning to evaluate environmental drivers of post fire vegetation recovery in the mount kenya forest
topic Post-fire vegetation recovery (PVR)
Land surface temperature
Burn severity
Random forest model
Remote sensing
Mount Kenya forest ecosystem
url https://doi.org/10.1007/s44288-025-00196-5
work_keys_str_mv AT loventaanyangootieno integratingremotesensingandmachinelearningtoevaluateenvironmentaldriversofpostfirevegetationrecoveryinthemountkenyaforest
AT terryamolootieno integratingremotesensingandmachinelearningtoevaluateenvironmentaldriversofpostfirevegetationrecoveryinthemountkenyaforest
AT brianrotich integratingremotesensingandmachinelearningtoevaluateenvironmentaldriversofpostfirevegetationrecoveryinthemountkenyaforest
AT katharinalohr integratingremotesensingandmachinelearningtoevaluateenvironmentaldriversofpostfirevegetationrecoveryinthemountkenyaforest
AT harisonkiplagatkipkulei integratingremotesensingandmachinelearningtoevaluateenvironmentaldriversofpostfirevegetationrecoveryinthemountkenyaforest