Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science

The invasion of Prosopis juliflora poses a growing threat to dryland ecosystems and pas-toral livelihoods across East Africa. This study presents an integrative approach that combines satellite remote sensing, machine learning, and participatory GIS (PGIS) to de-tect and map the spatial extent and s...

Full description

Bibliographic Details
Main Authors: Cherotich, Fredah, Galgallo, Diba, Dhulipala, Ram, Whitbread, Anthony M, Paliwal, Ambica
Format: Preprint
Language:Inglés
Published: 2025
Subjects:
Online Access:https://hdl.handle.net/10568/178907
_version_ 1855528869899010048
author Cherotich, Fredah
Galgallo, Diba
Dhulipala, Ram
Whitbread, Anthony M
Paliwal, Ambica
author_browse Cherotich, Fredah
Dhulipala, Ram
Galgallo, Diba
Paliwal, Ambica
Whitbread, Anthony M
author_facet Cherotich, Fredah
Galgallo, Diba
Dhulipala, Ram
Whitbread, Anthony M
Paliwal, Ambica
author_sort Cherotich, Fredah
collection Repository of Agricultural Research Outputs (CGSpace)
description The invasion of Prosopis juliflora poses a growing threat to dryland ecosystems and pas-toral livelihoods across East Africa. This study presents an integrative approach that combines satellite remote sensing, machine learning, and participatory GIS (PGIS) to de-tect and map the spatial extent and socio-ecological impacts of Prosopis juliflora in Baringo County, Kenya. We evaluated the performance of three satellite platforms, Sentinel-1, Sentinel-2, and PlanetScope, using a Random Forest classifier trained on field-collected presence–absence data and vegetation indices. Sentinel-2 outperformed the other sensors, achieving a classification accuracy of 90.65%, with key variables including Visible At-mospherically Resistant Index (VARI), Ratio Vegetation Index (RVI) and red-edge bands emerging as the most important predictors. To enhance contextual understanding and validate remote sensing outputs, we conducted PGIS sessions with gender-disaggregated community groups, capturing local perceptions of invasion hotspots and blocked access to grazing routes and water sources. The comparison of satellite-derived maps and PGIS outputs revealed strong spatial congruence, particularly along water bodies, roads, and croplands. Our findings demonstrate the potential of combining Earth observation and citizen science to generate actionable knowledge for managing invasive species in da-ta-scarce dryland environments. This hybrid framework supports inclusive and spatially targeted interventions for rangeland restoration and ecosystem resilience.
format Preprint
id CGSpace178907
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
record_format dspace
spelling CGSpace1789072025-12-17T07:58:35Z Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science Cherotich, Fredah Galgallo, Diba Dhulipala, Ram Whitbread, Anthony M Paliwal, Ambica Prosopis juliflora rangeland degradation remote sensing machine learning artificial intelligence citizen science The invasion of Prosopis juliflora poses a growing threat to dryland ecosystems and pas-toral livelihoods across East Africa. This study presents an integrative approach that combines satellite remote sensing, machine learning, and participatory GIS (PGIS) to de-tect and map the spatial extent and socio-ecological impacts of Prosopis juliflora in Baringo County, Kenya. We evaluated the performance of three satellite platforms, Sentinel-1, Sentinel-2, and PlanetScope, using a Random Forest classifier trained on field-collected presence–absence data and vegetation indices. Sentinel-2 outperformed the other sensors, achieving a classification accuracy of 90.65%, with key variables including Visible At-mospherically Resistant Index (VARI), Ratio Vegetation Index (RVI) and red-edge bands emerging as the most important predictors. To enhance contextual understanding and validate remote sensing outputs, we conducted PGIS sessions with gender-disaggregated community groups, capturing local perceptions of invasion hotspots and blocked access to grazing routes and water sources. The comparison of satellite-derived maps and PGIS outputs revealed strong spatial congruence, particularly along water bodies, roads, and croplands. Our findings demonstrate the potential of combining Earth observation and citizen science to generate actionable knowledge for managing invasive species in da-ta-scarce dryland environments. This hybrid framework supports inclusive and spatially targeted interventions for rangeland restoration and ecosystem resilience. 2025-12-02 2025-12-17T07:58:34Z 2025-12-17T07:58:34Z Preprint https://hdl.handle.net/10568/178907 en Open Access Cherotich, F., Galgallo, G., Dhulipala, R., Whitbread, A. and Paliwal, A. 2025. Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science. Preprints. https://doi.org/10.20944/preprints202512.0171.v1
spellingShingle Prosopis juliflora
rangeland degradation
remote sensing
machine learning
artificial intelligence
citizen science
Cherotich, Fredah
Galgallo, Diba
Dhulipala, Ram
Whitbread, Anthony M
Paliwal, Ambica
Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science
title Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science
title_full Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science
title_fullStr Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science
title_full_unstemmed Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science
title_short Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science
title_sort tracking rangeland degradation from prosopis invasion in kenyan rangeland a multi source approach combining remote sensing machine learning and citizen science
topic Prosopis juliflora
rangeland degradation
remote sensing
machine learning
artificial intelligence
citizen science
url https://hdl.handle.net/10568/178907
work_keys_str_mv AT cherotichfredah trackingrangelanddegradationfromprosopisinvasioninkenyanrangelandamultisourceapproachcombiningremotesensingmachinelearningandcitizenscience
AT galgallodiba trackingrangelanddegradationfromprosopisinvasioninkenyanrangelandamultisourceapproachcombiningremotesensingmachinelearningandcitizenscience
AT dhulipalaram trackingrangelanddegradationfromprosopisinvasioninkenyanrangelandamultisourceapproachcombiningremotesensingmachinelearningandcitizenscience
AT whitbreadanthonym trackingrangelanddegradationfromprosopisinvasioninkenyanrangelandamultisourceapproachcombiningremotesensingmachinelearningandcitizenscience
AT paliwalambica trackingrangelanddegradationfromprosopisinvasioninkenyanrangelandamultisourceapproachcombiningremotesensingmachinelearningandcitizenscience