Identifying suitable dam sites using geospatial data and machine learning: a case study of the katsina-ala river in Benue State, Nigeria

Sustainable water resource management in Nigeria faces significant challenges due to suboptimal dam site selection, exacerbating flood risks and inefficient water utilization. This study addresses this gap by developing a robust geospatial and machine learning-integrated Multi-Criteria Decision Anal...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Earth science informatics Ročník 18; číslo 3; s. 497
Hlavní autoři: Akajiaku, Ugochukwu Charles, Ohimain, Elijah Ige, Olodiama, Ebikombo-ere B., Eteh, Desmond Rowland, Winston, Ayebawanaemi G., Chukwuemeka, Prince, Otutu, Anslem O., Bamiekumo, Becky Peremoboere, Imoni, Okes
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2025
Springer Nature B.V
Témata:
Accuracy
Algorithms
Analytic hierarchy process
Community
Construction sites
Dam construction
Dams
Damsites
Datasets
Decision analysis
Decision making
Digital Elevation Models
Earth and Environmental Science
Earth Sciences
Earth System Sciences
Economic development
Elevation
Environmental impact
Environmental risk
Flood management
Flood risk
Floods
Geographic information systems
Hydroelectric power
Hydrologic data
Hydrology
Information Systems Applications (incl.Internet)
Land cover
Land use
Machine learning
Multiple criterion
Ontology
Optimization
Rainfall
Rainfall data
Remote sensing
Rivers
Simulation and Modeling
Site selection
Space Exploration and Astronautics
Space Sciences (including Extraterrestrial Physics
Spatial analysis
Spatial data
Stream order
Streams
Subjectivity
Support vector machines
Sustainability management
Sustainable development
Topography
Water consumption
Water management
Water resources management
Water use
Nigeria
Flood risk mitigation
GIS
Deep learning
Dam
Machine learning
Geospatial analysis
Water access
ISSN:1865-0473, 1865-0481
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Sustainable water resource management in Nigeria faces significant challenges due to suboptimal dam site selection, exacerbating flood risks and inefficient water utilization. This study addresses this gap by developing a robust geospatial and machine learning-integrated Multi-Criteria Decision Analysis (MCDA) approach to identify optimal dam sites along the Katsina-Ala River in Benue State. Using geospatial datasets, including Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM), Sentinel-2 imagery, and historical rainfall data, we employed the Analytical Hierarchy Process (AHP) to assign weights to key suitability factors. Elevation, stream order, slope, distance from the stream, land use/land cover, rainfall, soil, and geology were considered, with stream order (34%) and slope (21%) identified as the most influential criteria. Machine learning models, specifically Support Vector Machine (SVM) classification, were utilized for validation, achieving an 82% agreement with expert assessments. Results indicate that areas with lower elevations (108–151 m), gentle slopes, proximity to streams (≤ 300 m), and high rainfall (218–224 mm) are most suitable for dam construction. Proposed Sites 1 (KA1) and 2 (KA2) were identified as optimal locations based on their high suitability scores. This research highlights the effectiveness of integrating machine learning, geospatial analysis, and MCDA in enhancing decision-making processes for dam site selection. The suitability map aids policymakers in developing resilient infrastructure and sustainable water management in flood-prone areas. This study helps mitigate flood risks, optimize water use, and promote long-term environmental and socio-economic sustainability in Nigeria by addressing critical gaps in current practices.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1865-0473
1865-0481
DOI:10.1007/s12145-025-01974-y