Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support
This study presents the development and integration of predictive models for the Normalized Difference Vegetation Index (NDVI) and Bare Soil Index (BSI) using the XGBoost algorithm within the North Rift Weather Prediction System (NRWPS) to enhance ecosystem monitoring in Kenya's North Rift regi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844025009296 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856751568486400 |
|---|---|
| author | John W. Makokha Peter W. Barasa Geoffrey W. Khamala |
| author_facet | John W. Makokha Peter W. Barasa Geoffrey W. Khamala |
| author_sort | John W. Makokha |
| collection | DOAJ |
| description | This study presents the development and integration of predictive models for the Normalized Difference Vegetation Index (NDVI) and Bare Soil Index (BSI) using the XGBoost algorithm within the North Rift Weather Prediction System (NRWPS) to enhance ecosystem monitoring in Kenya's North Rift region. Trained on a comprehensive dataset spanning 1995 to 2020, which includes precipitation (from the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS)), temperature (TerraClimate), historical NDVI (Landsat 4–5 Thematic Mapper (from 1995 to 2013) and Landsat 7 Enhanced Thematic Mapper plus (ETM+) (from 2014 to 2020)), and BSI (SoilGrids) data, the models effectively capture the complex relationships between environmental factors and vegetation health. The BSI model achieved an MSE of 0.029, an MAE of 0.019, and an R-squared score of 0.93, while the NDVI model yielded an MSE of 0.002, an MAE of 0.024, and an R-squared score of 0.945. These results demonstrate the models' strong predictive accuracy, enabling precise assessments of vegetation health and bare soil exposure. By analyzing temporal variations in vegetation health and land degradation from 1995 to 2020, the study identifies a significant inverse relationship between NDVI and BSI, where increasing bare soil exposure corresponds to declining vegetation health. The analysis also reveals that climatic factors particularly temperature (minimum and maximum) and precipitation play a critical role in shaping these trends, with high temperatures after 2000 associated with reduced NDVI, while regions with higher precipitation show healthier vegetation and lower BSI. The successful development of the NRWPS model provides significant opportunities for informing land management strategies, conservation efforts, and agricultural practices, enabling data-driven decision-making. Moreover, its integration into larger decision support systems allows for proactive interventions to mitigate land degradation and climate change stressors. This study emphasizes the importance of sustainable land-use practices and climate adaptation strategies to preserve vegetation health and manage ecosystem vulnerabilities effectively in the wake of regional climate change with the North Rift region most affected. |
| format | Article |
| id | doaj-art-8aaa99f07ada453ea76bc2f7dcd3c914 |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-8aaa99f07ada453ea76bc2f7dcd3c9142025-02-12T05:31:26ZengElsevierHeliyon2405-84402025-02-01114e42549Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision supportJohn W. Makokha0Peter W. Barasa1Geoffrey W. Khamala2Department of Science, Technology and Engineering, Kibabii University, Bungoma, Kenya; Corresponding author.Department of Computer Science, Kibabii University, Bungoma, KenyaDepartment of Science, Technology and Engineering, Kibabii University, Bungoma, KenyaThis study presents the development and integration of predictive models for the Normalized Difference Vegetation Index (NDVI) and Bare Soil Index (BSI) using the XGBoost algorithm within the North Rift Weather Prediction System (NRWPS) to enhance ecosystem monitoring in Kenya's North Rift region. Trained on a comprehensive dataset spanning 1995 to 2020, which includes precipitation (from the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS)), temperature (TerraClimate), historical NDVI (Landsat 4–5 Thematic Mapper (from 1995 to 2013) and Landsat 7 Enhanced Thematic Mapper plus (ETM+) (from 2014 to 2020)), and BSI (SoilGrids) data, the models effectively capture the complex relationships between environmental factors and vegetation health. The BSI model achieved an MSE of 0.029, an MAE of 0.019, and an R-squared score of 0.93, while the NDVI model yielded an MSE of 0.002, an MAE of 0.024, and an R-squared score of 0.945. These results demonstrate the models' strong predictive accuracy, enabling precise assessments of vegetation health and bare soil exposure. By analyzing temporal variations in vegetation health and land degradation from 1995 to 2020, the study identifies a significant inverse relationship between NDVI and BSI, where increasing bare soil exposure corresponds to declining vegetation health. The analysis also reveals that climatic factors particularly temperature (minimum and maximum) and precipitation play a critical role in shaping these trends, with high temperatures after 2000 associated with reduced NDVI, while regions with higher precipitation show healthier vegetation and lower BSI. The successful development of the NRWPS model provides significant opportunities for informing land management strategies, conservation efforts, and agricultural practices, enabling data-driven decision-making. Moreover, its integration into larger decision support systems allows for proactive interventions to mitigate land degradation and climate change stressors. This study emphasizes the importance of sustainable land-use practices and climate adaptation strategies to preserve vegetation health and manage ecosystem vulnerabilities effectively in the wake of regional climate change with the North Rift region most affected.http://www.sciencedirect.com/science/article/pii/S2405844025009296North riftClimate resilienceData-drivenWeather predictionReal-time forecasting and agricultural decision supportNorth rift weather prediction system |
| spellingShingle | John W. Makokha Peter W. Barasa Geoffrey W. Khamala Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support Heliyon North rift Climate resilience Data-driven Weather prediction Real-time forecasting and agricultural decision support North rift weather prediction system |
| title | Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support |
| title_full | Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support |
| title_fullStr | Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support |
| title_full_unstemmed | Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support |
| title_short | Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support |
| title_sort | enhancing climate resilience a data driven north rift weather prediction system for real time forecasting and agricultural decision support |
| topic | North rift Climate resilience Data-driven Weather prediction Real-time forecasting and agricultural decision support North rift weather prediction system |
| url | http://www.sciencedirect.com/science/article/pii/S2405844025009296 |
| work_keys_str_mv | AT johnwmakokha enhancingclimateresilienceadatadrivennorthriftweatherpredictionsystemforrealtimeforecastingandagriculturaldecisionsupport AT peterwbarasa enhancingclimateresilienceadatadrivennorthriftweatherpredictionsystemforrealtimeforecastingandagriculturaldecisionsupport AT geoffreywkhamala enhancingclimateresilienceadatadrivennorthriftweatherpredictionsystemforrealtimeforecastingandagriculturaldecisionsupport |