Automatic generation of impact-based drought forecast, implications for early warning and action in East Africa

Rasheed, Nishadh Kalladath Abdul; Otieno, Viola; Misiani, Herbert; Ouma, Jully; Otenyo, Erick; Kinuya, Jason; Amdihun, Ahmed

doi:10.5194/egusphere-egu23-10940

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, forecasting future drought conditions is crucial for preventing agricultural and hydrological resource damage in models that can be used to predict drought severity classes (Son et al, 2023). Furthermore, impact-based drought forecasting can provide critical information for disaster preparedness and adaptation, and increase community resilience (Rasheed et al, 2023). Lastly, forecasting droughts on a seasonal timescale can provide useful insights into the increase in the frequency and intensity of extreme events and their location (Monte et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning to Forecast Drought Index for the Mekong Delta

Duc

2024

Preprint

View full text Add to dashboard Cite

Droughts have a substantial effect on water resources, agriculture, and ecosystems on a worldwide scale. In the Mekong Delta of Vietnam, droughts exacerbated by climate change are significantly endangering the region's agricultural sustainability and output. Conventional forecasting techniques frequently do not capture the intricate dynamics of meteorological phenomena associated to drought effectively, prompting the exploration of more advanced methodologies. This work utilises artificial intelligence, particularly machine learning methods like Gradient Boosting and Extreme Gradient Boosting (XGBoost), to enhance drought prediction in the Mekong Delta. The study utilises data from 11 meteorological stations spanning from 1990 to 2022 to create and evaluate Machine Learning models based on several climatic factors. We utilise Gradient Boosting and XGBoost algorithms to estimate the Standardised Precipitation-Evapotranspiration Index (SPEI) and evaluate their effectiveness in comparison to conventional forecasting techniques. The results show that Machine Learning, particularly XGBoost, surpasses traditional approaches in predicting SPEI accuracy at various time scales. XGBoost demonstrates skill in understanding the complex relationships between climatic factors, with R² values falling between 0.90 and 0.94 for 1-month forecasts. The progress highlights the potential of Machine Learning in improving drought management and adaptation tactics, proposing the incorporation of Machine Learning forecasting models into decision-making processes to enhance drought resistance in susceptible areas.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning to Forecast Drought Index for the Mekong Delta

Duc

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, forecasting future drought conditions is crucial for preventing agricultural and hydrological resource damage in models that can be used to predict drought severity classes [8]. Furthermore, impact-based drought forecasting can provide critical information for disaster preparedness and adaptation, and increase community resilience [9]. Lastly, forecasting droughts on a seasonal timescale can provide useful insights into the increase in the frequency and intensity of extreme events and their location [10].…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning to Forecast Drought Index for the Mekong Delta

Duong,

Phong,

et al. 2024

Preprint

View full text Add to dashboard Cite

Droughts have a substantial effect on water resources, agriculture, and ecosystems on a worldwide scale. In the Mekong Delta of Vietnam, droughts exacerbated by climate change are significantly endangering the region's agricultural sustainability and output. Conventional forecasting techniques frequently do not capture the intricate dynamics of meteorological phenomena associated to drought effectively, prompting the exploration of more advanced methodologies. This work utilises artificial intelligence, par-ticularly machine learning methods like Gradient Boosting and Extreme Gradient Boosting (XGBoost), to enhance drought pre-diction in the Mekong Delta. The study utilises data from 11 meteorological stations spanning from 1990 to 2022 to create and evaluate Machine Learning models based on several climatic factors. We utilise Gradient Boosting and XGBoost algorithms to estimate the Standardised Precipitation-Evapotranspiration Index (SPEI) and evaluate their effectiveness in comparison to con-ventional forecasting techniques. The results show that Machine Learning, particularly XGBoost, surpasses traditional approaches in predicting SPEI accuracy at various time scales. XGBoost demonstrates skill in understanding the complex relationships between climatic factors, with R² values falling between 0.90 and 0.94 for 1-month forecasts. The progress highlights the potential of Machine Learning in improving drought management and adaptation tactics, proposing the incorporation of Machine Learning forecasting models into decision-making processes to enhance drought resistance in susceptible areas.

show abstract

Quantifying Drought Impacts Based on the Reliability–Resiliency–Vulnerability Framework over East Africa

Babaousmail,

Ayugi,

Hammad

et al. 2024

Climate

View full text Add to dashboard Cite

Drought poses a significant threat to water resources in East Africa, necessitating a comprehensive assessment of its impacts for effective mitigation strategies. This study utilizes two global gridded SPEI datasets to analyze drought characteristics (i.e., frequency, duration, and severity) in East Africa from 1981 to 2021. To estimate the sustainability of water resources over the region, the study employed the Reliability–Resiliency–Vulnerability framework (RRV) that aggregates the drought characteristics (i.e., frequency, duration, and severity). Drought is deemed to have occurred when the SPEI value falls below −1, so the threshold for water demand (RRV) is also computed at a threshold level of −1. The findings indicate pronounced changes in drought patterns across East Africa, with evidence of varying degrees of recovery and resilience in different regions. Employing the RRV framework over the East Africa region to determine how the region can cope with the effects of drought revealed a median range of RRV of 0.61 to 0.80, indicating a sustainable situation during the study period. This indicates that despite the recorded drought incidences, the water catchments of lakes, rivers, and major water towers are not threatened and, thus, less vulnerable. Although certain regions exhibit declining resilience and vulnerability to drought impacts, there is a need for targeted mitigation measures and policy interventions to safeguard water resources.

show abstract

Automatic generation of impact-based drought forecast, implications for early warning and action in East Africa

Cited by 3 publications

References 0 publications

Application of Machine Learning to Forecast Drought Index for the Mekong Delta

Application of Machine Learning to Forecast Drought Index for the Mekong Delta

Application of Machine Learning to Forecast Drought Index for the Mekong Delta

Quantifying Drought Impacts Based on the Reliability–Resiliency–Vulnerability Framework over East Africa

Contact Info

Product

Resources

About