EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine learning-based drought prediction using Palmer Drought Severity Index and TerraClimate data in Ethiopia

Tadele Melese iD, Gizachew Assefa, Baye Terefe iD, Tatek Belay, Getachew Bayable iD, Abebe Senamew

PLOS One · 18.06.2025 · 20 (6) · e0326174

DOI: 10.1371/journal.pone.0326174 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 18.06.2025. Verfasst von Tadele Melese und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Natural Resource Management, College of Agriculture and Environmental Science, Bahir Dar University, Bahir Dar, Ethiopia. Hauptthemen laut MEDLINE: Droughts, Machine Learning. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate drought prediction is essential for proactive water management and agricultural planning, especially in regions like Ethiopia that are highly susceptible to climate variability. This study investigates the classification of the Palmer Drought Severity Index (PDSI) using machine learning models trained on TerraClimate data, incorporating variables such as precipitation, temperature, soil moisture, and vapor pressure deficit. We employed several classifiers Logistic Regression, Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Decision Tree, Random Forest, Gradient Boosting, Naive Bayes, AdaBoost, and XGBoost with Logistic Regression serving as a baseline statistical approach for comparison. To address data imbalance across drought classes, we applied a hybrid resampling method combining manual upsampling and SMOTE. Hyperparameter tuning was conducted using grid search and cross-validation. Random Forest outperformed all models, achieving an accuracy of 71.18%, F1-score of 0.71, and ROC AUC of 0.9000. Gradient Boosting and SVM also performed well with ROC AUC values of 0.8982 and 0.8681, respectively. SHAP analysis revealed that soil moisture, precipitation, and vapor pressure deficit were the most influential features in predicting drought severity. For benchmarking, an ARIMA (3,1,2) time-series model was applied but yielded poor performance (RMSE = 1.789, R² = −0.077), confirming the advantages of non-linear machine learning techniques for complex climate data. The results highlight the utility of ensemble learning in environmental modelling, offering valuable insights for drought early warning systems and climate resilience planning in Ethiopia. Future work should explore integrating localized predictors and real-time data to enhance prediction robustness.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DroughtsMachine LearningEthiopiaSupport Vector MachineSoil

Substanzen

Soil

Autor:innen und Institutionen

  • Department of Natural Resource Management, College of Agriculture and Environmental Science, Bahir Dar University, Bahir Dar, Ethiopia.
  • Department of Information System science, Faculty of Science and Engineering, Soka University, Tokyo, Japan.
  • Department of Land Administration and Survey, Institute of Land Administration and Survey, Debre Markos University, Debre Markos, Ethiopia.
  • Department of Geography, Injibara University, Injibara, Ethiopia.
  • Department of Geography, College of Social Science and Humanities, Debre Tabor University, Debre Tabor, Ethiopia.

ORCID-Profile: Tadele Melese, Baye Terefe, Getachew Bayable

Zitieren

APA

Melese, T., Assefa, G., Terefe, B., Belay, T., Bayable, G., & Senamew, A. (2025). Machine learning-based drought prediction using Palmer Drought Severity Index and TerraClimate data in Ethiopia. PLOS One, 20(6), e0326174. https://doi.org/10.1371/journal.pone.0326174

Vancouver

Melese T, Assefa G, Terefe B, Belay T, Bayable G, Senamew A. Machine learning-based drought prediction using Palmer Drought Severity Index and TerraClimate data in Ethiopia. PLOS One. 2025;20(6):e0326174. doi:10.1371/journal.pone.0326174

BibTeX
@article{Melese2025,
  author = {Melese, Tadele and Assefa, Gizachew and Terefe, Baye and Belay, Tatek and Bayable, Getachew and Senamew, Abebe},
  title = {Machine learning-based drought prediction using Palmer Drought Severity Index and TerraClimate data in Ethiopia},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {6},
  pages = {e0326174},
  doi = {10.1371/journal.pone.0326174}
}
Kostenlos starten →