Machine Learning-Based Hydrological Drought Prediction Integrating Teleconnections and Hydrological Memory in a Semi-Arid Basin, Algeria
6 affiliations
- 1Department of Civil Engineering, Erzincan Binali Yildirim University, Erzincan 24060, Türkiye
- 2Laboratory of Water & Environment, Faculty of Nature and Life Sciences, University Hassiba Benbouali of Chlef, B.P 78C, Ouled Fares, Chlef 02180, Algeria
- 3Department of Civil Engineering, Siirt University, Siirt 56100, Türkiye
- 4Department of Geography, Nakhchivan State University, AZ 7012 Nakhchivan, Azerbaijan
- 5Geography Department, Faculty of Arts and Sciences, Igdir University, Igdir 76000, Türkiye
- 6G.B. Pant National Institute of Himalayan Environment, Garhwal Regional Centre, Srinagar 246174, Uttarakhand, India
Abstract
Hydrological drought forecasting in semi-arid basins is challenging due to the combined influence of meteorological forcing, large-scale atmospheric teleconnections, and basin memory processes, which are rarely jointly analysed within a leakage-free predictive framework. This study addresses this gap by evaluating gradient-boosted trees and neural forecasting models for one-month-ahead prediction of the Standardized Runoff Index (SRI) in two sub-basins of the Wadi Sahaouat Basin, Algeria. The models include gradient-boosted regression trees (GBRT), A-N-BEATS, A-N-HiTS, and TiDE, representing distinct forecasting architectures. Predictors consist of the Standardised Precipitation Index (SPI), seven teleconnection indices (NAO, AO, EAWR, SCAND, MEI, SOI, WeMO), and their one- to three-month lags. Two scenarios are tested: Scenario 1 uses SPI and teleconnection lags only, while Scenario 2 additionally includes lagged SRI values (SRI_lag1–3) to represent hydrological memory. A train-only Variance Inflation Factor (VIF > 10) procedure is applied to remove multicollinearity without data leakage. In Basin 1, SRI lags were excluded due to strong collinearity with SPI lags (r = 0.984), resulting in identical inputs for both scenarios. In Basin 2, SRI lags were retained to assess their predictive contribution. GBRT achieved the best overall performance across both basins and scenarios, with mean RMSE, NSE, and KGE values of 0.0682, 0.9907, and 0.8945, respectively. TiDE ranked second overall, with a mean RMSE of 0.1166, followed by A-N-HiTS in third place with a mean RMSE of 0.1203 and A-N-BEATS with the weakest overall performance, with a mean RMSE of 0.2159. These results indicate that gradient-boosted trees remain highly competitive with neural models for small monthly hydrological datasets and that the value of hydrological memory is basin-dependent and varies according to its independence from concurrent meteorological forcing.
Related
- Projection of hydrological droughts in the upper Hanjiang River under the climate change impact based on stacking machine learning model
- Estimation of hydrological drought using regional risk ranking and machine learning algorithms
- GLORIF1, a global river flow dataset created by integrating process-based modelling and machine learning
- A novel deep learning prediction method for PM2.5 integrating improved MSTL decomposition and FATA optimization algorithm
- Machine-learning prediction of freezing temperature in Pb-contaminated soils remediated with biochar
BibTeX
@article{katipoglu2026machine,
title = {{Machine Learning-Based Hydrological Drought Prediction Integrating Teleconnections and Hydrological Memory in a Semi-Arid Basin, Algeria}},
author = {Okan Mert Katipoğlu and Mohammed Achite and Veysi Kartal and Mehmet Ali Çelik and Kusum Pandey},
journal = {Atmosphere},
year = {2026},
month = jul,
doi = {10.3390/atmos17070670},
url = {https://doi.org/10.3390/atmos17070670},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine Learning-Based Hydrological Drought Prediction Integrating Teleconnections and Hydrological Memory in a Semi-Arid Basin, Algeria
AU - Okan Mert Katipoğlu
AU - Mohammed Achite
AU - Veysi Kartal
AU - Mehmet Ali Çelik
AU - Kusum Pandey
PY - 2026
DA - 2026/07/04
JO - Atmosphere
DO - 10.3390/atmos17070670
UR - https://doi.org/10.3390/atmos17070670
AB - Hydrological drought forecasting in semi-arid basins is challenging due to the combined influence of meteorological forcing, large-scale atmospheric teleconnections, and basin memory processes, which are rarely jointly analysed within a leakage-free predictive framework. This study addresses this gap by evaluating gradient-boosted trees and neural forecasting models for one-month-ahead prediction of the Standardized Runoff Index (SRI) in two sub-basins of the Wadi Sahaouat Basin, Algeria. The models include gradient-boosted regression trees (GBRT), A-N-BEATS, A-N-HiTS, and TiDE, representing distinct forecasting architectures. Predictors consist of the Standardised Precipitation Index (SPI), seven teleconnection indices (NAO, AO, EAWR, SCAND, MEI, SOI, WeMO), and their one- to three-month lags. Two scenarios are tested: Scenario 1 uses SPI and teleconnection lags only, while Scenario 2 additionally includes lagged SRI values (SRI_lag1–3) to represent hydrological memory. A train-only Variance Inflation Factor (VIF > 10) procedure is applied to remove multicollinearity without data leakage. In Basin 1, SRI lags were excluded due to strong collinearity with SPI lags (r = 0.984), resulting in identical inputs for both scenarios. In Basin 2, SRI lags were retained to assess their predictive contribution. GBRT achieved the best overall performance across both basins and scenarios, with mean RMSE, NSE, and KGE values of 0.0682, 0.9907, and 0.8945, respectively. TiDE ranked second overall, with a mean RMSE of 0.1166, followed by A-N-HiTS in third place with a mean RMSE of 0.1203 and A-N-BEATS with the weakest overall performance, with a mean RMSE of 0.2159. These results indicate that gradient-boosted trees remain highly competitive with neural models for small monthly hydrological datasets and that the value of hydrological memory is basin-dependent and varies according to its independence from concurrent meteorological forcing.
SN - 2073-4433
ER -