article · Sustainability
Managing water reserves in semi-arid regions requires accurate tools to forecast reservoir storage under fluctuating environmental conditions. Researchers evaluated several modelling approaches to forecast water level changes at the Gaborone and Bokaa dams in Botswana between 2001 and 2019. The models examined included multivariate linear regression, vector autoregression, random forest regression, and a multilayer perceptron artificial neural network, assessing drivers such as land use, rainfall, temperature, and broader climate indices. Standard linear regression proved inadequate for capturing complex, non-linear relationships. Vector autoregression excelled at capturing the influence of land-use changes, while the neural network model provided the highest accuracy when processing climate variables. Ultimately, combining vector autoregression with neural networks into a hybrid model delivered the best performance, effectively addressing both linear and non-linear dynamics driven by land use and climate.
Dams in semi-arid environments are vulnerable to changing weather patterns and land use, making water security challenging. Demonstrating how artificial intelligence and hybrid statistical models capture these environmental dynamics helps water resource managers improve predictive planning. Reliable forecasts allow authorities to anticipate water shortages, optimise reservoir release strategies, and better protect urban and regional water supplies against climate variability.
This applied research provides an analytical framework suitable for integration into hydrological forecasting software and decision-support systems used by water utilities and catchment management authorities. Because the findings are based on retrospective historical data from two dams, the approach is at an applied research stage. Operational commercialisation would require developing real-time data ingestion pipelines, automated validation tools, and testing across broader geographical regions.
AI-generated from the published abstract. Always read the original work before citing.
To predict the variability of dam water levels, parametric Multivariate Linear Regression (MLR), stochastic Vector AutoRegressive (VAR), Random Forest Regression (RFR) and Multilayer Perceptron (MLP) Artificial Neural Network (ANN) models were compared based on the influences of climate factors (rainfall and temperature), climate indices (DSLP, Aridity Index (AI), SOI and Niño 3.4) and land-use land-cover (LULC) as the predictor variables. For the case study of the Gaborone dam and the Bokaa dam in the semi-arid Botswana, from 2001 to 2019, the prediction results showed that the linear MLR is not robust for predicting the complex non-linear variabilities of the dam water levels with the predictor variables. The stochastic VAR detected the relationship between LULC and the dam water levels with R2 > 0.95; however, it was unable to sufficiently capture the influence of climate factors on the dam water levels. RFR and MLP-ANN showed significant correlations between the dam water levels and the climate factors and climate indices, with a higher R2 value between 0.890 and 0.926, for the Gaborone dam, compared to 0.704–0.865 for the Bokaa dam. Using LULC for dam water predictions, RFR performed better than MLP-ANN, with higher accuracy results for the Bokaa dam. Based on the climate factors and climate indices, MLP-ANN provided the best prediction results for the dam water levels for both dams. To improve the prediction results, a VAR-ANN hybrid model was found to be more suitable for integrating LULC and the climate conditions and in predicting the variability of the linear and non-linear time-series components of the dam water levels for both dams.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/su142214934
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
