Application of Artificial Neural Networks (ANN) in Climate Modeling: Predicting Rainfall and River Discharge
Abstract views: 49
/ 
PDF downloads: 23
Keywords:
Artificial Neural Network (ANN), Rainfall Forecasting, River Discharge, Climate Modeling, Hydrology, BackpropagationAbstract
Accurate prediction of rainfall and river discharge is essential for effective water resource
management, flood forecasting, and climate adaptation. This study investigates long-term variations in
temperature, precipitation, river discharge, and land cover from 1970 to 2023 in the Kokcha River Basin,
Afghanistan, using hydrometeorological records and GIS-based analysis. A feedforward Multilayer
Perceptron (MLP) artificial neural network, trained with the backpropagation algorithm, was developed to
forecast rainfall and river discharge based on long-term hydroclimatic data. Model performance was
evaluated using the coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean
Absolute Error (MAE). The ANN model achieved high predictive accuracy (R² = 0.87 for rainfall and
0.91 for discharge), outperforming conventional regression and time-series models. These results
demonstrate the capability of ANN-based models to capture complex nonlinear hydrological relationships
and support robust short-term forecasting and adaptive water management in data-scarce regions.
Downloads
References
M. Saeed et al., “Flood hazard zonation using an artificial neural network model: A case study of kabul river basin, Pakistan,” Sustainability (Switzerland), vol. 13, no. 24, Dec. 2021, doi: 10.3390/su132413953.
J. Lee, C. G. Kim, J. E. Lee, N. W. Kim, and H. Kim, “Application of artificial neural networks to rainfall forecasting in the Geum River Basin, Korea,” Water (Switzerland), vol. 10, no. 10, Oct. 2018, doi: 10.3390/w10101448.
M. Saeed et al., “Flood hazard zonation using an artificial neural network model: A case study of kabul river basin, Pakistan,” Sustainability (Switzerland), vol. 13, no. 24, Dec. 2021, doi: 10.3390/su132413953.
S. Maddah, B. Mojaradi, and H. Alizadeh, “Improving deep learning-based flood susceptibility modeling by integrating data balancing technique and dual-input convolutional neural network,” Natural Hazards, vol. 121, no. 15, pp. 17555–17577, Aug. 2025, doi: 10.1007/s11069-025-07482-y.
N. A. Akhundzadah, S. Soltani, and V. Aich, “Impacts of climate change on the water resources of the Kunduz River Basin, Afghanistan,” Climate, vol. 8, no. 10, Oct. 2020, doi: 10.3390/CLI8100102.
M. Ghulami, “Assessment of climate change impacts on water resources and agriculture in data-scarce Kabul basin, Afghanistan,” Dec. 2017, Accessed: Jan. 26, 2025. [Online]. Available: https://theses.hal.science/tel-01737052
N. A. Akhundzadah, “Analyzing Temperature, Precipitation, and River Discharge Trends in Afghanistan’s Main River Basins Using Innovative Trend Analysis, Mann–Kendall, and Sen’s Slope Methods,” Climate, vol. 12, no. 12, p. 196, Nov. 2024, doi: 10.3390/cli12120196.
S. A. Alawi and S. Özkul, “Impact assessment of climate change on water resources of the Kokcha watershed: a sub-basin of the Amu Darya river basin in Afghanistan,” Journal of Water and Climate Change, vol. 14, no. 5, pp. 1656–1671, May 2023, doi: 10.2166/WCC.2023.504.
B. S. N. Reddy, S. K. Pramada, and T. Roshni, “Monthly surface runoff prediction using artificial intelligence: A study from a tropical climate river basin,” Journal of Earth System Science, vol. 130, no. 1, Dec. 2021, doi: 10.1007/s12040-020-01508-8.
S. Oad, M. A. Imteaz, and F. Mekanik, “Artificial Neural Network (ANN)-Based Long-Term Streamflow Forecasting Models Using Climate Indices for Three Tributaries of Goulburn River, Australia,” Climate, vol. 11, no. 7, Jul. 2023, doi: 10.3390/cli11070152.
V. Isazade, A. baser Qasimi, M. S. Namivandi, M. S. Amin, and G. Ahlem, “Landslide Susceptibility Assessment Using Recurrent Neural Network (RNN)—A Case of Chabahar and Konarak in Iran,” Indian Geotechnical Journal, 2025, doi: 10.1007/s40098-025-01220-8.
M. H. Salmani and E. Salmani Jajaei, “Forecasting models for flow and total dissolved solids in Karoun river-Iran,” J Hydrol (Amst), vol. 535, pp. 148–159, Apr. 2016, doi: 10.1016/J.JHYDROL.2016.01.085.
N. A. Akhundzadah, S. Soltani, and V. Aich, “Impacts of climate change on the water resources of the Kunduz River Basin, Afghanistan,” Climate, vol. 8, no. 10, Oct. 2020, doi: 10.3390/CLI8100102.
A. B. Qasimi, V. Isazade, E. Enayat, Z. Nadry, and A. H. Majidi, “Landslide susceptibility mapping in Badakhshan province, Afghanistan: a comparative study of machine learning algorithms,” Geocarto Int, vol. 38, no. 1, 2023, doi: 10.1080/10106049.2023.2248082.
H. Shams, A. Khan, K. Haleem, and S. Mahmood, “Assessing the effects of climate and land-use change on flood recurrence in Kokcha River, Afghanistan,” Journal of Water and Climate Change, vol. 15, no. 5, pp. 2464–2483, 2024, doi: 10.2166/wcc.2024.043.
M. S. S. Danish et al., “Afghanistan’s aspirations for energy independence: Water resources and hydropower energy,” Renew Energy, vol. 113, pp. 1276–1287, 2017, doi: 10.1016/j.renene.2017.06.090.
M. Hafezparast and S. Marabi, “Prediction of discharge using artificial neural network and IHACRES models due to climate change,” Journal of Renewable Energy and Environment, vol. 8, no. 3, pp. 75–85, Jun. 2021, doi: 10.30501/jree.2021.257941.1162.
G. E. de M. e. Costa, F. C. M. de Menezes Filho, F. A. Canales, M. C. Fava, A. R. A. Brandão, and R. P. de Paes, “Assessment of Time Series Models for Mean Discharge Modeling and Forecasting in a Sub-Basin of the Paranaíba River, Brazil,” Hydrology 2023, Vol. 10, Page 208, vol. 10, no. 11, p. 208, Nov. 2023, doi: 10.3390/HYDROLOGY10110208.
S. Ullah, M. Abbas, and X. Qiao, “Impact assessment of land-use alteration on land surface temperature in Kabul using machine learning algorithm,” J Spat Sci, 2024, doi: 10.1080/14498596.2024.2364283.
A. A. Obasi, K. N. Ogbu, L. C. Orakwe, and I. E. Ahaneku, “Rainfall-river discharge modelling for flood forecasting using Artificial Neural Network (ANN),” Journal of Water and Land Development, vol. 44, pp. 98–105, 2020, doi: 10.24425/jwld.2019.127050.
