Data Mining of 24-Hour Cumulative Precipitation Data in Iran Using Machine Learning: Multilayer Perceptron Neural Network and Decision Tree

Faraji, Mozaffar; Rezaii Banafsheh Daragh, Majid; Sarisarraf, Behroz; Khorshid Dust, Ali Mohammad

doi:10.22059/ije.2025.395276.1870

Data Mining of 24-Hour Cumulative Precipitation Data in Iran Using Machine Learning: Multilayer Perceptron Neural Network and Decision Tree

Document Type : Research Article

Authors

¹ PhD Student, Department of Climatology, University of Tabriz, Tabriz, Iran

² Professor, Department of Climatology, University of Tabriz, Tabriz, Iran

10.22059/ije.2025.395276.1870

Abstract

Research Topic: This study examines 24-hour cumulative precipitation data in Iran and predicts rainfall amounts over various time periods using data mining and machine learning.
Objective: To develop an accurate model for predicting 24-hour cumulative precipitation in regions of Iran using multilayer neural networks and decision trees to improve hydrological planning and water resource management.
Method: A daily precipitation dataset D was collected from Iranian stations and prepared using normalization. Two machine learning models including MLP with activation function σ and decision tree with entropy criterion were implemented. The models’ performance was evaluated and compared with accuracy, precision, and error criteria.
Results: The MLP model demonstrated efficiency in estimating monthly precipitation by minimizing MSE to 0.04. The decision tree analysis classified Iran provinces into seven clusters based on precipitation characteristics; clusters 4 and 7 represent provinces with minimum (including Isfahan, Sistan and Baluchestan, Yazd) and maximum precipitation (including Gilan, Kohgiluyeh and Boyer-Ahmad, Mazandaran), respectively. Linear regression showed a significant effect of the time variable with 0.209 on precipitation variance.
Conclusions: The use of machine learning, especially neural networks, is effective in analyzing hydrological data in Iran and can help improve precipitation forecasting systems.

Keywords

Main Subjects

Climate Change

References

Akbari, M., & Sayad, V. (2021). Analysis of climate change studies in Iran. Journal of Natural Geography Research, 53(1), 37–74. (in Persian)

Asakereh, H., & Mottalebizad, S. (2017). Comparison of SDSM and artificial neural networks performance in predicting minimum temperature changes (Case study: Urmia station). Spatial Planning, 21(4), 140–160. (in Persian)

Asakereh, H., Masoudian, S. A., & Torkarani, F. (2021). Disentangling the role of internal and external factors in the decadal variability of annual rainfall in Iran during the last four decades (1976–2015). Journal of Natural Geography Research, 53(1), 91–107. https://doi.org/10.22059/jphgr.2021.304776.1007529

Babaei Hesar, S., & Ghazavi, R. (2015). Comparison of time series and neural network models with emission scenario results in rainfall prediction. Water and Soil, 29(4), 943–953. (in Persian)

Bahrami, M., Salari, A., Amiri, M. J., & Bahrami, A. (2023). Performance evaluation of artificial neural network in estimating rainfall using climatic and geographic data (Case study: Fars province). Irrigation and Water Engineering, 13(3), 121–140. https://doi.org/10.22125/iwe.2023.168171

Cybenko, G. (1989). Approximations by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, 2, 183–192. https://doi.org/10.1080/19373260802659226

Dastorani, M. T., & Afkhami, H. (2011). Application of artificial neural networks on drought prediction in Yazd (Central Iran). Desert, 16(1), 39–48. (in Persian)

Dehghani Navid, V., Vafakhah, M., & Bahrehmand, A. R. (2016). Rainfall-runoff modeling using artificial neural network and adaptive neuro-fuzzy network in Kasilian watershed. Watershed Management Research Journal, 7(13), 128–137. (in Persian)

Esmaeilian, M. (2005). Comprehensive SPSS Guide. Naghoos Publications. (in Persian)

Esmaeilian, M., Vahdat, J., & Heidardoust, H. (2016). R software guide. University of Mohaghegh Ardabili Publications. (in Persian)

Fallah Ghalhari, G., & Shakeri, F. (2015). Application of artificial neural networks in winter rainfall forecasting. Iranian Journal of Watershed Management Science & Engineering, 9(31), 98–110. (in Persian)

Faraji, M., Rezaei Banafsheh, M., Sari Sarraf, B., & Khorshiddoost, A. (2023). Numerical simulation of climate change in Iran using artificial neural network algorithm. Climate Change Researches, 4(14), 43–64. (in Persian)

Faraji, M., Rezaei Banafsheh, M., Sari Sarraf, B., & Khorshiddoost, A. (2024). Data mining of 24-hour air temperature in Iran using machine learning multilayer perceptron neural network. Climate Change Researches, 5(20), 33–48. https://doi.org/10.30488/ccr.2024.458168.1216

Ghermezechashme, B., Rasouli, A. A., Rezaei Banafsheh, M., Massah Bavani, A. R., & Khorshiddoost, A. M. (2015). Uncertainty assessment of neural network model in downscaling HadCM3 using bootstrap confidence interval method. Journal of Watershed Engineering and Management, No. 3, 306–316. (in Persian)

Gholizadeh, M. H., & Darand, M. (2011). Monthly rainfall forecasting using artificial neural networks (Case study: Tehran). Journal of Natural Geography Research, 42(7), 51–63. (in Persian)

Jahanbakhsh Asl, S., Sari Sarraf, B., Asakereh, H., & Shirmohammadi, S. (2020). Analysis of temporal-spatial changes of critical rainfalls (extreme high) in the west of Iran during the years 1965–2016. Journal of Environmental Hazards Analysis, 7(1), 89–106. (in Persian)

Moon, S. H., Kim, Y. H., Lee, Y. H., & Moon, B. R. (2019). Application of machine learning to an early warning system for very short-term heavy rainfall. Journal of Hydrology, 568, 1042–1054. https://doi.org/10.1016/j.jhydrol.2018.11.060

Pakdaman, M. (2022). The effect of training algorithm type of multilayer perceptron neural network on the accuracy of monthly rainfall forecast of Iran, case study: ECMWF model. Journal of Earth and Space Physics, 48(1), 213–226. https://dor.isc.ac/dor/20.1001.1.2538371.1401.48.1.14.2 (in Persian)

*R Programming Language. Available functions guide.

S Programming Language. Available functions guide.

Sadatinejad, S. J., Soleimani Sardo, F., & Mirzavand, M. (1403). Modeling and Predicting Climatic Parameters Using the CanESM2 Model Under RCP Scenarios (Case Study: Karaj Station). Ecohydrology Journal, 11(3), 411-426. doi: 10.22059/ije.2024.382370.1845 (in Persian).

Shahbaii Kotnaei, A., & Asakereh, H. (2023). Evaluation of fuzzy clustering and artificial neural network methods in spatial zoning of annual rainfall in Iran. Journal of Water and Soil Science, 27(1), 17–32. (in Persian)

Shahgholian, K., Bazrafshan, J., & Irannejad, P. (2023). Synoptic weather variables and data mining methods for predicting regional heavy precipitation over the southwest of Iran. Theoretical and Applied Climatology, 147, 401–416. https://link.springer.com/article/10.1007/s12040-021-01725-9

Subrahmanyam, K. V., Ramsenthil, C., Girach Imran, A., Chakravorty, A., Sreedhar, R., Ezhilrajan, E., & Jha, C. S. (2021). Prediction of heavy rainfall days over a peninsular Indian station using the machine learning algorithms. Journal of Earth System Science, No. 130, 1–9. https://doi.org/10.21203/rs.3.rs-3768340/v

Tajbar, M., Khourshid Doost, S., Saeed Jahanbakhsh Asl, S. (2022). Application of Artificial Intelligence Approach in Studying the Impact of Large-Scale Climatic Drivers on Rainfall in Balochistan, Pakistan. Journal of Geography and Environmental Planning, 33(87), 1-20 (in Persian).