Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions

Kağan Eryürük; Şule Eryürük

doi:10.64808/engineeringperspective.1914439

Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions

Abstract

Accurate precipitation forecasting is essential for water resource management, agricultural planning, and climate resilience, particularly in semiarid regions such as Konya Province, Türkiye, which receives approximately 300 to 350 mm of rainfall annually and is highly vulnerable to drought. This study presents a systematic comparative evaluation of eight forecasting models applied to monthly precipitation data spanning the period from 1958 to 2025. The models evaluated include SARIMAX, LASSO, CatBoost, LightGBM, XGBoost, Multilayer Perceptron (MLP), Long Short Term Memory (LSTM), and a hybrid LSTM and XGBoost framework. Model inputs comprise six key meteorological variables, namely temperature, humidity, evaporation, sunshine duration, wind speed, and precipitation, supplemented by sinusoidal seasonal encodings and lagged or rolling features depending on the model structure. A chronological 70/10/20 train, validation, and test split was applied to all machine learning models, while SARIMAX used the full dataset with exogenous regressors. Performance was evaluated using seven complementary metrics: R², RMSE, MAE, NSE, MAPE, KGE, and PBIAS. The results reveal a clear three tier performance hierarchy. The hybrid LSTM and XGBoost framework achieved the highest accuracy (R² = 0.945, RMSE = 5.46 mm), demonstrating that combining temporal feature extraction with nonlinear residual learning substantially improves predictive performance. Tree based ensemble models, including CatBoost, LightGBM, and XGBoost, formed an intermediate tier with R² values around 0.70, effectively capturing seasonal variability but tending to underestimate extreme rainfall events. Linear and standalone deep learning models, including SARIMAX, LASSO, MLP, and LSTM, constituted the weakest tier. These findings confirm that hybrid architectures offer the most reliable framework for precipitation forecasting in semiarid regions, with direct implications for sustainable water management and climate adaptation planning.

Keywords

References

Griggs, D. J., & Noguer, M. (2002). Climate change 2001: The scientific basis. Weather, 57, 267–269. https://doi.org/10.1256/004316502320517344
Asadi, M., & Karami, M. (2021). Modeling of relative humidity trends in Iran. Modeling Earth Systems and Environment, 8, 1035–1045. https://doi.org/10.1007/s40808-021-01093-9
Pasquini, L., van Aardenne, L., Godsmark, C. N., et al. (2020). Emerging climate change-related public health challenges in Africa: A case study of the heat-health vulnerability of informal settlement residents in Dar es Salaam, Tanzania. Science of the Total Environment, 747, 141355. https://doi.org/10.1016/j.scitotenv.2020.141355
Kogo, B. K., Kumar, L., & Koech, R. (2021). Climate change and variability in Kenya: A review of impacts on agriculture and food security. Environment, Development and Sustainability, 23, 23–43. https://doi.org/10.1007/s10668-020-00589-1
Ridwan, W. M., Sapitang, M., Aziz, A., et al. (2021). Rainfall forecasting model using machine learning methods: Case study Terengganu, Malaysia. Ain Shams Engineering Journal, 12, 1651–1663. https://doi.org/10.1016/j.asej.2020.09.011
Acar, R., Katipoğlu, O. M., & Çırağ, B. (2026). Hybrid VMD-EMD Enhanced Machine Learning Models for Daily Reference Evapotranspiration Forecasting. Engineering Perspective, 6(3), 354–373. https://doi.org/10.64808/engineeringperspective.1906862
Rezaei Aderyani, F., Mousavi, S. J., & Jafari, F. (2022). Short-term rainfall forecasting using machine learning-based approaches of PSO-SVR, LSTM and CNN. Journal of Hydrology, 614, 128463. https://doi.org/10.1016/j.jhydrol.2022.128463
Deger, İ. H. (2026). Flood Frequency and Temporal Variability Analysis of Yeşilırmak Basin Under Homogeneity and Change Point Criteria. Engineering Perspective, 6(2), 185–209. https://doi.org/10.64808/engineeringperspective.1896337

Fletcher, T. D., Andrieu, H., & Hamel, P. (2013). Understanding management and modelling of urban hydrology and its consequences for receiving waters: A state of the art. Advances in Water Resources, 51, 261–279. https://doi.org/10.1016/j.advwatres.2012.09.001
Debortoli, N. S., Camarinha, P. I. M., Marengo, J. A., et al. (2017). An index of Brazil’s vulnerability to expected increases in natural flash flooding and landslide disasters in the context of climate change. Natural Hazards, 86, 557–582. https://doi.org/10.1007/s11069-016-2705-2
Ming, X., Liang, Q., Xia, X., et al. (2020). Real-time flood forecasting based on 2-D hydrodynamic model and weather predictions. Water Resources Research, 56, e2019WR025583. https://doi.org/10.1029/2019WR025583
Kumar, V., Sharma, K. V., Caloiero, T., et al. (2023). Overview of flood modeling approaches: Recent advances. Hydrology, 10, 141. https://doi.org/10.3390/hydrology10070141
Sham, F. A. F., El-Shafie, A., Wan Jaafar, W. Z., et al. (2025). Advances in AI-based rainfall forecasting. Results in Engineering, 27, 105774. https://doi.org/10.1016/j.rineng.2025.105774
Glade, T. (2000). Applying probability determination to refine landslide-triggering rainfall thresholds using an empirical approach. Pure and Applied Geophysics, 157, 1059–1079. https://doi.org/10.1007/s000240050017
He, X., Guan, H., Zhang, X., et al. (2014). A wavelet-based multiple linear regression model for forecasting monthly rainfall. International Journal of Climatology, 34, 1898–1912. https://doi.org/10.1002/joc.3809
Choubin, B., Khalighi-Sigaroodi, S., Malekian, A., et al. (2016). Multiple linear regression, multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals. Hydrological Sciences Journal, 61, 1001–1009. https://doi.org/10.1080/02626667.2014.966721
Swain, S., Patel, P., & Nandi, S. (2017). A multiple linear regression model for precipitation forecasting over Cuttack district, Odisha, India. In 2017 2nd International Conference for Convergence in Technology (I2CT) (pp. 355–357). IEEE. https://doi.org/10.1109/I2CT.2017.8226150
Bostan, P. A., Heuvelink, G. B. M., & Akyurek, S. Z. (2012). Comparison of regression and kriging techniques for mapping the average annual precipitation of Turkey. International Journal of Applied Earth Observation and Geoinformation, 19, 115–126. https://doi.org/10.1016/j.jag.2012.04.010
He, C., Wei, J., Song, Y., et al. (2021). Seasonal prediction of summer precipitation in the Yangtze River valley: Comparison of machine learning and climate model predictions. Water, 13, 3294. https://doi.org/10.3390/w13223294
Cappelli, F., Conigliani, C., Consoli, D., et al. (2023). Climate change and armed conflicts in Africa: Temporal persistence, non-linear climate impact and geographical spillovers. Economia Politica, 40, 517–560. https://doi.org/10.1007/s40888-022-00271-x
Pour, S. H., Wahab, A. K. A., & Shahid, S. (2020). Physical–empirical models for predicting seasonal rainfall extremes in Malaysia. Atmospheric Research, 233, 104720. https://doi.org/10.1016/j.atmosres.2019.104720
Diop, L., Samadianfard, S., Bodian, A., et al. (2020). Annual rainfall forecasting using hybrid artificial intelligence model: Integration of multilayer perceptron with whale optimization algorithm. Water Resources Management, 34, 733–746. https://doi.org/10.1007/s11269-019-02473-8
Demir, V. (2025). Deep learning-based multi-source precipitation forecasting in arid regions using different optimizations: A case study from Konya, Turkey. Forecasting, 7, 60. https://doi.org/10.3390/forecast7040060
Kamir, E., Waldner, F., & Hochman, Z. (2020). Estimating wheat yields in Australia using climate records satellite image time series and machine learning. ISPRS Journal of Photogrammetry and Remote Sensing, 160, 124–135. https://doi.org/10.1016/j.isprsjprs.2019.11.008
Kumar, V., Kedam, N., Sharma, K. V., et al. (2023). Machine learning models for predicting rainfall in metropolitan cities. Sustainability, 15, 13724. https://doi.org/10.3390/su151813724
Haq, D. Z., Novitasari, R. C., Hamid, A., et al. (2021). Long short-term memory algorithm for rainfall prediction based on El-Nino and IOD data. Procedia Computer Science, 179, 829–837. https://doi.org/10.1016/j.procs.2021.01.071
Chen, C., Zhang, Q., Kashani, M. H., et al. (2022). Forecast of rainfall distribution based on fixed sliding window long short-term memory. Engineering Applications of Computational Fluid Mechanics, 16, 248–261. https://doi.org/10.1080/19942060.2021.2009374
Elsayed, S., Gupta, M., Chaudhary, G., et al. (2023). Interpretation of the influence of hydrometeorological variables on soil temperature prediction using deep learning. Knowledge-Based Engineering and Sciences, 4, 55–77. https://doi.org/10.51526/kbes.2023.4.1.55-77
Cui, Z., Qing, X., Chai, H., et al. (2021). Real-time rainfall–runoff prediction using light gradient boosting machine coupled with singular spectrum analysis. Journal of Hydrology, 603, 127124. https://doi.org/10.1016/j.jhydrol.2021.127124
Shahriar, S. A., Kayes, I., Hasan, K., et al. (2021). Potential of ARIMA–ANN, ARIMA–SVM, DT and CatBoost for PM2.5 forecasting. Atmosphere, 12, 100. https://doi.org/10.3390/atmos12010100
Karbasi, M., Jamei, M., Ali, M., et al. (2022). Hybrid autoencoder–decoder GRU model with empirical wavelet transform and Boruta–CatBoost for significant wave height forecasting. Journal of Cleaner Production, 379, 134820. https://doi.org/10.1016/j.jclepro.2022.134820
Parlak, B. O., & Yavaşoğlu, H. A. (2023). Comparison of regression algorithms to predict average air temperature. International Journal of Engineering Research and Development, 15, 312–322. https://doi.org/10.29137/umagd.1232020
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, 785–794. https://doi.org/10.1145/2939672.2939785
Li, M., Yao, Y., Feng, Z., et al. (2025). Hydrological drought prediction and its influencing features analysis based on a machine learning model. Natural Hazards and Earth System Sciences, 25, 4299–4316. https://doi.org/10.5194/nhess-25-4299-2025
Demir, V. (2025). Evaluation of Solar Radiation Prediction Models Using AI: A Performance Comparison in the High-Potential Region of Konya, Türkiye. Atmosphere, 16, 398. https://doi.org/10.3390/atmos16040398
Demir, V., Fu, M., Abba, S. I. et al. (2025). Performance assessment of advanced data-intelligence models for solar radiation forecasting: a case study in a high solar potential region. Climatic Change, 178, 177. https://doi.org/10.1007/s10584-025-04012-4
Mulla, S., Pande, C. B., & Singh, S. K. (2024). Time series forecasting of monthly rainfall using SARIMAX model. Water Resources Management, 38, 1825–1846. https://doi.org/10.1007/s11269-024-03756-5
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9, 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Citakoglu, H., Aktürk, G. & Demir, V. Hybrid machine learning for drought prediction at multiple time scales: a case study of Ağrı station, Türkiye. Acta Geophysica 73, 1643–1677 (2025). https://doi.org/10.1007/s11600-024-01501-5
Tulukcu, E. (2020). Sustainability in planning landscape areas of Konya province. Asian Journal of Advanced Research and Reports, 14, 85–91. https://doi.org/10.9734/ajarr/2020/v14i430345
Serdaroğlu Sağ, N. (2021). Assessment of urban development pattern and urban sprawl using Shannon’s entropy: A case study of Konya (Turkey). Journal of Human Sciences, 18, 252–265. https://doi.org/10.14687/jhs.v18i2.6158
Yener, A., & Özaydın, G. (2023). Determination of efficiency and factors affecting efficiency in maize production in Konya Province (Cumra District). Turkish Journal of Agriculture and Natural Sciences, 10, 1079–1087. https://doi.org/10.30910/turkjans.1109856
Gokmen, M., Vekerdy, Z., Lubczynski, M. W., et al. (2013). Assessing groundwater storage changes using remote sensing-based evapotranspiration and precipitation at a large semiarid basin scale. Journal of Hydrometeorology, 14, 1733–1753. https://doi.org/10.1175/JHM-D-12-0156.1
Kaplan, C. H., Büyükyıldız, M., & Köyceğiz, C. (2024). Comparison of interpolation methods in the spatial distribution of monthly precipitation data in Konya closed basin. Konya Journal of Engineering Sciences, 12, 920–940. https://doi.org/10.36306/konjes.1537038
Zhang, L., & Jánošík, D. (2024). Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches. Expert Systems with Applications, 241, 122686. https://doi.org/10.1016/j.eswa.2023.122686
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31, 6638–6648.
Hancock, J. T., & Khoshgoftaar, T. M. (2020). CatBoost for big data: An interdisciplinary review. Journal of Big Data, 7, 94. https://doi.org/10.1186/s40537-020-00369-8
Tibshirani, R. (1996). Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society: Series B, 58, 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning. New York: Springer. https://doi.org/10.1007/978-0-387-84858-7
Medeiros, M. C., Vasconcelos, G. F. R., Veiga, Á., et al. (2019). Forecasting inflation in a data-rich environment: Machine learning benefits. Journal of Business & Economic Statistics, 39, 98–119. https://doi.org/10.1080/07350015.2019.1637745
Campisi, G., Muzzioli, S., & De Baets, B. (2024). A comparison of machine learning methods for predicting the direction of the US stock market on the basis of volatility indices. International Journal of Forecasting, 40, 869–880. https://doi.org/10.1016/j.ijforecast.2023.07.002
Zou, H., & Hastie, T. (2005). Regularization and variable selection via the Elastic Net. Journal of the Royal Statistical Society: Series B, 67, 301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x
Ziel, F. (2016). Forecasting electricity spot prices using LASSO: On Capturing the Autoregressive Intraday Structure. IEEE Transactions on Power Systems, 31, 4977–4987. https://doi.org/10.1109/TPWRS.2016.2521545
Ke, G., Men, Q., Finley, T. W., et al. (2017). LightGBM: A highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems, 3149–3157.
Xiao, H., Shen, X., Li, J., et al. (2025). A method for filling traffic data based on feature-based combination prediction model. Scientific Reports, 15, 8441. https://doi.org/10.1038/s41598-025-92547-y
Salman, A. G., Heryadi, Y., Abdurahman, E., et al. (2018). Single-layer and multi-layer LSTM models for weather forecasting. Procedia Computer Science, 135, 89–98. https://doi.org/10.1016/j.procs.2018.08.153
Gong, Y., Zhang, Y., Wang, F., et al. (2024). Deep learning for weather forecasting: A CNN–LSTM hybrid model for predicting historical temperature data. Applied Computational Engineering, 99, 168–174. https://doi.org/10.54254/2755-2721/99/20251758
Teixeira, R., Cerveira, A., Pires, E. J. S., et al. (2024). Enhancing weather forecasting integrating LSTM and GA. Applied Sciences, 14, 5769. https://doi.org/10.3390/app14135769
Dutot, A.-L., Rynkiewicz, J., Steiner, F. E., et al. (2007). A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions. Environmental Modelling & Software, 22, 1261–1269. https://doi.org/10.1016/j.envsoft.2006.08.002
Voyant, C., Tamas, W., Nivet, M.-L., et al. (2014). Meteorological time series forecasting with pruned multilayer perceptron and 2-stage Levenberg-Marquardt method. International Journal of Modelling, Identification and Control, 23, 287–294.
Xu, T., Zhang, Y., Zhang, C., et al. (2024). Reconstruction of missing climate data with spatio-temporal multilayer perceptron. Theoretical and Applied Climatology, 155, 5835–5847. https://doi.org/10.1007/s00704-024-04945-3
Wei, L., Yang, X., Liu, G., Dai, R., Sundararajan, A., & Sarwat, A. I. (2020). A hybrid approach for weather-based power interruption forecasting using multilayer perceptrons and parametric models. In 2020 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) (1–5). IEEE. https://doi.org/10.1109/APPEEC48164.2020.9220606
Roy, D. S. (2020). Forecasting air temperature using deep neural networks. Procedia Computer Science, 178, 38–46. https://doi.org/10.1016/j.procs.2020.11.005
Jiang, Q., Cioffi, F., Li, W., et al. (2024). Hybrid multilayer perceptron and convolutional neural network model to predict extreme regional precipitation dominated by the large-scale atmospheric circulation. Atmospheric Research, 304, 107362. https://doi.org/10.1016/j.atmosres.2024.107362
Shah, V., Patel, N., Shah, D., et al. (2024). Forecasting maximum temperature using SARIMAX. Sustainability, 16, 7183. https://doi.org/10.3390/su16167183
Elshewey, A. M., Shams, M. Y., Elhady, A. M., et al. (2023). A novel WD-SARIMAX model for temperature forecasting using daily Delhi climate dataset. Sustainability, 15, 757. https://doi.org/10.3390/su15010757
Milli, M. (2025). Designing a residual-enhanced hybrid Prophet–LSTM framework for urban air pollution forecasting in Beijing. Scientific Reports, 15, 43646. https://doi.org/10.1038/s41598-025-27510-y
Kandamali, D. F., Porter, E., Porter, W. M., et al. (2025). Hybrid LSTM method for multistep soil moisture prediction using historical soil moisture and weather data. AgriEngineering, 7, 260. https://doi.org/10.3390/agriengineering7080260
Kachalla, I. A., Ghiaus, C., Ademuwagun, A., et al. (2025). Data-driven hybrid SARIMAX–MLP framework for energy consumption prediction in residential micro-grid. Results in Engineering, 26, 105336. https://doi.org/10.1016/j.rineng.2025.105336
Zouzou, Y., & Çıtakoğlu, H. (2021). Reference evapotranspiration prediction from limited climatic variables using support vector machines and Gaussian processes. Avrupa Bilim ve Teknoloji Dergisi, 28, 346–351. https://doi.org/10.31590/ejosat.999319
Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I—A discussion of principles. Journal of Hydrology, 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6
Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting. Butterworth-Heinemann.
Kling, H., Fuchs, M., & Paulin, M. (2012). Runoff conditions in the upper Danube basin under an ensemble of climate change scenarios. Journal of Hydrology, 424–425, 264–277. https://doi.org/10.1016/j.jhydrol.2012.01.011
Gupta, H. V., Sorooshian, S., & Yapo, P. O. (1999). Status of automatic calibration for hydrologic models: Comparison with multilevel expert calibration. Journal of Hydrologic Engineering, 4(2), 135–143. https://doi.org/10.1061/(ASCE)1084-0699(1999)4:2(135)
Başakın, E. E., Ekmekcioğlu, Ö., Çıtakoğlu, H., & Özger, M. (2022). A new insight to the wind speed forecasting: robust multi-stage ensemble soft computing approach based on pre-processing uncertainty assessment. Neural Computing and Applications, 34, 783–812. https://doi.org/10.1007/s00521-021-06424-6
Zouzou, Y., & Citakoglu, H. (2023). General and regional cross-station assessment of machine learning models for estimating reference evapotranspiration. Acta Geophysica, 71, 927–947. https://doi.org/10.1007/s11600-022-00939-9
Saroughi, M., Katipoğlu, O. M., Aktürk, G., Gul, E., Simsek, O., & Citakoglu, H. (2025). Daily prediction of Urmia Lake water level using remote sensing data and honey badger optimization-based data-driven models. Acta Geophysica, 73, 2909–2933. https://doi.org/10.1007/s11600-024-01520-2

Details

Primary Language

English

Subjects

Water Resources Engineering, Civil Engineering (Other)

Journal Section

Research Article

Authors

Kağan Eryürük ^*
0000-0003-3993-839X
Türkiye

Şule Eryürük
0000-0003-2746-1598
Türkiye

Publication Date

May 22, 2026

Submission Date

March 23, 2026

Acceptance Date

May 21, 2026

Published in Issue

Year 2026 Volume: 6 Number: 3

DOI

https://doi.org/10.64808/engineeringperspective.1914439

IZ

https://izlik.org/JA67SR28UM

Cite

RIS / Bibtex

APA

Eryürük, K., & Eryürük, Ş. (2026). Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions. Engineering Perspective, 6(3), 428-445. https://doi.org/10.64808/engineeringperspective.1914439

AMA

1.Eryürük K, Eryürük Ş. Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions. engineeringperspective. 2026;6(3):428-445. doi:10.64808/engineeringperspective.1914439

Chicago

Eryürük, Kağan, and Şule Eryürük. 2026. “Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions”. Engineering Perspective 6 (3): 428-45. https://doi.org/10.64808/engineeringperspective.1914439.

EndNote

Eryürük K, Eryürük Ş (May 1, 2026) Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions. Engineering Perspective 6 3 428–445.

IEEE

[1]K. Eryürük and Ş. Eryürük, “Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions”, engineeringperspective, vol. 6, no. 3, pp. 428–445, May 2026, doi: 10.64808/engineeringperspective.1914439.

ISNAD

Eryürük, Kağan - Eryürük, Şule. “Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions”. Engineering Perspective 6/3 (May 1, 2026): 428-445. https://doi.org/10.64808/engineeringperspective.1914439.

JAMA

1.Eryürük K, Eryürük Ş. Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions. engineeringperspective. 2026;6:428–445.

MLA

Eryürük, Kağan, and Şule Eryürük. “Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions”. Engineering Perspective, vol. 6, no. 3, May 2026, pp. 428-45, doi:10.64808/engineeringperspective.1914439.

Vancouver

1.Kağan Eryürük, Şule Eryürük. Comparative Assessment of Machine Learning and Statistical Models for Precipitation Forecasting in Semi-Arid Regions. engineeringperspective. 2026 May 1;6(3):428-45. doi:10.64808/engineeringperspective.1914439