Evaluation of Data Mining and Artificial Intelligence Methods to Predict Daily Precipitation
Main Article Content
Abstract
Precipitation is the most important weather parameter, which has direct and indirect effects on life on our planet. One of the most relevant climate change consequences is extreme weather conditions, such as floods and droughts. Up to now, climate model projections have remained uncertain, therefore, more accurate precipitation modelling techniques are necessary. Due to the complexity of relationships among metrological parameters, traditional statistical modelling tools are ineffective in forecasting and predicting weather conditions. In this study, data mining techniques were applied to metrological data to predict daily precipitation using Multilinear regression (MLR) along with two artificial intelligence (AI) techniques, specifically Artificial Neural Networks (ANN) and Neuro-Fuzzy Inference System (ANFIS). A total of 10 daily metrological variables, for 13 years, namely Maximum temperature (Tmax), minimum temperature (Tmin), maximum humidity (Hmax), minimum humidity (Hmin), wind speed (Ws), wind direction (Wd), cloud cover (Cv), sea pressure (SEAp), station pressure (STAp) and relative humidity (RH) are used to predict precipitation (P). Both AI systems showed acceptable results predicting daily precipitation from observed meteorological parameters with a coefficient of determination (R2) of 0.75 and 0.72 for model calibration of ANN and ANFIS methods, respectively. The results of the ANN and ANFIS testing methods were 0.55 and 0.62, respectively. Outcomes of the study showed that the ANN model may have overfitted the results in the calibration section of the process compared to the ANFIS method, which performed better in the testing section of the evaluation process. In ANFIS modelling, for several input variables up to 6 variables, this study recommends using the grid partition method to divide variable ranges into membership functions. For input variables of more than 6 variables, sub-clustering method is recommended.
Article Details
Section
How to Cite
References
Abdullah, J. B., and Hamaamin, Y. A., 2020. Temporal variation of drinking water quality parameters for Sulaimani city, Kurdistan region, Iraq. UHD Journal of Science and Technology, 4(2), pp.99-106. https://doi.org/10.21928/uhdjst.v4n2y2020.pp99-106
Aftab, S., Ahmad, M., Hameed, N., Bashir, M. S., Ali, I., Nawaz, Z., 2018. Rainfall prediction using data mining techniques: A systematic literature review. International journal of advanced computer science and applications, 9(5). https://dx.doi.org/10.14569/IJACSA.2018.090518
AL-Suhaili, R. H., and Karim, R. A., 2014. Spatial prediction of monthly precipitation in Sulaimani governorate using artificial neural network models. Journal of Engineering, 20(03), pp.15-27. https://doi.org/10.31026/j.eng.2014.03.02
Aoulmi, Y., Marouf, N., Amireche, M., 2021. The assessment of artificial neural network rainfall-runoff models under different input meteorological parameters: Case study: Seybouse basin, Northeast Algeria. Journal of Water and Land Development, pp. 38-47. https://doi.org/10.24425/jwld.2021.138158
Beale, M. H., Hagan, M. T., and Demuth, H. B., 2017. Neural network toolbox. User’s Guide. The MathWorks, Inc.
Chu, J., Liu, X., Zhang, Z., Zhang, Y., and He, M., 2021. A novel method overcoming overfitting of artificial neural networks for accurate prediction: application on thermophysical properties of natural gas. Case Studies in Thermal Engineering, 28, P. 101406. https://doi.org/10.1016/j.csite.2021.101406
Frost, J., 2019. Introduction to statistics: An intuitive guide for analyzing data and unlocking discoveries. Amazon: Bellevue, WA, USA, 2020.
Frost, J., 2020. Hypothesis Testing: An Intuitive Guide for Making Decisions. Statistics by Jim Publishing; Amazon: Bellevue, WA, USA, 2020.
Gore, R. D., and Gawali, B. W. 2023. Analysis of weather parameters using machine learning. In the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies. (ACVAIT 2022) (pp. 569-589). Atlantis Press. https://doi.org/10.2991/978-94-6463-196-8_44
Gupta, G. K., 2014. Introduction to data mining with case studies. PHI Learning Pvt. Ltd. ISBN-13 : 978 8120350021.
Hamaamin, Y. A., and Faraj, B.A., 2023. Optimal locations for BMPs stormwater management for Sulaymaniyah city industrial zone, KRG, Iraq. Environment and Ecology Research 11(3), pp.411-420. https://doi.org/10.13189/eer.2023.110301
Hamaamin, Y. A., 2017. Developing of rainfall intensity-duration-frequency model for Sulaimani city. Journal of Zankoy Sulaimani, 19(3-4), pp.10634. http://dx.doi.org/10.17656/jzs.10634
Hamaamin, Y. A., Rashed, K. A., Ali, Y. M., and Abdalla, T. A., 2022. Evaluation of ANFIS and regression techniques in estimating soil compression index for cohesive soils. Journal of Engineering, 28(10), pp.28-41. https://doi.org/10.31026/j.eng.2022.10.03
Hamdan, A., Ibekwe, K. I., Etukudoh, E. A., Umoh, A. A., and Ilojianya, V. I., 2024. AI and machine learning in climate change research: A review of predictive models and environmental impact. World Journal of Advanced Research and Reviews, 21(1), pp. 1999-2008. https://doi.org/10.30574/wjarr.2024.21.1.0257
Han, S. H., Kim, K. W., Kim, S., and Youn, Y. C., 2018. Artificial neural network: Understanding the basic concepts without mathematics. Dementia and neurocognitive disorders, 17(3), pp.83-89. https://doi.org/10.12779%2Fdnd.2018.17.3.83
Judd, C. M., McClelland, G. H., and Ryan, C. S., 2017. Data analysis: A model comparison approach to regression, ANOVA, and beyond. Routledge. ISBN 9781138819832.
Kisi, O., Shiri, J., and Tombul, M., 2013. Modeling rainfall-runoff process using soft computing techniques. Computers & Geosciences, 51, pp.108-117. https://doi.org/10.1016/j.cageo.2012.07.001
Lind, P., 2023. Kilometer-scale climate modeling of precipitation in the Nordic region, PhD dissertation, Department of Meteorology, Stockholm University.
Li, H., Li, S., and Ghorbani, H., 2024. Data-driven novel deep learning applications for the prediction of rainfall using meteorological data. Frontiers in Environmental Science, 12, 1445967. https://doi.org/10.3389/fenvs.2024.1445967
Liyew, C. M., and Melese, H. A., 2021. Machine learning techniques to predict daily rainfall amount. Journal of Big Data, 8, pp.1-11. https://doi.org/10.1186/s40537-021-00545-4
Liu, H., Fung, J. C., Lau, A. K., and Li, Z., 2024. Enhancing quantitative precipitation estimation of NWP models with fundamental meteorological variables and a transformer-based deep learning model. Earth and Space Science, 11(4), e2023EA003234. https://doi.org/10.1029/2023EA003234
Mucherino, A., Papajorgji, P., and Pardalos, P. M., 2009. Data mining in agriculture. Springer Science & Business Media. eBook ISBN 978-0-387-88615-2
MathWorks, 2018. MATLAB Fuzzy Logic Toolbox User’s Guide2, The MathWorks, Inc.
Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., and Veith, T. L. 2007. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE, 50(3), 885-900.
Ott, R. L., and Longnecker, M. 2015. An introduction to statistical methods and data analysis. Cengage Learning Inc. ISBN-13: 978-1305269477
Pathan, M. S., Wu, J., Lee, Y. H., Yan, J., and Dev, S., 2021. Analyzing the impact of meteorological parameters on rainfall prediction. In 2021 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), pp. 100-101. https://doi.org/10.23919/USNC-URSI51813.2021.9703664
Rahman, M. A., 2020. Improvement of rainfall prediction model by using fuzzy logic. American Journal of Climate Change, 9(4), pp.391-399. https://doi.org/10.4236/ajcc.2020.94024
Rashid, H. M., 2024. Drought assessment based on different meteorological drought indices in Sulaymaniyah governorate, KRG, Iraq. Journal of Engineering, 30(9), pp.190-215. https://doi.org/10.31026/j.eng.2024.09.10
Raval, M., Sivashanmugam, P., Pham, V., Gohel, H., Kaushik, A., and Wan, Y., 2021. Automated predictive analytics tool for rainfall forecasting. Scientific Reports, 11(1), p.17704. https://doi.org/10.1038/s41598-021-95735-8
Rojas-Campos, A., Langguth, M., Wittenbrink, M., and Pipa, G., 2023. Deep learning models for generation of precipitation maps based on numerical weather prediction. Geoscientific Model Development, 16(5), pp.1467-1480. https://doi.org/10.5194/gmd-16-1467-2023
Sammen, S. S., Kisi, O., Ehteram, M., El-Shafie, A., Al-Ansari, N., Ghorbani, M. A., and Shahid, S., 2023. Rainfall modeling using two different neural networks improved by metaheuristic algorithms. Environmental Sciences Europe, 35(1), p.112. https://doi.org/10.1186/s12302-023-00818-0
Shabbir, M., Chand, S., and Iqbal, F., 2023. A novel hybrid framework to model the relationship of daily river discharge with meteorological variables. Meteorology, Hydrology, and Water Management. Research and Operational Applications, 11(2), pp.70-94. https://doi.org/10.26491/mhwm/187899
Shamshirband, S., Gocić, M., Petković, D., Saboohi, H., Herawan, T., Kiah, M. L. M., and Akib, S., 2014. Soft-computing methodologies for precipitation estimation: A case study. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(3), pp.1353-1358. https://doi.org/10.1109/JSTARS.2014.2364075
Turhan, E., 2021. A comparative evaluation of the use of artificial neural networks for modeling the rainfall-runoff relationship in water resources management. Journal of Ecological Engineering, 22(5). https://doi.org/10.12911/22998993/135775