Rainfall prediction includes forecasting the occurrence of rainfall and projecting the amount of rainfall over the modeled area. Rainfall is the result of various natural phenomena such as temperature, humidity, atmospheric pressure, and wind direction, and is therefore composed of various factors that lead to uncertainties in the prediction of the same. In this work, different machine learning and deep learning models are used to (a) predict the occurrence of rainfall, (b) project the amount of rainfall, and (c) compare the results of the different models for classification and regression purposes. The dataset used in this work for rainfall prediction contains data from 49 Australian cities over a 10-year period and contains 23 features, including location, temperature, evaporation, sunshine, wind direction, and many more. The dataset contained numerous uncertainties and anomalies that caused the prediction model to produce erroneous projections. We, therefore, used several data preprocessing techniques, including outlier removal, class balancing for classification tasks using Synthetic Minority Oversampling Technique (SMOTE), and data normalization for regression tasks using Standard Scalar, to remove these uncertainties and clean the data for more accurate predictions. Training classifiers such as XGBoost, Random Forest, Kernel SVM, and Long-Short Term Memory (LSTM) are used for the classification task, while models such as Multiple Linear Regressor, XGBoost, Polynomial Regressor, Random Forest Regressor, and LSTM are used for the regression task. The experiment results show that the proposed approach outperforms several state-of-the-art approaches with an accuracy of 92.2% for the classification task, a mean absolute error of 11.7%, and an R2 score of 76% for the regression task.
Citation: Sarth Kanani, Shivam Patel, Rajeev Kumar Gupta, Arti Jain, Jerry Chun-Wei Lin. An AI-Enabled ensemble method for rainfall forecasting using Long-Short term memory[J]. Mathematical Biosciences and Engineering, 2023, 20(5): 8975-9002. doi: 10.3934/mbe.2023394
Rainfall prediction includes forecasting the occurrence of rainfall and projecting the amount of rainfall over the modeled area. Rainfall is the result of various natural phenomena such as temperature, humidity, atmospheric pressure, and wind direction, and is therefore composed of various factors that lead to uncertainties in the prediction of the same. In this work, different machine learning and deep learning models are used to (a) predict the occurrence of rainfall, (b) project the amount of rainfall, and (c) compare the results of the different models for classification and regression purposes. The dataset used in this work for rainfall prediction contains data from 49 Australian cities over a 10-year period and contains 23 features, including location, temperature, evaporation, sunshine, wind direction, and many more. The dataset contained numerous uncertainties and anomalies that caused the prediction model to produce erroneous projections. We, therefore, used several data preprocessing techniques, including outlier removal, class balancing for classification tasks using Synthetic Minority Oversampling Technique (SMOTE), and data normalization for regression tasks using Standard Scalar, to remove these uncertainties and clean the data for more accurate predictions. Training classifiers such as XGBoost, Random Forest, Kernel SVM, and Long-Short Term Memory (LSTM) are used for the classification task, while models such as Multiple Linear Regressor, XGBoost, Polynomial Regressor, Random Forest Regressor, and LSTM are used for the regression task. The experiment results show that the proposed approach outperforms several state-of-the-art approaches with an accuracy of 92.2% for the classification task, a mean absolute error of 11.7%, and an R2 score of 76% for the regression task.
| [1] | R. K. Gupta, A. Jain, J. Wang, V. P. Singh, S. Bharti, Artificial intelligence of things for weather forecasting and climatic behavioral analysis, IGI Global, (2022), 1–277. https://doi.org/10.4018/978-1-6684-3981-4 |
| [2] | G. Kulesa, Weather and aviation: How does weather affect the safety and operations of airports and aviation, and how does FAA work to manage weather-related effects?, in The Potential Impacts of Climate Change on Transportation Workshop, (2002), 1–10. https://doi.org/10.1016/j.media.2013.04.012 |
| [3] | Economic Losses Due to Climatic Changes, 2022. Available from: https://www.mnw.cn/news/fj/. |
| [4] | V. Sharma, S. van de Graaff, B. Loechel, D. Franks, Extractive resource development in a changing climate: learning the lessons from extreme weather events in Queensland, Australia: Final report, 2012. Available from: http://hdl.handle.net/102.100.100/101882?index = 1. |
| [5] | J. Abbot, J. Marohasy, Using artificial intelligence to forecast monthly rainfall under present and future climates for the Bowen Basin, Queensland, Australia, Int. J. Sustainable Dev. Plann., 10 (2015), 66–75. |
| [6] | A. Zhong, D. Hudson, O. Alves, G. Wang, H. Hendon, Predictive Ocean Atmosphere Model for Australia (POAMA), in 10th EMS Annual Meeting, (2010), 2010–2016. |
| [7] | E. Vamsidhar, K. V. S. R. P. Varma, P. S. Rao, R. Satapati, Prediction of rainfall using backpropagation neural network model, Int. J. Comput. Sci. Eng., 2 (2010), 1119–1121. |
| [8] |
A. Y. Barrera-Animas, L. O. Oyedele, M. Bilal, T. D. Akinosho, J. M. D. Delgado, L. A. Akanbi, Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting, Mach. Learn. Appl., 7 (2022), 100204. https://doi.org/10.1016/j.mlwa.2021.100204 doi: 10.1016/j.mlwa.2021.100204
|
| [9] | A. J. Hill, R. S. Schumacher, Forecasting excessive rainfall with random forests and a deterministic convection-allowing model, Weather Forecast., 36 (2021) 1693–1711. https://doi.org/10.1175/WAF-D-21-0026.1 |
| [10] | S. A. Fayaz, M. Zaman, M. A. Butt, Knowledge discovery in geographical sciences—A systematic survey of various machine learning algorithms for rainfall prediction, in International Conference on Innovative Computing and Communications, Springer, 1388 (2022), 593–608. https://doi.org/10.1007/978-981-16-2597-8_51 |
| [11] |
X. Xing, C. Wu, J. Li, X. Li, L. Zhang, R. He, Susceptibility assessment for rainfall-induced landslides using a revised logistic regression method, Nat. Hazards, 106 (2021), 97–117. https://doi.org/10.1007/s11069-020-04452-4 doi: 10.1007/s11069-020-04452-4
|
| [12] |
M. Marjanovic, M. Krautblatter, B. Abolmasov, U. Duric, C. Sandic, V. Nikolic, The rainfall-induced landsliding in Western Serbia: A temporal prediction approach using Decision Tree technique, Eng. Geol., 232 (2018), 147–159. https://doi.org/10.1016/j.enggeo.2017.11.021 doi: 10.1016/j.enggeo.2017.11.021
|
| [13] | X. Zhou, H. Wen, Z. Li, H. Zhang, W. Zhang, An interpretable model for the susceptibility of rainfall-induced shallow landslides based on SHAP and XGBoost, Geocarto Int., (2022), 1–27. doilinkhttps://doi.org/10.1080/10106049.2022.2076928 |
| [14] | A. Jain, R. Gairola, S. Jain, A. Arora, Thwarting spam on Facebook: Identifying spam posts using machine learning techniques, Res. Anthol. Mach. Learn. Tech. Methods Appl., (2022), 693–713. https://doi.org/10.4018/978-1-6684-6291-1.ch037 |
| [15] | N. T. Jani, R. K. Gupta, S. K. Bharti, A. Jain, Advancements in weather forecasting with deep learning, Artif. Intell. Things Weather Forecast. Clim. Behav. Anal., (2022), 75–86. https://doi.org/10.4018/978-1-6684-3981-4.ch006 |
| [16] |
K. C. Luk, J. E. Ball, A. Sharma, An application of artificial neural networks for rainfall forecasting, Math. Comput. model., 33 (2001), 683-693. https://doi.org/10.1016/S0895-7177(00)00272-7 doi: 10.1016/S0895-7177(00)00272-7
|
| [17] |
K. Abhishek, M. P. Singh, S. Ghosh, A. Anand, Weather forecasting model using artificial neural network, Procedia Technol., 4 (2012), 311–318. https://doi.org/10.1016/j.protcy.2012.05.047 doi: 10.1016/j.protcy.2012.05.047
|
| [18] | K. Abhishek, R. Ranjan, S. Kumar, A rainfall prediction model using artificial neural network, in 2012 IEEE Control and System Graduate Research Colloquium, (2012), 82–87. doilinkhttps://doi.org/10.1109/ICSGRC.2012.6287140 |
| [19] |
T. Saba, A. Rehman, J. S. AlGhamdi, Weather forecasting based on hybrid neural model, Appl. Water Sci., 7 (2017), 3869–3874. https://doi.org/10.1007/s13201-017-0538-0 doi: 10.1007/s13201-017-0538-0
|
| [20] |
M. Biswas, T. Dhoom, S. Barua, Weather forecast prediction: An integrated approach for analyzing and measuring weather data, Int. J. Comput. Appl., 975 (2018), 8887. https://doi.org/10.5120/ijca2018918265 doi: 10.5120/ijca2018918265
|
| [21] | C. Z. Basha, N. Bhavana, P. Bhavya, V. Sowmya, Rainfall prediction using machine learning & deep learning techniques, in 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), (2020), 92–97. https://doi.org/10.1109/ICESC48915.2020.9155896 |
| [22] | A. Doroshenko, V. Shpyg, R. Kushnirenko, Machine learning to improve numerical weather forecasting, in 2020 IEEE 2nd International Conference on Advanced Trends in Information Theory (ATIT), (2020), 353–356. https://doi.org/10.1109/ATIT50783.2020.9349325 |
| [23] |
N. K. A. Appiah-Badu, Y. M. Missah, L. K. Amekudzi, N. Ussiph, T. Frimpong, E. Ahene, Rainfall prediction using machine learning algorithms for the various ecological zones of Ghana, IEEE Access, 10 (2021), 5069–5082. https://doi.org/10.1109/ACCESS.2021.3139312 doi: 10.1109/ACCESS.2021.3139312
|
| [24] |
M. Raval, P. Sivashanmugam, V. Pham, H. Gohel, A. Kaushik, Y. Wan, Automated predictive analytics tool for rainfall forecasting, Sci. Rep., 11 (2021), 1–13. https://doi.org/10.1038/s41598-021-95735-8 doi: 10.1038/s41598-021-95735-8
|
| [25] |
W. M. Ridwan, M. Sapitang, A. Aziz, K. F. Kushiar, A. N. Ahmed, A. El-Shafie, Rainfall forecasting model using machine learning methods: Case study Terengganu, Malaysia, Ain Shams Eng. J., 12 (2021), 1651–1663. https://doi.org/10.1016/j.asej.2020.09.011 doi: 10.1016/j.asej.2020.09.011
|
| [26] |
F. R. Adaryani, S. J. Mousavi, F. Jafari, Short-term rainfall forecasting using machine learning-based approaches of PSO-SVR, LSTM and CNN, J. Hydrol., 614 (2022), 128463. https://doi.org/10.1016/j.jhydrol.2022.128463 doi: 10.1016/j.jhydrol.2022.128463
|
| [27] |
S. Fahad, F. Su, S. U. Khan, M. R. Naeem, K. Wei, Implementing a novel deep learning technique for rainfall forecasting via climatic variables: An approach via hierarchical clustering analysis, Sci. Total Environ., 854 (2023), 158760. https://doi.org/10.1016/j.scitotenv.2022.158760 doi: 10.1016/j.scitotenv.2022.158760
|
| [28] | Kaggle Dataset, Rain in Australia, 2022. Available from: https://www.kaggle.com/datasets/jsphyg/weather-dataset-rattle-package. |
| [29] | P. Pedamkar, Statistics for machine learning, 2022. Available from: https://www.educba.com/statistics-for-machine-learning/. |
| [30] |
N. V. Chawla, K. W. Bowyer, L. O. Hall, W. P. Kegelmeyer, SMOTE: synthetic minority over-sampling technique, J. Artif. Intell. Res., 16 (2002), 321–357. https://doi.org/10.1613/jair.953 doi: 10.1613/jair.953
|
| [31] |
Y. Han, J. Kim, D. Enke, A machine learning trading system for the stock market based on N-period Min-Max labeling using XGBoost, Expert Syst. Appl., 211 (2023), 118581. https://doi.org/10.1016/j.eswa.2022.118581 doi: 10.1016/j.eswa.2022.118581
|
| [32] |
M. Esteve, J. Aparicio, J. J. Rodriguez-Sala, J. Zhu, Random Forests and the measurement of super-efficiency in the context of Free Disposal Hull, Eur. J. Oper. Res., 304 (2023), 729–744. https://doi.org/10.1016/j.ejor.2022.04.024 doi: 10.1016/j.ejor.2022.04.024
|
| [33] |
X. Xie, Y. Li, S. Sun, Deep multi-view multiclass twin support vector machines, Informa. Fusion, 91 (2023), 80–92. https://doi.org/10.1016/j.inffus.2022.10.005 doi: 10.1016/j.inffus.2022.10.005
|
| [34] |
V. H. Pereira-Ferrero, L. P. Valem, D. C. G. Pedronette, Feature augmentation based on manifold ranking and LSTM for image classification, Expert Syst. Appl., 213 (2023), 118995. https://doi.org/10.1016/j.eswa.2022.118995 doi: 10.1016/j.eswa.2022.118995
|
| [35] | A. Banik, T. K. Bandyopadhyay, S. K. Biswal, V. Panchenko, S. Garhwal, Comparative performance assessment of multi-linear regression and artificial neural network for prediction of permeate flux of disc-shaped membrane, Intelligent Computing and Optimization, Lecture Notes in Networks and Systems, Springer, 569 (2023), 24–33. https://doi.org/10.1007/978-3-031-19958-5_3 |
| [36] |
J. Dong, W. Zeng, L. Wu, J. Huang, T. Gaiser, A. K. Srivastava, Enhancing short-term forecasting of daily precipitation using numerical weather prediction bias correcting with XGBoost in different regions of China, Eng. Appl. Artif. Intell., 117 (2023), 105579. https://doi.org/10.1016/j.engappai.2022.105579 doi: 10.1016/j.engappai.2022.105579
|
| [37] |
K. Sarkodie, A. Fergusson-Rees, M. Abdulkadir, N. Y. Asiedu, Gas-liquid flow regime identification via a non-intrusive optical sensor combined with polynomial regression and linear discriminant analysis, Ann. Nucl. Energy, 180 (2023), 109424. https://doi.org/10.1016/j.anucene.2022.109424 doi: 10.1016/j.anucene.2022.109424
|
| [38] |
F. Ricardo, P. Ruiz-Puentes, L. H. Reyes, J. C. Cruz, O. Alvarez, D. Pradilla, Estimation and prediction of the air-water interfacial tension in conventional and peptide surface-active agents by random forest regression, Chem. Eng. Sci., 265 (2023), 118208. https://doi.org/10.1016/j.ces.2022.118208 doi: 10.1016/j.ces.2022.118208
|
| [39] |
J. Chen, Y. Zhang, J. Wu, W. Cheng, Q. Zhu, SOC estimation for lithium-ion battery using the LSTM-RNN with extended input and constrained output, Energy, 262 (2023), 125375. https://doi.org/10.1016/j.energy.2022.125375 doi: 10.1016/j.energy.2022.125375
|
| [40] | S. Iyer, A. Jain, J. Wang, Handbook of research on lifestyle sustainability and management solutions using AI, big data analytics, and visualization, IGI Global, (2022), 1–411. https://doi.org/10.4018/978-1-7998-8786-7 |
| [41] | N. Oswal, Predicting rainfall using machine learning techniques, preprint, arXiv: 1910.13827. |
| [42] | Z. He, Rain prediction in Australia with active learning algorithm, in 2021 International Conference on Computers and Automation (CompAuto), (2021), 14–18. https://doi.org/10.1109/CompAuto54408.2021.00010 |
Figures(16) / Tables(13)
Sarth Kanani, Shivam Patel, Rajeev Kumar Gupta, Arti Jain, Jerry Chun-Wei Lin. An AI-Enabled ensemble method for rainfall forecasting using Long-Short term memory[J]. Mathematical Biosciences and Engineering, 2023, 20(5): 8975-9002. doi: 10.3934/mbe.2023394
DownLoad: