Heavy rainfall classification using Genetic Programming
227 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.77.2022.150-160Keywords:
Genetic Programming; Imbalance classification; Heavy rain classification.Abstract
Classification of overwhelming heavy rainfall is a critical issue in the field of meteorology because it has extraordinary effects on people's lives and economies. Every year, a huge number of people all over the world suffer serious consequences from overwhelming precipitation events such as flooding and disease spreads. In this paper, we use Genetic Programming (GP) to predict if there will be heavy rain the next day. GP is an evolution-based machine learning methodology that can identify the model’s functional form as well as its numerical coefficients. Our model was trained and evaluated on a data set collected from 17 stations in Vietnam’s provinces. The experimental results show that models constructed using GP can perform better for heavy rain classification than models using other popular machine learning methods.
References
[1]. IFRC, "World Disaster Report 2020," International Federation of Red Cross and Red Crescent Societies, 2020.
[2]. V. D. B. D. N. L. N. L. Duc, "Research and quantitative ranifall forecasting from HRM and GSM model products," Vietnam Journal of Hydrometerorology, vol. 592, pp. 17-27, 2010.
[3]. S. V. a. F. H. P. G. Espejo, "A Survey on the Application of Genetic Programming to Classification," IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 40, no. 2, pp. 121-144, 2010.
[4]. N. S. A. B. A. Kumar, "A novel fitness function in genetic programming for medical data classification," Journal of Biomedical Informatics, vol. 112, 2020.
[5]. L. M. P. V. M. a. V. K. A. J. K. Kishore, "Application of genetic programming for multicategory pattern classification," IEEE Transactions on Evolutionary Computation, vol. 4, no. 3, pp. 242-258, 2000.
[6]. C. K. H. Liu, "A genetic programming-based approach to the classification of multiclass microarray datasets," Bioinformatics, vol. 25, no. 3, 2009.
[7]. K. T. T. W. E. T. X. Y. P. Wang, "Multiobjective genetic programming for maximizing ROC performance," Neurocomputing, vol. 125, pp. 102-118, 2014.
[8]. M. E. R. L. K. T. T. B. a. X. Y. P. Wang, "Convex Hull-Based Multiobjective Genetic Programming for Maximizing Receiver Operating Characteristic Performance," IEEE Transactions on Evolutionary Computation, vol. 19, no. 2, pp. 188-200, 2015.
[9]. A. P. S. A. a. T. M. K. Deb, "A fast and elitist multiobjective genetic algorithm: NSGA-II," IEEE Transactions on Evolutionary Computation, vol. 6, no. 2, pp. 182-197, 2002.
[10]. J. R. Koza, “Genetic Programming”. On the Programming of Computers by Means of Natural Selection, Massachusetts: MIT Press, Cambridge, 1992.
[11]. O. J. Dunn, "Multiple comparisons among means," J. Amer. Stat. Assoc., pp. 52-64, 2012.
[12]. S. a. P. L. a. B. G. a. P. S. a. S. Z. a. B. J. a. H. R. a. C. A. Luke, "Ecj: A java-based evolutionary computation research system," Downloadable versions and documentation can be found at the following url: http://cs. gmu. edu/eclab/projects/ecj, 2006.
[13]. J. R. Quinlan, “C4. 5: programs for machine learning”, Elsevier, 2014.
[14]. Y. a. L. J. a. L. J. a. Z. X. Song, "An efficient instance selection algorithm for k nearest neighbor regression," Neurocomputing, vol. 251, pp. 26-34, 2017.
[15]. R. M. a. L. E. I. Balabin, "Support vector machine regression (SVR/LS-SVM)—an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data," Analyst, vol. 136, no. 8, pp. 1703-1712, 2011.
[16]. M. a. F. E. a. H. G. a. P. B. a. R. P. a. W. I. H. Hall, "The WEKA data mining software: an update," ACM SIGKDD explorations newsletter, vol. 11, pp. 10-18, 2009.
[17]. H. M. Doucette J., "GP Classification under Imbalanced Data sets: Active Sub-sampling and AUC Approximation," in Genetic Programming. EuroGP 2008. Lecture Notes in Computer Science, Heidelberg, Springer, Berlin, Heidelberg, 2008, pp. 266-277.
[18]. N. A. ArvindKumar, "A novel fitness function in genetic programming for medical data classification," Journal of Biomedical Informatics, vol. 112, no. 103623, pp. 1-6, 2020.
[19]. H. B. M. B. K. S. T. &. L. S. W. Madsen, "Data assimilation in rainfall-runoff forecasting," in Hydroinformatics 2000, 4th International Conference of Hydroinformatics, 23–27 July 2000, Cedar Rapids, Iowa, USA, 2000.
[20]. J. P. &. M. H. Drécourt, "Role of domain knowledge in datadrivenmodeling," in Proceedings 4th DHI Software Conference & DHI Software Courses. 6–8 June 2001, DHI, Helsingør, Denmark, 2001.
[21]. P. A. &. C. P. F. Whigham, "Modelling rainfall-runoff using genetic programming," Math. Comput. Modell., vol. 33, pp. 707-721, 2001.
[22]. S. T. K. E. C. &. P. O. Khu, "An evolutionary-based real-time updating technique for an operational rainfall-runoff forecasting model," Complexity and Integrated Resources Management, Trans., vol. 1, pp. 141-146, 2004.
[23]. J. R. P. J. S. J. &. R. D. Rabuñal, "Determination of the unit hydrograph of a typical urban basin using genetic programming and artificial neural networks," Hydrol. Process, vol. 21, no. 4, p. 476–485, 2004.
[24]. K. Rodríguez-Vázquez, "Genetic programming in time series modelling: an application to meteorological data," in Proceedings 2001 Congress on Evolutionary Computation, Seoul, Korea, 2001.
[25]. Guven, "Linear genetic programming for time-series modelling of daily flow rate," J. Earth Sci., p. 137–146., 2009.
[26]. W. N. P. K. R. E. &. F. F. D. Banzhaf, “Genetic Programming: An Introduction.”, California: Morgan Kaufmann, 1998.
[27]. S.-Y. G. T. R. K. S. T. B. V. K. M. &. M. N. Liong, "Genetic programming: a new paradigm in rainfall–runoff modelling," J. AWRA 38, pp. 705-718, 2002.
[28]. D. A. W. G. A. &. D. J. Savic, "A genetic programming approach to rainfall–runoff modelling," Wat. Res. Mngmnt., p. 219–231, 1999.
