.svg){kind=logo}
ANALYZING TREND AND FORECASTING OF RAINFALL IN SOUTHERN PHILIPPINES USING MACHINE LEARNING APPROACH
Keywords:
climate change, ENSO, ARIMA, SARIMA, neural network autoregression.DOI:
https://doi.org/10.17654/0972361722006Abstract
In this study, the rainy trend in Philippines started to increase in 2008 and seems to plateau until it declines in 2014. This study conforms to the global phenomenon brought about by El Niño. This paper also acknowledges research finding that in 2015-2016, dry El Niño conditions affected about a third of the country. This one-third is mostly situated in the northern part of the Philippines.
A model is good if its performance (e.g. RMSE) using “training set” is very similar to the performance using the “test set”. NNAR model has an RMSE of 76.09 and 76.33 for the training set and test set, respectively, outperforming ARIMA and SARIMA.
A much better NNAR model was found. However, this study found that the model is an overfit. Recommendations for dealing with the issue of overfitting are mentioned including k-fold cross-validation and having a larger data set.
Received: July 11, 2021
Revised: August 12, 2021
Accepted: November 12, 2021
References
Chuang Zhao, Bing Liu, Shilong Piao, Xuhui Wang, David B. Lobell, Yao Huang, Mengtian Huang, Yitong Yao, Simona Bassu, Philippe Ciais, Jean-Louis Durand, Joshua Elliott, Frank Ewert, Ivan A. Janssens, Tao Li, Erda Lin, Qiang Liu, Pierre Martre, Christoph Müller, Shushi Peng, Josep Peñuelas, Alex C. Ruane, Daniel Wallach, Tao Wang, Donghai Wu, Zhuo Liu, Yan Zhu, Zaichun Zhu and Senthold Asseng, Temperature increase reduces global yields of major crops in four independent estimates, Proc. Natl. Acad. Sci. 114(35) (2017), 9326 9331. doi: 10.1073/PNAS.1701762114
G. Bagtasa, Contribution of tropical cyclones to rainfall in the Philippines, J. Clim. 30(10) (2017), 3621-3633, doi: 10.1175/JCLI-D-16-0150.1
W. Luzano, Multivariate extension of the singular spectrum analysis a new tool in understanding the intraseasonal-oscillation (ISO) of Philippines summer monsoon and its association with extreme rainfall events, Glob. NEST Journal Global NEST Int. J. 2020, doi: 10.30955/gnj.003202
Lemuel Clark P. Velasco, Ruth P. Serquiña, Mohammad Shahin A. Abdul Zamad, Bryan F. Juanico and Junneil C. Lomocso, Performance analysis of multilayer perceptron neural network models in week-ahead rainfall forecasting, (IJACSA) International Journal of Advanced Computer Science and Applications 10(3) (2019), 578. [Online]. Available: www.ijacsa.thesai.org
D. Dayal, S. Swain, A. K. Gautam, S. S. Palmate, A. Pandey and S. K. Mishra, Development of ARIMA model for monthly rainfall forecasting over an Indian river basin, World Environmental and Water Resources Congress 2019: Watershed Management, Irrigation and Drainage, and Water Resources Planning and Management - Selected Papers from the World Environmental and Water Resources Congress 2019, 2019, pp. 264-271, doi: 10.1061/9780784482339.027
M. P. Darji, V. K. Dabhi and H. B. Prajapati, Rainfall forecasting using neural network: A survey, Conference Proceeding - 2015 International Conference on Advances in Computer Engineering and Applications, ICACEA 2015, Jul. 2015, pp. 706-713, doi: 10.1109/ICACEA.2015.7164782
O. A. Fashae, A. O. Olusola, I. Ndubuisi and C. G. Udomboso, Comparing ANN and ARIMA model in predicting the discharge of River Opeki from 2010 to 2020, River Res. Appl. 35(2) (2019), 169-177. doi: 10.1002/rra.3391
S. Naidu K. CH. V, SARIMA modeling and forecasting of seasonal rainfall patterns in India, Int. J. Math. Trends Technol. 38(1) (2016), 15-22.
doi: 10.14445/22315373/ijmtt-v38p504
11.3 Neural network models, Forecasting: Principles and Practice (2nd ed), https://otexts.com/fpp2/nnetar.html (accessed Jul. 10, 2021).
Rainfall Time Series Analysis and Forecasting, by Dery Kurniawan, Towards Data Science, https://towardsdatascience.com/rainfall-time-series-analysis-and-forecasting-87a29316494e (accessed Feb. 01, 2021).
L. A. Acosta, E. A. Eugenio, P. B. M. Macandog, D. B. Magcale-Macandog, E. K. H. Lin, E. R. Abucay, A. L. Cura and M. G. Primavera, Loss and damage from typhoon-induced floods and landslides in the Philippines: Community perceptions on climate impacts and adaptation options, Int. J. Glob. Warm. 9(1) (2016), 33-65. doi: 10.1504/IJGW.2016.074307.
K. Patrick and R. Mendoza, Locating the ideological in the functional: a multimodal critical analysis of online news reports on Typhoon Lando, Asia-Pacific Soc. Sci. Rev. 19(1) (2019), 202-210.
M. A. Abid, M. Almazroui, F. Kucharski, E. O’Brien and A. E. Yousef, ENSO relationship to summer rainfall variability and its potential predictability over Arabian Peninsula region, NPJ Clim. Atmos. Sci. 1(1) (2018), 1-7.
doi: 10.1038/s41612-017-0003-7.
Climate Prediction Center - ONI.
https://origin.cpc.ncep.noaa.gov/products/analysis_monitoring/ensostuff/ONI_v5.php (accessed: July 11, 2021).
Striking a Balance: Managing El Niño and La Niña in Philippines, Agriculture - Philippines, ReliefWeb, https://reliefweb.int/report/philippines/striking-balance-managing-el-ni-o-and-la-ni-philippines-agriculture (accessed: July 11, 2021).
J. Lu and S. Meyer, Forecasting flu activity in the United States: benchmarking an endemic-epidemic beta model, Int. J. Environ. Res. Public Heal. 17(4) (2020), 1381. doi: 10.3390/IJERPH17041381.
Prediction intervals for NNETAR models, Rob J. Hyndman.
https://robjhyndman.com/hyndsight/nnetar-prediction-intervals/(accessed: May 2, 2021).
Regression - What are good RMSE values? Cross Validated,
https://stats.stackexchange.com/questions/56302/what-are-good-rmse-values accessed: July 10, 2021.
Climate Prediction Center - ONI.
Striking a Balance: Managing El Niño and La Niña in Philippines’ Agriculture - Philippines | ReliefWeb.
5 Tips to Reduce Under and Over Fitting of Forecast Models, Demand-Planning.com. https://demand-planning.com/2019/09/02/5-tips-to-reduce-over-and-underfitting-of-forecast-models/ (accessed: July 10, 2021).
Downloads
Published
Issue
Section
License
Copyright (c) 2021 Pushpa Publishing House, Prayagraj, India
This work is licensed under a Creative Commons Attribution 4.0 International License.
____________________________
Attribution: Credit Pushpa Publishing House as the original publisher, including title and author(s) if applicable.
No Derivatives: Modifying or creating derivative works not allowed without written permission.
Contact Pushpa Publishing House for more info or permissions.
Journal Impact Factor: 
