Rainfall, Wind Speed, and Temperature Forecast Using Triple Exponential Smoothing and Gradient Descent
Abstract
The global community strives to minimize the impact of disasters through various actions, for example, mapping flood-prone areas. Flood-prone areas need to be identified correctly, predicted, understood, and socialized to minimize risks when a disaster occurs regarding death, property damage, and socio-economic losses. This type of data-based prediction has been developed and implemented widely and can be applied to predictions related to hydrology. Data mining approaches (estimation, classification, clustering, and time-series forecast) have significantly influenced research related to flood prediction in recent years. The time-series flood forecast has been widely used in previous research using various statistical and data-mining methods. Predicting floods that occur in coastal areas is less discussed than river floods. One method that is often used is exponential smoothing. Determining damping factor values (alpha, beta, and gamma) in the triple exponential smoothing method, in general, is to use all values from 0 to 1 to find the most optimal damping factor, this takes quite a long time and results generally appear with less accuracy. So, a combination of the triple exponential smoothing algorithm is proposed to perform tTimeseries forecast, and the gradient descent algorithm is used as an optimization algorithm to obtain optimal weight values for alpha, beta, and gamma in triple exponential smoothing.
Keywords: triple exponential smoothing, gradient descent, flood forecast, flood prediction, time-series forecast
References
[1] Marijnissen RJC, Kok M, Kroeze C, van Loon-Steensma JM. Flood risk reduction by parallel flood defences – Case-study of a coastal multifunctional flood protection zone. Coast Eng 2021;167. https://doi.org/10.1016/j.coastaleng.2021.103903.
[2] Koks EE, Le Bars D, Essenfelder AH, Nirandjan S, Sayers P. The impacts of coastal flooding and sea level rise on critical infrastructure: a novel storyline approach. Sustain Resilient Infrastruct 2023;8:237–61. https://doi.org/10.1080/23789689.2022.2142741.
[3] Panezai S, Moniruzzaman, Saqib SE, Rahman MS, Ferdous Z, Asghar S, et al. Rural households’ food security and its determinants in coastal regions of Bangladesh. Nat Resour Forum 2022;46:200–20. https://doi.org/10.1111/1477-8947.12250.
[4] Saravanan S, Abijith D. Flood susceptibility mapping of Northeast coastal districts of Tamil Nadu India using Multi-source Geospatialdata and Machine Learning techniques. Geocarto Int 2022;37:15252–81. https://doi.org/10.1080/10106049.2022.2096702.
[5] Shan X, Wang J, Wen J, Hu H, Wang L, Yin J, et al. Using Multidisciplinary Analysis to Develop Adaptation Options against Extreme Coastal Floods. Int J Disaster Risk Sci 2022;13:577–91. https://doi.org/10.1007/s13753-022-00421-6.
[6] Latif S, Simonovic SP. Trivariate Probabilistic Assessments of the Compound Flooding Events Using the 3-D Fully Nested Archimedean (FNA) Copula in the Semiparametric Distribution Setting. Water Resour Manag 2023;37:1641–93. https://doi.org/10.1007/s11269-023-03448-6.
[7] Khouakhi A, Villarini G. On the relationship between atmospheric rivers and high sea water levels along the U.S. West Coast. Geophys Res Lett 2016;43:8815–22. https://doi.org/10.1002/2016GL070086.
[8] Lavers DA, Villarini G. The contribution of atmospheric rivers to precipitation in Europe and the United States. J Hydrol 2015;522:382–90. https://doi.org/10.1016/j.jhydrol.2014.12.010.
[9] Kamath RS, Kamat RK. Time-series analysis and forecasting of rainfall at Idukki district, Kerala: Machine learning approach. Disaster Adv 2018;11:27–33.
[10] Hayder IM, Al-Amiedy TA, Ghaban W, Saeed F, Nasser M, Al-Ali GA, et al. An Intelligent Early Flood Forecasting and Prediction Leveraging Machine and Deep Learning Algorithms with Advanced Alert System. Processes 2023;11. https://doi.org/10.3390/pr11020481.
[11] de Faria EL, Albuquerque MP, Gonzalez JL, Cavalcante JTP, Albuquerque MP. Predicting the Brazilian stock market through neural networks and adaptive exponential smoothing methods. Expert Syst Appl 2009;36:12506–9. https://doi.org/10.1016/j.eswa.2009.04.032.
[12] Ostertagová E, Ostertag O. Forecasting using simple exponential smoothing method. Acta Electrotech Inform 2013;12:10198. https://doi.org/10.2478/v10198-012-0034-2.
[13] Mi J, Huang G. Dynamic Prediction of Performance Degradation Characteristics of Direct-Drive Electro-Hydraulic Servo Valves. Appl Sci 2023;13:7231. https://doi.org/10.3390/app13127231.
[14] Susila IMD, Atmojo YP, Srinadi NLP, Suradarma IB, Yuningsih L, Rini ES. Performance Analysis of the Triple Exponential Smoothing Method During the Covid19 Pandemic on Tourist Visit Data. 2022 1st Int. Conf. Inf. Syst. Inf. Technol., IEEE; 2022, p. 358–63. https://doi.org/10.1109/ICISIT54091.2022.9872863.
[15] Djakaria I. Djalaluddin Gorontalo Airport Passenger Data Forecasting with Holt’s- Winters’ Exponential Smoothing Multiplicative Event-Based Method. J Phys Conf Ser 2019;1320:012051. https://doi.org/10.1088/1742-6596/1320/1/012051.
[16] Halim MH, Wook M, Hasbullah NANAA, Razali NNAMAM, Hamid HECECHHECEC. Comparative Assessment of Data Mining Techniques for Flash Flood Prediction. Int J Adv Soft Comput Its Appl 2022;14:125–45. https://doi.org/10.15849/IJASCA.220328.09.
[17] Ayyad M, Hajj MR, Marsooli R. Machine learning-based assessment of storm surge in the New York metropolitan area. Sci Rep 2022;12. https://doi.org/10.1038/s41598- 022-23627-6.
[18] Xiang Z, Yan J, Demir I. A Rainfall-Runoff Model With LSTM-Based Sequence-to-Sequence Learning. Water Resour Res 2020;56:1–17. https://doi.org/10.1029/2019WR025326.