The Support Vector Regression with L1 Norm: Application to Weather Radar Data in Adjusting Rainfall Errors

In hydrological research, accurate rainfall data is the primary subject for the minimization of potential loss of life and property that is mainly caused by floods. However, there is a difficulty in getting precise rainfall data for poorly gauged locations, especially in mountainous areas. Weather radar instruments can be the remedy accompanied by some errors. And, these errors should be removed before the implementation of this product. This paper presents the results of the research on radar rainfall estimate errors with support vector regression (SVR) method using the observed rain gauge data. The paper depicts the methodological base of the algorithm that covers additive and multiplicative corrections and the results of practical implementations considering the locations of gauge measurements. The preliminary results show that the SVR has a location-oriented performance. The multiplicative and additive correction factors show decreasing and polynomial trends respectively, as the distance from the radar location increase. Another particular outcome is that the SVR shows better results for the stations located in the mid-range (mainly for 40-60 km) contrary to the nearest ones. Since the systematic error in the radar data is nonlinear, the SVR method would show a promising result with a combination of other optimization techniques.

Keywords:

Support Vector Regression, weather radar data flood, error minimization,

PDF

___

WMO, WMO atlas of Mortality and Economic Losses from Weather, Climate and Water Extremes (1970–2019). 2021. [Online]. Available: https://library.wmo.int/doc_num.php?explnum_id=10989
X. Sun, R. G. Mein, T. D. Keenan, and J. F. Elliott, “Flood estimation using radar and raingauge data,” Journal of Hydrology, vol. 239, no. 1, pp. 4–18, Dec. 2000, doi: 10.1016/S0022-1694(00)00350-4.
C. Chwala and H. Kunstmann, “Commercial microwave link networks for rainfall observation: Assessment of the current status and future challenges,” WIREs Water, vol. 6, no. 2, p. e1337, 2019, doi: 10.1002/wat2.1337.
L. J. Battan, “Vertical Air Motions and the Z-R Relation,” J. Appl. Meteor., vol. 15, no. 10, pp. 1120–1121, Oct. 1976, doi: 10.1175/1520-0450(1976)015<1120:VAMATR>2.0.CO;2.
I. Emmanuel, H. Andrieu, and P. Tabary, “Evaluation of the new French operational weather radar product for the field of urban hydrology,” Atmospheric Research, vol. 103, pp. 20–32, Jan. 2012, doi: 10.1016/j.atmosres.2011.06.018.
I. V. Sideris, M. Gabella, R. Erdin, and U. Germann, “Real-time radar–rain-gauge merging using spatio-temporal co-kriging with external drift in the alpine terrain of Switzerland,” Quarterly Journal of the Royal Meteorological Society, vol. 140, no. 680, pp. 1097–1111, 2014, doi: 10.1002/qj.2188.
G. Villarini and W. F. Krajewski, “Review of the Different Sources of Uncertainty in Single Polarization Radar-Based Estimates of Rainfall,” Surv Geophys, vol. 31, no. 1, pp. 107–129, Jan. 2010, doi: 10.1007/s10712-009-9079-x.
A. Ozkaya and A. E. Yılmaz, “Muğla Radarı Yağış Tahmin Hatalarının L2 ve L∞ Normlarıyla Analizi,” İstanbul, Dec. 2021. [Online]. Available: https://meteouzal.itu.edu.tr/#/en/home
V. Vapnik, The Nature of Statistical Learning Theory. Springer Science & Business Media, 1999.
P.-F. Pai and W.-C. Hong, “A recurrent support vector regression model in rainfall forecasting,” Hydrological Processes, vol. 21, no. 6, pp. 819–827, 2007, doi: 10.1002/hyp.6323.
W.-C. Hong and P.-F. Pai, “Potential assessment of the support vector regression technique in rainfall forecasting,” Water Resour Manage, vol. 21, no. 2, pp. 495–513, Feb. 2007, doi: 10.1007/s11269-006-9026-2.
Z. Zeng, W. W. Hsieh, A. Shabbar, and W. R. Burrows, “Seasonal prediction of winter extreme precipitation over Canada by support vector regression,” Hydrology and Earth System Sciences, vol. 15, no. 1, pp. 65–74, Jan. 2011, doi: 10.5194/hess-15-65-2011.
A. Danandeh Mehr, V. Nourani, V. Karimi Khosrowshahi, and M. A. Ghorbani, “A hybrid support vector regression–firefly model for monthly rainfall forecasting,” Int. J. Environ. Sci. Technol., vol. 16, no. 1, pp. 335–346, Jan. 2019, doi: 10.1007/s13762-018-1674-2.
Y. Xiang, L. Gou, L. He, S. Xia, and W. Wang, “A SVR–ANN combined model based on ensemble EMD for rainfall prediction,” Applied Soft Computing, vol. 73, pp. 874–883, Dec. 2018, doi: 10.1016/j.asoc.2018.09.018.
A. G. Yilmaz, “The effects of climate change on historical and future extreme rainfall in Antalya, Turkey,” Hydrological Sciences Journal, vol. 60, no. 12, pp. 2148–2162, Dec. 2015, doi: 10.1080/02626667.2014.945455.