FORECASTING MISSING DATA USING DIFFERENT METHODS FOR ROAD MAINTAINERS

Jānis Pekša


Last modified: 04.04.2019

Abstract

Observations collected from meteorological stations that are available to road maintainers and used for experimental purposes in this paper. Unfortunately, these observations are insufficient to make good forecasting that is needed for road maintainers. Those meteorological stations are located next to the road surface in the territory of the Republic of Latvia. The road maintainers can make forecasting using this data what is needed for the winter months. It is up to the road maintainers in winter months to process decision-making on road surface smudging with anti-slip chemical materials. The missing data in each meteorological station exists from time to time. The paper represents the possibility of using several approaches to fill out these missing data. This process is needed to be more accurate in predicting specific parameters aggregated from meteorological stations. These approaches are compared between the three closest meteorological stations available in the Republic of Latvia. The relevant data are for the winter months of 2017-2018. To conclude which is more accurate with VAS "Latvijas valsts celi" data set.

Keywords


missing data; time-series; forecasting

References


[1]   Yozgatligil, C., Aslan, S., Iyigun, C. and Batmaz, I., 2013. Comparison of missing value imputation methods in time series: the case of Turkish meteorological data. Theoretical and applied climatology, 112(1-2), 143-167, https://doi.org/10.1007/s00704-012-0723-x

[2]   Jeffrey, S.J., Carter, J.O., Moodie, K.B. and Beswick, A.R., 2001. Using spatial interpolation to construct a comprehensive archive of Australian climate data. Environmental Modelling & Software, 16(4), 309-330.

[3]   Spadavecchia, L. and Williams, M., 2009. Can spatio-temporal geostatistical methods improve high resolution regionalization of meteorological variables?. Agricultural and Forest Meteorology, 149(6-7), 1105-1117.

[4]   Dibike, Y.B. and Coulibaly, P., 2005. Hydrologic impact of climate change in the Saguenay watershed: comparison of downscaling methods and hydrologic models. Journal of hydrology, 307(1-4), 145-163, https://doi.org/10.1016/j.jhydrol.2004.10.012

[5]   Taylor, J.W., De Menezes, L.M. and McSharry, P.E., 2006. A comparison of univariate methods for forecasting electricity demand up to a day ahead. International Journal of Forecasting, 22(1), 1-16, https://doi.org/10.1016/j.ijforecast.2005.06.006

[6]   Subramanya, K., 2013. Engineering Hydrology, 4e. Tata McGraw-Hill Education.

[7]   Dudani, S.A., 1976. The distance-weighted k-nearest-neighbor rule. IEEE Transactions on Systems, Man, and Cybernetics, (4), 325-327.

[8]   Haykin, S.S., 2009. Neural networks and learning machines/Simon Haykin. New York: Prentice Hall.

[9]   Giannone, D., Reichlin, L. and Small, D., 2008. Nowcasting: The real-time informational content of macroeconomic data. Journal of Monetary Economics, 55(4), 665-676.

[10] Bagheri, M., Nurmanova, V., Abedinia, O., Naderi, M.S., Naderi, M.S. and Ghadimi, N., 2018, June. A Novel Wind Power Forecasting Based Feature Selection and Hybrid Forecast Engine Bundled with Honey Bee Mating Optimization. In 2018 IEEE International Conference on Environment and Electrical Engineering (EEEIC/I&CPS Europe), 1-6.

[11] Sharp, J.J. and Sawden, P.G., 2013. BASIC hydrology. Elsevier.

[12] Cuypers, W., Van Gestel, N., Voet, A., Kruth, J.P., Mingneau, J. and Bleys, P., 2009. Optical measurement techniques for mobile and large-scale dimensional metrology. Optics and Lasers in Engineering, 47(3-4), 292-300, https://doi.org/10.1016/j.optlaseng.2008.03.013

[13] Fabbri, R., Costa, L.D.F., Torelli, J.C. and Bruno, O.M., 2008. 2D Euclidean distance transform algorithms: A comparative survey. ACM Computing Surveys (CSUR), 40(1), 2.

[14] Acuna, E. and Rodriguez, C., 2004. The treatment of missing values and its effect on classifier accuracy. In Classification, clustering, and data mining applications. Springer, Berlin, Heidelberg, 639-647, https://doi.org/10.1007/978-3-642-17103-1_60

[15] Barrientos, R.J., Gómez, J.I., Tenllado, C., Matias, M.P. and Marin, M., 2011, August. kNN query processing in metric spaces using GPUs. In European Conference on Parallel Processing. Springer, Berlin, Heidelberg, 380-392, https://doi.org/10.1007/978-3-642-23400-2_35

[16] Gylfason, T. and Hochreiter, E., 2011. Growing Together: Croatia and Latvia. Comparative Economic Studies, 53(2), 165-197.

[17] Zhang, Z., 2018. Artificial neural network. In Multivariate Time Series Analysis in Climate and Environmental Research, 1-35, https://doi.org/10.1007/978-3-319-67340-0_1

[18] Murata, N., Yoshizawa, S. and Amari, S.I., 1994. Network information criterion-determining the number of hidden units for an artificial neural network model. IEEE Transactions on Neural Networks, 5(6), 865-872, https://doi.org/10.1109/72.329683

[19] Park, T. and Lee, S., 2004. A Bayesian approach for estimating link travel time on urban arterial road network. In International Conference on Computational Science and Its Applications, 1017-1025, https://doi.org/10.1007/978-3-540-24707-4_114

[20] Chaudhari, P. and Soatto, S., 2018. Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks. In 2018 Information Theory and Applications Workshop (ITA), 1-10