Comparison of missing value imputation methods in time series: the case of Turkish meteorological data

Date

2013-04-01

Author

Yozgatlıgil, Ceylan
İyigün, Cem
Batmaz, İnci

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

260
views

0
downloads

This study aims to compare several imputation methods to complete the missing values of spatio-temporal meteorological time series. To this end, six imputation methods are assessed with respect to various criteria including accuracy, robustness, precision, and efficiency for artificially created missing data in monthly total precipitation and mean temperature series obtained from the Turkish State Meteorological Service. Of these methods, simple arithmetic average, normal ratio (NR), and NR weighted with correlations comprise the simple ones, whereas multilayer perceptron type neural network and multiple imputation strategy adopted by Monte Carlo Markov Chain based on expectation-maximization (EM-MCMC) are computationally intensive ones. In addition, we propose a modification on the EM-MCMC method. Besides using a conventional accuracy measure based on squared errors, we also suggest the correlation dimension (CD) technique of nonlinear dynamic time series analysis which takes spatio-temporal dependencies into account for evaluating imputation performances. Depending on the detailed graphical and quantitative analysis, it can be said that although computational methods, particularly EM-MCMC method, are computationally inefficient, they seem favorable for imputation of meteorological time series with respect to different missingness periods considering both measures and both series studied. To conclude, using the EM-MCMC algorithm for imputing missing values before conducting any statistical analyses of meteorological data will definitely decrease the amount of uncertainty and give more robust results. Moreover, the CD measure can be suggested for the performance evaluation of missing data imputation particularly with computational methods since it gives more precise results in meteorological time series.

Subject Keywords

North-Atlantic Oscillation, Temperature Variability, Monthly Precipitation, Minimum Temperatures, Rainfall Variations, Strange Attractors, Forest Climatology, Turkey, Maximum, Trends

URI

https://hdl.handle.net/11511/42652

Journal

THEORETICAL AND APPLIED CLIMATOLOGY

DOI

https://doi.org/10.1007/s00704-012-0723-x

Collections

Department of Statistics, Article

Suggestions

OpenMETU
Core

Comparison of Kalman filter and Bayesian-MAP approaches in the spatio-temporal solution of the inverse electrocardiography Ters elektrokardiyografinin zaman-uzamsal çözümünde Kalman filtre ve Bayes-MAP yöntemlerinin karşilaştirilmasi Aydin, Ümit; Serinağaoğlu Doğrusöz, Yeşim (2010-07-15) In this study some of the spatial and spatio-temporal methods for the solution of the inverse problem of electrocardiography (ECG) are compared with each other. Comparisons are also made for the cases with geometric errors, where the location of the heart is shifted for 10mm and the size of the heart is reduced by 5%. The compared methods are the Kalman filter and Bayesian maximum a posteriori estimation (MAP). Two different Bayesian-MAP algorithms are used. While one uses only spatial information the other...
Accuracy analyses of numeric weather prediction-based stratiform and convective precipitation shortterm forecasts over Turkey Aydın, Beril; Yücel, İsmail; Yılmaz, Mustafa Tuğrul; Department of Civil Engineering (2023-1) This study was carried out to determine whether convective and stratiform (large-scale) precipitation datasets obtained from 5 model forecast-based products would be an adequate alternative for regions where station-based observation networks are sparse. Verification of precipitation types (convective or stratified) from numerical weather forecast (NWP) models (ALARO, CFS, ECMWF HRES, GFS, WRF) is done using station-based observations. Statistical assessments between these precipitation types in different t...
Evaluation of a satellite-based global flood monitoring system Yılmaz, Koray Kamil; Tian, Yudong; Hong, Yang; Pierce, Harold F. (2010-01-01) This study provides an initial evaluation of a global flood monitoring system (GFMS) using satellite-based precipitation and readily available geospatial datasets. The GFMS developed by our group uses a relatively simple hydrologic model, based on the run-off curve number method, to transform precipitation into run-off. A grid-to-grid routing scheme moves run-off downstream. Precipitation estimates are from the TRMM Multi-satellite Precipitation Analysis (TMPA). We first evaluated the TMPA algorithm using a...
Comparison of method of lines and finite difference solutions of 2-D Navier-Stokes equations for transient laminar pipe flow Selçuk, Nevin; Tanrikulu, S (2002-03-10) Performances of method of lines (MOL) and finite difference method (FDM) were tested from the viewpoints of solution accuracy and central processing unit (CPU) time by applying them to the solution of time-dependent 2-D Navier-Stokes equations for transient laminar flow without/with sudden expansion and comparing their results with steady-state numerical predictions and measurements previously reported in the literature. Predictions of both methods were obtained on the same computer by using the same order ...
Comparison of Temperature Profile and Heat Transfer Predictions With Statistically Modeled Data From a Cooled 1 1 2 Stage High Pressure Transonic Turbine Kahveci, Harika Senem (2013-06-03) This paper compares predictions from a 3-D Reynolds-Averaged Navier-Stokes code and a statistical representation of measurements from a cooled 1-1/2 stage high-pressure transonic turbine to quantify predictive process sensitivity. A multivariable regression technique was applied to both the inlet temperature measurements obtained at the inlet rake, and the wall temperature and heat transfer measurements obtained via heat-flux gauges on the blade airfoil surfaces. By using the statistically-modeled temperatu...

Citation Formats

C. Yozgatlıgil, C. İyigün, and İ. Batmaz, “Comparison of missing value imputation methods in time series: the case of Turkish meteorological data,” THEORETICAL AND APPLIED CLIMATOLOGY, pp. 143–167, 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/42652.