ASSESSMENT OF THE ACCURACY OF METEOROLOGICAL DATA OBTAINED FROM A VIRTUAL WEATHER STATION FOR THE PURPOSE OF ESTIMATING ETO FOR THE CONDITIONS OF THE SOUTH UKRAINE
Abstract
The article presents an assessment of the accuracy of meteorological data obtained from the Visual Crossing Weather Data (VWS VCWD) virtual meteorological station and the calculated reference evapotranspiration (ETo) based on these data for the conditions of southern Ukraine. It has been established that the data on air temperature and relative humidity are obtained with high accuracy, with MAPE and RMSE errors of 4,5% and 0,94°C and 9,1% and 7,53%, respectively. Good accuracy is characteristic of dew point temperature and solar radiation, with MAPE and RMSE errors of 20,9% and 1,44 °C and 17,4% and 3,41 MJ/m²·day, respectively. Dew point temperature data can also be obtained with satisfactory accuracy depending on the observation period. The MAPE and RMSE errors for water vapor pressure deficit are 46,2% and 0,21 kPa, respectively, which corresponds to satisfactory accuracy. Depending on the observation period, water vapor pressure deficit data can also be obtained with unsatisfactory accuracy. Wind speed data at a height of 2 m, obtained with unsatisfactory accuracy, have MAPE and RMSE errors of 104,3% and 1,20 m/s, respectively. To improve the accuracy of the meteorological data obtained, correction factors were calculated, and when applied, the accuracy of all meteorological data obtained is improved. The possibility of calculating ET using data from the Visual Crossing Weather Data virtual meteorological station for the period April-September with good accuracy has been confirmed. The MAPE error was 13,7%, and the RMSE was 0.62 mm. To improve the accuracy of ET calculations in southern Ukraine, a correction factor of 0.95 must be used. Taking this into account, the accuracy of ET calculations for the period May-August increases to 89%, and the RMSE is 0,63 mm. The use of refined meteorological data reduces the accuracy of ET calculations by 4,8% and increases the RMSE by 0,15 mm. Based on the results of the research, a web application will be developed to calculate ET and ETc using the FAO56-RM methodology with data from VWS Visual Crossing Weather Data.
References
2. Franco, B.M., Hernández-Callejo, L. & Navas-Gracia, L.M. (2020). Virtual weather stations for meteorological data estimations. Neural Comput & Applic, 32, 12801–12812.
3. Daly, C., Gibson, W.P., Taylor, G.H., Johnson, G.L., & Pasteris, P. (2002). A Knowledge-Based Approach to the Statistical Mapping of Climate. Climate Research, 22, 99-113. DOI: http://dx.doi.org/10.3354/cr022099
4. Visual Crossing Weather Data. Historical Weather Data & Weather Forecast Data. (2025). Retrieved from: https://www.visualcrossing.com
5. Urribarri, D.K. & Larrea, M.L. (2022). A visualization technique to assist in the comparison of large meteorological datasets, Computers & Graphics, 104, 1-10. DOI: https://doi.org/10.1016/j.cag.2022.02.011.
6. Mason, E.G., Salekin, S. & Morgenroth, J.A. (2017). Comparison between meteorological data from the New Zealand National Institute of Water and Atmospheric Research (NIWA) and data from independent meteorological stations. N.Z. j. of For. Sci. 47, 7.
7. Benyahya L., Caissie, D., El-Jabi, N., & Satish, M.G. (2010). Comparison of microclimate vs. remote meteorological data and results applied to a water temperature model (Miramichi River, Canada). Journal of Hydrology, 380, 247-259.
8. Allen, R.G., Dhungel, R., Dhungana, B., Huntington, Ju., Kilic A., & Morton, Ch. (2021). Conditioning point and gridded weather data under aridity conditions for calculation of reference evapotranspiration. Agricultural Water Management, 245, 106531.
9. Zhou, N. S., Wu, L. F., Yang, Q. L., Dong, J., Yang, L., & Li, Y. (2024). A high-quality gap-filled daily ETo dataset for China during 1951–2021 from synoptic stations using machine learning models, Earth Syst. Sci. Data Discuss. [preprint], https://doi.org/10.5194/essd-2024-229.
10. Allen, R. G. (1996). Assessing Integrity of Weather Data for Reference Evapotranspiration Estimation. Journal of Irrigation and Drainage Engineering, 122(2), 97–106. DOI: https://doi.org/10.1061/(asce)0733-9437(1996)122:2(97)
11. Dunkerly, C., Huntington J.L., McEvoy D., Morway A., & Allen R.G. (2024). Agweather-qaqc: An Interactive Python Package for Quality Assurance and Quality Control of Daily Agricultural Weather Data and Calculation of Reference Evapotranspiration. Journal of Open Source Software, 9(97), 6368. DOI: https://doi.org/10.21105/joss.06368.
12. Isaak, D.J, Horan, D.L., & Wollrab, Sh.P. (2024). Air temperature data source affects inference from statistical stream temperature models in mountainous terrain. Journal of Hydrology X, 22, 100172. DOI: https://doi.org/10.1016/j.hydroa.2024.100172
13. Hassani, A., Santos, G.S., Schneider, P. & et al. (2024). Interpolation, Satellite-Based Machine Learning, or Meteorological Simulation? A Comparison Analysis for Spatio-temporal Mapping of Mesoscale Urban Air Temperature. Environ Model Assess, 29, 291–306.
14. da Nóbrega, B.S., & Lima, W.G. (2023). Comparative study among solar radiation data estimated by satellite images and measured by meteorological stations in the Paraíba state. Cuadernos de Educación y Desarrollo, 15 (1), 620–637. DOI: https://doi.org/10.55905/cuadv15n1-033
15. Mitrushi, D., Berberi, P., Muda, V., Buzra, U., Berdufi, I., & Topçiu, D. (2016). A comparative study of satellite estimation for solar insolation in Albania with ground measurements. AIP Conference Proceedings, 1722(1):280006.
16. Zhuravlov, O.V., Shatkovskyi, A.P., Cherevychnyi, Y.O., Scherbatiuk, M.V., & Liubitskyi V.V. (2024). Assessment of the accuracy of meteorological data obtained from virtual and automatic weather stations for the conditions of Ukrainian Polissya. Land reclamation and water management, 2 (120), 87-98. DOI: https://doi.org/10.31073/mivg202402-396
17. Volk, J.M., Huntington, J.L., Melton, F.S., & Allen R (2024). Assessing the accuracy of OpenET satellite-based evapotranspiration data to support water resource and land management applications. Nature Water. DOI: https://doi.org/10.1038/s44221-023-00181-7
18. Luo, Y., Traore, S., & Lyu, X. (2015). Medium Range Daily Reference Evapotranspiration Forecasting by Using ANN and Public Weather Forecasts. Water Resour Manage, 29, 3863–3876. DOI: https://doi.org/10.1007/s11269-015-1033-8
19. Zhuravlov, O.V., Shatkovskyi, A.P., Scherbatiuk, M.V., Liubitskyi V.V., & Karuna V.V. (2025). Estimation of the accuracy of the calculation of reference and actual evapotranspiration based on virtual weather station data for Polissya region of Ukraine. Land reclamation and water management, 1(121), 79-88 DOI: https://doi.org/10.31073/mivg202501-411
20. FieldClimate - Metos® by Pessl instrument. (2025). Retrieved from: https://ng.fieldclimate.com
21. Allen, R.G., Pereira, L.S., Raes, D., & Smith, M. (1998). Crop evapotranspiration. Guidelines for computing crop water requirements. FAO Irrig. Drain. Paper No. 56, Rome: FAO. Retrieved from: http://www.fao.org/3/x0490e/x0490e00.htm
22. Roberts, A. (2023). Mean Absolute Percentage Error (MAPE): What You Need To Know. Retrieved from: https://arize.com/blog-course/mean-absolute-percentage-error-mape-what-you-need-to-know/
23. Lewis, C.D. (1982). Industrial and business forecasting methods. London: Butterworths. P.144
24. Olumide, S. (2023). Root Mean Square Error (RMSE) In AI: What You Need To Know. Retrieved from: https://arize.com/blog-course/root-mean-square-error-rmse-what-you-need-to-know/
25. Watts, V. (2022). Introduction to Statistics. An Excel-Based Approach. London, Ontario: Fanshawe College Pressbooks. P. 916.
Retrieved from: https://ecampusontario.pressbooks.pub/introstats/
26. Meteopost. Archive of meteorological data. View the actual weather for a specific date. (2025). Retrieved from: https://meteopost.com/weather/archive)
