Estimation of Atmospheric Precipitable Water in Thailand using an Artificial Neural Network


Sumaman Buntoung Jindarat Pariyothon Patsakorn Detkhon


        In this work, an Artificial Neural Network (ANN) was proposed to estimate monthly average precipitable water (PW) using ambient air relative humidity, ambient air temperature, saturated water vapour pressure and the order of the month as input data. The PW data measured from ground-based sunphotometer were used as output data. The multilayer perceptron ANN using the back propagation training algorithm with two hidden layers was employed for deriving the PW. A five-year period (2009-2013) of the data collected from four meteorological stations, namely Chiang Mai (18.98°N, 98.98°E), Ubon Ratchathani (15.25°N, 104.87°E), Bangkok (13.67°N, 100.60°E) and Songkhla (7.20°N, 100.60°E) were used to train the ANN. An independent two-year period (2014-2015) of the data from the same stations were used to evaluate the performance of the trained ANN model. The result shows that PW at the four stations derived from the ANN agrees well with those obtained from the measurement, with the discrepancy in terms of root mean square error (RMSE) and mean bias error (MBE) of 7.5% and -0.1%, respectively.

Keywords: precipitable water, artificial neural network, back propagation algorithm  


Abbasy, S., Abbasi, M., Asgari, J., & Ghods, A. (2017). Precipitable water vapour estimation using the permanent single GPS station in Zanjan, Iran. Meteorological Applications, 24, 415-422.
Akatsuka, S., Oyoshi, K., & Takeuchi, W. (2010). Mapping of precipitable water using MTSAT data. In Proceedings of 31st Asian Conference on Remote Sensing (ACRS), Vietnam: Hanoi.
Basili, P., Bonafoni, S., Mattioli, V., Pelliccia, F., Serpolla, A, Bocci, E., & Ciotti, P. (2008). Development of a neural network for precipitable water vapor retrieval over ocean and land. In 2008 Microwave Radiometry and Remote Sensing of the Environment, 11-14 March 2008 (pp. 1-4). Firenze, Italy: Institute of Electrical and Electronics Engineers.
Bruegge, C. J., Conel, J. E., Green, R. O., Margolis, J. S., Holm, R. G., & Toon, G. (1992). Water vapor column abundance retrievals during FIFE. Journal of Geophysical Research: Atmospheres, 97(D17), 18759-18768.
Frank, E., Hall, M. A., & Witten, I. H. (2016). The WEKA Workbench. USA: Morgan Kaufmann.
Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences, Atmospheric Environment, 32(14–15), 2627-2636.
Hay, J. E. (1971). Precipitable water over Canada: II distribution. Atmosphere, 9(4), 101-111.
Holben, B. N., Eck, T. F., Slutsker, I. a., Tanre, D., Buis, J., Setzer, A., & Nakajima, T. (1998). AERONET—A federated instrument network and data archive for aerosol characterization. Remote sensing of environment, 66(1), 1-16.
Hung, N. Q., Babel, M. S., Weesakul, S., & Tripathi, N. K. (2009). An artificial neural network model for rainfall forecasting in Bangkok, Thailand. Hydrology and Earth System Science, 13, 1413–1425.
Iqbal, M. (1983). An Introduction to Solar Radiation. New York, USA: Academic Press.
Kämpfer, N. (2013). Monitoring atmospheric water vapour, Ground-Based Remote Sensing and In-situ Methods. New York, USA: Springer.
Kurtgoz, Y., Karagoz, M., & Deniz, E. (2017). Biogas engine performance estimation using ANN. Engineering Science and Technology, an International Journal, 20, 1563–1570.
Lv, C., Xing, Y., Zhang, J., Na, X., Li, Y., Liu, T., … Wang, F.Y. (2018). Levenberg–Marquardt Backpropagation Training of Multilayer Neural Networks for State Estimation of a Safety-Critical Cyber-Physical System. IEEE Transactions on Industrial Informatics, 14(8), 3436-3446.
Maghrabi, A., & Dajani, H. M. (2013). Estimation of precipitable water vapour using vapour pressure and air temperature in an arid region in central Saudi Arabia. Journal of the Association of Arab Universities for Basic and Applied Sciences, 14(1), 1-8.
Nunez, M. (1993). The development of a satellite-based insolation model for the tropical western Pacific Ocean. International Journal of Climatology, 13(6), 607-627.
Pérez-Ramírez, D., Whiteman, D. N., Smirnov, A., Lyamani, H., Holben, B. N., Pinker, R., … Alados-Arboledas, L. (2014). Evaluation of AERONET precipitable water vapor versus microwave radiometry, GPS, and radiosondes at ARM sites. Journal of Geophysical Research: Atmospheres, 119, 9596–9613.
Phokate, S., & Atyotha, V. (2018). Determination of the aount of water vapor in the troposphere over Thailand using surface data. Kasem Bundit Engineering Journal, 8, 364-372.
Reagan, J. A., Thome, K., Herman, B., & Gall, R. (1987). Water vapor measurements in the 0.94 micron absorption band: Calibration, measurements and data applications. Electrical and Computer Engineering, 5, 63-67.
Reitan, C. H. (1960). Distribution of precipitable water vapor over the continental United States. Bulletin of the American Meteorological Society, 41(2), 79-87.
Senkal, O. (2015). Solar radiation and precipitable water modeling for Turkey using artificial neural networks. Meteorology and Atmospheric Physics, 127, 481-488.
Shastri, N., & Pathak, K. (2018). Estimation of perceptible water vapor of atmosphere using artificial neural network, support vector machine and multiple linear regression algorithm and their comparative study. AIP Conferernce Proceeding, 1953(1), 140114-1–140114-4.
Taylor, F. W. (2005). Elementary climate physics. England: Oxford University Press.
Yari, E., Ayoobi, A., & Ghassemi, H. (2014). Applying the Artificial Neural Network to Estimate the Drag Force for an Autonomous Underwater Vehicle. Open Journal of Fluid Dynamics, 4, 334-346.
Yue, Y., & Ye, T. (2019). Predicting precipitable water vapor by using ANN from GPS ZTD data at Antarctic Zhongshan Station. Journal of Atmospheric and Solar-Terrestrial Physics, 191, 1-9.

Research Articles


How to Cite
BUNTOUNG, Sumaman; PARIYOTHON, Jindarat; DETKHON, Patsakorn. Estimation of Atmospheric Precipitable Water in Thailand using an Artificial Neural Network. Naresuan University Journal: Science and Technology (NUJST), [S.l.], v. 29, n. 2, p. 11-20, sep. 2020. ISSN 2539-553X. Available at: <>. Date accessed: 03 dec. 2021. doi: