Estimation of Atmospheric Water Vapor from ANFIS Technique and Its Validation with GPS Data

Main Article Content

Wayan Suparta Kemal Maulana Alhasa


Adaptive neuro-fuzzy inference system (ANFIS) is a prospective approach in modeling weather parameters based on learning from historical data used. This study presented the comparison of tropospheric precipitable water vapor (PWV) between ANFIS and Global Positioning System (GPS) for areas in Pekan, Pahang, Malaysia. The PWV value was estimated with the ANFIS model with the surface meteorological data as inputs. The accuracy of PWV from ANFIS has been validated with PWV from GPS measurements for the period of 2010. The result showed that the ANFIS PWV has a similar trend with the GPS PWV (r = 0.999 at the 99% confidence level) and found a difference of 0.024%. The PWV from ANFIS was calculated 0.035% higher compared to GPS PWV and found a similar character in two seasonal monsoons. This indicates that the PWV obtained with ANFIS model agreed very well with GPS measurements and it can be implemented to monitor atmospheric variability as well as climate change studies in the absence of GPS data


Download data is not yet available.

Article Details

How to Cite
SUPARTA, Wayan; ALHASA, Kemal Maulana. Estimation of Atmospheric Water Vapor from ANFIS Technique and Its Validation with GPS Data. JURNAL INFOTEL, [S.l.], v. 11, n. 1, p. 8-14, mar. 2019. ISSN 2460-0997. Available at: <>. Date accessed: 26 june 2019. doi:


[1] C. Rocken, T. Van Hove, J. Johnson, F. Solheim, C. Alber, and R. Ware, “GPS/STROM – GPS sensing of atmospheric water vapour for meteorology,” J. Atmos. Ocea. Tech., vol. 12, pp. 468-478, 1995.
[2] Z. Liu, B. Chen, S. T. Chan, Y. Cao, Y. Gao, K. Zhang, and J. Nichol, “Analysis and modelling of water vapour and temperature changes in Hong Kong using a 40?year radiosonde record: 1973–2012,” Intern. J. Clim., vol. 35, no. 3, pp. 462-474, 2015.
[3] M. Bevis, S. Businger, T. A. Herring, C. Rocken, R. A. Anthes, and R. H. Ware, “GPS meteorology: Remote sensing of atmospheric water vapor using the global positioning system,” J. Geophys. Res., vol. 97, pp. 15787-15801, 1992.
[4] R. Norman, J. Le Marshall, K. Zhang, C. S. Wang, B. A. Carter, W. Rohm, T. Manning, S. Gordon, and Y. Li, “Comparing GPS radio occultation observations with radiosonde measurements in the Australian region. In Earth on the Edge: Science for a Sustainable Planet,” in Proc. IAG Assembly, 2011, pp. 51-57, 2011.
[5] W. Suparta, "Observations of Precipitable Water Vapor along the Maritime Continent Associated with El Niño-Southern Oscillation Activity,", Ann. Geophys., vol. 61, no. 5, RS556, 2018, doi: 10.4401/ag-7600.
[6] Suparta, W., A. Iskandar, M. S. Jit Singh, M. A. Mohd Ali, B. Yatim, and A. N. Mohd Yatim (2013). Analysis of GPS water vapor variability during the 2011 La Niña event over the western Pacific Ocean,” Ann. Geophys., vol. 563, R0330, doi:10.4401/ag-6261.
[7] W. Suparta and R. Rosnani, “Spatial Interpolation of GPS PWV and Meteorological Variables over the West Coast of Peninsular Malaysia during 2013 Klang Valley Flash Flood,” Atmospheric Research, vol. 168, pp. 205–219, 2016.
[8] W. Suparta, J. Adnan, and M. A. Mohd. Ali, “Dynamical features of GPS PWV variation associated with lightning activity,” International Journal of Remote Sensing,” vol. 37, no. 6, pp. 1376-1390, 2016.
[9] W. Suparta, "The use of GPS meteorology for climate change detection," In Proc. 2012 International Conference in Green and Ubiquitous Technology, pp. 71-73, 2012, doi: 10.1109/GUT.2012.6344191.
[10] W. Suparta, “Utilization of GPS tropospheric delays for climate research,” Journal of Physics: Conference Series, vol. 846, 012001, 2017.
[11] M. Bevis, S. Businger, and S. Chiswel “GPS meteorology: Mapping zenith wet delay onto precipitable water,” J. Appl. Meteorol., vol. 33, issue 3, pp. 379-386, 1994.
[12] W. Suparta, Z. A. Abdul Rashid, M. A. Mohd. Ali, B. Yatim and G. J. Fraser, “Observations of Antarctic precipitable water vapor and its response to the solar activity based on GPS sensing,” J. Atmos. Sol. Terr. Phys., vol. 70, pp. 1419-1447, 2008.
[13] W. Suparta, and K. M. Alhasa, “Modeling of precipitable water vapor using an adaptive neuro-fuzzy inference system in the absence of the GPS network,” J. Appl. Meteorol. Clim., vol. 55, no. 10, pp. 2283-2300, 2016.
[14] W. Suparta, “The development of GPS TroWav tool for atmospheric–terrestrial studies,” J. Phys. Conf. Ser., vol. 495, 012037, 2014.
[15] UNAVCO, “TEQC - The Toolkit for GNSS Data,”, accessed 20 February 2019.
[16] Z. Bai and Y. Feng, “GPS water vapor estimation using interpolated surface meteorological data from Australian automatic weather stations,” Journal of Global Positioning Systems, vol. 2, no. 2, pp. 83-89, 2003.
[17] W. Suparta and K. M. Alhasa, "Modeling of Tropospheric Delays Using ANFIS," Germany: Springer International, 2016, ISBN: 978-3-319-28437-8.
[18] V. Nourani and M. Komasi, “A geomorphology-based ANFIS model for multi-station modeling of rainfall–runoff process,” Journal of Hydrology, vol. 490, pp. 41-55, 2013.
[19] W. Suparta and K. M. Alhasa, "Modeling of zenith path delay over Antarctica using an adaptive neuro fuzzy inference system technique," Expert Systems With Applications, vol. 42, no. 3, pp. 1050-1064, 2015.