Assessment of machine learning techniques for prediction of integrated water vapor using meteorological data

Nirmala  Bai Jadala; Miriyala Sridhar; D. Venkata Ratnam; Gopa Dutta

doi:10.15625/2615-9783/17373

Author affiliations

Authors

Nirmala Bai Jadala Department of ECE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur Dt, 522302, A.P, India
Miriyala Sridhar Department of ECE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur Dt, 522302, A.P, India
D. Venkata Ratnam Department of ECE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Guntur Dt, 522302, A.P, India
Gopa Dutta Department of ECE, Vignana Bharathi Institute of Technology, Hyderabad, India

DOI:

https://doi.org/10.15625/2615-9783/17373

Keywords:

Integrated water vapor, machine learning, prediction, rational quadratic Gaussian process regression, neural networks

Abstract

Weather and Climatological studies are very important in assessing atmospheric conditions like storms and cyclones. Integrated water vapor (IWV) is an important greenhouse gas in the atmosphere responsible for the Earth's radiative balance. Global Positioning System (GPS) observations have been used for monitoring the IWV variability. The IWV estimations are carried out using ground-based GPS observations at Hyderabad (17.4°N, 78.46°E), India using GAMIT software. GAMIT is GPS analysis software developed by MIT, USA. It takes input as GPS observation data containing pseudo ranges, navigation data containing ephemeris, clock errors, g-files with orbital information, and meteorological data like pressure, temperature, and relative humidity to calculate IWV. However, estimating IWV for forecasting applications is impossible with a GPS system. This paper introduces a methodology to predict IWV during normal days and severe cyclonic events using machine learning (ML) techniques. Rational quadratic Gaussian process regression (RQ-GPR) and neural network (NN) algorithms are considered for identifying suitable ML prediction algorithms over tropical conditions. Meteorological surface data like Pressure, Temperature, and relative humidity are given as input to the machine learning models. The IWV values computed from GPS are compared with the model's predicted values. RQ-GPR model is showing good accuracy with the IWV values computed from GPS against the NN model. The correlation coefficient (ρ) achieved for RQ-GPR is 0.93, and 0.86 is obtained for the NN model.

The RMSE (Root Mean Square Error) of the predicted IWV value with RQ-GPR is better than the NN model. We have obtained mean square error (MSE) and mean absolute error (MAE) as 18.146 kg/m² and 3.0762 kg/m² for RQ-GPR and 27.509 kg/m² and 3.9102 kg/m² for the NN model which is showing RQ-GPR is a suitable model for forecasting applications. The HUDHUD cyclonic event that occurred in October 2014 is considered for testing the proposed ML algorithms. RQ-GPR model has better results in the Prediction of IWV than the NN model. The RMSE value obtained is 2.837 kg/m² for RQ-GPR and 3.327 kg/m² obtained from the NN model. The results indicate that the RQ-GPR model has more accuracy than the other IWV prediction models. The prediction results are helpful for meteorology, weather, and climatology studies and useful to improve the accuracy of the regional numerical weather prediction models.

Downloads

Download data is not yet available.

References

Ahmed S. Alghamdi, Polat K., Alghoson A., Alshdadi A.A., Ahmed A., EL -Latif E.L.A., 2020. Gaussian Process Regression (GPR) based non-invasive continuous blood pressure prediction method from cuff oscillometric signal. Applied Acoustics, 164, 107256.

Aiguo Dai, Meehl G.A., Washington W.M., Wigley T.M.L., Arblaster J.M., 2001. Ensemble simulation of twenty-first century climate changes: Business-as-usual versus CO2 stabilization. Bull. Am. Meteorol. Soc., 82(11), 2377-2388. https://www.jstor.org/stable/26215289.

Aiguo Dai, Wang J.H., Ware R.H., Van Hove T., 2002. Diurnal variation in water vapor over North America and its implications for sampling errors in radiosonde humidity. J. Geophys. Res., 107(D10), 4090. https://doi.org/10.1029/2001JD000642.

Allan C. Just., Liu Y., Sorek-Hamer M., Rush J., Dorman M., Chatfield R., Wang Y., Lyapustin A., Kloog I., 2020. Gradient boosting machine learning to improve satellite-derived column water vapor measurement error. Atmos. Meas. Tech., 13, 4669-4681. https://doi.org/10.5194/amt-13-4669-2020.

Black H.D., 1978. An easily implemented algorithm for the tropospheric range correction. J. Geophys. Res., 83(B4), 1825-1828.

Burman P., 1989. A comparative study ordinary cross-validation, v-fold cross validation and the repeated learning-testing methods. Biometrika., 83(B4), 1825-1828.

C.E. Rasmussen, Williams C.K.I., 2006. Gaussian processes for machine learning. The MIT press, Cambridge, MA. ISBN 026218253X.

C.K.I. Williams, 1998. Prediction with Gaussian process: from linear regression to linear Prediction and beyond, in learning in graphical models. Springer.

Christian Ruckstuhl, Philipona R., Morland J., Ohmura A., 2007. Observed relationship between surface specific humidity, integrated water vapor, and longwave downward radiation at different altitudes. J. Geophys. Res., 112, D03302. Doi: 10.1029/2006JD007850.

G. Lanyi, 1984. Tropospheric delay effects in radio interferometry. TDA progress report., 42-78, 152-159.

H.S. Hopefield, 1971. Tropospheric effect on electromagnetically measured range: prediction from surface weather data. Radio. Sci., 6(3), 357-367. https://doi.org/10.1029/RS006i003p00357.

Hong Liang, Cao Y., Wan X., Xu Z., Wang H., Hu H., 2015. Meteorological applications of precipitable water vapor measurements retrieved by the national GNSS network of China. Geodesy and Geodynamics, 2, 135-142. http://doi:org/10.1016/j.geog.2015.03.001.

Isaac M. Held, Soden B.J., 2000. Water vapor feedback and global warming. Annu. Rev. Energy Environ., 25, 441-475. https://doi.org/10.1146/annurev.energy.25.1.441.

J.K. Kiehl, Trenberth K.E., 1997. Earth's Annual Global Mean energy budget. Bull. Am. Meteor. Soc., 78, 197-208. https://doi.org/10.1175/1520-0477(1997)078%3C0197:EAGMEB%3E2.0.CO;2.

J. Saastamoinen, 1973. Contributions to the theory of atmospheric refraction Part II, Refraction corrections in satellite geodesy. Bull. Geodes, 25, 1935-1948.

J.T. Houghton, Ding Y., Griggs D.J., Noguer M., Vander Winden P.J., Dai X., Maskell K., Johnson C.A., 2001. Climate Change 2001. The Scientific Basis. Contribution of Working Group 1 to the Third Assessment Report. Cambridge Univ. Press, New York, 881pp.

Jingping Duan, Bevis M., Fang P., Bock Y., Chiswell S., Businger S., Rocken C., Solheim F., Hove T.V., Ware R., Mcclusky S., Herring T.A., King R.W., 1995. GPS meteorology: Direct of the absolute value of precipitable water. J. Applied. Meteorology, 35, 830- 838. https://www.jstor.org/stable/26187904.

K. Liu, Liu B., Xu C., 2009. Intelligent analysis model of slope nonlinear displacement time series based on genetic-gaussian process regression algorithm of combined kernel function. Chinese Journal of Rock Mechanics and Engineering, 10, 2128-2134.

Kenneth H. Recknow, 1999. Water quality prediction and probability network models. Canadian Journal of Fisheries and Aquatic Sciences, 56, 1150-1158. https://doi.org/10.1139/f99-040.

Kevin E. Trenberth, Dai A.G., Rasmussen R.M., Parsons D.B., 2003. The changing character of precipitation. Bull. Am. Meteorol. Soc., 84(9), 1205-1217. https://doi.org/10.1175/BAMS-84-9-1205.

Kim J.H., 2009. Estimating classification error rate: Repeated cross-validation, Repeated hold-out and bootstrap. Computational statistics and data Analysis., 53, 3735-3745.

Kohavi R., 1995. A study of cross validation and bootstrap for accuracy estimation and model selection. International joint conference on artificial intelligence, 14(2), 1137-1145.

Lara Uusitalo, 2007. Advantages and challenges of bayesian networks in environmental modelling. Ecological Modelling, 203, 312-318.

Mayank Jain, Manandhar S., Lee Y.H., Winkler S., Dev S., 2020. Forecasting Precipitable Water Vapor using LSTMs. IEEE USNC-CNC-URSI North American Radio Science Meeting, 147-148. http://doi:10.23919/USNC/URSI49741.2020.9321614.

Michael Bevis, Businger S., Herring T.A., Rocken C., Anthes R.A., Ware R.H., 1992. GPS meteorology: Remote sensing of atmospheric water vapor using the global positioning system. J. Geophys. Res. Atmos., 97, 15787-15801. https://doi.org/10.1029/92JD01517.

N.B. Jadala, Sridhar M., Dashora N., Dutta G., 2020. Annual, seasonal and diurnal variations of integrated water vapor using GPS observations over Hyderabad, a tropical station. Adv. Space Res., 65, 529-540. http://doi.org/10.1016/j.asr.2019.10.002.

Nguyen Ngoc L., Coleman R., 2021. Assessment and reduction of zenith path delay biases due to day boundary effect. Vietnam Journal of Earth Sciences, 43(4), 546-554. https://doi.org/10.15625/2615-9783/16587.

Pedro Benevides, Catalao J., Nico G., 2019. Neural Network approach to forecast hourly intense rainfall using GNSS precipitable water vapour and meteorological sensors. Remote Sens., 11(8), 966.

Senkal O., et al., 2012. Precipitable Water vapour modelling using Artificial neural network in Cukurova region. Environ Monit Assess (Springer), 184, 141-147. http://doi.org/10.1007/s10661-011-1953-6.

Sheng Hong., Zhou Z., Lu C., Wang B., Zhao T., 2015. Bearing remaining life prediction using Gaussian process regression with composite kernel functions. J. Vibro Engineering, 75, 695-704.

Subimal Ghosh, 2010. SVM-PGSL coupled approach for statistical downscaling to predict rainfall from GCM output. J. Geophys. Res., 115, D22102.

T. Ragne Emardson, Elgered G., Johansson J.M., 1998. Three months of continuous monitoring of atmospheric water vapor with a network of Global positioning system receivers. J. Geophys. Res., 103, 1807-1920.

Vladislav V. Kalinnikov, Khutorova O.G., 2017. Diurnal variations in integrated water vapor derived from a GPS ground network in the Volga-Ural region of Russia. Ann. Geophys., 35, 453-464,

Wang B., Alruyemi I., 2021. Comprehensive Modeling in Predicting Biodiesel Density Using Gaussian Process Regression Approach. BioMed Research International, 1-13. https://doi.org/10.1155/2021/6069010.

Wayan Suparta., Alhasa K.M., 2015. Modeling of zenith path delay over Antarctica using an Adaptive neuro fuzzy inference system technique. Expert Systems with Applications, 42, 1050-1064. https://doi.org/10.1016/j.eswa.2014.09.029.

Wayan Suparta, Samah A.A., 2020. Rainfall prediction by using ANFIS time series technique in South Tengerang, Indonesia. Geodesy and Geodynamics, 11, 411-417, http://doi.org/10.1016/j.geog.2020.08.001.

Wei Gao., Karbasi M., Hasanipanah M., Zhang X., Guo J., 2017. Developing GPR model for forecasting the rock fragmentation in surface mines. Engineering with Computers Springer, 34(3). http://doi.org/10.1007/s00366-017-0544-8.

Yoshua Bengio, Courville A., Vincent P., 2013. Representation learning: A review and new perspectives. IEEE Trans Pattern Anal Mach Intell, 35, 1798-1828. https://doi:10.1109/TPAMI.2013.50.

Zhengdone Bai, Feng Y., 2003. GPS water vapour estimation using interpolated surface meteorological data from Australian automatic weather stations. J. Global. Pos. Sys., 2, 83-89.