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

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.