Open Journal of Geology, 2018, 8, 987-1001 http://www.scirp.org/journal/ojg ISSN Online: 2161-7589 ISSN Print: 2161-7570 DOI: 10.4236/ojg.2018.810059 Sep. 26, 2018 987 Open Journal of Geology Accurate Imputation for Relative Humidity over Pakistan Gathered from AQUA Satellite Usman Saleem 1 , Mian Sohail Akram 1 , Muhammad Fahad Ullah 2 , Faisal Rehman 2* 1 Institute of Geology, University of the Punjab, Lahore, Pakistan 2 Departments of Earth Sciences, University of Sargodha, Sargodha, Pakistan Abstract The relative humidity in the atmosphere captured by AQUA satellite contains missing matrices. In order to fill such missing values four very popular im- putation techniques: Bilinear, Inverse Distance Weighting, Natural Neighbor and Nearest Interpolations were tested. Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Coefficient of Determination (R 2 ) and Correla- tion Coefficient (Corr), were used to check the accuracy of these interpola- tions. It was found that the Inverse Distance Weighting and Nearest Interpo- lation were proved not to be suited. Natural interpolation gave accurate re- sults than the aforementioned two interpolations. Missing values of relative humidity were accurately refilled with Bilinear Interpolation. This interpola- tion produced RMSE of ±0.543 for relative humidity over 100, 150, 200, 250, 300, 400, 500 hPa while for 600, 700, 850 and 925 hPa RMSE remainnear to 1. A perfect fit to the surface and very strong correlation (value near to 0.99) was found between actual and imputed relative humidity data through Bili- near Interpolation. Therefore it was concluded that the Bilinear Interpolation is the most accurate and best imputation for missing values of relative hu- midity form 100 to 1000 hPa levels. Keywords Imputation, Humidity, Aqua Satellite , Pakistan 1. Introduction Metrological data collected from satellites mostly contain gaps. Such gaps in data set occur due to less efficient sampling of satellite subsystem [1] [2]. Using missing data may produce misleading in purposed outcome of the research [3]. For the best use of relative humidity data, it is necessary to have best estimate of the gaps in satellite captured data with imputation techniques [1] [4] [5] [6]. Sa- How to cite this paper: Saleem, U., Akram, M.S., Ullah, M.F. and Rehman, F. (2018) Accurate Imputation for Relative Humidity over Pakistan Gathered from AQUA Satellite. Open Journal of Geology, 8, 987-1001. https://doi.org/10.4236/ojg.2018.810059 Received: August 16, 2018 Accepted: September 23, 2018 Published: September 26, 2018 Copyright © 2018 by authors and Scientific Research Publishing Inc. This work is licensed under the Creative Commons Attribution International License (CC BY 4.0). http://creativecommons.org/licenses/by/4.0/ Open Access