Estimation of dew point temperature using SVM and ELM for humid and semi-arid regions of India

Abstract The dew point temperature is the temperature at which the moisture in the air begins to condense into dew or water droplets. The accurate estimation of the dew point temperature is very important as it controls the heat stress on humans, detects fluctuations of evaporation rates, and humidity trends. The dew point temperature is a significant parameter particularly required in various hydrological, climatological and agronomical related researches. This study proposes Support Vector Machine (SVM) and Extreme Learning Machine (ELM) models for the estimation of daily dew point temperature. The daily measured weather data (Wet bulb temperature, relative humidity, vapor pressure and dew point temperature) of humid and semi-arid regions of India were used for model development. The statistical indices, namely Mean Absolute Error, Root Mean Square Error, and Nash Sutcliffe Efficiency were adopted to evaluate the performances of these two models. The merit of the ELM model is evaluated against SVM technique in the estimation of dew point temperature. The proposed ELM models demonstrated much greater capability than the SVM models in the estimation of daily dew point temperature.

[1]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[2]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[3]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[4]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[5]  P. Robinson,et al.  Temporal trends in United States dew point temperatures , 2000 .

[6]  Chee Kheong Siew,et al.  Extreme learning machine: RBF network case , 2004, ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004..

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  M. Lawrence.  The relationship between relative humidity and the dewpoint temperature in moist air - A simple conversion and applications , 2005 .

[9]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[10]  Dew‐point temperature , 2007 .

[11]  Gerrit Hoogenboom,et al.  ENSEMBLE ARTIFICIAL NEURAL NETWORKS FOR PREDICTION OF DEW POINT TEMPERATURE , 2008, Appl. Artif. Intell..

[12]  L. Oudin,et al.  Estimating potential evapotranspiration without continuous daily data: possible errors and impact on water balance simulations , 2010 .

[13]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[14]  F. Chang,et al.  A spatial neural fuzzy network for estimating pan evaporation at ungauged sites , 2011 .

[15]  Mohammad Zounemat-Kermani.  Hourly predictive Levenberg–Marquardt ANN and multi linear regression models for predicting of dew point temperature , 2012, Meteorology and Atmospheric Physics.

[16]  Ozgur Kisi,et al.  Estimation of dew point temperature using neuro-fuzzy and neural network techniques , 2013, Theoretical and Applied Climatology.

[17]  Paresh Chandra Deka,et al.  Support vector machine applications in the field of hydrology: A review , 2014, Appl. Soft Comput..

[18]  Ozgur Kisi,et al.  Estimation of daily dew point temperature using genetic programming and neural networks approaches , 2014 .

[19]  Dennis R. Heldman,et al.  Encyclopedia of agricultural, food, and biological engineering , 2014 .

[20]  Shervin Motamedi,et al.  Extreme learning machine based prediction of daily dew point temperature , 2015, Comput. Electron. Agric..

[21]  Sungwon Kim,et al.  Modeling the physical dynamics of daily dew point temperature using soft computing techniques , 2015 .

[22]  Shimon Rachmilevitch,et al.  The role of dew in Negev Desert plants , 2015, Oecologia.

[23]  Paresh Chandra Deka,et al.  An extreme learning machine approach for modeling evapotranspiration using extrinsic inputs , 2016, Comput. Electron. Agric..

[24]  Yu Feng,et al.  Comparison of ELM, GANN, WNN and empirical models for estimating reference evapotranspiration in humid region of Southwest China , 2016 .

[25]  A. Kamsin,et al.  A hybrid computational intelligence method for predicting dew point temperature , 2016, Environmental Earth Sciences.