Open Access Open Access  Restricted Access Subscription or Fee Access

Evaporation estimation using multilayer neural network – A case study for Chhattisgarh plains

Diwakar Naidu

Abstract


Evaporation being one of the most important components of the hydrological cycle, it is important to know its relationship with other climatic factors for developing strategies for effective water resource management especially for agricultural purposes. There are few direct and indirect methods in practice for the measurement or computation of evaporation losses. This study is conducted to demonstrate the ability of multilayer neural network (MLNN) with back propagation weight update mechanism to estimate the evaporation losses in Chhattisgarh Plains region using other climatic factors. The meteorological parameters considered for estimation of evaporation are temperature, humidity, vapour pressure, wind speed and sunshine hours.  Results indicate that MLNN model with complete set of meteorological parameters, is able to estimate evaporation losses precisely with monthly and weekly time series. However, the results are little inferior with daily time series. It is also evident that with less number of input features the performance accuracy of MLNN reduces in estimating evaporation.  

:Evaporation being one of the most important components of the hydrological cycle, it is important to know its relationship with other climatic factors for developing strategies for effective water resource management especially for agricultural purposes. There are few direct and indirect methods in practice for the measurement or computation of evaporation losses. This study is conducted to demonstrate the ability of multilayer neural network (MLNN) with back propagation weight update mechanism to estimate the evaporation losses in Chhattisgarh Plains region using other climatic factors. The meteorological parameters considered for estimation of evaporation are temperature, humidity, vapour pressure, wind speed and sunshine hours.  Results indicate that MLNN model with complete set of meteorological parameters, is able to estimate evaporation losses precisely with monthly and weekly time series. However, the results are little inferior with daily time series. It is also evident that with less number of input features the performance accuracy of MLNN reduces in estimating evaporation. 


Full Text:

PDF

Refbacks

  • There are currently no refbacks.


This site has been shifted to https://stmcomputers.stmjournals.com/