International Journal of Agricultural Engineering

R. V. Meshram ¹, M. M. Deshmukh ¹, S. B. Wadatkar ¹, M. U. Kale ¹, A. N. Mankar ¹

Affiliations
1 Department of Irrigation and Drainage Engineering, Dr. Panjabrao Deshmukh Krishi Vidyapeeth, Akola (M.S.), IN

Abstract

The study has been undertaken to predict one month ahead ETo using artificial neural networks (ANNs). Climatic parameters for 35 years (1977-2011) were collected for Akola station. The ETo was estimated by using standard Penman-Monteith method which was further used for development and validation of the ANN models as the observed data on ETo was not available. The ANN models were developed using different input combinations. The models learned to predict one month ahead ETo (i.e. ET_o,t+1) for Akola using Levenberg-Marquardt learning method. The training results were compared with each other, and performance evaluations were done for untrained data. Based on results obtained, the ANN model with architecture of 4-12-1 (four, twelve and one neuron(s) in the input, hidden, and output layers, respectively) was found to be the best amongst all the models with minimum standard error (SE) of estimates of 0.74 mm day^-1 and correlation co-efficient of 0.9260. From the study it is concluded that ANN4 model had given better performance with mean absolute error of estimates (MAE) and ischolar_main mean square error (RMSE) of 0.20 and 0.27 mm day^-1, respectively, mean absolute relative error (MARE) of 5.7 per cent and model efficiency of 0.9745.

Keywords

Reference Evapotranspiration, ANN, Levenberg-Marquardt.

Full Text

     

R. V. Meshram ¹, M. M. Deshmukh ¹, M. V. Kawle ¹, S. B. Wadatkar ¹

Affiliations
1 Department of Irrigation and Drainage Engineering, Dr. Panjabrao Deshmukh Krishi Vidyapeeth, AKOLA (M.S.), IN

Abstract

Climatic parameters (maximum temperature, minimum temperature, wind speed, bright sunshine hours, morning relative humidity, evening relative humidity and open pan evaporation) for 37 years (1971-2007) were collected from Agricultural Meteorological Observatory Dr. PDKV, Akola. Mean monthly climatic data for the period were used to determine reference evapotranspiration (ET₀) by FAO-56 Penman-Monteith method. The trends of change of these parameters were analyzed by working out seven years moving average and forming regression equations. The mean monthly maximum air temperature showed slightly decreasing trend for most of the months during the year except February, August and December. Whereas, there was unsteady variation in minimum air temperature and showed linear increasing trend during monsoon period. There was strong variation in wind speed and bright sunshine hours and showed continuous linear decreasing trend. However, mean monthly morning and evening relative humidity showed the linear increasing trend for most of the period of the year. The mean monthly pan evaporation also showed the decreasing trend throughout year. There was major variation in monthly reference evapotranspiration and showed linear decreasing trend for all the months of the year.

Keywords

Moving Averages, Reference Evapotranspiration, Trend Analysis.

Full Text