Academic Journals Database
Disseminating quality controlled scientific knowledge

Prediction of daily pan evaporation using neural networks models

ADD TO MY LIST
 
Author(s): Parameshwar Sidramappa Shirgure | G S Rajput

Journal: Scientific Journal of Agriculture
ISSN 2322-2425

Volume: 1;
Issue: 5;
Start page: 126;
Date: 2012;
Original page

Keywords: Artificial neural networks | Back propagation algorithm | Coefficient of determination | Evaporation | Index of agreement | Modeling | Multiple linear regression | Pan evaporation

ABSTRACT
The investigation was carried out to develop and test the daily pan evaporation prediction models using various weather parameters as input variables with artificial neural network (ANN) and validated with the independent subset of data for five different locations in India. The measured variables included daily observations of maximum and minimum temperature, maximum and minimum relative humidity, wind speed, sunshine hours, rainfall and pan evaporation.  In this general model (GM) model development and evaluation has been done for the five locations viz. NRCC, Nagpur (M.S.); JNKVV, Jabalpur (M.P.); PDKV, Akola (M.S.); ICRISAT, Hyderabad (A.P.) and MPUAT, Udaipur (Raj.). The daily data of pan evaporation and other inputs for two years was considered for model development and subsequent 1-2 years data for validation. Weather data consisting of 3305 daily records from 2002 to 2006 were used to develop the GM models of daily pan evaporation. Additional weather of Nagpur station, which included 2139 daily records from 1996 - 2004, served as an independent evaluation data set for the performance of the models. The model plan strategy with all inputs has shown better performance than the reduced number of inputs. The General ANN models of daily pan evaporation with all available variables as a inputs was the most accurate model delivering an R2 of 0.84 and a root mean square error 1.44 mm for the model development data set. The GM evaluation with Nagpur model development (NMD) data shown lowest RMSE (1.961 mm), MAE (0.038 mm) and MARE (2.30 %) and highest r (0.848), R2 (0.719) and d (0.919) with ANN GM  M-1with all input variables.
RPA Switzerland

RPA Switzerland

Robotic process automation

    

Tango Rapperswil
Tango Rapperswil