National Academy of Agricultural Sciences (NAAS)
|
PRINT ISSN : 2319-7692
Online ISSN : 2319-7706 Issues : 12 per year Publisher : Excellent Publishers Email : editorijcmas@gmail.com / submit@ijcmas.com Editor-in-chief: Dr.M.Prakash Index Copernicus ICV 2018: 95.39 NAAS RATING 2020: 5.38 |
Agriculture is the major deciding factor of Indian economy and Paddy is the principal crop cultivated extensively in all the districts of Tamil Nadu. Thiruvarur district in Tamil Nadu leads paddy cultivation with an area of 1,78,080 ha in crop yield production. Eventually, Artificial Neural Network (ANN) techniques have emerged to be important for predicting and maximising the crop yield for the benefit of farmers. This research is based on the development of trained Neural Network models for predicting the paddy yield by varying the input parameters including both controllable and uncontrollable factors. The models have been experimented with different input parameters of paddy and training patterns. For this purpose, real data set from the Department of Agricultural Meteorology, Department of Soil Sciences, Department of Economics, Directorate of CARDS, Tamil Nadu Agricultural University, Coimbatore and Tamil Nadu Rice Research Institute, Aduthurai, were collected. The collected data were intensively studied, the modus operando using the data was arrived at, and taken for various experiments. The experiments show that the trained neural network produced a minimum error which indicated that the test model is capable of predicting and maximising the paddy yield in Thiruvarur. The major objectives of this paper are to: (i) explore if Artificial Neural Network models with back propagation could efficiently predict rice yield in Thiruvarur district under various climatic conditions; ground-specific rainfall, ground-specific weather variables (sunshine hours, solar radiation, maximum and minimum temperature, daily wind speed values) and historic yield data; (ii) analyse the changes of model performance with variations of ANN model parameters; and (iii) calculate the accuracy by which crop yield prediction is made.
Citations |
 |
 |
 |
 |
