The prediction of rice yields plays a major role in reducing food security problems in India and also suggests that government agencies manage the over or under situations of production. Advanced machine learning techniques are playing a vital role in the accurate prediction of rice yields in dealing with nonlinear complex situations instead of traditional statistical methods. In the present study, the researchers made an attempt to predict the rice yield through support vector regression (SVR) models with various kernels (linear, polynomial, and radial basis function) for India overall and the top five rice producing states by considering influence parameters, such as the area under cultivation and production, as independent variables for the years 1962–2018. The best-fitted models were chosen based on the cross-validation and hyperparameter optimization of various kernel parameters. The root-mean-square error (RMSE) and mean absolute error (MAE) were calculated for the training and testing datasets. The results revealed that SVR with various kernels fitted to India overall, as well as the major rice producing states, would explore the nonlinear patterns to understand the precise situations of yield prediction. This study will be helpful for farmers as well as the central and state governments for estimating rice yield in advance with optimal resources.

Rainfall forecast is a hotspot in meteorological studies in the last few years. The key difficulty in forecast accuracy lies in the nonlinearity of rainfall data. Considering the potential of support vector machine (SVM) to solve nonlinear time series, this paper develops an SVM-based model based on the monthly rainfall data from 1901 to 2015 in Northwest India. The forecast accuracies of four different kernels were compared, including linear, polynomial, radial basis function (RBF) and sigmoid kernels. The comparison shows that the SVM-based model with the RBF kernel achieved the smallest root mean squared error (RMSE) at the lookback of 25, C=1, γ =0.01 and =0.1. Our research provides an effective tool to predict rainfall in regions with similar meteorological conditions to northwest India.

In India, due to the blessing by the outbreak of the National Food Security Mission, the production of cereals such as wheat, rice etc, has increased in an alarming rate. In this Study, forecasting is done with the help Auto Regressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM-NN) models on the basis of the historical data of rice cultivation from the year 1950-51 to 2017-18. The well fitted ARIMA models for the parameters such as Area under Cultivation (0,1,1), Production (0,1,1) and Yielding (2,2,1) are obtained from the significant spikes of their respective Auto Correlation Function (ACF) and Partial Auto Correlation Function (PACF) plots. But, the models fitted with a supervised deep learning neural network known as LSTM-NN are found much better time series forecasting model than the ARIMA models. The performances of these models validated with the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) values. From the study, the LSTM-NN's are more flexible and able to develop accurate models for predicting the behavior of agricultural parameters than the ARIMA models.

No abstract