sis 20(24): e8

Research Article

Forecasting of Rice Cultivation in India–A Comparative Analysis with ARIMA and LSTM-NN Models

Download119 downloads
  • @ARTICLE{10.4108/eai.13-7-2018.161409,
        author={Kiran  Kumar  Paidipati and Arjun  Banik},
        title={Forecasting of Rice Cultivation in India--A Comparative Analysis with ARIMA and LSTM-NN Models},
        journal={EAI Endorsed Transactions on Scalable Information Systems},
        volume={7},
        number={24},
        publisher={EAI},
        journal_a={SIS},
        year={2019},
        month={11},
        keywords={Food Security, Rice Cultivation, ARIMA and LSTM-NN Models},
        doi={10.4108/eai.13-7-2018.161409}
    }
    
  • Kiran Kumar Paidipati
    Arjun Banik
    Year: 2019
    Forecasting of Rice Cultivation in India–A Comparative Analysis with ARIMA and LSTM-NN Models
    SIS
    EAI
    DOI: 10.4108/eai.13-7-2018.161409
Kiran Kumar Paidipati1,*, Arjun Banik1
  • 1: Department of Statistics, Pondicherry University, Puducherry-605014, India
*Contact email: kirankumarpaidipati@gmail.com

Abstract

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.