Deep-LSTM Model for Wheat Crop Yield Prediction in India

Preeti Saini, Bharti Nagpal

20222022 Fifth International Conference on Computational Intelligence and Communication Technologies (CCICT)14 citationsDOI

Abstract

In India, Agriculture is the prominent economic domain in which early-season Crop Yield Prediction can help the farmers to prepare their decision policies. With the emergence of the Artificial Intelligence arena, Deep Learning techniques are overcome the traditional Statistical Methods for Yield prediction ampersand forecasting of Crops. The present study focuses on the Yield prediction of Wheat Crops in India using a Deep-LSTM model. The dataset was considered from 1950-to 2019 year. The results were evaluated using Root Mean Square Error, and Mean Square Error and Compared with the existing machine learning methods. The outcomes revealed that Deep-LSTM provides a lower RMSE value of 0.20 and better accuracy in forecasting in comparison to traditional methods. This study is helpful for farmers Crop season.

Topics & Concepts

Mean squared errorYield (engineering)Deep learningAgricultureCrop yieldCropArtificial intelligenceMachine learningComputer scienceAgricultural engineeringStatisticsMathematicsAgronomyGeographyForestryEngineeringMaterials scienceArchaeologyMetallurgyBiologySmart Agriculture and AISpectroscopy and Chemometric AnalysesAgricultural Economics and Practices