AGRO INFORMATIS FOR YEILD PREDICTION

Abstract

The study of data mining is essential to extract meaningful information by analyzing large volumes of data from various sources. Agriculture, being a key industry in any country, has a direct impact on the Gross Domestic Product (GDP). Agricultural production and market prices are important factors in generating revenue within the agricultural sector. Higher crop yields result in increased income and profit for farmers, whereas lower yields can negatively affect agricultural GDP. Therefore, monitoring crop yield becomes very important for strengthening the country’s economic resources. Earlier yield prediction methods were mainly based on manual calculations, which sometimes resulted in errors due to inaccurate or incomplete inputs. To overcome these limitations, this study presents a new approach using neural network models to improve the accuracy of yield predictions. This research examines the use of hybrid and deep learning models such as Long Short Term Memory (LSTM), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) to determine the most accurate model and evaluate prediction performance. Several experiments are conducted using farm production datasets collected from Kaggle to assess the effectiveness of these algorithms. The proposed approach analyzes the predictive capability of each model through these experiments, providing useful insights for future agricultural productivity forecasting. These results can significantly improve the accuracy and reliability of yield predictions, benefiting the agricultural sector and supporting the country’s economic growth.