Deep Learning for Crop Yield Forcasting in Agriculture Using Multilayer Perceptron and Convolutional Neural Networks

Abstract

The primary challenge facing the agricultural sector, which is essential for ensuring global food security, is enhancing crop productivity while effectively addressing the challenges posed by plant diseases. Advanced technologies have the potential to completely transform agricultural methods, especially in the areas of computer vision and machine learning. This study uses meteorological as well as fruit and vegetables image datasets to create an integrated agricultural decision support system for crop yield estimation and disease prediction. By enabling early plant disease detection and precise crop yield estimates, the system seeks to improve precision agriculture techniques. To analyze and classify the images and predict the possibility of crop disease harming fruits and vegetables, a Convolutional Neural Network (CNN) deep learning model is used. The Multilayer Perceptron algorithm is used to train the model using a large dataset that contains historical meteorological data, allowing it to identify patterns and connections between environmental conditions. Finally, farmers receive an SMS notice with prediction specifics.

Plant phenotyping relevance

植物画像から病害状態を推定し、気象・画像データから収量を推定するCNN/MLP統合手法が研究の中心であり、単なる生物学的実験のルーチン測定ではない。

Code and data availability

保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。