Design and Implementation of a Cloud-Based Smart Agriculture System for Crop Yield Prediction using a Hybrid Deep Learning Algorithm

Abstract

This article proposes a cloud-based smart agriculture system for crop yield prediction using hybrid deep learning techniques. The study aims to improve crop yield prediction accuracy and facilitate decision-making for farmers. The system utilizes a hybrid deep learning approach that combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to process multi-sensor data, including weather data, soil moisture data, and crop growth data. The CNNs are used to extract spatial features from the input data, while the RNNs are used to capture temporal dependencies. The proposed model is employed on a cloud platform, allowing farmers to access the system from anywhere using a web-based interface. Experimental results show that the proposed hybrid deep learning approach outperforms traditional machine learning methods for crop yield prediction, achieving a prediction accuracy of over 90%. Its ability to predict crop yields properly was demonstrated by its decreased MAE and RMSE to 2.17% and 2.94% respectively. It also showed a better fit between the expected and actual data, with a higher R-squared value. The proposed system has the potential to improve the efficiency and profitability of farming operations and contribute to sustainable agriculture practices.