Real-Time Crop Yield Forecasting Using Deep Learning and Cloud-Based Image Analytics in Precision Agriculture
Main Article Content
Abstract
Estimating and predicting crop yields are very important for making farming more productive and long-lasting. It is necessary to use advanced technologies like Deep Learning (DL) and cloud-based real-time image processing because traditional methods are not always accurate or on time. The SatNet Enhanced Algorithm is described in this work. It is a new way to measure and predict crop yields that uses satellite images handled on a cloud platform. The study used deep learning model on crop monitoring data and synthetic data that has generated using cloud model in real time, looked at how food yields have been estimated in the past. The given research study based on popular Deep Learning methods like Random Forest (RF), Long Short-Term Memory networks (LSTM), and Convolutional Neural Networks (CNN). The study use these methods as a starting point for our comparisons. The proposed method is based on the SatNet Enhanced Algorithm, which combines better image processing methods with a custom neural network topology made for high-resolution satellite data. A strong cloud-based system makes real-time processing possible and speeds up data handling and analysis. The finding of study show that the SatNet model enhance better result with deep learning methods. This improvement in speed shows how well it works to combine advanced image processing in the cloud with custom deep learning models. Using SatNet not only improves the accuracy of crop yield predictions, but it also provides a flexible and effective option that can be used in a wide range of locations and with different types of crops. This new development looks like it will have big benefits for strategy planning in agriculture and managing resources.