AI-Based Framework for Enhancing Yield in Precision Agriculture Systems
Keywords:
Precision agriculture, crop yield prediction, hybrid CNN-LSTM, deep learning, Tensor Flow, remote sensing, data fusion.Abstract
We propose a framework based on AI to help improve the prediction of crop yield in precision agriculture by using a Hybrid CNN-LSTM network built with Tensor Flow. Using data from drones and satellites as well as weather and soil moisture data over time, the framework explains the various growth factors influencing crops. Using CNN for spatial features and LSTM for handling sequence, the model achieves better prediction accuracy than traditional machine learning does. Results from experiments show the model accurately forecasts yields, making the use of resources for irrigation, fertilizer and pests more efficient. Tensor Flow supports expanding agriculture workloads and making them available everywhere. This work reveals that advanced methods in deep learning architecture can assist sustainable farming, improve how farmers make decisions and raise farming output.
