A Unified Machine Learning Framework for Crop Yield Prediction and Agricultural Resource Optimization
- Version
- Download 14
- File Size 447.83 KB
- File Count 1
- Create Date 12 March 2026
- Last Updated 12 March 2026
A Unified Machine Learning Framework for Crop Yield Prediction andAgricultural Resource Optimization
Vaishnavi Ramesh, Shraddha Gotawale, Shriraj Salunke, Kartik Gavali
Department of Computer Science, MIT ADT University, Pune, India
vaishnavi.r.445@gmail.com, shraddhagotawale321@gmail.com, salunkeshriraj@gmail.com,
kartikgavali20@gmail.com
Abstract—Ensuring reliable crop yield prediction is essential for maintaining food security and promoting sustainable agricultural development. Conventional yield estimation methods largely depend on historical data trends and manual observations, which often become unreliable under changing climate conditions and environmental uncertainties. In recent years, Artificial Intelligence (AI) techniques, particularly machine learning (ML) and deep learning (DL), have shown strong potential in improving prediction accuracy. These approaches utilize diverse data sources such as weather patterns, soil characteristics, satellite imagery, and IoT based sensor inputs to generate more precise forecasts. This paper provides a detailed review of AI-based techniques used for crop yield prediction and optimization. It examines various models, including regression approaches, ensemble learning methods, convolutional neural networks (CNN), and long shortterm memory (LSTM) networks. Additionally, the study compares different methodologies, datasets, strengths,and limitations. Finally, future research directions are highlighted,focusing interpretable,scalable,on and the development of climate-daptive AIsolutions.
Keywords-Artificial Intelligence, Crop Yield Prediction,MachineLearning,DeepAgriculture, Yield Optimization
Download