Advanced Techniques for Agricultural Crop Yield Prediction Using Machine Learning and Computer Vision

Advanced Techniques for Agricultural Crop Yield Prediction Using Machine Learning and Computer Vision

연구 분야: Artificial Intelligence

학회: International Conference on Advanced Informatics for Computing Research

Predictions of agricultural crop yield have increasingly relied on computer vision and machine learning strategies in recent years. Using these methods, the prospective yield of a crop can be determined by analyzing several characteristics, climate, crop health, crop yield, and soil conditions are all included. Predicting crop yield is an essential task in agriculture, as it helps farmers make judgments regarding irrigation, planting, and harvesting. Machine learning and computer vision are two emerging technologies that have shown promise in crop yield prediction. This paper examines recent advancements in machine learning and computer vision agriculture crop yield prediction methods. Multiple Machine Learning methods, including CNN-LSTM, RNN- LSTM, ANN, RF, and MLR, are employed. In this research work, it is also assessing the efficacy of these techniques and approaches. Convolutional neural networks (CNN) are the most accurate machine learning model for predicting agricultural production, according to our findings.