CROP YIELD PREDICTION

ABSTRACT Accurate crop yield prediction is crucial for sustainable agriculture, food security, and efficient resource management. Traditional forecasting methods often fail to capture the complex interactions among climatic, agronomic, and environmental factors, leading to inaccurate estimates and economic losses. This study proposes a hybrid deep learning approach combining Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs) to predict crop yield by integrating key agricultural and climatic parameters such as crop type, rainfall, temperature, and pesticide usage.The CNN-GRU model was developed to extract spatial features through CNN layers and capture sequential and temporal patterns using GRU layers, enabling accurate multi-seasonal crop yield forecasting. The model was trained and validated on comprehensive agricultural datasets, achieving an R² score of 0.8919, high precision, and recall metrics. Multiple test cases demonstrated the model’s ability to predict high and low yields for crops such as Potatoes and Soybeans, confirming its robustness and reliability as a decision-support tool.The system was deployed through a user-friendly Streamlit web application, providing real-time access for farmers, policymakers, and agricultural stakeholders. By bridging the gap between advanced computational techniques and practical agricultural decision-making, the proposed CNN-GRU model supports informed planning, optimal resource allocation, and improved food production. This study demonstrates the potential of hybrid deep learning approaches to enhance modern agricultural practices and contribute to sustainable food security.