Crop Recommendation and Yield Prediction using Machine learning and Deep learning models

Agriculture remains the predominant livelihood provider in India contributing to India's Gross Domestic Product (GDP). Recent advancements in technology like precision agriculture and agri-tech solutions, have improved efficiency. However, the domain faces challenges due to climate change, water scarcity, and land degradation. This research focuses on leveraging machine learning (ML) and deep learning (DL) models to address these challenges through crop recommendation and yield prediction. In this paper a combined system for crop recommendation and yield prediction is done using a comprehensive dataset that has factors like pH, rainfall, state name, crop type, crop name, N, P, K, humidity, area in hectares, production, temperature, and yield in tons per hectare. Preprocessing techniques were applied to improve data quality and model accuracy. The dataset is trained using machine learning models (K-Nearest Neighbors, Random Forest and Decision Tree) and deep learning models (Artificial Neural Network-ANN, Long Short-Term Memory-LSTM, Deep Neural Network-DNN). The findings indicate that K-Nearest Neighbors (KNN) and Random Forest among the other ML models provide superior accuracy. Random Forest (RF) achieved the best accuracy in crop recommendation (99.3%) and KNN performed well in yield prediction (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score: 0.985). Among DL models, LSTM has higher efficiency both in terms of crop recommendation (97%) and yield prediction (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score: 0.930). Integration of these models will help farmers to make decisions related to crop selection and the yield which will eventually result in increased productivity and sustainability. The insights from this paper highlights the advantages of data driven approaches in handling difficulties encountered by farmers, thus paving way for a sustainable and food secure future.