• RASHAMVIR KAUR GRANG
• SAKSHAM SHARMA
• AANCHAL YADAV

Accurate crop yield prediction is important for guaranteeing food security and sustainability in agriculture. Previous research has demonstrated the potential of machine learning for crop yield prediction, with Random Forest often emerging as the most effective algorithm. This research investigates the efficacy of various machine learning algorithms for predicting crop yield in Punjab, India, using historical data. We focus on comparing the performance of Random Forest (RF), Support Vector Machine (SVM) and Linear Regression in accurately estimating crop yield using historical data from Punjab and other algorithms on a dataset encompassing rice and wheat crops, weather parameters, and their yield characteristics. Our objective is to identify the most effective algorithm for predicting crop yield in the context of Punjab's agricultural landscape. We compare the performance of the models based on metrics like mean squared error (MSE), Root Mean Squared Error (RMSE) and R2. This study aims to contribute to the development of reliable crop yield prediction models in Punjab, empowering farmers and agricultural stakeholders with informed decision-making for optimizing yield and sustainable resource management.

Crop yield prediction, Machine Learning, Random Forest, Support Vector Machine, Linear Regression, Sustainability

"Future Harvests: Predicting Crop Yields", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.b253-b258, May-2024, Available :http://www.jetir.org/papers/JETIR2405134.pdf

"Future Harvests: Predicting Crop Yields", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppb253-b258, May-2024, Available at : http://www.jetir.org/papers/JETIR2405134.pdf