Crops growth prediction using machine learning techniques

Abstract

This study explores machine learning for crop growth prediction in Algeria using soil, and crop data. The technique has potential for accurate and efficient yield prediction for effective agricultural planning. Optimal parameter values were identified, emphasizing their importance for different datasets. Results vary depending on data characteristics. Implications for farmers, policymakers, and organizations include improved decision-making and resource allocation for increased production and food security. Further research is needed to evaluate other machine learning techniques for sustainable and resilient agriculture