Machine learning-based prediction of lettuce growth utilising online environmental datasets

Conventional agriculture struggles to keep pace with the increasing global demand for food while coping with environmental limitations, resource scarcity, and climate variability. Traditional farming practices struggle to optimise crop production sustainably, often resulting in inefficient resource use and reduced crop yields. This paper explores the potential of smart farming technologies, particularly using machine learning, to tackle agricultural challenges and enhance productivity. Using publicly available datasets, this study examined the correlations between environmental parameters such as temperature, light intensity and humidity, to better understand their impact on crop growth and yield. Machine learning techniques were used to analyse, uncover patterns and predict the optimal conditions for crop production. The study demonstrates the effectiveness of data-driven insights in identifying influential environmental variables and optimising farming practices, supporting the case for a transition towards technology-driven agriculture.