Abstract
In the face of escalating demands for sustainable agriculture, this study introduces an innovative approach by deploying an intelligent monitoring and management system that utilises Internet of Things (IoT) sensors and machine learning algorithms. Focused on enhancing the precision of irrigation and fertilisation in farming, the system collects realtime data on soil moisture, temperature, and other vital parameters. A predictive random forest model, trained on historical crop data and current environmental conditions, analyses this data to accurately forecast water and fertiliser requirements. The model demonstrated an 87.4% accuracy for predicting irrigation needs and 85.7% for fertilisation, significantly optimising resource use and reducing environmental impact. The findings reveal that such technologies promise to revolutionise agricultural practices by making them more efficient and sustainable. They also highlight the challenges in their adoption, including the need for initial investment and overcoming the digital divide. This research underscores the potential of IoT and machine learning in achieving precision agriculture, marking a crucial step towards sustainable farming solutions that cater to the growing global food demands while preserving environmental resources.