Machine Learning Solutions for Sustainable Rambutan Farming: A Needs Assessment for Disease Detection

The farming of “fruits” is of massive significance to the economy of Conner which is tagged as the “fruit basket of Apayao”; it sustains the people in the community and also creates some business opportunities on the side. However, the fruit faces numerous diseases, reducing its quality and marketability, leading to significant economic losses for farmers and stakeholders. This study conducts a needs analysis to assess the specific challenges local farmers and stakeholders face in disease detection and management practices. The study used a mixed research method participated by 128 local farmers and experts, using surveys and interviews. The study’s findings determined the needs and deficiencies in the areas of knowledge, technology, and resources. Moreover, it also found that traditional methods for disease detection in rambutan fruit involve manual inspection by experts, which is labor-intensive, time-consuming, and subject to human error and often fails to provide timely detection, leading to ineffective disease management strategies. The results obtained will provide a significant input by which smart disease detection systems be suitably designed that meet the particular needs found in Conner, Apayao. This study is the baseline for developing sustainable and profitable rambutan farming in Conner, Apayao by presenting the design of a solution that utilizes machine learning technologies for disease detection and management.