Agriculture is facing significant challenges such as rising food demand, food safety concerns, environmental sustainability issues and climate change, all of which are severely affecting global food security. Currently, over 815 million people are chronically hungry, with nearly 64% of them living in Asia (Friha et al. 2021; Pathak et al. 2020). In traditional farming systems, the late detection of crop stress, diseases and nutrient deficiencies often leads to reduced yield, lower crop quality and inefficient use of resources such as water, fertilizers and pesticides. Therefore, the adoption of modern technologies like drones and machine learning has become essential to improve risk assessment, disaster response and transparent evidence-based decision-making to support vulnerable farmers and enhance food security (Debangshi 2021). In recent years, unmanned aerial vehicles (UAVs) have gained increasing popularity due to their flexibility, ease of operation and ability to capture high spatial resolution data, enabling rapid and non-destructive extraction of crop phenotypic information (Deng et al. 2018). Equipped with RGB, multispectral and thermal sensors, drones generate large volumes of high-resolution data across different crop growth stages and field conditions. These data can be efficiently analyzed using machine learning algorithms such as Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN). This integration enables early detection of crop stress and diseases, accurate yield prediction, improved irrigation scheduling and precise input management. Overall, it enhances productivity, resource-use efficiency and supports sustainable agriculture.