Machine Learning for Global Food Security: A Concise Overview

Food insecurity has become one of the major global issues in present times. To overcome this, national and international communities have taken various strategies to ensure continuous food production, food supply, and food safety. However, achieving sustainable food security globally is an intricate task, as it depends on several factors, such as rising population, falling water tables, increasing soil erosion, lack of fertile cultivation land, climate change, flattening yields, unethical practices in agriculture, war-threatened supply chain, and short space of time available for preparation. Over the years, several research and development initiatives have been carried out to investigate these issues and mitigate them for moving toward a strong viable food security system. This paper provides a concise overview of the recent advancements in fighting against food insecurity using machine learning (ML) technologies from the perspectives of climate change, sufficient food production, food safety, and nutrient food supply. At last, this paper ends by highlighting the shortcomings of the current approaches and providing future direction in adopting ML for global food security.