A world hunger crisis has risen since 2019 when COVID-19 hit the world. This pandemic has shifted this generation back in time, and now it is very important to be involved in new techniques that are effective in terms of better yield with less toxins. With the rate at which the population is growing, it is expected that by the year 2050, the world population would cross 9 billion. This exponential rise would require the food production to rise by 70 to 80%. This is a matter of concern for agriculture and food industries. As the world is in the fourth industrial revolution, it is the need of the hour to embed artificial intelligence and machine learning algorithms with agriculture. This research aims to accumulate different methodologies that are present and come up with a critical analysis. These methodologies have the capability to increase the yield, predict the diseases, and even increase the safety and help enhance traceability.
TopIntroduction
To feed 9-10 billion people by 2050, global food production is estimated to need to rise by 60–110% (Krishna, 2016; Rockstrom et al., 2017). As a result, agriculture's long-term viability is critical to ensuring food security and to eradicate hunger for the world's ever-increasing population. Furthermore, a well-written system involving traceability has become a necessity for controlling quality in the food chain as a result of various food safety scandals and accidents in the food business, such as bovine spongiform encephalopathy and dioxin in poultry (Ben-Ayed et al., 2013). Furthermore, weather and climate change circumstances, as well as long-term water management due to shortage, will be major issues in the coming years. For these reasons, a deliberate shift away from the existing paradigm of increased agricultural output and toward agricultural sustainability is urgently required. Helping farmers and stakeholders make better decisions by adopting sustainable agriculture practises, particularly through the use of digital technologies such as the Internet of Things (IoT), Artificial Intelligence (AI), and cloud computing, is a critical choice for anticipating efficient solutions. Additionally, AI components (machine and deep learning algorithms) are frequently integrated with location intelligence technology. The purpose of this research is to highlight the most important uses of artificial intelligence and machine learning in the agri-food industry.
AI technology has just been available for use in the agri-food industry. In reality, AI approaches contribute significantly to understanding a model's identification, service generation, and decision-making processes as well as support for various agri-food applications and supply chain stages. In agriculture, the main purpose of AI is to give accuracy and anticipating decisions in order to increase productivity while preserving resources.(Patel et al., 2021)
The Food demand is expected to rise from 60% to 97% percent by 2050 as the world's population grows (Suchithra & Pai, 2020). Thus, AI has been used to meet this food demand in areas such as supply chain management, food sorting, production development, food quality enhancement, and adequate industrial hygiene.(Ahumada & Villalobos, 2009; Ben Ayed et al., 2017; Kamilaris & Prenafeta-Boldú, 2018) Food safety has been identified as one of the most pressing challenges in the food business, prompting the development of smart packaging technologies to meet the requirements of the food supply chain. The state of foods is monitored through intelligent packaging, which provides details on the food's quality while in storage and transportation (Gaurav et al., 2019). Another study looked into intelligent packaging as a method for reducing food waste, and found that there have been roughly 45 recent improvements in the field of optical systems for freshness monitoring.