JAN 23, 2022

The Food and Agriculture Organization of the United Nations is a specialized agency of the United Nations that leads international efforts to eliminate hunger and works towards nutrition and food security. It is an organization that is headquartered in Rome, Italy. The aim of this organization is to achieve food security for all and to ensure that people have regular access to enough high-quality food to lead healthy lives. FAO works across 130 countries across the globe.

The FAO is using AI for strengthening global access to agricultural information and knowledge over the Geospatial platform. Machine learning and AI are used in cutting edge qualitative remote sensing in agriculture, to know the world-class cloud computing capabilities, enabling unprecedented cross-sectoral known discovery by integrating data on land, soil, climate, water, fisheries, livestock, crops, forestry, social, trade and economic and much more.

Crops phenology and crop calendar are essential to many agricultural applications. This project uses time-series satellite remote sensing data and auxiliary data to generate crop phenology data and crop calendar, employing machine learning and GEO-AI. There are 2 phases of the project. First, algorithm development is committed in several pilot regions and then a global dataset will be produced.

The Food and Agriculture Organization (FAO) has implemented two programs in which AI increases food security and improves agriculture sustainability, the FAO’s WaPOR portal and the Agriculture Stress Index System (ASIS). Both systems monitor water usage in agriculture in different ways. The FAO’s WaPOR portal monitors water in the Near East and African regions. It does this through open-source technology that gathers massive amounts of data. Simultaneously, the AI analyzes the data to determine the best water use for different crops and regions and uploads the information in real-time. ASIS works similarly to NEWS. It is a satellite system that works as an early detection system for droughts or other water shortages. ASIS breaks down the information from a global standpoint to each country and region. Doing this allows people to be proactive in their preparation for impending droughts by improving water usage and shoring up logistics of moving aid to an area troubled by food shortages, thereby preventing hunger.

FAO has explored the use of AI in fish species identification using Google Cloud AutoML. The Cloud AutoML is a suite of machine learning products that enables developers with limited machine learning expertise to train high-quality models specific to their business needs. It relies on Google’s state-of-the-art transfer learning and neural architecture search technology. After testing different approaches, the FAO CSI team concluded using Google AutoML performed better and was quicker to develop than building the models ourselves even when starting with massively pre-trained models. The team also discovered that good quality data was needed and a good mark-up workflow.

Another exploratory work was using ML to extract objects of interest from remote sensing imagery via a GeoML pipeline. The GeoML pipeline was developed on Google ML and standalone for desktop use. Artificial intelligence is used by FAO to make better use of scarce resources like water and energy. FAO has developed a publicly accessible near real-time database using satellite data that allows monitoring of agricultural water productivity and advanced water management.

Through innovation, technology adoption and mechanization the agri-food systems have managed to survive until now, with a growing fear of whether amidst mounting global challenges (such as climate change, political unrests, etc.) would the food systems cope with increasing food demands. The adoption of technologies, such as AI and machine learning, could improve agricultural productivity. There are claims that AI capabilities could someday exceed human capabilities. As a result, there is a growing call that these new technologies should be researched and be produced in a way that they do not interfere with human rights, are environmentally friendly, and thus not marginalize the poor and most vulnerable. In this vein, FAO is one of the signatories for the “Rome Call for AI Ethics”.

The future of artificial intelligence seems to be bright within the food and agriculture sector and with a likelihood of transforming agri-food systems if upscaled homogeneously. FAO has adopted this technology in the areas highlighted above and the signatory to the Rome call for AI ethics affirms FAOs commitment to adopting sustainable technologies with consideration to the human rights and rights of the poor and the marginalized.