Abu Dhabi students develop AI-based solution for food safety, reducing waste – News

The AI ​​model attempts to create a two-way conversation between farmers and supermarkets where both parties would mutually benefit

Two students from the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) have created an algorithm that could revolutionize the agricultural industry in the United Arab Emirates while reducing food waste and improving food safety.

Sarah Al Barri and Mugariya Farooq have developed a machine learning framework to detect plant diseases by taking pictures using a drone and predicting crop yield through key information provided on a mobile app. The artificial intelligence-based solution for the agriculture industry consists of two main parts that work together, the machine learning master’s students said.

“In the first part, computer vision is trained to diagnose diseases at an early stage in plant crops. Because of their popularity, and therefore impact, we chose tomatoes, potatoes and peppers. In the second part, a machine learning model is trained to accurately predict the actual yield of a planted farm. Early disease detection reduces resources such as water, fertilizers and pesticides that could be wasted growing diseased plants,” Al Barri said.

Early disease detection and yield knowledge will help the farming community stabilize the supply and demand of different crops.

“This can let farmers know in advance how much they need to produce so they can allocate and manage their resources accordingly. If supply and demand are equal, prices stabilize. If fruit and vegetable prices don’t fluctuate, supermarkets won’t have to dispose of the huge amounts of food they normally do, thus limiting food waste,” Farooq noted.

The AI ​​model attempts to create a two-way conversation between farmers and supermarkets where both parties would mutually benefit.

“With AI, farmers would be able to have informed and planned financial decisions on which plant to cull early, and how much resources they should invest in planting new crops,” Farooq pointed out.

Explaining how AI can be used in agriculture, Farooq highlighted the role of drones in the project.

“AI models need to be integrated into an infrastructure or tool to be used. Although not yet applied, our suggestion and vision for our AI model is that the task of plant disease detection could be implementation on a drone that takes photos, processes them and provides a comprehensive diagnostic report.For the crop yield prediction task, a mobile application should be developed where a farmer could provide information about the type of crop, water input, fertilizer and pesticide use, and land area, and application output gives the expected yield by region.”

The duo found the sustainable solution for a two-day agricultural hackathon organized by the Abu Dhabi Agriculture and Food Safety Authority (ADAFSA) in November.

READ ALSO :

“The hackathon had two components: analysis of biosecurity readiness and food security. We chose food safety. Our decision was driven by powerful statistics. For example, in the United Arab Emirates, an average person wastes about 224 kg of food every year and we believed that an AI-based solution would be able to solve this problem,” added Farooq.

The project won second place in the agricultural hackathon and pocketed the 30,000 Dh prize. They showcased the solution at the Masdar Innovate booth during Abu Dhabi Sustainability Week and the Global Future Energy Summit, and most recently at the UAE Innovates event at Expo 2020 Dubai.

Earlier this month, Ne’ma, a new national initiative to address the problem of food loss and waste, was launched in the country. It aims to encourage public and private sector entities to collectively address food waste and encourage responsible consumption to preserve food resources for a sustainable future.