Through the following links, you can move to the menu or to the main text in this page.

Interview with a Scientist who Promotes an Agritech Project Joined by 2,245 Teams Worldwide to Achieve a Safe and Reliable Food Supply

“I Want to Revolutionize Agriculture to Solve Food-related Problems”

As the global population rises, the number of farm workers is declining, and food shortages are becoming a greater concern. Research and development are proceeding into advanced technologies such as ICT and robotics to improve crop yields and quality, and to make farm work more efficient and less labor intensive. These technologies are being proactively introduced into agriculture.

With this in mind, an international project called Global Wheat Dataset led by researchers in agricultural image analysis technology was launched in November 2019. It brings together experts from universities and research institutes in Japan, France, Canada, Switzerland, UK, Australia, and China.

The objective of this project is to create a model*1 that can use AI to automatically measure the number of different types of wheat heads grown in a range of environments so that farmers can predict the growth of wheat in any environmental conditions. We interviewed Assistant Professor Wei Guo of the Institute for Sustainable Agro-ecosystem Services at the University of Tokyo’s Graduate School of Agricultural and Life Sciences, as well as a director from Kubota’s Advanced Systems R&D Center, which cosponsored the project. They explain the significance of the project and their visions for the future of farming.

  1. *1.Specific calculation formulas and methods used for AI output.

A Project to Create Models for Counting Wheat Heads for Future Farming

What was the objective in launching the Global Wheat Dataset project?

“In wheat cultivation and research, we count the number of wheat heads per unit of area to determine the yield. This is mostly done visually, so it requires a lot of time and effort. There has been research into models for automatic measurement of wheat heads, but they are based on limited experimental data, and they lack versatility. Creating a large-scale, highly versatile model for automatic measurement requires instant improvement in the diversity of our data. That is why we launched this project. First, we compiled more than 4,500 images of wheat that we labeled*2 to build a Global Wheat Head Detection dataset*3, and we made this available.

  1. *2.The process of attaching correct answers to data to be used by AI for learning (annotation). For example, images of wheat are labeled with information such as the variety, soil condition, and climate conditions.
  2. *3.A collection of data to be processed by a program.
  • Assistant Professor Wei Guo of the Institute for Sustainable Agro-ecosystem Services at the University of Tokyo’s Graduate School of Agricultural and Life Sciences. He came to Japan in 2006 and completed his doctoral course (Doctor of Agriculture) at the Graduate School of Agricultural and Life Sciences, University of Tokyo in 2014. He has been in his current position since 2019. He specializes in agricultural informatics and plant phenotyping.

This image dataset contains a massive amount of data. What are some of the difficulties you faced when building it?

“The sizes and photographing methods of the images of wheat we collected from various countries were different, so we first had to make the images consistent based on standards we set within the project. We also had to establish criteria for producing the learning data*4, such as whether to include nodules (thornlike projections from the wheat tips) when labeling, or whether to label wheat heads when only part of them is visible. Without production criteria for learning data, we could run into problems such as one researcher labelling things that others did not label. To avoid this, researchers in each country sent labeled data to one another for corrections. They went back and forth many times with the project data to determine the production criteria.”

  1. *4.Data used by AI for learning.
  • Image dataset of wheat heads that have been labeled (photos courtesy of Global Wheat Dataset)

An Engineer Mindset Accelerates Smart Agriculture

This project was launched with the University of Tokyo in Japan, INRAE (National Research Institute for Agriculture, Food and Environment) in France, the University of Queensland in Australia, and the University of Saskatchewan in Canada. Through outreach to various countries and institutions and online promotion, it has expanded to include nine research institutions in seven countries.

Using the Global Wheat Head Detection dataset constructed through international collaborative research by these institutions, Dr. Guo and his team put out a call for models to measure wheat head numbers from images. They sponsored the Global Wheat Head Detection Competition with cash prizes for the most accurate models.

The competition, held from April to August 2020, attracted 2,245 teams from around the world, with teams from Vietnam winning first place, the United States second, and Slovenia third. The top three models will be made open source to be used by various companies and organizations, with the hopes that they will accelerate the use of AI in agriculture.

The Competition Generates a Huge Response.

“Although we promoted the competition at conferences and to the scientific community, I think it helped that we collected the models with Kaggle*5, which is frequented by data scientists from around the world. It was a novel idea to have a competition themed around wheat, since most of them involve cars or people.”

  1. *5.A platform for data science competitions where companies and researchers submit data and data scientists compete to create the best models for them.

What have you gained by holding this competition?

“It was very informative to see the excellent models that the engineers created using their way of thinking. To improve the accuracy of image analysis, it’s important for us to think as engineers would think. If agricultural scientists like us can adopt the engineer way of thinking that data scientists have, I think we will be able to further accelerate agriculture that uses data to predict growth.”

How do you see the project developing from here forward?

“Building the image dataset and holding the competition were steps toward realizing smarter agriculture using AI on farms. To add more diversity to our research, I want to develop future activities by adding members from regions that are not currently participating, such as Africa, South America, and India. In the future, we hope to create a venue for providing big data on agriculture and encourage people in countries and territories throughout the world to take greater interest in farming.”

  • Dr. Guo’s laboratory is building a program that can recognize wheat heads in real time. It learns multiple images of wheat displayed slideshow style on an AI computing platform connected to a camera.

Seeking to Revolutionize Agriculture and Realize “Easier Farming”

This project focuses on wheat, which has an astounding number of both producers and researchers and attracts tremendous interest worldwide. Dr. Guo explains the reason: “We want to revolutionize agriculture by producing research results on a major crop.”

“‘Walking farming,’ which was the work of humans or animals, advanced to ‘sitting farming’ with the advent of tractors. This increased efficiency by tens or hundreds of times. My dream is to launch a revolution toward ‘easier farming’ that takes this even further to enable farm work to be done without even going to the field. Today, even if farmers do their work on tractors, they need to check the status of the field with their eyes. I would like to change the kinds of eyes they use.”

Dr. Guo cites as an example the use of smart glasses. These would allow farmers to see the state of the field from any location and check data analyzing the growth of crops. Based on this information, farmers could tell machines to do work such as spraying chemicals or fertilizers at the appropriate times, and the machines could do this work automatically. This is the future of agriculture he envisions.

What inspired your dream to revolutionize agriculture and change the future of farming?

“I want to solve food-related problems. I talk about starting a revolution, but we need diversity that can be realized in many different countries and territories. What is a diverse revolution? What comes next after tractors? That’s what I have been trying to determine. The technology that would start a revolution has not yet been introduced; and when it is, cooperation of various companies will be essential so that it can be used in various farming circumstances. Kubota is one of those companies. I hope we can combine our cutting-edge knowledge and technologies to achieve the vision of ‘easier agriculture’ that enables stable, high-yield production of safe and secure food in any country or territory.”

  • “I envision farming that people can do even when they are asleep,” Dr. Guo says with a smile.

Kubota Supports Initiatives for a Stable Supply of Safe and Reliable Food

As we confront the challenges that many farmers face, we at Kubota are working to promote Smart Agriculture that will change the future of farming with an approach that combines the use of data with machinery automation. We asked Hiroyuki Araki, General Manager of Advanced Systems R&D Department I in the Advanced Systems R&D Center of the Research and Development Headquarters, about the reasons for co-sponsoring the Global Wheat Dataset.

  • Hiroyuki Araki joined Kubota in 1989, starting his career at Kubota Computer Inc. He now leads advanced research into Smart Agriculture for the globe as the General Manager of Advanced Systems R&D Department I in the Advanced Systems R&D Center.

Why did Kubota decide to cosponsor the Global Wheat Dataset project?

“The research being conducted with the Global Wheat Dataset project is part of what is necessary to make agricultural machinery more intelligent in terms of assessing the growth of crops and performing the work needed at each step. This is in line with Kubota’s vision for the future of farming – providing a stable supply of safe and reliable food. The image dataset created for this project along with the models that won the competition will be made open source so they can serve as a common platform that people involved in farming around the world can use to improve agriculture. And the efforts to build this common platform are being supported by Kubota in the form of sponsorship.”

How will the results of this project, including the image dataset and the wheat head detection model, be utilized by companies?

“In addition to using the open source models and image datasets, we can apply these outstanding modeling methods and image dataset labeling techniques to our own development. And by using this dataset and its massive amount of data, we could dramatically accelerate data processing speed. For example, crop growth data collected over many years based on location information can be analyzed from multiple angles, including soil and climate conditions and watering methods, to predict crop growth with greater accuracy. This can help AI suggest what farming work needs to be done next. This is the vision for data-driven precision agriculture that we aim for at the Advanced Systems R&D Center. Another benefit is the ability to work closely with smart agriculture researchers around the world and experience the latest global technologies they are studying.”

Aiming for Automation of Integrated Farming Systems

Given the global decline in farming populations and the growing sense of crisis about food shortages due to population growth, efforts like this project are under way throughout the world to make proactive use of the latest IT advancements in agriculture.

For example, there are robots that use machine learning to automatically determine the ripeness and size of fruits such as strawberries and apples. There are also applications that can let farmers know the nutrients of crops and if they need added fertilizer just by holding a smartphone over them. All kinds of smart apps are emerging that can help solve farming-related issues with technology. The global market for so-called “agritech” is predicted to grow by an average of over 18% from 2019 to 2025. In the midst of this global trend, Kubota is looking toward the next steps for realizing the future of farming through collaborations with global networks such as this project.

“Kubota has globalized based on technologies that have produced products with high quality and durability and has realized the automation of farming through its in-house efforts. The next step is to automate integrated agriculture systems for local crops in different areas. To enable more intelligent agricultural machinery and provide a stable supply of safe and reliable crops in every region, we need the most advanced ICT and AI technologies, including systems and algorithms that can handle huge amounts of data. As part of our open innovation, I want us to integrate the areas Kubota excels at with those of our external partners such as research institutes and universities to realize automation of integrated agricultural systems.”

  • Mr. Araki shares his hopes for future developments: “We could build a network with research institutes around the world that are part of the Global Wheat Dataset project, and exchange information on what advanced technologies to study next. Those are some of the developments I’m considering.”

The notion that it is too difficult to introduce advanced technologies such as ICT and AI to agriculture is outdated. Today, the use of advanced technologies in farming is accelerating all over the world. Given this backdrop, Kubota is supporting the Global Wheat Dataset project, which was launched with the goal of solving food problems and further advancing agriculture, as a partner aiming to ensure a stable supply of safe and reliable food. By applying advanced technologies to farming with the world’s top scientists, as this project does, we can make greater advancements in the field of agriculture, bringing further growth in its potential as well as connections across the world.

From Kubota Press (Japan)
Kubota Press (Japan) is Kubota’s owned media that covers the fields of food, water, and the environment from the perspectives of people, technology, and communities to convey where Kubota is today and give a realistic picture of where we work.