BreakThrough Study Idea

Data acquisition is barrier of agricultural development. Overseas that strength is intellectual propertyMasayuki Hirafuji<Series 2 / complete>

Study Idea


  • facebook
  • twitter

Agriculture where there are no time series data and unsolved problems mount

In the second half of the first round, I talked about "Agriculture is difficult." What is the reason? That is because the number of data required for agriculture is enormous. Also, the number of variables is enormous. There are many factors to think about, such as disease and regionality, consumer preferences, economic fluctuations. Previous agriculture has relied on intuition and experience. Since there was no data, it is a matter of necessity to do so.

Furthermore, in agriculture, unknown challenges are piled up. Even when new herbicides and pesticides are developed, resistant weeds and microorganisms will appear in no time. The speed of its evolution is too early. Why is this happening? It is doubtful to be explained by Darwin's theory of evolution. It is also the hybrid stress. Hybrid strain stress means that multiplication of genetically distant varieties and certain varieties indicate that an F1 that is good will be born, but I do not know why children who exceed their parents' abilities appear.

In some areas of Hokkaido, there are farmers growing only wheat. In agriculture, there is a problem of continuous disorder that makes it easier to get sick if only the same crop is cultivated every year, but there is no constant disorder there. But, because there is no data, experts do not know the reason.
In agriculture, we have no choice but to produce with unknown things left behind. Eventually, it became commonplace, but what we do not understand is hard to improve.

To clarify these phenomena, time series data is useful. Taking evidence continuously at regular intervals, but this is very difficult. We need to withstand harsh heat and cold, typhoons, etc. and keep data consistently for years or decades. Therefore, the field server developed in 2001 was established. This is an outdoor sensing IoT device with weather resistance against harsh outdoor environments. You can gather data such as images, temperature, humidity, solar radiation, soil moisture content, and soil temperature unattended, and collect vast amounts of data in real time via the Internet. However, there was a problem in the operational environment even though the equipment could be made. Farmers had no network infrastructure. For that reason, we have overcome it by constructing a network infrastructure that relays wireless LANs on our own.

After that, we created a field server (developed since around 2009) that made the specification open source, so that everyone can efficiently collect data. The one with the smallest configuration is a simple one that can only measure soil moisture and soil temperature, but developed from the feeling that agriculture will change if farmers can easily measure themselves freely. The communication environment also improved considerably compared with around 2001. Moreover, a new communication technology (LoRa) that can communicate over a long distance spreads, even if the height of the antenna is low, communication has become possible far enough. In the past, it was necessary to make the height of the antenna considerably higher than the crop so that radio waves are not blocked by plants. When the position of the antenna is raised, since the housing becomes long and hits the boom of the boom sprayer (Pesticide spreader), it has to be removed every time pesticide spraying is done and then it has to be installed again.

Open field server with shorter enclosure height in Lora

From DNA to traits. Overseas develop the next agricultural business

The breed improvement that is the core of the intellectual property business in agriculture is accelerated by the use of ICT and abroad are one step ahead. Also, the various intellectual property is produced in the processing of seeds. Taking "Tensai" as an example, while Japanese organizations are stopped by breeding, overseas do chemical treatment and temperature treatment called priming and furthermore coat the seeds with fungicides and useful microorganisms alive, and they are raising the added value of grains. This kind of therapy brings about various benefits such as prevention of diseases and promotion of growth. The seeds can be sold by orders of magnitude higher by intellectual property such as new varieties and priming, bringing huge profits.

The cost performance of "DNA sequencer" of DNA reading device is up at twice the pace of Moore's law in semiconductors. At present, DNA such as microorganisms can be read at a low cost of several thousand yen, and this field has come to a stage where it can no longer be profitable by DNA analysis alone. Therefore, overseas who have invested large amounts of funds in biotechnology research are focusing on traits (phenotype, nature, and characteristics of organisms). DNA data cannot be utilized without the trait data in the first place, but the trait data is still minimal. In the future, you will earn skills to quickly gather data on traits useful for agriculture such as 'weak to disease' and 'high yield.' Indeed, many overseas ventures have entered. In agriculture exhibitions such as Europe, investments in this field have become conspicuous. Since DNA data has already been stocked in massive amounts, overseas forces are aiming for the next business opportunity called "Trait." However, it is regrettable that there is little such information in Japan and it has not become a topic.

Next time I will explain about agricultural data acquisition efforts and unmanned agriculture.

< series 2 / complete >

Masayuki Hirafuji
University of Tokyo graduate school Agricultural Life Science Graduate School attached Ecological Harmonization Agriculture Organization International Field Phenomenic Research Base Appointed Professor Dream Science Holdings Co., Ltd. · CEO

1983 Graduated from the University of Tokyo Life Science course. He experiences such as Ministry of Agriculture, Forestry and Fisheries · Agricultural Research Center (Current Agricultural Research Organization) Chief Researcher, Research Agency for Agriculture, Forestry and Fisheries Technology Conference Secretariat, and Director of Agricultural Research Institute so far. He specializes in computational biology, modeling and measurement control of biological and ecological systems, research on space farms, comfortable living spaces, using IT, complex systems, artificial ecosystem technology.

◇Main book
"Bioexpert systems - AI/neurocomputing in biological production" (Corona Inc.) published in April 1990

share by SNS

related article