+81-70-6442-9514 1-1-1 Midori-cho Nishitokyo-city,Tokyo,188-0002,Japan
  • 日本語

Welcome to Laboratory of Field Phenomics at UTokyo

The current Lab was established in November 2021, with financial support from Sarabetsu Village , Hokkaido.
We are developing algorithms and applications for high throughput and high precision evaluation of the growth and performance of organisms from the cellular level to the population level, using image pattern recognition, machine learning, and sensing technologies. We also contribute to accelerating the social implementation of such new technologies in actual agricultural fields.

Research Topics.

In agricultural research and smart agriculture, methods for collecting, analyzing, and evaluating detailed data on crop growth conditions and growing environments in the field are important fundamental technologies. A research base (University of Tokyo Satellite Office) has been established to promote advanced research in field phenomics, IoT, AI, Big Data, etc. This endowed chair aims to further develop field phenomics and related technologies by building on the achievements there, utilizing the campus for research and education, and taking advantage of the great advantages of the local location, which facilitates joint research with local farmers, related companies, and others. In addition, the foundation for accelerating the social implementation of these applications will be established in a manner that is close to the field. To this end, we will also strengthen collaboration with local farmers, government, and schools.
The main research topics are:

  • Plant phenotyping use image processing and machine learning.
  • Field sensing use IoT, Robot, Tractor, Drone and satellite.
  • Agriculture Big data.

Projects

Current Projects List

01

Research on CPS infrastructure for the creation of big data-driven AI agriculture, AIP, JST'

URL

PI: Prof. Masayuki Hirafuji

02

India-Japan Joint Research Laboratory Programme, SICORP, JST

Data Science-based Farming Support System for Sustainable Crop Production under Climatic Change
PI: Prof. Seishi Ninomiya

URL Video
03

Exploring and Managing human-bee conflict in Asian cities using AI, Google AI for Social Good.

PI: Prof. Wei Guo

URL
04

Machine Learning applied to high–throughput feature extraction from imagery to map spatial variability(GRDC), Australia.

PI: Prof. Wei Guo

URL
05

Redesigning ideal crop canopy architecture using drone-based phenotyping techniques. (JSPS KAKENHI C)

PI: Prof. Wei Guo

URL
06

Smart-breeding system for Innovative Agriculture (grant number: BAC1003) (MAFF)

育種ビッグデータの整備および情報解析技術を活用した高度育種システムの開発.農林水産省(MAFF)

Co-PI: Prof. Wei Guo

URL
07

Research project for technologies to strengthen the international competitiveness of Japan's agriculture and food industry (MAFF)

AIを活用したスマート除草システムの開発.農林水産省(MAFF)

Co-PI: Prof. Wei Guo

URL
08

Construction of modeling method considering the hierarchical structure of data collected on different scales.(NEDO)

Co-PI: Prof. Hiroyoshi Iwata

URL(page 20)
09

戦略的スマート農業技術等の開発・改良-輸出拡大に直結する青果用かんしょの出荷工程における腐敗低減技術の開発.農林水産省(MAFF)

Co-PI: Prof. Wei Guo

URL

Finished Projects List

 Knowledge Discovery by Constructing AgriBigData (CREST)

URL

To be continued

To be continued

Development and demonstration of high-performance rice breeding support pipeline for semiarid area (aXis)

The purpose of this research is to develop and validate high-performance breeding system for a staple food, rice in order to achieve stable and increased productivity even in semi-arid areas of India, where water supply is becoming increasingly unstable due to climate change.

This study consists of the following tasks:
1. Design and implementation of elemental technologies for high performance rice breeding support system
2. Test operation and evaluation of the integrated high-performance rice breeding support system

URL

Research Program on Climate Change Adaptation (RPCCA)

Development of a support system for optimising agricultural production under global environmental change

We develop meteorological models, crop models, soil and water models, etc., to accurately estimate the three factors that determine crop cultivation - weather, soil and water conditions - from downscaling data, and simulate crop yield and quality based on the results. The results of the simulations are then integrated to develop a support system for optimising agricultural production in order to achieve optimal cultivation management (fertiliser, irrigation, timing of cultivation, crop rotation, etc.) that also takes into account profitability at the farm level, and optimal water management at the regional and basin level.

URL Video

Green Network of Excellence - Environmental Information (GRENE-ei)

To be continued

To be continued

URL

Advanced information systems for agriculture, forestry and fisheries

To be continued

To be continued

Multiplication Information Navigator ArgInfo

To be continued

To be contiued

Database model coordination system (DMCS)

To be continued

To be continued

URL

Accelerated Social Return Programme (ASRP)

To be continued

To be continued

Semi-arid area paddy rice breeding efficiency support Construction and verification evaluation of AI ecosystem, JST

Leader: Prof. Seishi Ninomiya

To be continued

Publications

» View more in Zotero

Events

What happens in our Lab

Read more

Members

Professors

Wei GUO (郭威)

PI, Endowed Chair Supervisor, Associate Professor
Research area: Machine Learning, Image processing, Plant Phenotyping
Engaged in research on the development of field sensing techniques using drones and robots, image processing, high-throughput phenotyping algorithms using machine learning and their application in agriculture.

James BURRIDGE

Project Assistant Professor
Research area: Plant and crop physiology, resource acquisition and utilization, phenotypic integration
Specialist in root systems with experience in water acquisition and use dynamics. Committed to applying research advancements to directly impact farmers, accelerating breeding of climate resilient crop varieties and developing more efficient and climate resilient cropping systems.

Pieter BLOK

Project Assistant Professor
Research area: Computer Vision, Deep Learning, Plant Phenotyping, Agricultural Robotics
Expertise in developing and implementing image processing algorithms on agricultural robots and plant phenotyping platforms. Currently, primarily focused on the development of deep learning algorithms in the agricultural domain.

Seishi Ninomiya (二宮正士)

Project Professor, Emeritus professor of UTokyo
Research area: application of information science and technology to crop breeding and research and development of agricultural information systems.
Principal Investigator of JST SICORP "Sustainable Crop Production Support System under Climate Change Enabled by Data Science".

Masayuki Hirafuji (平藤雅之)

Project Professor
Research area: field sensing, AI in agriculture
Principal investigator of the JST AIP accelerator proposal "Research on CPS infrastructure for the creation of big data-driven AI agriculture".
He has been involved in research on artificial intelligence in agriculture, on the analysis and modelling of plants and other complex systems, on closed ecosystem models (soil-grown space farms that protect against radiation and recycle oxygen and water), and on the development of field servers that automatically collect field data and analyse the big data obtained using AI.

(Concurrent )

Hiroyoshi Iwata (岩田洋佳)

Associate Professor
Research area: biometrics, statistical genetics, populaiton genetics, information science
PI of Laboratory of Biometry and Bioinformatics
To support future global population growth, productivity must increase at an accelerated rate through genetic improvements in crops and improved cultivation techniques. In order to tackle these problems, we are conducting methodological and empirical research to extract "knowledge" from a large amount of information on crops, such as genomes, gene expression, cultivation environment data, and image data, in order to improve agricultural productivity.

Awards

Senior Researcher Awards

  • 2022.05 農業情報学会, 新農林社国際賞:郭威.
  • 2020.05 農業情報学会, 学術奨励賞:郭威.
  • 2019.04 国立研究開発法人科学技術振興機構, AIPネットワークラボ長賞:郭威.
  • 2019.09 一般社団法人日本育種学会, 第136回講演会日本育種学会優秀発表賞:郭威, 石川吾郎, 常松浩史, 柳澤貴司, 藤田雅也, 山田哲也, 米丸淳一.
  • 2019.03 公益財団法人計測自動制御学会, SI2018優秀講演賞:野中摂護・二宮正士・郭威・影山颯・長船雅矢.
  • 2016.12 一般社団法人日本育種学会 第130回講演会日本育種学会優秀発表賞:野下浩司・郭威・加賀秋人・岩田洋佳.

Students Awards

  • 2023.08 Fifth International Workshop on Machine Learning for Cyber-Agricultural Systems (MLCAS2023),Best Oral Presentation Award:Tang LI
  • 2021.07 The 8th International Horticulture Research Conference, Second place award for the poster competition: Grison Sylvain, Mayura B. Takada, Yohei Higuchi, Yusei Ishikawa, Yuki G. Baba, Tokihiro Fukatsu, Wei Guo.
  • 2021.05 農業情報学会2021年度年次大会,若手研究者イノベーション賞:王浩舟,加藤洋一郎,郭威.

Access

Institute for Sustainable Agro-ecosystem Services Graduate School of Agricultural and Life Science, The University of Tokyo

Location: (35.736308, 139.539411)

1-1-1 Midori-cho Nishitokyo-city,Tokyo,188-0002,Japan
東京都西東京市緑町1-1-1

Access

Seibu Shinjuku Line:
15 minutes walk from Tanashi Station North Exit.
Take the Seibu Bus from the No. 2 or No. 3 bus stop at the north exit of Tanashi Station.
Bus Stop #3: Tanashi Station (Danchi) bound for Hibarigaoka Station (Tanashi 43) (approx. 15 min. ride), 3 min. walk from Rokkaku Jizo-son-mae Bus Stop.
Bus stop #2: Tanashi Station (Yado) bound for Hibarigaoka Station (Tan42) (approx. 15 min. ride), 5 min. walk from Kitahara 2-chome bus stop.
Seibu Ikebukuro Line:
20 minute walk from the south exit of Hibarigaoka Station.
Take the Seibu bus from the No. 2 or No. 3 bus stop at the south exit of Hibarigaoka Station.
Bus stop #2: Bus bound for Musashi Sakai Station via Danchi (Sakai 04), Bus bound for Tanashi Station via Danchi (Tanashi 43) (approx. 15 min. ride), 3 min. walk from Rokkaku Jizoson-mae Bus Stop.
Bus Stop #3: Bus bound for Musashi Sakai Station via Yado (Sakai 03) (15-minute ride), 5-minute walk from Oyado Bus Stop