Updated on 2025/08/19

写真a

 
中嶌 洸太
 
Organization
Faculty of Environmental, Life, Natural Science and Technology Special-Appointment Assistant Professor
Position
Special-Appointment Assistant Professor
External link

Research Interests

  • Above-ground biomass

  • Image analysis

  • Deep learning

  • Phenotyping

Education

  • Kyoto University   大学院農学研究科   農学専攻

    2022.4 - 2025.3

      More details

    Country: Japan

    Notes: 博士課程

    researchmap

  • Kyoto University   大学院農学研究科   農学専攻

    2020.4 - 2022.3

      More details

    Country: Japan

    Notes: 修士課程

    researchmap

Research History

  • Japan Society for the Promotion of Science   特別研究員DC2

    2024.4 - 2025.3

      More details

    Country:Japan

    researchmap

  • 京都大学大学院

    2022.4 - 2024.3

      More details

    Country:Japan

    researchmap

Professional Memberships

  • Crop Science Society of Japan

    2020.1

      More details

 

Papers

  • Robustness of the RGB image-based estimation for rice above-ground biomass by utilizing the dataset collected across multiple locations Reviewed

    Kota Nakajima, Kazuki Saito, Yasuhiro Tsujimoto, Toshiyuki Takai, Atsushi Mochizuki, Tomoaki Yamaguchi, Ali Ibrahim, Salifou Goube Mairoua, Bruce Haja Andrianary, Keisuke Katsura, Yu Tanaka

    Smart Agricultural Technology   11   100998 - 100998   2025.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Elsevier BV  

    DOI: 10.1016/j.atech.2025.100998

    researchmap

  • Biomass estimation of World rice (Oryza sativa L.) core collection based on the convolutional neural network and digital images of canopy

    Kota Nakajima, Yu Tanaka, Keisuke Katsura, Tomoaki Yamaguchi, Tomoya Watanabe, Tatsuhiko Shiraiwa

    Plant Production Science   26 ( 2 )   187 - 196   2023

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1080/1343943X.2023.2210767

    Scopus

    researchmap

  • Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images. International journal

    Yu Tanaka, Tomoya Watanabe, Keisuke Katsura, Yasuhiro Tsujimoto, Toshiyuki Takai, Takashi Sonam Tashi Tanaka, Kensuke Kawamura, Hiroki Saito, Koki Homma, Salifou Goube Mairoua, Kokou Ahouanton, Ali Ibrahim, Kalimuthu Senthilkumar, Vimal Kumar Semwal, Eduardo Jose Graterol Matute, Edgar Corredor, Raafat El-Namaky, Norvie Manigbas, Eduardo Jimmy P Quilang, Yu Iwahashi, Kota Nakajima, Eisuke Takeuchi, Kazuki Saito

    Plant phenomics (Washington, D.C.)   5   0073 - 0073   2023

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Rice (Oryza sativa L.) is one of the most important cereals, which provides 20% of the world's food energy. However, its productivity is poorly assessed especially in the global South. Here, we provide a first study to perform a deep-learning-based approach for instantaneously estimating rice yield using red-green-blue images. During ripening stage and at harvest, over 22,000 digital images were captured vertically downward over the rice canopy from a distance of 0.8 to 0.9 m at 4,820 harvesting plots having the yield of 0.1 to 16.1 t·ha-1 across 6 countries in Africa and Japan. A convolutional neural network applied to these data at harvest predicted 68% variation in yield with a relative root mean square error of 0.22. The developed model successfully detected genotypic difference and impact of agronomic interventions on yield in the independent dataset. The model also demonstrated robustness against the images acquired at different shooting angles up to 30° from right angle, diverse light environments, and shooting date during late ripening stage. Even when the resolution of images was reduced (from 0.2 to 3.2 cm·pixel-1 of ground sampling distance), the model could predict 57% variation in yield, implying that this approach can be scaled by the use of unmanned aerial vehicles. Our work offers low-cost, hands-on, and rapid approach for high-throughput phenotyping and can lead to impact assessment of productivity-enhancing interventions, detection of fields where these are needed to sustainably increase crop production, and yield forecast at several weeks before harvesting.

    DOI: 10.34133/plantphenomics.0073

    PubMed

    researchmap

MISC

  • Improving the accuracy of growth estimation using UAV aerial images by utilizing data augmentation with reconstruction of pseudo-canopy data

    山内陽広, 山口友亮, 中嶌洸太, 田中佑, 桂圭佑

    日本作物学会講演会要旨集   257th   2024

  • Construction of Deep Learning-Based Estimation Model for the Days Before Heading of Rice Using Image Analysis

    田村拓巳, 中嶌洸太, 田中佑, 白岩立彦

    日本作物学会講演会要旨集   257th   2024

  • Development of a diagnostic technique for fertilizer application using a rice biomass estimation model based on deep learning

    望月篤, 中嶌洸太, 田中佑, 中村充明

    日本作物学会関東談話会報(Web)   38   2023

  • Time-course genome wide association study for the photosynthetic induction in rice

    谷吉和貴, 中嶌洸太, 西村和紗, 田中佑, 白岩立彦

    日本作物学会講演会要旨集   256th   2023

  • Effect of labor-saving addition of training data by pseudo-labeling on the versatility of deep learning-based estimation model for rice biomass

    中嶌洸太, 田中佑, 桂圭佑, 山口友亮, 齋藤和樹, 齋藤和樹, 齋藤和樹, 辻本泰弘, 渡邊智也, 望月篤, 白岩立彦

    日本作物学会講演会要旨集   256th   2023

  • Construction of deep learning-based estimation model for rice biomass and its robustness to shooting time and lack of hills

    中嶌洸太, 田中佑, 桂圭佑, 山口友亮, 齋藤和樹, 齋藤和樹, 辻本泰弘, 渡邊智也, 白岩立彦

    日本作物学会講演会要旨集   254th   2022

  • Estimation of rice biomass using deep learning-based model for cultivars having diverse plant types

    中嶌洸太, 田中佑, 桂圭佑, 山口友亮, 白岩立彦

    日本作物学会講演会要旨集   251st   2021

  • Deep learning-based robust estimation for rice biomass using digital image of canopy

    中嶌洸太, 田中佑, 田中佑, 桂圭佑, 白岩立彦

    日本作物学会講演会要旨集   249th   2020

▼display all

Awards

  • Presentation Award (Oral)

    2021.9   The 10th Asian Crop Science Association Conference   Deep Learning-Based Robust Estimation for Rice Biomass Using Digital Image of Canopy

     More details