ID | 66235 |
FullText URL | |
Author |
Tanaka, Yu
Graduate School of Environmental, Life, Natural Science and Technology, Okayama University
Watanabe, Tomoya
Graduate School of Mathematics, Kyushu University
Katsura, Keisuke
Graduate School of Agriculture, Tokyo University of Agriculture and Technology
Tsujimoto, Yasuhiro
Japan International Research Center for Agricultural Sciences
Takai, Toshiyuki
Japan International Research Center for Agricultural Sciences
Tanaka, Takashi Sonam Tashi
Graduate School of Environmental, Life, Natural Science and Technology, Okayama University
Kawamura, Kensuke
Japan International Research Center for Agricultural Sciences
Saito, Hiroki
Tropical Agriculture Research Front, Japan International Research Center for Agricultural Sciences
Homma, Koki
Graduate School of Agricultural Science, Tohoku University
Mairoua, Salifou Goube
Africa Rice Center (AfricaRice)
Ahouanton, Kokou
Africa Rice Center (AfricaRice)
Ibrahim, Ali
Africa Rice Center (AfricaRice), Regional Station for the Sahel
Senthilkumar, Kalimuthu
Africa Rice Center (AfricaRice)
Semwal, Vimal Kumar
Africa Rice Center (AfricaRice), Nigeria Station
Matute, Eduardo Jose Graterol
Latin American Fund for Irrigated Rice - The Alliance of Bioversity International and CIAT
Corredor, Edgar
Latin American Fund for Irrigated Rice - The Alliance of Bioversity International and CIAT
El-Namaky, Raafat
Rice Research and Training Center, Field Crops Research Institute, ARC
Manigbas, Norvie
Philippine Rice Research Institute (PhilRice)
Quilang, Eduardo Jimmy P.
Philippine Rice Research Institute (PhilRice)
Iwahashi, Yu
Graduate School of Agriculture, Kyoto University
Nakajima, Kota
Graduate School of Agriculture, Kyoto University
Takeuchi, Eisuke
Graduate School of Agriculture, Kyoto University
Saito, Kazuki
Graduate School of Agriculture, Kyoto University
|
Abstract | 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.
|
Published Date | 2023-07-28
|
Publication Title |
Plant Phenomics
|
Volume | volume5
|
Publisher | American Association for the Advancement of Science (AAAS)
|
Start Page | 0073
|
ISSN | 2643-6515
|
Content Type |
Journal Article
|
language |
English
|
OAI-PMH Set |
岡山大学
|
Copyright Holders | © 2023 Yu Tanaka et al.
|
File Version | publisher
|
DOI | |
Web of Science KeyUT | |
Related Url | isVersionOf https://doi.org/10.34133/plantphenomics.0073
|
License | https://creativecommons.org/licenses/by/4.0/
|
Citation | Yu Tanaka, Tomoya Watanabe, Keisuke Katsura, Yasuhiro Tsujimoto, Toshiyuki Takai, Takashi Sonam Tashi Tanaka, Kensuke Kawamura, Hiroki Saito, Koki Homma, Salifou Goube Mairoua, et al. Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images. Plant Phenomics. 2023;5:0073.DOI:10.34133/plantphenomics.0073
|
Funder Name |
European Union and International Fund for Agricultural Development (IFAD)
CGIAR Research Program (CRP) on rice agri-food systems
Japan Society for the Promotion of Science
JICA/JST SATREPS
|
助成番号 | 19H02939
20H02968
21K19104
JPMJSA1608
|