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

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...

Full description

Bibliographic Details
Main Authors: Tanaka, Y., Watanabe, T., Katsura, K., Tsujimoto, Y., Takai, T., Tanaka, T.S.T., Kawamura, K., Saito, H., Homma, K., Ahouanton, K., Ibrahim, A., Senthilkumar, K., Semwal, V.K., Matute, E.J.G., Corredor, E., El-Namaky, R., Manigbas, N., Quilang, E.J.P., Iwahashi, Y., Nakajima, K., Takeuchi, E., Saito, K., Mairoua, S.G.
Format: Journal Article
Language:Inglés
Published: Elsevier 2023
Subjects:
Online Access:https://hdl.handle.net/10568/132700
_version_ 1855528256510361600
author Tanaka, Y.
Watanabe, T.
Katsura, K.
Tsujimoto, Y.
Takai, T.
Tanaka, T.S.T.
Kawamura, K.
Saito, H.
Homma, K.
Ahouanton, K.
Ibrahim, A.
Senthilkumar, K.
Semwal, V.K.
Matute, E.J.G.
Corredor, E.
El-Namaky, R.
Manigbas, N.
Quilang, E.J.P.
Iwahashi, Y.
Nakajima, K.
Takeuchi, E.
Saito, K.
Mairoua, S.G.
author_browse Ahouanton, K.
Corredor, E.
El-Namaky, R.
Homma, K.
Ibrahim, A.
Iwahashi, Y.
Katsura, K.
Kawamura, K.
Mairoua, S.G.
Manigbas, N.
Matute, E.J.G.
Nakajima, K.
Quilang, E.J.P.
Saito, H.
Saito, K.
Semwal, V.K.
Senthilkumar, K.
Takai, T.
Takeuchi, E.
Tanaka, T.S.T.
Tanaka, Y.
Tsujimoto, Y.
Watanabe, T.
author_facet Tanaka, Y.
Watanabe, T.
Katsura, K.
Tsujimoto, Y.
Takai, T.
Tanaka, T.S.T.
Kawamura, K.
Saito, H.
Homma, K.
Ahouanton, K.
Ibrahim, A.
Senthilkumar, K.
Semwal, V.K.
Matute, E.J.G.
Corredor, E.
El-Namaky, R.
Manigbas, N.
Quilang, E.J.P.
Iwahashi, Y.
Nakajima, K.
Takeuchi, E.
Saito, K.
Mairoua, S.G.
author_sort Tanaka, Y.
collection Repository of Agricultural Research Outputs (CGSpace)
description 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.
format Journal Article
id CGSpace132700
institution CGIAR Consortium
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1327002025-11-12T04:57:59Z Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images Tanaka, Y. Watanabe, T. Katsura, K. Tsujimoto, Y. Takai, T. Tanaka, T.S.T. Kawamura, K. Saito, H. Homma, K. Ahouanton, K. Ibrahim, A. Senthilkumar, K. Semwal, V.K. Matute, E.J.G. Corredor, E. El-Namaky, R. Manigbas, N. Quilang, E.J.P. Iwahashi, Y. Nakajima, K. Takeuchi, E. Saito, K. Mairoua, S.G. energy data rice food systems 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. 2023 2023-11-03T11:09:42Z 2023-11-03T11:09:42Z Journal Article https://hdl.handle.net/10568/132700 en Open Access application/pdf Elsevier Tanaka, Y., Watanabe, T., Katsura, K., Tsujimoto, Y., Takai, T., Tanaka, T.S.T., Kawamura, K., Saito, H., Homma, K., Mairoua,S.G., Ahouanton, K., Ibrahim, A., Senthilkumar, K., Semwal, V.K., Matute, E.J.G., Corredor, E., El-Namaky, R., Manigbas, N., Quilang, E.J.P,. Iwahashi, Y., Nakajima, K., Takeuchi, E. and Saito, K. 2023. Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images. Plant Phenomics 5:0073.
spellingShingle energy
data
rice
food systems
Tanaka, Y.
Watanabe, T.
Katsura, K.
Tsujimoto, Y.
Takai, T.
Tanaka, T.S.T.
Kawamura, K.
Saito, H.
Homma, K.
Ahouanton, K.
Ibrahim, A.
Senthilkumar, K.
Semwal, V.K.
Matute, E.J.G.
Corredor, E.
El-Namaky, R.
Manigbas, N.
Quilang, E.J.P.
Iwahashi, Y.
Nakajima, K.
Takeuchi, E.
Saito, K.
Mairoua, S.G.
Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images
title Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images
title_full Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images
title_fullStr Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images
title_full_unstemmed Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images
title_short Deep Learning Enables Instant and Versatile Estimation of Rice Yield Using Ground-Based RGB Images
title_sort deep learning enables instant and versatile estimation of rice yield using ground based rgb images
topic energy
data
rice
food systems
url https://hdl.handle.net/10568/132700
work_keys_str_mv AT tanakay deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT watanabet deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT katsurak deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT tsujimotoy deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT takait deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT tanakatst deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT kawamurak deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT saitoh deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT hommak deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT ahouantonk deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT ibrahima deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT senthilkumark deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT semwalvk deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT matuteejg deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT corredore deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT elnamakyr deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT manigbasn deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT quilangejp deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT iwahashiy deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT nakajimak deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT takeuchie deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT saitok deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages
AT mairouasg deeplearningenablesinstantandversatileestimationofriceyieldusinggroundbasedrgbimages