Deep learning-based estimation of rice yield using RGB image

Crop productivity is poorly assessed globally. Here, we provide a deep learning-based approach for estimating rice yield using RGB images. During ripening stage and at harvest, over 22,000 digital images were captured vertically downwards over the rice canopy from a distance of 0.8 to 0.9 m, and r...

Descripción completa

Detalles Bibliográficos
Autores principales: Tanaka, Y, Watanabe, T., Katsura, K., Tsujimoto, Y., Takai, T., Tanaka, T., Kawamura, K., Saito, H., Homma, K., Mairoua, S., Ahouanton, K., Ibrahim, A., Senthilkumar, Kalimuthu, Semwal, V., Corredor, E., El-Namaky, R., Manigbas,N., Quilang, E.J.P., Iwahashi, Y., Nakajima, K., Takeuchi, E., Saito, Kazuki
Formato: Preprint
Lenguaje:Inglés
Publicado: Research Square Platform LLC 2021
Materias:
Acceso en línea:https://hdl.handle.net/10568/125823
_version_ 1855525221131354112
author Tanaka, Y
Watanabe, T.
Katsura, K.
Tsujimoto, Y.
Takai, T.
Tanaka, T.
Kawamura, K.
Saito, H.
Homma, K.
Mairoua, S.
Ahouanton, K.
Ibrahim, A.
Senthilkumar, Kalimuthu
Semwal, V.
Corredor, E.
El-Namaky, R.
Manigbas,N.
Quilang, E.J.P.
Iwahashi, Y.
Nakajima, K.
Takeuchi, E.
Saito, Kazuki
author_browse Ahouanton, K.
Corredor, E.
El-Namaky, R.
Homma, K.
Ibrahim, A.
Iwahashi, Y.
Katsura, K.
Kawamura, K.
Mairoua, S.
Manigbas,N.
Nakajima, K.
Quilang, E.J.P.
Saito, H.
Saito, Kazuki
Semwal, V.
Senthilkumar, Kalimuthu
Takai, T.
Takeuchi, E.
Tanaka, T.
Tanaka, Y
Tsujimoto, Y.
Watanabe, T.
author_facet Tanaka, Y
Watanabe, T.
Katsura, K.
Tsujimoto, Y.
Takai, T.
Tanaka, T.
Kawamura, K.
Saito, H.
Homma, K.
Mairoua, S.
Ahouanton, K.
Ibrahim, A.
Senthilkumar, Kalimuthu
Semwal, V.
Corredor, E.
El-Namaky, R.
Manigbas,N.
Quilang, E.J.P.
Iwahashi, Y.
Nakajima, K.
Takeuchi, E.
Saito, Kazuki
author_sort Tanaka, Y
collection Repository of Agricultural Research Outputs (CGSpace)
description Crop productivity is poorly assessed globally. Here, we provide a deep learning-based approach for estimating rice yield using RGB images. During ripening stage and at harvest, over 22,000 digital images were captured vertically downwards over the rice canopy from a distance of 0.8 to 0.9 m, and rice yields were obtained in the corresponding area ranging from 0.1 and 16.1 t ha −1 . A convolutional neural network (CNN) applied to these data at harvest predicted 70% variation in rice yield with a relative root mean square error (rRMSE) of 0.22. Images obtained during the ripening stage can also be used to forecast the final rice yield. Our work suggests that this low-cost, hands-on, and rapid approach can provide a breakthrough solution to assess the impact of productivity-enhancing interventions and identify fields where these are needed to sustainably increase crop production
format Preprint
id CGSpace125823
institution CGIAR Consortium
language Inglés
publishDate 2021
publishDateRange 2021
publishDateSort 2021
publisher Research Square Platform LLC
publisherStr Research Square Platform LLC
record_format dspace
spelling CGSpace1258232024-11-13T09:00:15Z Deep learning-based estimation of rice yield using RGB image Tanaka, Y Watanabe, T. Katsura, K. Tsujimoto, Y. Takai, T. Tanaka, T. Kawamura, K. Saito, H. Homma, K. Mairoua, S. Ahouanton, K. Ibrahim, A. Senthilkumar, Kalimuthu Semwal, V. Corredor, E. El-Namaky, R. Manigbas,N. Quilang, E.J.P. Iwahashi, Y. Nakajima, K. Takeuchi, E. Saito, Kazuki crop yield rice crop production Crop productivity is poorly assessed globally. Here, we provide a deep learning-based approach for estimating rice yield using RGB images. During ripening stage and at harvest, over 22,000 digital images were captured vertically downwards over the rice canopy from a distance of 0.8 to 0.9 m, and rice yields were obtained in the corresponding area ranging from 0.1 and 16.1 t ha −1 . A convolutional neural network (CNN) applied to these data at harvest predicted 70% variation in rice yield with a relative root mean square error (rRMSE) of 0.22. Images obtained during the ripening stage can also be used to forecast the final rice yield. Our work suggests that this low-cost, hands-on, and rapid approach can provide a breakthrough solution to assess the impact of productivity-enhancing interventions and identify fields where these are needed to sustainably increase crop production 2021-10-29 2022-12-07T08:57:15Z 2022-12-07T08:57:15Z Preprint https://hdl.handle.net/10568/125823 en Open Access Research Square Platform LLC Tanaka, Y., Watanabe, T., Katsura, K., Tsujimoto, Y., Takai, T., Tanaka, T., Kawamura, K., Saito, H., Homma, K., Mairoua, S., Ahouanton, K., Ibrahim, A., Senthilkumar, K., Semwal, V., Corredor, E., El-Namaky, R., Manigbas, N., Quilang, E., Iwahashi, Y., Nakajima, K., Takeuchi, E. and Saito, K. 2021. Deep learning-based estimation of rice yield using, RGB image. Preprint
spellingShingle crop yield
rice
crop production
Tanaka, Y
Watanabe, T.
Katsura, K.
Tsujimoto, Y.
Takai, T.
Tanaka, T.
Kawamura, K.
Saito, H.
Homma, K.
Mairoua, S.
Ahouanton, K.
Ibrahim, A.
Senthilkumar, Kalimuthu
Semwal, V.
Corredor, E.
El-Namaky, R.
Manigbas,N.
Quilang, E.J.P.
Iwahashi, Y.
Nakajima, K.
Takeuchi, E.
Saito, Kazuki
Deep learning-based estimation of rice yield using RGB image
title Deep learning-based estimation of rice yield using RGB image
title_full Deep learning-based estimation of rice yield using RGB image
title_fullStr Deep learning-based estimation of rice yield using RGB image
title_full_unstemmed Deep learning-based estimation of rice yield using RGB image
title_short Deep learning-based estimation of rice yield using RGB image
title_sort deep learning based estimation of rice yield using rgb image
topic crop yield
rice
crop production
url https://hdl.handle.net/10568/125823
work_keys_str_mv AT tanakay deeplearningbasedestimationofriceyieldusingrgbimage
AT watanabet deeplearningbasedestimationofriceyieldusingrgbimage
AT katsurak deeplearningbasedestimationofriceyieldusingrgbimage
AT tsujimotoy deeplearningbasedestimationofriceyieldusingrgbimage
AT takait deeplearningbasedestimationofriceyieldusingrgbimage
AT tanakat deeplearningbasedestimationofriceyieldusingrgbimage
AT kawamurak deeplearningbasedestimationofriceyieldusingrgbimage
AT saitoh deeplearningbasedestimationofriceyieldusingrgbimage
AT hommak deeplearningbasedestimationofriceyieldusingrgbimage
AT mairouas deeplearningbasedestimationofriceyieldusingrgbimage
AT ahouantonk deeplearningbasedestimationofriceyieldusingrgbimage
AT ibrahima deeplearningbasedestimationofriceyieldusingrgbimage
AT senthilkumarkalimuthu deeplearningbasedestimationofriceyieldusingrgbimage
AT semwalv deeplearningbasedestimationofriceyieldusingrgbimage
AT corredore deeplearningbasedestimationofriceyieldusingrgbimage
AT elnamakyr deeplearningbasedestimationofriceyieldusingrgbimage
AT manigbasn deeplearningbasedestimationofriceyieldusingrgbimage
AT quilangejp deeplearningbasedestimationofriceyieldusingrgbimage
AT iwahashiy deeplearningbasedestimationofriceyieldusingrgbimage
AT nakajimak deeplearningbasedestimationofriceyieldusingrgbimage
AT takeuchie deeplearningbasedestimationofriceyieldusingrgbimage
AT saitokazuki deeplearningbasedestimationofriceyieldusingrgbimage