Integrated phenology and climate in rice yields prediction using machine learning methods

Rice (Oryza sativa L.) is a staple cereal crop and its demand is substantially increasing with the growth of the global population. Precisely predicting rice yields are of vital importance to ensure the food security in countries like China, where rice accounts for one-fifth of the total agricultura...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yahui Guo, Yongshuo Fu, Fanghua Hao, Xuan Zhang, Wenxiang Wu, Xiuliang Jin, Christopher Robin Bryant, J. Senthilnath
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Early mature rice Machine learning (ML) methods Multiple linear regression (MLR) Rice yield prediction Phenology Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/681319c8e6d3410cbf182d64fffda8c6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:681319c8e6d3410cbf182d64fffda8c6
record_format	dspace
spelling	oai:doaj.org-article:681319c8e6d3410cbf182d64fffda8c62021-12-01T04:29:49ZIntegrated phenology and climate in rice yields prediction using machine learning methods1470-160X10.1016/j.ecolind.2020.106935https://doaj.org/article/681319c8e6d3410cbf182d64fffda8c62021-01-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X20308748https://doaj.org/toc/1470-160XRice (Oryza sativa L.) is a staple cereal crop and its demand is substantially increasing with the growth of the global population. Precisely predicting rice yields are of vital importance to ensure the food security in countries like China, where rice accounts for one-fifth of the total agricultural production. Previous studies found that the rice yields had been significantly impacted by climate change. In addition, phenological variables were found to be important factors concerning rice yields due to its fundamental role in carbon allocation between plant organs, but its impacts on rice yields were seldom evaluated. In this study, eleven combinations of phenology, climate and geography data were tested to predict the site-based rice yields using a traditional regression-based method (MLR, multiple linear regression), and more advanced three machine learning (ML) methods: backpropagation neural network (BP), support vector machine (SVM) and random forest (RF). The results showed that ML methods were more precise than MLR method. The combination using the integrated phenology, climate during growing season and geographical information was better for yields predictions than other combinations across the ML methods, e.g. the difference RMSE (R2) between prediction and observed rice yields were 800 (0.24), 737 (0.33), and 744 (0.31) kg/ha for BP, SVM and RF, respectively. The SVM had achieved the highest precisions in yield predictions and the phenological variables substantially improved the accuracy of yield predictions, and the relative importance of phenological variables were even similar as climatic variables. We highlight the phenology and climate need to be accurately represented in the crop models to improve the accuracy in rice yield prediction under climate change conditions using integrated ML methods.Yahui GuoYongshuo FuFanghua HaoXuan ZhangWenxiang WuXiuliang JinChristopher Robin BryantJ. SenthilnathElsevierarticleEarly mature riceMachine learning (ML) methodsMultiple linear regression (MLR)Rice yield predictionPhenologyEcologyQH540-549.5ENEcological Indicators, Vol 120, Iss , Pp 106935- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Early mature rice Machine learning (ML) methods Multiple linear regression (MLR) Rice yield prediction Phenology Ecology QH540-549.5
spellingShingle	Early mature rice Machine learning (ML) methods Multiple linear regression (MLR) Rice yield prediction Phenology Ecology QH540-549.5 Yahui Guo Yongshuo Fu Fanghua Hao Xuan Zhang Wenxiang Wu Xiuliang Jin Christopher Robin Bryant J. Senthilnath Integrated phenology and climate in rice yields prediction using machine learning methods
description	Rice (Oryza sativa L.) is a staple cereal crop and its demand is substantially increasing with the growth of the global population. Precisely predicting rice yields are of vital importance to ensure the food security in countries like China, where rice accounts for one-fifth of the total agricultural production. Previous studies found that the rice yields had been significantly impacted by climate change. In addition, phenological variables were found to be important factors concerning rice yields due to its fundamental role in carbon allocation between plant organs, but its impacts on rice yields were seldom evaluated. In this study, eleven combinations of phenology, climate and geography data were tested to predict the site-based rice yields using a traditional regression-based method (MLR, multiple linear regression), and more advanced three machine learning (ML) methods: backpropagation neural network (BP), support vector machine (SVM) and random forest (RF). The results showed that ML methods were more precise than MLR method. The combination using the integrated phenology, climate during growing season and geographical information was better for yields predictions than other combinations across the ML methods, e.g. the difference RMSE (R2) between prediction and observed rice yields were 800 (0.24), 737 (0.33), and 744 (0.31) kg/ha for BP, SVM and RF, respectively. The SVM had achieved the highest precisions in yield predictions and the phenological variables substantially improved the accuracy of yield predictions, and the relative importance of phenological variables were even similar as climatic variables. We highlight the phenology and climate need to be accurately represented in the crop models to improve the accuracy in rice yield prediction under climate change conditions using integrated ML methods.
format	article
author	Yahui Guo Yongshuo Fu Fanghua Hao Xuan Zhang Wenxiang Wu Xiuliang Jin Christopher Robin Bryant J. Senthilnath
author_facet	Yahui Guo Yongshuo Fu Fanghua Hao Xuan Zhang Wenxiang Wu Xiuliang Jin Christopher Robin Bryant J. Senthilnath
author_sort	Yahui Guo
title	Integrated phenology and climate in rice yields prediction using machine learning methods
title_short	Integrated phenology and climate in rice yields prediction using machine learning methods
title_full	Integrated phenology and climate in rice yields prediction using machine learning methods
title_fullStr	Integrated phenology and climate in rice yields prediction using machine learning methods
title_full_unstemmed	Integrated phenology and climate in rice yields prediction using machine learning methods
title_sort	integrated phenology and climate in rice yields prediction using machine learning methods
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/681319c8e6d3410cbf182d64fffda8c6
work_keys_str_mv	AT yahuiguo integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods AT yongshuofu integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods AT fanghuahao integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods AT xuanzhang integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods AT wenxiangwu integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods AT xiuliangjin integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods AT christopherrobinbryant integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods AT jsenthilnath integratedphenologyandclimateinriceyieldspredictionusingmachinelearningmethods
_version_	1718405847038558208

Integrated phenology and climate in rice yields prediction using machine learning methods

Ejemplares similares