Developing machine learning models with multi-source environmental data to predict wheat yield in China

Li, L; Wang, B; Feng, P; Li Liu, D; He, Q; Zhang, Y; Wang, Y; Li, S; Lu, X; Yue, C; Li, Y; He, J; Feng, H; Yang, G; Yu, Q

Developing machine learning models with multi-source environmental data to predict wheat yield in China

Li, L Wang, B Feng, P

Li Liu, D He, Q

Zhang, Y Wang, Y Li, S Lu, X Yue, C Li, Y He, J Feng, H Yang, G Yu, Q

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Computers and Electronics in Agriculture, 2022, 194
Issue Date:: 2022-03-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0168169922001077-main.pdf		4.62 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Li, L
dc.contributor.author	Wang, B
dc.contributor.author	Feng, P https://orcid.org/0000-0003-4845-9876
dc.contributor.author	Li Liu, D
dc.contributor.author	He, Q https://orcid.org/0000-0001-9585-3716
dc.contributor.author	Zhang, Y
dc.contributor.author	Wang, Y
dc.contributor.author	Li, S
dc.contributor.author	Lu, X
dc.contributor.author	Yue, C
dc.contributor.author	Li, Y
dc.contributor.author	He, J
dc.contributor.author	Feng, H
dc.contributor.author	Yang, G
dc.contributor.author	Yu, Q
dc.date.accessioned	2023-02-22T05:16:00Z
dc.date.available	2023-02-22T05:16:00Z
dc.date.issued	2022-03-01
dc.identifier.citation	Computers and Electronics in Agriculture, 2022, 194
dc.identifier.issn	0168-1699
dc.identifier.issn	1872-7107
dc.identifier.uri	http://hdl.handle.net/10453/166322
dc.description.abstract	Crop yield is controlled by different environmental factors. Multi-source data for site-specific soils, climates, and remotely sensed vegetation indices are essential for yield prediction. Algorithms of data-model fusion for crop growth monitoring and yield prediction are complicated and need to be optimized to deal with model uncertainty. This study integrated multi-source environmental variables (e.g., satellite-based vegetation indices, climate data, and soil properties) into random forest (RF) and support vector machine (SVM) models for wheat yield prediction in China. The performance of both RF and SVM models was investigated using different types of vegetation indices associated with other predictors. Relative importance and partial dependence analyses were used to identify the main predictors and their relationships with wheat yield. We found that using remotely sensed vegetation indices improved our model precision, and that near-infrared reflectance of terrestrial vegetation (NIRv) was slightly better than normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) in predicting yield. NIRv was better in detecting climate stress on crops, and could capture more information regarding crop growth and yield formation. Compared with the SVM model, the RF model with NIRv and other covariates had better performance in wheat yield prediction, with R2 and RMSE being 0.74 and 758 kg/ha respectively. We also found that NIRv from jointing to heading was the most important predictor in determining yield, followed by solar radiation (especially during tillering–heading), relative humidity (during planting–tillering), soil organic carbon, and wind speed (throughout the growing season). In addition, wheat yield exhibited threshold-like responses to most factors based on our RF model. These threshold values can help to better understand how different environmental factors limit wheat yield, which will provide useful information for climate-adaptive crop management. Our findings demonstrated the potential of using NIRv for yield prediction. This approach is broadly applicable to other regions globally using publicly available data.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Computers and Electronics in Agriculture
dc.relation.isbasedon	10.1016/j.compag.2022.106790
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	07 Agricultural and Veterinary Sciences, 08 Information and Computing Sciences, 09 Engineering
dc.subject.classification	Agronomy & Agriculture
dc.title	Developing machine learning models with multi-source environmental data to predict wheat yield in China
dc.type	Journal Article
utslib.citation.volume	194
utslib.for	07 Agricultural and Veterinary Sciences
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Life Sciences
utslib.copyright.status	closed_access	*
dc.date.updated	2023-02-22T05:15:58Z
pubs.publication-status	Published
pubs.volume	194

Abstract:

Crop yield is controlled by different environmental factors. Multi-source data for site-specific soils, climates, and remotely sensed vegetation indices are essential for yield prediction. Algorithms of data-model fusion for crop growth monitoring and yield prediction are complicated and need to be optimized to deal with model uncertainty. This study integrated multi-source environmental variables (e.g., satellite-based vegetation indices, climate data, and soil properties) into random forest (RF) and support vector machine (SVM) models for wheat yield prediction in China. The performance of both RF and SVM models was investigated using different types of vegetation indices associated with other predictors. Relative importance and partial dependence analyses were used to identify the main predictors and their relationships with wheat yield. We found that using remotely sensed vegetation indices improved our model precision, and that near-infrared reflectance of terrestrial vegetation (NIRv) was slightly better than normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) in predicting yield. NIRv was better in detecting climate stress on crops, and could capture more information regarding crop growth and yield formation. Compared with the SVM model, the RF model with NIRv and other covariates had better performance in wheat yield prediction, with R2 and RMSE being 0.74 and 758 kg/ha respectively. We also found that NIRv from jointing to heading was the most important predictor in determining yield, followed by solar radiation (especially during tillering–heading), relative humidity (during planting–tillering), soil organic carbon, and wind speed (throughout the growing season). In addition, wheat yield exhibited threshold-like responses to most factors based on our RF model. These threshold values can help to better understand how different environmental factors limit wheat yield, which will provide useful information for climate-adaptive crop management. Our findings demonstrated the potential of using NIRv for yield prediction. This approach is broadly applicable to other regions globally using publicly available data.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/166322