Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking Technique
Crop growth and development is a dynamic and complex process, and the essence of yield formation is the continuous accumulation of photosynthetic products from multiple fertility stages. In this study, a new stacking method for integrating multiple growth stages information was proposed to improve t...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/24/12164 |
_version_ | 1797506677685092352 |
---|---|
author | Changchun Li Yilin Wang Chunyan Ma Weinan Chen Yacong Li Jingbo Li Fan Ding Zhen Xiao |
author_facet | Changchun Li Yilin Wang Chunyan Ma Weinan Chen Yacong Li Jingbo Li Fan Ding Zhen Xiao |
author_sort | Changchun Li |
collection | DOAJ |
description | Crop growth and development is a dynamic and complex process, and the essence of yield formation is the continuous accumulation of photosynthetic products from multiple fertility stages. In this study, a new stacking method for integrating multiple growth stages information was proposed to improve the performance of the winter wheat grain yield (GY) prediction model. For this purpose, crop canopy hyperspectral reflectance and leaf area index (LAI) data were obtained at the jointing, flagging, anthesis and grain filling stages. In this case, 15 vegetation indices and LAI were used as input features of the elastic network to construct GY prediction models for single growth stage. Based on Stacking technique, the GY prediction results of four single growth stages were integrated to construct the ensemble learning framework. The results showed that vegetation indices coupled LAI could effectively overcome the spectral saturation phenomenon, the validated R<sup>2</sup> of each growth stage was improved by 10%, 22.5%, 3.6% and 10%, respectively. The stacking method provided more stable information with higher prediction accuracy than the individual fertility results (R<sup>2</sup> = 0.74), and the R<sup>2</sup> of the model validation phase improved by 236%, 51%, 27.6%, and 12.1%, respectively. The study can provide a reference for GY prediction of other crops. |
first_indexed | 2024-03-10T04:36:52Z |
format | Article |
id | doaj.art-a4599c8df766435e976c05405235995d |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T04:36:52Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-a4599c8df766435e976c05405235995d2023-11-23T03:44:10ZengMDPI AGApplied Sciences2076-34172021-12-0111241216410.3390/app112412164Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking TechniqueChangchun Li0Yilin Wang1Chunyan Ma2Weinan Chen3Yacong Li4Jingbo Li5Fan Ding6Zhen Xiao7School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454099, ChinaCrop growth and development is a dynamic and complex process, and the essence of yield formation is the continuous accumulation of photosynthetic products from multiple fertility stages. In this study, a new stacking method for integrating multiple growth stages information was proposed to improve the performance of the winter wheat grain yield (GY) prediction model. For this purpose, crop canopy hyperspectral reflectance and leaf area index (LAI) data were obtained at the jointing, flagging, anthesis and grain filling stages. In this case, 15 vegetation indices and LAI were used as input features of the elastic network to construct GY prediction models for single growth stage. Based on Stacking technique, the GY prediction results of four single growth stages were integrated to construct the ensemble learning framework. The results showed that vegetation indices coupled LAI could effectively overcome the spectral saturation phenomenon, the validated R<sup>2</sup> of each growth stage was improved by 10%, 22.5%, 3.6% and 10%, respectively. The stacking method provided more stable information with higher prediction accuracy than the individual fertility results (R<sup>2</sup> = 0.74), and the R<sup>2</sup> of the model validation phase improved by 236%, 51%, 27.6%, and 12.1%, respectively. The study can provide a reference for GY prediction of other crops.https://www.mdpi.com/2076-3417/11/24/12164grain yieldhyperspectral vegetation indexleaf area indexelastic networkstacking technology |
spellingShingle | Changchun Li Yilin Wang Chunyan Ma Weinan Chen Yacong Li Jingbo Li Fan Ding Zhen Xiao Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking Technique Applied Sciences grain yield hyperspectral vegetation index leaf area index elastic network stacking technology |
title | Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking Technique |
title_full | Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking Technique |
title_fullStr | Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking Technique |
title_full_unstemmed | Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking Technique |
title_short | Improvement of Wheat Grain Yield Prediction Model Performance Based on Stacking Technique |
title_sort | improvement of wheat grain yield prediction model performance based on stacking technique |
topic | grain yield hyperspectral vegetation index leaf area index elastic network stacking technology |
url | https://www.mdpi.com/2076-3417/11/24/12164 |
work_keys_str_mv | AT changchunli improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique AT yilinwang improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique AT chunyanma improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique AT weinanchen improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique AT yacongli improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique AT jingboli improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique AT fanding improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique AT zhenxiao improvementofwheatgrainyieldpredictionmodelperformancebasedonstackingtechnique |