Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing

Timely and accurate monitoring of above-ground biomass (AGB) is of great significance for indicating crop growth status, predicting yield, and assessing carbon dynamics. Compared with the traditional time-consuming and laborious method through destructive sampling, UAV remote sensing provides a time...

Full description

Saved in:
Bibliographic Details
Main Authors: Guolan Xian, Jiangang Liu, Yongxin Lin, Shuang Li, Chunsong Bian
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Plants
Subjects:
Online Access:https://www.mdpi.com/2223-7747/13/23/3356
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850107127184490496
author Guolan Xian
Jiangang Liu
Yongxin Lin
Shuang Li
Chunsong Bian
author_facet Guolan Xian
Jiangang Liu
Yongxin Lin
Shuang Li
Chunsong Bian
author_sort Guolan Xian
collection DOAJ
description Timely and accurate monitoring of above-ground biomass (AGB) is of great significance for indicating crop growth status, predicting yield, and assessing carbon dynamics. Compared with the traditional time-consuming and laborious method through destructive sampling, UAV remote sensing provides a timely and efficient strategy for estimating biomass. However, the universality of remote sensing retrieval models with multi-feature fusion under different management practices and cultivars are unknown. The spectral, textural, and structural features extracted by UAV multispectral and RGB imaging, coupled with agricultural meteorological parameters, were integrated to estimate the AGB in potato during the whole growth period. Six advanced modeling algorithms, including random forest (RF), partial least squares regression (PLSR), multiple linear regression (MLR), simple linear regression (SLR), ridge regression (RR), and lasso regression (LR) models, were adopted to evaluate the ability of estimating AGB by single feature and multi-feature information fusion. The results indicate the following: (1) The newly proposed variety-dependent indicator growth process ratio (GPR) can improve the model accuracy by over 20%. (2) The fusion of vegetation indices, canopy cover, growing degree days, and GPR achieved higher accuracy to estimate AGB at all growth stages compared with single feature model. (3) RF model performed best for the estimation of AGB during the whole growth period with R<sup>2</sup> 0.79 and rRMSE 0.24 ton/ha. The study demonstrated that the fusion of multi-feature coupled with the machine learning algorithm achieved the best performance for estimating potato AGB under different management practices and cultivars, which can be a potential and useful phenotyping strategy for estimating AGB at refined plot scale during the whole growth period.
format Article
id doaj-art-dc417e9ebbac4f26b57e5bf32437502c
institution OA Journals
issn 2223-7747
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Plants
spelling doaj-art-dc417e9ebbac4f26b57e5bf32437502c2025-08-20T02:38:39ZengMDPI AGPlants2223-77472024-11-011323335610.3390/plants13233356Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote SensingGuolan Xian0Jiangang Liu1Yongxin Lin2Shuang Li3Chunsong Bian4State Key Laboratory of Vegetable Biobreeding, Institute of Vegetables and Flowers, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaState Key Laboratory of Vegetable Biobreeding, Institute of Vegetables and Flowers, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaState Key Laboratory of Vegetable Biobreeding, Institute of Vegetables and Flowers, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaState Key Laboratory of Vegetable Biobreeding, Institute of Vegetables and Flowers, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaState Key Laboratory of Vegetable Biobreeding, Institute of Vegetables and Flowers, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaTimely and accurate monitoring of above-ground biomass (AGB) is of great significance for indicating crop growth status, predicting yield, and assessing carbon dynamics. Compared with the traditional time-consuming and laborious method through destructive sampling, UAV remote sensing provides a timely and efficient strategy for estimating biomass. However, the universality of remote sensing retrieval models with multi-feature fusion under different management practices and cultivars are unknown. The spectral, textural, and structural features extracted by UAV multispectral and RGB imaging, coupled with agricultural meteorological parameters, were integrated to estimate the AGB in potato during the whole growth period. Six advanced modeling algorithms, including random forest (RF), partial least squares regression (PLSR), multiple linear regression (MLR), simple linear regression (SLR), ridge regression (RR), and lasso regression (LR) models, were adopted to evaluate the ability of estimating AGB by single feature and multi-feature information fusion. The results indicate the following: (1) The newly proposed variety-dependent indicator growth process ratio (GPR) can improve the model accuracy by over 20%. (2) The fusion of vegetation indices, canopy cover, growing degree days, and GPR achieved higher accuracy to estimate AGB at all growth stages compared with single feature model. (3) RF model performed best for the estimation of AGB during the whole growth period with R<sup>2</sup> 0.79 and rRMSE 0.24 ton/ha. The study demonstrated that the fusion of multi-feature coupled with the machine learning algorithm achieved the best performance for estimating potato AGB under different management practices and cultivars, which can be a potential and useful phenotyping strategy for estimating AGB at refined plot scale during the whole growth period.https://www.mdpi.com/2223-7747/13/23/3356UAVabove-ground biomassmulti-feature fusionmachine learningplant phenotypingpotato
spellingShingle Guolan Xian
Jiangang Liu
Yongxin Lin
Shuang Li
Chunsong Bian
Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing
Plants
UAV
above-ground biomass
multi-feature fusion
machine learning
plant phenotyping
potato
title Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing
title_full Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing
title_fullStr Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing
title_full_unstemmed Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing
title_short Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing
title_sort multi feature fusion for estimating above ground biomass of potato by uav remote sensing
topic UAV
above-ground biomass
multi-feature fusion
machine learning
plant phenotyping
potato
url https://www.mdpi.com/2223-7747/13/23/3356
work_keys_str_mv AT guolanxian multifeaturefusionforestimatingabovegroundbiomassofpotatobyuavremotesensing
AT jiangangliu multifeaturefusionforestimatingabovegroundbiomassofpotatobyuavremotesensing
AT yongxinlin multifeaturefusionforestimatingabovegroundbiomassofpotatobyuavremotesensing
AT shuangli multifeaturefusionforestimatingabovegroundbiomassofpotatobyuavremotesensing
AT chunsongbian multifeaturefusionforestimatingabovegroundbiomassofpotatobyuavremotesensing