Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets

Leaf mass per area (LMA) and leaf nitrogen concentration (LNC) are both essential parameters in plant ecology, which can reflect the growth status of plants. The features of LMA and LNC can be captured using spectral reflectance in a remote sensing approach. While the relationships between spectra a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingbo Wang, Mengzhu He, Lin Sun, Yong He, Zengwei Zheng
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/1/46
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849219731097124864
author Yingbo Wang
Mengzhu He
Lin Sun
Yong He
Zengwei Zheng
author_facet Yingbo Wang
Mengzhu He
Lin Sun
Yong He
Zengwei Zheng
author_sort Yingbo Wang
collection DOAJ
description Leaf mass per area (LMA) and leaf nitrogen concentration (LNC) are both essential parameters in plant ecology, which can reflect the growth status of plants. The features of LMA and LNC can be captured using spectral reflectance in a remote sensing approach. While the relationships between spectra and leaf trait variance across different species with estimation performance are unclear, the development of assessment and transferable models to predicate LMA and LNC are prevented. Hence, we analyzed the variance of raw spectra and spectral data difference with four pretreated approaches (SG—Savitzky–Golay filter, SNV—Standard Normalized Variate, MSC—Multiplicative Scatter Correction analysis, and normalize), LMA, and LNC over six remote sensing datasets by a transfer component analysis (TCA) approach. Spectra combined with the Successive Projections Algorithm (SPA) were also presented to extract wavelengths with higher important coefficients to minimize the redundancy of datasets. The variance of normalized spectra between different datasets showed a minor degree of variance, and LNC spectra variance was decreased by the SPA. The results also showed that a smaller LMA and LNC variance is presented over different datasets when the trait values with higher distribution probabilities are close to each other. The LNC and LMA estimation performance in transfer models established by partial least squares regression (PLS), support vector regression (SVR), extreme gradient boosting (XGB), and random forest regression (RFR) algorithms across different datasets were employed, in which the RFR transfer models performed good prediction results. The relationships between spectra and leaf trait variance and estimation performance in RFR transfer models over different datasets were evaluated. LMA distance has a significant influence on estimation performance in the transfer model, and the variance of spectra with all pretreated approaches showed a very significant effect on LNC accession performance. Furthermore, we proposed a weight coefficient of spectral data updating combined with the TCA and RFR approach (WDT-RFR) transfer model to improve transferability between datasets and promote estimation performance in the transfer model. Compared to the RFR transfer model using spectra without updating, the root mean square error (<i>RMSE</i>) of the WDT-RFR transfer model with 5% samples transferred to estimate LMA and LNC increased by 7.9% and 4.8% on average, respectively. The estimation results showed that our transfer model showed a superior estimation performance.
format Article
id doaj-art-fa75da4a58e64fc29b204f8b332906da
institution Kabale University
issn 2077-0472
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-fa75da4a58e64fc29b204f8b332906da2025-01-10T13:13:31ZengMDPI AGAgriculture2077-04722024-12-011514610.3390/agriculture15010046Transfer Learning Estimation and Transferability of LNC and LMA Across Different DatasetsYingbo Wang0Mengzhu He1Lin Sun2Yong He3Zengwei Zheng4College of Biosystems Engineering & Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering & Food Science, Zhejiang University, Hangzhou 310058, ChinaSchool of Computer & Computing Science, Hangzhou City University, Hangzhou 310015, ChinaCollege of Biosystems Engineering & Food Science, Zhejiang University, Hangzhou 310058, ChinaSchool of Computer & Computing Science, Hangzhou City University, Hangzhou 310015, ChinaLeaf mass per area (LMA) and leaf nitrogen concentration (LNC) are both essential parameters in plant ecology, which can reflect the growth status of plants. The features of LMA and LNC can be captured using spectral reflectance in a remote sensing approach. While the relationships between spectra and leaf trait variance across different species with estimation performance are unclear, the development of assessment and transferable models to predicate LMA and LNC are prevented. Hence, we analyzed the variance of raw spectra and spectral data difference with four pretreated approaches (SG—Savitzky–Golay filter, SNV—Standard Normalized Variate, MSC—Multiplicative Scatter Correction analysis, and normalize), LMA, and LNC over six remote sensing datasets by a transfer component analysis (TCA) approach. Spectra combined with the Successive Projections Algorithm (SPA) were also presented to extract wavelengths with higher important coefficients to minimize the redundancy of datasets. The variance of normalized spectra between different datasets showed a minor degree of variance, and LNC spectra variance was decreased by the SPA. The results also showed that a smaller LMA and LNC variance is presented over different datasets when the trait values with higher distribution probabilities are close to each other. The LNC and LMA estimation performance in transfer models established by partial least squares regression (PLS), support vector regression (SVR), extreme gradient boosting (XGB), and random forest regression (RFR) algorithms across different datasets were employed, in which the RFR transfer models performed good prediction results. The relationships between spectra and leaf trait variance and estimation performance in RFR transfer models over different datasets were evaluated. LMA distance has a significant influence on estimation performance in the transfer model, and the variance of spectra with all pretreated approaches showed a very significant effect on LNC accession performance. Furthermore, we proposed a weight coefficient of spectral data updating combined with the TCA and RFR approach (WDT-RFR) transfer model to improve transferability between datasets and promote estimation performance in the transfer model. Compared to the RFR transfer model using spectra without updating, the root mean square error (<i>RMSE</i>) of the WDT-RFR transfer model with 5% samples transferred to estimate LMA and LNC increased by 7.9% and 4.8% on average, respectively. The estimation results showed that our transfer model showed a superior estimation performance.https://www.mdpi.com/2077-0472/15/1/46leaf spectraleaf traitsleaf mass per arealeaf nitrogen concentrationtransfer learning
spellingShingle Yingbo Wang
Mengzhu He
Lin Sun
Yong He
Zengwei Zheng
Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets
Agriculture
leaf spectra
leaf traits
leaf mass per area
leaf nitrogen concentration
transfer learning
title Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets
title_full Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets
title_fullStr Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets
title_full_unstemmed Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets
title_short Transfer Learning Estimation and Transferability of LNC and LMA Across Different Datasets
title_sort transfer learning estimation and transferability of lnc and lma across different datasets
topic leaf spectra
leaf traits
leaf mass per area
leaf nitrogen concentration
transfer learning
url https://www.mdpi.com/2077-0472/15/1/46
work_keys_str_mv AT yingbowang transferlearningestimationandtransferabilityoflncandlmaacrossdifferentdatasets
AT mengzhuhe transferlearningestimationandtransferabilityoflncandlmaacrossdifferentdatasets
AT linsun transferlearningestimationandtransferabilityoflncandlmaacrossdifferentdatasets
AT yonghe transferlearningestimationandtransferabilityoflncandlmaacrossdifferentdatasets
AT zengweizheng transferlearningestimationandtransferabilityoflncandlmaacrossdifferentdatasets