{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:52:38Z","timestamp":1785909158701,"version":"3.56.0"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>Leaf chlorophyll content (LCC) is a key indicator for assessing the photosynthetic capacity and nutritional status of winter wheat. Among traditional LCC estimation methods, empirical models lack a physical basis and have poor generalisability, while physical models are widely applicable but suffer from ill-posed inversion problems. Hybrid inversion methods, which integrate radiation transfer models such as PROSAIL with machine learning, offer both the interpretability of physical models and the efficiency of machine learning; however, they are still affected by the domain shift between simulated and measured data, which limits their generalisation performance. Transfer Component Analysis (TCA), a domain adaption method, can effectively alleviate this problem. In this study, hyperspectral and LCC data were collected in the field, and simulated data were generated using the PROSAIL model; a sensitivity analysis was conducted to identify LCC-sensitive bands. A genetic algorithm was applied to the measured data for band selection and, together with the results of the sensitivity analysis, yielded an optimal set of 30 characteristic bands for subsequent modelling. Three datasets were constructed: measured data only, a direct mixture of measured and simulated data, and a TCA-fused mixture of measured and simulated data. Four models\u2014gradient boosting regression (GBR), random forest (RF), support vector regression (SVR) and deep neural network (DNN)\u2014were developed for each dataset. The results show that: (1) the LCC-sensitive bands are concentrated in the 450\u2013660 nm and 680\u2013720 nm ranges; (2) the model built on the TCA-fused data (R\u00b2 = 0.722, RMSE\u00a0=\u00a06.792) outperformed those built on the measured-only data (R\u00b2 = 0.682, RMSE\u00a0=\u00a07.259) and the directly mixed data (R\u00b2 = 0.616, RMSE\u00a0=\u00a07.976); (3) for the TCA-fused data, the four models differed considerably in accuracy, with SVR performing best (R\u00b2 = 0.723, RMSE\u00a0=\u00a05.363), followed by RF (R\u00b2 = 0.630, RMSE\u00a0=\u00a06.201) and GBR (R\u00b2 = 0.575, RMSE\u00a0=\u00a06.650), whereas the DNN performed worst (R\u00b2 = 0.388, RMSE\u00a0=\u00a07.947), probably owing to the limited sample size.<\/jats:p>","DOI":"10.3389\/fpls.2026.1921769","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:40:59Z","timestamp":1785908459000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A hybrid PROSAIL inversion framework for winter wheat LCC using hyperspectral data and transfer learning"],"prefix":"10.3389","volume":"17","author":[{"given":"Xueqing","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Intelligent Manufacturing, Anhui Science and Technology University","place":["Chuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligent Manufacturing, Anhui Science and Technology University","place":["Chuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Nian","sequence":"additional","affiliation":[{"name":"College of Resources and Environment, Anhui Science and Technology University","place":["Chuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jikai","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Resources and Environment, Anhui Science and Technology University","place":["Chuzhou, China"]},{"name":"Anhui Engineering Research Center of Smart Crop Planting and Processing Technology, Anhui Science and Technology University","place":["Chuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinwei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Resources and Environment, Anhui Science and Technology University","place":["Chuzhou, China"]},{"name":"Anhui Engineering Research Center of Smart Crop Planting and Processing Technology, Anhui Science and Technology University","place":["Chuzhou, China"]},{"name":"Anhui Province Key Laboratory of Functional Agriculture and Functional Food, Anhui Science and Technology University","place":["Chuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.rse.2004.06.016","article-title":"Object-based retrieval of biophysical canopy variables using artificial neural nets and radiative transfer models","volume":"93","author":"Atzberger","year":"2004","journal-title":"Remote Sens. Environ."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/rs10010085","article-title":"Evaluation of the PROSAIL model capabilities for future hyperspectral model environments: A review study","volume":"10","author":"Berger","year":"2018","journal-title":"Remote Sens."},{"key":"B3","doi-asserted-by":"publisher","first-page":"e49","DOI":"10.1093\/bioinformatics\/btl242","article-title":"Integrating structured biological data by kernel maximum mean discrepancy","volume":"22","author":"Borgwardt","year":"2006","journal-title":"Bioinformatics"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.fcr.2025.109745","article-title":"Trends in crop yield estimation via data assimilation based on multi-interdisciplinary analysis","volume":"322","author":"Cao","year":"2025","journal-title":"Field Crops Res."},{"key":"B5","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1111\/j.1399-3054.2012.01639.x","article-title":"A new optical leaf-clip meter for simultaneous non-destructive assessment of leaf chlorophyll and epidermal flavonoids","volume":"146","author":"Cerovic","year":"2012","journal-title":"Physiol. Plant"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy13071806","article-title":"Soil organic carbon prediction based on different combinations of hyperspectral feature selection and regression algorithms","volume":"13","author":"Chang","year":"2023","journal-title":"Agronomy"},{"key":"B7","doi-asserted-by":"publisher","first-page":"182","DOI":"10.11975\/j.issn.1002-6819.202408057","article-title":"Inversion of the leaf area index for the multiple types of crops based on the tasselled cap-vegetation isoline patterns","volume":"41","author":"Chen","year":"2025","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0034-4257(02)00035-4","article-title":"Retrieval of canopy biophysical variables from bidirectional reflectance: Using prior information to solve the ill-posed inverse problem","volume":"84","author":"Combal","year":"2003","journal-title":"Remote Sens. Environ."},{"key":"B9","first-page":"155","article-title":"Support vector regression machines","author":"Drucker","year":"1996"},{"key":"B10","first-page":"347","article-title":"LAI estimation of winter wheat based on the fusion of texture-color features and vegetation index","volume":"54","author":"Fan","year":"2023","journal-title":"Trans. Chin. Soc. For. Agric. Machinery."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"B12","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.isprsjprs.2018.03.005","article-title":"Derivation of global vegetation biophysical parameters from EUMETSAT Polar System","volume":"139","author":"Garc\u00eda-Haro","year":"2018","journal-title":"ISPRS. J. Photogramm. Remote Sens."},{"key":"B13","volume-title":"Genetic Algorithms in Search, Optimization, and Machine Learning","author":"Goldberg","year":"1989"},{"key":"B14","first-page":"836","article-title":"The EFAST method for the global sensitivity analysis of the model parameters","volume":"28","author":"He","year":"2013","journal-title":"Remote Sens. Technol. Appl."},{"key":"B15","doi-asserted-by":"publisher","first-page":"S56","DOI":"10.1016\/j.rse.2008.01.026","article-title":"PROSPECT + SAIL models: A review of use for vegetation characterization","volume":"113","author":"Jacquemoud","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.04846","article-title":"Sound source localization for a source inside a structure using Ac-CycleGAN","author":"Kita","year":"2023"},{"key":"B17","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.rse.2004.11.017","article-title":"Use of coupled canopy structure dynamic and radiative transfer models to estimate biophysical canopy characteristics","volume":"95","author":"Koetz","year":"2005","journal-title":"Remote Sens. Environ."},{"key":"B18","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1002\/jsfa.8462","article-title":"Comparison of partial least squares and random forests for evaluating relationship between phenolics and bioactivities of Neptunia oleracea","volume":"98","author":"Lee","year":"2018","journal-title":"J. Sci. Food Agric."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2024.114559","article-title":"A radiative transfer model for characterizing photometric and polarimetric properties of leaf reflection: Combination of PROSPECT and a polarized reflection function","volume":"318","author":"Li","year":"2025","journal-title":"Remote Sens. Environ."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2025.2496403","article-title":"An efficient retrieval method on Google Earth Engine and comparison with hybrid methods: A case study of leaf area index retrieval","volume":"18","author":"Li","year":"2025","journal-title":"Int. J. Digital. Earth"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1093\/plphys\/kiab322","article-title":"Estimating leaf area index using unmanned aerial vehicle data: Shallow vs. deep machine learning algorithms","volume":"187","author":"Liu","year":"2021","journal-title":"Plant Physiol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"734","DOI":"10.3724\/sp.j.1047.2013.00734","article-title":"Current status and perspectives of leaf area index retrieval from optical remote sensing data","volume":"15","author":"Liu","year":"2013","journal-title":"J. Geo-info. Sci."},{"key":"B23","first-page":"2200","article-title":"Transfer feature learning with joint distribution adaptation","author":"Long","year":"2013"},{"key":"B24","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1080\/15481603.2021.1877435","article-title":"Investigating different versions of PROSPECT and PROSAIL for estimating spectral and biophysical properties of photosynthetic and non-photosynthetic vegetation in mixed grasslands","volume":"58","author":"Lu","year":"2021","journal-title":"GISci. Remote Sens."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cocom.2025.e01139","article-title":"Machine learning-driven materials discovery: Unlocking next-generation functional materials \u2013 A review","volume":"45","author":"Nematov","year":"2025","journal-title":"Comput. Condens. Matter."},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.indcrop.2023.117191","article-title":"Can biomass structural composition be predicted from a small dataset using a hybrid deep learning approach","volume":"203","author":"Okolie","year":"2023","journal-title":"Ind. Crops Prod."},{"key":"B27","first-page":"677","article-title":"Transfer learning via dimensionality reduction","author":"Pan","year":"2008"},{"key":"B28","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","article-title":"Domain adaptation via transfer component analysis","volume":"22","author":"Pan","year":"2011","journal-title":"IEEE Trans. Neural Networks"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"B30","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1016\/j.oregeorev.2015.01.001","article-title":"Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines","volume":"71","author":"Rodriguez-Galiano","year":"2015","journal-title":"Ore. Geol. Rev."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.95.144110","article-title":"Representation of compounds for machine-learning prediction of physical properties","volume":"95","author":"Seko","year":"2017","journal-title":"Phys. Rev. B."},{"key":"B32","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","article-title":"A tutorial on support vector regression","volume":"14","author":"Smola","year":"2004","journal-title":"Stat Computing."},{"key":"B33","first-page":"6","article-title":"Comparison and application of SCE-UA, genetic algorithm and simplex method","volume":"42","author":"Song","year":"2009","journal-title":"Eng. J. Wuhan. Univ."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3390\/rs15174303","article-title":"Carotenoid content estimation in tea leaves using noisy reflectance data","volume":"15","author":"Sonobe","year":"2023","journal-title":"Remote Sens."},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.24044","article-title":"Mitigating negative transfer via reducing environmental disagreement","author":"Sun","year":"2025"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random forest: A classification and regression tool for compound classification and QSAR modeling","volume":"43","author":"Svetnik","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"B37","first-page":"2562","article-title":"Effects of GA on the inversion of linear and nonlinear remote sensing models","author":"Tang","year":"2002"},{"key":"B38","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MGRS.2016.2548504","article-title":"Domain adaptation for the classification of remote sensing data: An overview of recent advances","volume":"4","author":"Tuia","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"B39","first-page":"277","article-title":"COMSPECT: A compact model for green vegetation reflectance spectra in the 400\u2013900 nm wavelength range","author":"Udal","year":"2020"},{"key":"B40","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/j.isprsjprs.2015.05.005","article-title":"Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical properties \u2013 A review","volume":"108","author":"Verrelst","year":"2015","journal-title":"ISPRS. J. Photogramm. Remote Sens."},{"key":"B41","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.rse.2011.11.002","article-title":"Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and -3","volume":"118","author":"Verrelst","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2021.112826","article-title":"Combining transfer learning and hyperspectral reflectance analysis to assess leaf nitrogen concentration across different plant species datasets","volume":"269","author":"Wan","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.106728","article-title":"Winter wheat chlorophyll content retrieval based on machine learning using in situ hyperspectral data","volume":"193","author":"Wang","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B44","doi-asserted-by":"publisher","first-page":"166","DOI":"10.11975\/j.issn.1002-6819.202308116","article-title":"Estimation of winter wheat chlorophyll content by combing canopy spectrum red edge parameters with random forest machine learning","volume":"40","author":"Wang","year":"2024","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14102245","article-title":"Estimation of cotton SPAD based on multi-source feature fusion and voting regression ensemble learning in intercropping pattern of cotton and soybean","volume":"14","author":"Wang","year":"2024","journal-title":"Agronomy"},{"key":"B46","first-page":"205","article-title":"Inversion of leaf area index of silage corn based on PROSAIL model","volume":"55","author":"Wang","year":"2024","journal-title":"Trans. Chin. Soc. For. Agric. Machinery."},{"key":"B47","doi-asserted-by":"publisher","first-page":"134","DOI":"10.11975\/j.issn.1002-6819.202407114","article-title":"Inversion of silage maize leaf area index based on machine learning optimized PROSAIL model","volume":"41","author":"Wang","year":"2025","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"B48","first-page":"3213","article-title":"A universal model for quantitative analysis of near-infrared spectroscopy based on transfer component analysis","volume":"44","author":"Wang","year":"2024","journal-title":"Spectrosc. Spectral. Anal."},{"key":"B49","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1051\/agro:2000105","article-title":"Investigation of a model inversion technique to estimate canopy biophysical variables from spectral and directional reflectance data","volume":"20","author":"Weiss","year":"2000","journal-title":"Agronomie"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.11873\/j.issn.1004-0323.2019.6.1235","article-title":"Retrieval of leaf area index by fusing prior information from remote sensing data","volume":"34","author":"Xu","year":"2019","journal-title":"Remote Sens. Technol. Appl."},{"key":"B51","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.11873\/j.issn.1004-0323.2025.6.1511","article-title":"Estimation of maize LAI based on PROSAIL model","volume":"40","author":"Yi","year":"2025","journal-title":"Remote Sens. Technol. Appl."},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.3390\/ijms23169087","article-title":"Feature selection and molecular classification of cancer phenotypes: A comparative study","volume":"23","author":"Zanella","year":"2022","journal-title":"Int. J. Mol. Sci."},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture14101685","article-title":"Quantitative analysis of vertical and temporal variations in the chlorophyll content of winter wheat leaves via proximal multispectral remote sensing and deep transfer learning","volume":"14","author":"Zhang","year":"2024","journal-title":"Agriculture"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.02552","article-title":"Adapting to continuous covariate shift via online density ratio estimation","author":"Zhang","year":"2024"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1016\/j.plaphe.2025.100004","article-title":"Dynamic maize true leaf area index retrieval with KGCNN and TL and integrated 3D radiative transfer modeling for crop phenotyping","volume":"7","author":"Zhao","year":"2025","journal-title":"Plant Phenomics."},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.00423","article-title":"Open-environment machine learning","author":"Zhou","year":"2022"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.3390\/f15060946","article-title":"Coupling the PROSAIL model and machine learning approach for canopy parameter estimation of Moso bamboo forests from UAV hyperspectral data","volume":"15","author":"Zhou","year":"2024","journal-title":"Forests"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2023.110164","article-title":"A fuzzy-set-based joint distribution adaptation method for regression and its application to online damage quantification for structural digital twin","volume":"191","author":"Zhou","year":"2023","journal-title":"Mech. Syst. Signal Process."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1921769\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:41:08Z","timestamp":1785908468000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1921769\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":58,"alternative-id":["10.3389\/fpls.2026.1921769"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1921769","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"article-number":"1921769"}}