[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123530-en":3,"doc-seo-123530-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123530,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Generalizability and transferability of machine learning models - using hyperspectral reflectance data for maize traits","Hyperspectral reflectance enables rapid, non-destructive phenotyping of plant leaves and supports machine learning for trait prediction, but transfer across environments remains a challenge. The study pairs hyperspectral reflectance with 25 anatomical, gas exchange, and chlorophyll fluorescence traits from 320 recombinant inbred lines across three seasons. Using nested cross-validation, it benchmarks PLSR versus SVR, compares performance under single, repeated, and calibration strategies, and tests aggregation effects on accuracy. Trait-specific generalizability varies by trait type, with structural/biochemical traits transferring best while physiological traits show reduced transferability. Results provide a rigorous benchmark and clarify opportunities and limitations for robust model generalization.","1 Generalizability and transferability of machine learning models  \n2 using hyperspectral reflectance data for maize traits  \n3 Rudan Xu 1,2,†, John Ferguson3,†, Matthieu Breil-Aubert4, Johannes Kromdijk4,*, and Zoran  \n4 Nikoloski 1,2, *  \n5 1Bioinformatics Department, Institute of Biochemistry and Biology, University of Potsdam, 6 Potsdam, Germany  \n7 2 Systems Biology and Mathematical Modelling Group, Max Planck Institute of Molecular  \n8 Plant Physiology, Potsdam, Germany  \n9 3 School of Life Sciences, University of Essex, Colchester, UK  \n10 4Department of Plant Sciences, University of Cambridge, Cambridge, UK  \n11 †These authors contributed equally.  \n12 *Corresponding authors.  \n13  \n14 Email address:  \n15 [xu2@uni-potsdam.de](xu2@uni-potsdam.de)  \n16 [jfergu@essex.ac.uk](jfergu@essex.ac.uk)  \n17 [mb2651@cam.ac.uk](mb2651@cam.ac.uk)  \n18 [jk417@cam.ac.uk](jk417@cam.ac.uk)  \n19 [nikoloski@mpimp-golm.mpg.de](nikoloski@mpimp-golm.mpg.de)[ ](nikoloski@mpimp-golm.mpg.de)20  \n21  \n22 Keywords  \n23 Hyperspectral reflectance, machine learning, Zea mays, model generalizability, anatomical traits, 24 chlorophyll fluorescence, gas exchange.  \n25  \n27 Abstract  \n28 Hyperspectral reflectance provides rapid, non-destructive phenotyping of plant leaves. These data  \n29 have been used to develop machine learning models for predicting diverse plant traits, yet key  \n30 challenges remain. We collected hyperspectral reflectance data together with 25 anatomical, gas  \n31 exchange, and chlorophyll fluorescence traits from 320 recombinant inbred lines grown over three  \n32 seasons. Using these data, we systematically (1) compare the performance of PLSR and SVR  \n33 across a wide range of traits, including also slow fluorescence kinetics, (2) assess model  \n34 generalizability and transferability, and (3) investigate how different aggregation strategies affect  \n35 predictive accuracy. Based on a nested cross-validation framework, single cross-validation with  \n36 MSE as metric performed comparably to repeated cross-validation or PRESS-based calibration.  \n37 Optimal performance of trait-specific predictions was found to be dependent on the combination  \n38 of model and data aggregation levels. Structural and biochemical traits showed the best  \n39 generalizability and transferability, whereas physiological traits, particularly those derived from  \n40 gas exchange and fluorescence kinetics, exhibited markedly reduced transferability. Together, 41 these results provide a rigorous benchmark for evaluating machine learning models for trait  \n42 prediction from hyperspectral reflectance data, and highlight both the opportunities and limitations  \n43 for achieving robust generalization across diverse environments and genotypes.  \n44  \n45 Abbreviations  \n46 HSR, hyperspectral reflectance; partial least squares regression, PLSR; number of component, 47 NoC; support vector regression, SVR; A-Ci curve, photosynthetic rate versus internal CO2  \n48 concentration curve; phosphoenolpyruvate carboxylase, PEPC; maximum rate of carboxylation by  \n49 PEPC, Vpmax ; asymptote of theA-Ci curve, Vmax ; photosystem II, PSII; quantum efficiency of PSII, 50 Fv/Fm; non-photochemical quenching, NPQ; PSII operating efficiency, ΦPSII; relative C  \n51 content,%C; relative N content,%N; stable carbon isotope ratio, δ 13C; stable nitrogen isotope  \n52 ratio, δ 15N; intrinsic water use efficiency, iWUE; stomatal conductance, gsw; coefficient of  \n53 determination, R2; cross-validation, CV; coefficients of variation, CVs; standard deviation, SD.  \n54 Introduction  \n55 Efforts to develop climate-resilient crops go hand-in-hand with advances in high-throughput  \n56 phenotyping technologies that can be deployed at scale in accelerated breeding 1,2 . Urgent  \n57 innovations in high-throughput profiling are needed given that many breeding targets involve  \n58 molecular and biochemical traits that are difficult to measure across large breeding populations3.  \n59 Hyperspectral refl","cbCaifqIXTTphrtk","https://ap.wps.com/l/cbCaifqIXTTphrtk","pdf",1585652,1,31,"English","en",105,"# Abstract\n# Keywords\n# Introduction\n## Hyperspectral reflectance for high-throughput phenotyping\n## Machine learning for trait prediction from HSR\n## Challenges in generalizability and modeling choices","[{\"question\":\"What data were collected for training and evaluating the machine learning models?\",\"answer\":\"Hyperspectral reflectance data from maize leaves were collected together with 25 traits covering anatomical traits, gas exchange, and chlorophyll fluorescence from 320 recombinant inbred lines across three seasons.\"},{\"question\":\"How were PLSR and SVR model performance compared?\",\"answer\":\"The study benchmarks PLSR and SVR using a nested cross-validation framework and evaluates performance with mean squared error, comparing single cross-validation, repeated cross-validation, and PRESS-based calibration.\"},{\"question\":\"What factors most affected transferability of predictions?\",\"answer\":\"Transferability depended on the combination of model type and the data aggregation level. Structural and biochemical traits showed better generalizability, while physiological traits—especially those derived from gas exchange and fluorescence kinetics—exhibited reduced transferability.\"}]","Generalizability and transferability of machine learning models - using hyperspectral reflectance data for maize traits | PDF",1785817160,78,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"generalizability-and-transferability-of-machine-learning-models-using-hyperspectral-reflectance-data-for-maize-traits","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/generalizability-and-transferability-of-machine-learning-models-using-hyperspectral-reflectance-data-for-maize-traits/123530/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data were collected for training and evaluating the machine learning models?","Question",{"text":75,"@type":76},"Hyperspectral reflectance data from maize leaves were collected together with 25 traits covering anatomical traits, gas exchange, and chlorophyll fluorescence from 320 recombinant inbred lines across three seasons.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were PLSR and SVR model performance compared?",{"text":80,"@type":76},"The study benchmarks PLSR and SVR using a nested cross-validation framework and evaluates performance with mean squared error, comparing single cross-validation, repeated cross-validation, and PRESS-based calibration.",{"name":82,"@type":73,"acceptedAnswer":83},"What factors most affected transferability of predictions?",{"text":84,"@type":76},"Transferability depended on the combination of model type and the data aggregation level. Structural and biochemical traits showed better generalizability, while physiological traits—especially those derived from gas exchange and fluorescence kinetics—exhibited reduced transferability.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]