{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T07:20:02Z","timestamp":1773818402439,"version":"3.50.1"},"reference-count":59,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2018,8,11]],"date-time":"2018-08-11T00:00:00Z","timestamp":1533945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["249178\/2013-3"],"award-info":[{"award-number":["249178\/2013-3"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Spectral, temporal and spatial dimensions are difficult to model together when predicting in situ plant traits from remote sensing data. Therefore, machine learning algorithms solely based on spectral dimensions are often used as predictors, even when there is a strong effect of spatial or temporal autocorrelation in the data. A significant reduction in prediction accuracy is expected when algorithms are trained using a sequence in space or time that is unlikely to be observed again. The ensuing inability to generalise creates a necessity for ground-truth data for every new area or period, provoking the propagation of \u201csingle-use\u201d models. This study assesses the impact of spatial autocorrelation on the generalisation of plant trait models predicted with hyperspectral data. Leaf Area Index (LAI) data generated at increasing levels of spatial dependency are used to simulate hyperspectral data using Radiative Transfer Models. Machine learning regressions to predict LAI at different levels of spatial dependency are then tuned (determining the optimum model complexity) using cross-validation as well as the NOIS method. The results show that cross-validated prediction accuracy tends to be overestimated when spatial structures present in the training data are fitted (or learned) by the model.<\/jats:p>","DOI":"10.3390\/rs10081263","type":"journal-article","created":{"date-parts":[[2018,8,13]],"date-time":"2018-08-13T11:27:13Z","timestamp":1534159633000},"page":"1263","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Machine Learning Using Hyperspectral Data Inaccurately Predicts Plant Traits Under Spatial Dependency"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6370-1240","authenticated-orcid":false,"given":"Alby D.","family":"Rocha","sequence":"first","affiliation":[{"name":"Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7500AE, Enschede, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6333-2553","authenticated-orcid":false,"given":"Thomas A.","family":"Groen","sequence":"additional","affiliation":[{"name":"Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7500AE, Enschede, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7446-8429","authenticated-orcid":false,"given":"Andrew K.","family":"Skidmore","sequence":"additional","affiliation":[{"name":"Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7500AE, Enschede, The Netherlands"},{"name":"Department of Environmental Science, Macquarie University, Sydney, NSW 2106, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7512-0574","authenticated-orcid":false,"given":"Roshanak","family":"Darvishzadeh","sequence":"additional","affiliation":[{"name":"Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7500AE, Enschede, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1026-5865","authenticated-orcid":false,"given":"Louise","family":"Willemen","sequence":"additional","affiliation":[{"name":"Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7500AE, Enschede, The Netherlands"}]}],"member":"1968","published-online":{"date-parts":[[2018,8,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ortenberg, F. (2011). Hyperspectral Sensor Characteristics: Airborne, Spaceborne, Hand-Held, and Truck-Mounted; Integration of Hyperspectral Data with LIDAR. Hyperspectral Remote Sensing of Vegetation, CRC Press.","DOI":"10.1201\/b11222-5"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"S92","DOI":"10.1016\/j.rse.2007.08.001","article-title":"Progress in field spectroscopy","volume":"113","author":"Milton","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1016\/j.ecolind.2016.11.003","article-title":"Optical trait indicators for remote sensing of plant species composition: Predictive power and seasonal variability","volume":"73","author":"Feilhauer","year":"2017","journal-title":"Ecol. Indic."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1023\/A:1007938526886","article-title":"Analysis of fine-scale spatial pattern of a grassland from remotely-sensed imagery and field collected data","volume":"13","author":"Lobo","year":"1998","journal-title":"Landscape Ecol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1659","DOI":"10.2307\/1939924","article-title":"Spatial Autocorrelation: Trouble or New Paradigm?","volume":"74","author":"Legendre","year":"1993","journal-title":"Ecology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.1365-2699.2011.02637.x","article-title":"Eight (and a half) deadly sins of spatial analysis: Spatial analysis","volume":"39","author":"Hawkins","year":"2012","journal-title":"J. Biogeogr."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/BF00048036","article-title":"Spatial pattern and ecological analysis","volume":"80","author":"Legendre","year":"1989","journal-title":"Vegetation"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1111\/j.1365-2699.2011.02523.x","article-title":"Spatial autocorrelation in predictors reduces the impact of positional uncertainty in occurrence data on species distribution modelling: Spatial autocorrelation and positional uncertainty","volume":"38","author":"Naimi","year":"2011","journal-title":"J. Biogeogr."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1111\/ecog.02881","article-title":"Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure","volume":"40","author":"Roberts","year":"2017","journal-title":"Ecography"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/0034-4257(89)90069-2","article-title":"Remote sensing of foliar chemistry","volume":"30","author":"Curran","year":"1989","journal-title":"Remote Sens. Environ."},{"key":"ref_11","first-page":"119","article-title":"Estimating canopy water content using hyperspectral remote sensing data","volume":"12","author":"Clevers","year":"2010","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1016\/j.isprsjprs.2011.09.013","article-title":"Mapping grassland leaf area index with airborne hyperspectral imagery: A comparison study of statistical approaches and inversion of radiative transfer models","volume":"66","author":"Darvishzadeh","year":"2011","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6279","DOI":"10.5194\/bg-10-6279-2013","article-title":"Remote sensing of LAI, chlorophyll and leaf nitrogen pools of crop- and grasslands in \ufb01ve European landscapes","volume":"10","author":"Boegh","year":"2013","journal-title":"Biogeosciences"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1038\/523403a","article-title":"Environmental science: Agree on biodiversity metrics to track from space","volume":"523","author":"Skidmore","year":"2015","journal-title":"Nature"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Qi, J., Inoue, Y., and Wiangwang, N. (2011). Hyperspectral Remote Sensing in Global Change Studies. Hyperspectral Remote Sensing of Vegetation, CRC Press.","DOI":"10.1201\/b11222-6"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Goodenough, D., Li, J., Asner, G., Schaepman, M., Ustin, S., and Dyk, A. (August, January 31). Combining Hyperspectral Remote Sensing and Physical Modeling for Applications in Land Ecosystems. Proceedings of the 2006 IEEE International Symposium on Geoscience and Remote Sensing, Denver, CO, USA.","DOI":"10.1109\/IGARSS.2006.518"},{"key":"ref_17","doi-asserted-by":"crossref","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":"ref_18","doi-asserted-by":"crossref","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":"ref_19","first-page":"80","article-title":"Hyperspectral Image Processing for Automatic Target Detection Applications","volume":"14","author":"Manolakis","year":"2003","journal-title":"Lincoln Lab. J."},{"key":"ref_20","first-page":"237","article-title":"Spectroscopic determination of leaf traits using infrared spectra","volume":"69","author":"Buitrago","year":"2018","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.isprsjprs.2013.03.004","article-title":"Changes in plant defense chemistry (pyrrolizidine alkaloids) revealed through high-resolution spectroscopy","volume":"80","author":"Carvalho","year":"2013","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_22","unstructured":"Skidmore, A.K., Turner, B.J., Brinkhof, W., and Knowles, E. (1997). Performance of a neural network: Mapping forests using gis and remotely sensed data. Photogramm. Eng. Remote Sens., 63."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yuan, H., Yang, G., Li, C., Wang, Y., Liu, J., Yu, H., Feng, H., Xu, B., Zhao, X., and Yang, X. (2017). Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models. Remote Sens., 9.","DOI":"10.3390\/rs9040309"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J.H. (2009). The Elements of Statistical Learning: Data Mining, Inference, And Prediction, Springer. [2nd ed.]. Springer series in statistics.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.isprsjprs.2017.09.012","article-title":"The Na\u00efve Overfitting Index Selection (NOIS): A new method to optimize model complexity for hyperspectral data","volume":"133","author":"Rocha","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to Statistical Learning: With Applications in R, Springer. Springer texts in statistics.","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kuhn, M., and Johnson, K. (2013). Applied Predictive Modeling, Springer.","DOI":"10.1007\/978-1-4614-6849-3"},{"key":"ref_28","unstructured":"Cochran, W.G. (1977). Sampling Techniques, Wiley. [3d ed.]. Wiley series in probability and mathematical statistics."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1111\/j.1600-0587.2012.07348.x","article-title":"Collinearity: A review of methods to deal with it and a simulation study evaluating their performance","volume":"36","author":"Dormann","year":"2013","journal-title":"Ecography"},{"key":"ref_30","first-page":"499","article-title":"Stability and Generalization","volume":"2","author":"Bousquet","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Brenning, A. (2012, January 22\u201327). Spatial cross-validation and bootstrap for the assessment of prediction rules in remote sensing: The R package sperrorest. Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany.","DOI":"10.1109\/IGARSS.2012.6352393"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2075","DOI":"10.1080\/01431160050021303","article-title":"Using vegetation reflectance variability for species level classification of hyperspectral data","volume":"21","author":"Cochrane","year":"2000","journal-title":"Int. J. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1590\/S0100-69162013000100018","article-title":"Influence of data acquisition geometry on soybean spectral response simulated by the prosail model","volume":"33","author":"Breunig","year":"2013","journal-title":"Eng. Agr\u00edc."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.agrformet.2016.02.001","article-title":"Comparison of optical LAI measurements under diffuse and clear skies after correcting for scattered radiation","volume":"221","author":"Pearse","year":"2016","journal-title":"Agric. For. Meteorol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.agrformet.2015.02.012","article-title":"Understanding the variability in ground-based methods for retrieving canopy openness, gap fraction, and leaf area index in diverse forest systems","volume":"205","author":"Woodgate","year":"2015","journal-title":"Agric. For. Meteorol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"16164","DOI":"10.3390\/rs71215817","article-title":"Evaluation of Sampling Methods for Validation of Remotely Sensed Fractional Vegetation Cover","volume":"7","author":"Mu","year":"2015","journal-title":"Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.spasta.2012.08.001","article-title":"A review of spatial sampling","volume":"2","author":"Wang","year":"2012","journal-title":"Spat. Stat."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"234","DOI":"10.2307\/143141","article-title":"A Computer Movie Simulating Urban Growth in the Detroit Region","volume":"46","author":"Tobler","year":"1970","journal-title":"Econ. Geogr."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/JSTARS.2012.2215582","article-title":"Multivariate Spatial Regression Models for Predicting Individual Tree Structure Variables Using LiDAR Data","volume":"6","author":"Babcock","year":"2013","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/s11749-010-0209-z","article-title":"A general science-based framework for dynamical spatio-temporal models","volume":"19","author":"Wikle","year":"2010","journal-title":"TEST"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Lovett, G.M., Jones, C.G., Turner, M.G., and Weathers, K.C. (2005). Ecosystem Function in Heterogeneous Landscapes, Springer.","DOI":"10.1007\/b104357"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"E185","DOI":"10.1073\/pnas.1210196109","article-title":"Hyperspectral remote sensing of foliar nitrogen content","volume":"110","author":"Knyazikhin","year":"2013","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1111\/j.2007.0906-7590.05171.x","article-title":"Methods to account for spatial autocorrelation in the analysis of species distributional data: A review","volume":"30","author":"Dormann","year":"2007","journal-title":"Ecography"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.spasta.2012.02.004","article-title":"Spatial statistics, spatial regression, and graph theory in ecology","volume":"1","author":"Fortin","year":"2012","journal-title":"Spat. Stat."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1111\/j.1365-3040.1992.tb00992.x","article-title":"Defining leaf area index for non-flat leaves","volume":"15","author":"Chen","year":"1992","journal-title":"Plant Cell Environ."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Bivand, R.S., G\u00f3mez-Rubio, V., and Rue, H. (2015). Spatial Data Analysis with R - INLA with Some Extensions. J. Stat. Softw., 63.","DOI":"10.18637\/jss.v063.i20"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1080\/01431160701268947","article-title":"Estimating structural and biochemical parameters for grassland from spectroradiometer data by radiative transfer modelling (PROSPECT+SAIL)","volume":"29","author":"Vohland","year":"2008","journal-title":"Int. J. Remote Sens."},{"key":"ref_48","first-page":"5","article-title":"Radiative Transfer Model parametrization for simulating the reflectance of meadow vegetation","volume":"18","year":"2014","journal-title":"Misc. Geogr."},{"key":"ref_49","unstructured":"Sobrino, J.A. (2002). Recent Advances in Quantitative Remote Sensing, Publicacions de la Universitat de Val\u00e8ncia. International Symposium on Recent Advances in Quantitative Remote Sensing."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"3030","DOI":"10.1016\/j.rse.2008.02.012","article-title":"PROSPECT-4 and 5: Advances in the leaf optical properties model separating photosynthetic pigments","volume":"112","author":"Feret","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Berger, K., Atzberger, C., Danner, M., D\u2019Urso, G., Mauser, W., Vuolo, F., and Hank, T. (2018). Evaluation of the PROSAIL Model Capabilities for Future Hyperspectral Model Environments: A Review Study. Remote Sens., 10.","DOI":"10.3390\/rs10010085"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.rse.2012.02.011","article-title":"Mapping spatio-temporal variation of grassland quantity and quality using MERIS data and the PROSAIL model","volume":"121","author":"Si","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/S0034-4257(98)00032-7","article-title":"Derivative Analysis of Hyperspectral Data","volume":"66","author":"Tsai","year":"1998","journal-title":"Remote Sens. Environ."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.rse.2015.03.033","article-title":"Multi-method ensemble selection of spectral bands related to leaf biochemistry","volume":"164","author":"Feilhauer","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"3762","DOI":"10.1016\/j.rse.2008.05.003","article-title":"A near-infrared narrow-waveband ratio to determine Leaf Area Index in orchards","volume":"112","author":"Delalieux","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/S0034-4257(99)00067-X","article-title":"Hyperspectral Vegetation Indices and Their Relationships with Agricultural Crop Characteristics","volume":"71","author":"Thenkabail","year":"2000","journal-title":"Remote Sens. Environ."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.agrformet.2013.02.013","article-title":"On the correct estimation of gap fraction: How to remove scattered radiation in gap fraction measurements?","volume":"174\u2013175","author":"Kobayashi","year":"2013","journal-title":"Agric. For. Meteorol."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1021\/ci0342472","article-title":"The Problem of Overfitting","volume":"44","author":"Hawkins","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Reichenau, T.G., Korres, W., Montzka, C., Fiener, P., Wilken, F., Stadler, A., Waldhoff, G., and Schneider, K. (2016). Spatial Heterogeneity of Leaf Area Index (LAI) and Its Temporal Course on Arable Land: Combining Field Measurements, Remote Sensing and Simulation in a Comprehensive Data Analysis Approach (CDAA). PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0158451"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/8\/1263\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:18:07Z","timestamp":1760195887000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/8\/1263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,11]]},"references-count":59,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2018,8]]}},"alternative-id":["rs10081263"],"URL":"https:\/\/doi.org\/10.3390\/rs10081263","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,11]]}}}