{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T09:33:46Z","timestamp":1761989626929,"version":"build-2065373602"},"reference-count":64,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008137","name":"Ontario Ministry of Natural Resources","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/100008137","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ontario Power Generation","award":["NA"],"award-info":[{"award-number":["NA"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Aerial-photo interpreted inventories of forest resources, including tree species composition, are valuable in forest resource management, but are expensive to create and can be relatively inaccurate. Because of differences among tree species in their spectral properties and seasonal phenologies, it might be possible to improve such forest resource inventory information (FRI) by using it in concert with multispectral satellite information from multiple time periods. We used Sentinel-2 information from nine spectral bands and 12 dates within a two-year period to model multivariate percent tree species composition in &gt;51,000 forest stands in the FRI of south-central Ontario, Canada. Accuracy of random forest (RF) and convolutional neural network (CNN) predictions were tested using species-specific basal area information from 155 0.25-ha field plots. Additionally, we created models using the Sentinel-2 information in concert with the field data and compared the accuracy of these models and the FRI-based models by use of basal areas from a second (13.7-ha) field data set. Based on average R2 values across species in the two field data sets, the Sentinel-FRI models outperformed the FRI, showing 1.5- and 1.7-fold improvements relative to the FRI for RF and 2.1- and 2.2-fold improvements for CNN (mean R2: 0.141\u20130.169 (FRI); 0.217\u20130.295 (RF); 0.307\u20130.352 (CNN)). Models created with the field data performed even better: improvements relative to the FRI were 2.1-fold for RF and 2.8-fold for CNN (mean R2: 0.169 (FRI); 0.356 (RF); 0.469 (CNN)). As predicted, R2 values between FRI- and field-trained predictions were higher than R2 values with the FRI. Of the 21 tree species evaluated, 8 relatively rare species had poor models in all cases. Our multivariate approach allowed us to use more FRI stands in model creation than if we had been restricted to stands dominated by single species and allowed us to map species abundances at higher resolution. It might be possible to improve models further by use of tree stem maps and incorporation of the effects of canopy disturbances.<\/jats:p>","DOI":"10.3390\/rs13214297","type":"journal-article","created":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T23:54:33Z","timestamp":1635292473000},"page":"4297","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory"],"prefix":"10.3390","volume":"13","author":[{"given":"Jay R.","family":"Malcolm","sequence":"first","affiliation":[{"name":"Institute of Forestry and Conservation, University of Toronto, 33 Willcocks St., Toronto, ON M5S 3B3, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0917-2074","authenticated-orcid":false,"given":"Braiden","family":"Brousseau","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, 10 King\u2019s College Road, Toronto, ON M5S 3G4, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6943-6097","authenticated-orcid":false,"given":"Trevor","family":"Jones","sequence":"additional","affiliation":[{"name":"Natural Resources Canada, Canadian Forest Service, Canadian Wood Fibre Centre, 1219 Queen St. East, Sault Ste Marie, ON P6A 2E5, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0686-2483","authenticated-orcid":false,"given":"Sean C.","family":"Thomas","sequence":"additional","affiliation":[{"name":"Institute of Forestry and Conservation, University of Toronto, 33 Willcocks St., Toronto, ON M5S 3B3, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2262","DOI":"10.1016\/j.foreco.2009.03.005","article-title":"Remote sensing and forest inventory for wildlife habitat assessment","volume":"257","author":"McDermid","year":"2009","journal-title":"For. Ecol. Manag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"247","DOI":"10.5558\/tfc83247-2","article-title":"Validating tree species composition in forest resource inventory for Nipissing Forest, Ontario, Canada","volume":"83","author":"Pinto","year":"2007","journal-title":"For. Chron."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"46","DOI":"10.5558\/tfc84046-1","article-title":"Yield prediction for mixed species stands in boreal Ontario","volume":"84","author":"Penner","year":"2008","journal-title":"For. Chron."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1007\/s10342-011-0577-2","article-title":"Satellite-based stand-wise forest cover type mapping using a spatially adaptive classification approach","volume":"131","author":"Stoffels","year":"2012","journal-title":"Eur. J. For. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1139\/cjfr-2020-0322","article-title":"From comprehensive field inventories to remotely sensed wall-to-wall stand attribute data\u2014A brief history of management inventories in the Nordic countries","volume":"51","author":"Maltamo","year":"2021","journal-title":"Can. J. For. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/978-94-017-8663-8_12","article-title":"Species-specific management inventory in Finland","volume":"Volume 27","author":"Maltamo","year":"2014","journal-title":"Forestry Applications of Airborne Laser Scanning: Concepts and Case Studies"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/S0378-1127(96)03940-0","article-title":"Identification and description of forested vegetation communities available to woodland caribou: Relating wildlife habitat to forest cover data","volume":"93","author":"Rettie","year":"1997","journal-title":"For. Ecol. Manag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"91","DOI":"10.5558\/tfc80091-1","article-title":"Potential indicators of the impacts of forest management on wildlife habitat in northeastern Ontario: A multivariate application of wildlife habitat suitability matrices","volume":"80","author":"Malcolm","year":"2004","journal-title":"For. Chron."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1016\/j.foreco.2008.05.037","article-title":"A novel approach to optimize management strategies for carbon stored in both forests and wood products","volume":"256","author":"Hennigar","year":"2008","journal-title":"For. Ecol. Manag."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1007\/s10584-020-02711-8","article-title":"Forest harvesting and the carbon debt in boreal east-central Canada","volume":"161","author":"Malcolm","year":"2020","journal-title":"Clim. Chang."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"439","DOI":"10.5558\/tfc2012-080","article-title":"Uncertainty in photo-interpreted forest inventory variables and effects on estimates of error in Canada\u2019s national forest inventory","volume":"88","author":"Magnussen","year":"2012","journal-title":"For. Chron."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.foreco.2007.06.033","article-title":"Accuracy of forest inventory mapping: Some implications for boreal forest management","volume":"252","author":"Thompson","year":"2007","journal-title":"For. Ecol. Manag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"77","DOI":"10.5558\/tfc86077-1","article-title":"A comparison of forest resource inventory, provincial land cover maps and field surveys for wildlife habitat analysis in the Great Lakes\u2014St. Lawrence forest","volume":"86","author":"Maxie","year":"2010","journal-title":"For. Chron."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"851","DOI":"10.5558\/tfc75851-5","article-title":"The validity of forest maps for the description of wildlife habitats on the local level\u2014A case study in the Abitibi-Temiscamingue region","volume":"75","author":"Potvin","year":"1999","journal-title":"For. Chron."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2457","DOI":"10.3390\/rs4082457","article-title":"Semi-supervised methods to identify individual crowns of lowland tropical canopy species using imaging spectroscopy and Lidar","volume":"4","author":"Asner","year":"2012","journal-title":"Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hartling, S., Sagan, V., Sidike, P., Maimaitijiang, M., and Carron, J. (2019). Urban tree species classification using a Worldview-2\/3 and LiDAR data fusion approach and deep learning. Sensors, 19.","DOI":"10.3390\/s19061284"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Immitzer, M., Neuwirth, M., B\u00f6ck, S., Brenner, H., Vuolo, F., and Atzberger, C. (2019). Optimal input features for tree species classification in central Europe based on multi-temporal Sentinel-2 data. Remote Sens., 11.","DOI":"10.3390\/rs11222599"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"172","DOI":"10.25518\/1780-4507.16524","article-title":"Forest mapping and species composition using supervised per pixel classification of Sentinel-2 imagery","volume":"22","author":"Bolyn","year":"2018","journal-title":"Biotech. Agron. Soc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1982","DOI":"10.1016\/j.rse.2007.03.032","article-title":"Combining national forest inventory field plots and remote sensing data for forest databases","volume":"112","author":"Tomppo","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.foreco.2017.07.017","article-title":"Multivariate inference for forest inventories using auxiliary airborne laser scanning data","volume":"401","author":"McRoberts","year":"2017","journal-title":"For. Ecol. Manag."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","article-title":"Random Forest in remote sensing: A review of applications and future directions","volume":"114","author":"Belgiu","year":"2016","journal-title":"ISPRS J. Photogramm."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Liu, Y., Gong, W., Hu, X., and Gong, J. (2018). Forest type identification with Random Forest using Sentinel-1A, Sentinel-2A, multi-temporal Landsat-8 and DEM data. Remote Sens., 10.","DOI":"10.3390\/rs10060946"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rezaee, M., Zhang, Y., Mishra, R., Tong, F., and Tong, H. (2018, January 19\u201320). Using a VGG-16 Network for individual tree species detection with an object-based approach. Proceedings of the 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2018, Beijing, Chinas.","DOI":"10.1109\/PRRS.2018.8486395"},{"key":"ref_24","unstructured":"Rowe, J.S. (1972). Forest Regions of Canada."},{"key":"ref_25","unstructured":"(2020, August 15). Environment Canada, Canadian Climate Normals 1981\u20132010, Haliburton, Ontario. Available online: https:\/\/climate.weather.gc.ca\/climate_normals\/."},{"key":"ref_26","unstructured":"OMNR (2001). Forest Information Manual."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Persson, M., Lindberg, E., and Reese, H. (2018). Tree species classification with multi-temporal Sentinel-2 data. Remote Sens., 10.","DOI":"10.3390\/rs10111794"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"104473","DOI":"10.1016\/j.cageo.2020.104473","article-title":"\u201csen2r\u201d: An R toolbox for automatically downloading and preprocessing Sentinel-2 satellite data","volume":"139","author":"Ranghetti","year":"2020","journal-title":"Comput. Geosci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.1139\/cjfr-2015-0018","article-title":"A simple area-based model for predicting airborne LiDAR first returns from stem diameter distributions: An example study in an uneven-aged, mixed temperate forest","volume":"45","author":"Spriggs","year":"2015","journal-title":"Can. J. For. Res."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Condit, R.S. (1998). Tropical Forest Census Plots\u2014Methods and Results from Barro Colorado Island, Panama and a Comparison with Other Plots, R G. Landes Company.","DOI":"10.1007\/978-3-662-03664-8"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1111\/gcb.12712","article-title":"CTFS-ForestGEO: A worldwide network monitoring forests in an era of global change","volume":"21","author":"Davies","year":"2015","journal-title":"Glob. Chang. Biol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1093\/treephys\/tpq005","article-title":"Photosynthetic capacity peaks at intermediate size in temperate deciduous trees","volume":"30","author":"Thomas","year":"2010","journal-title":"Tree Physiol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1002\/widm.12","article-title":"Multivariate random forests","volume":"1","author":"Segal","year":"2011","journal-title":"WIRES Data Min. Knowl."},{"key":"ref_35","unstructured":"Ishwaran, H., and Kogalur, U.B. (2020, January 16). Fast Unified Random Forests for Survival, Regression, and Classification (RF-SRC) 2020. R Package Version 2.9.3. Available online: https:\/\/cran.r-project.org\/web\/packages\/randomForestSRC\/randomForestSRC.pdf."},{"key":"ref_36","first-page":"360","article-title":"Estimation of forest structural and compositional variables using ALS data and multi-seasonal satellite imagery","volume":"78","author":"Shang","year":"2019","journal-title":"Int. J. Appl. Earth Obs."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lim, J., Kim, K.M., and Jin, R. (2019). Tree species classification using Hyperion and Sentinel-2 data with machine learning in South Korea and China. ISPRS Int. Geo-Inf., 8.","DOI":"10.3390\/ijgi8030150"},{"key":"ref_38","unstructured":"Oksanen, J., Blanchet, F.G., Friendly, M., Kindt, R., Legendre, P., McGlinn, D., Minchin, P.R., O\u2019Hara, R.B., Simpson, G.L., and Solymos, P. (2020, January 16). Vegan: Community Ecology Package 2019. R Package Version 2.5-6. Available online: https:\/\/cran.r-project.org\/web\/packages\/vegan\/vegan.pdf."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Khan, S., Hossein, R., Syed, A.S., Mohammed, B., Gerard, M., and Dickinson, S. (2018). A Guide to Convolutional Neural Networks for Computer Vision, Morgan & Claypool.","DOI":"10.1007\/978-3-031-01821-3_4"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.isprsjprs.2019.10.011","article-title":"Deep learning for conifer\/deciduous classification of airborne LiDAR 3D point clouds representing individual trees","volume":"158","author":"Hamraz","year":"2019","journal-title":"ISPRS J. Photogramm."},{"key":"ref_42","unstructured":"Wang, S., Cao, J., and Yu, P. (2020). Deep learning for spatio-temporal data mining: A survey. IEEE Trans. Knowl. Data Eng."},{"key":"ref_43","unstructured":"Ping, W., Peng, K., Gibiansky, A., Arik, S.\u00d6., Kannan, A., Narang, S., Raiman, J., and Miller, J. (2018). Deep voice 3: 2000-speaker neural text-to-speech. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Brousseau, B., Rose, J., and Eizenman, M. (2020). Hybrid eye-tracking on a smartphone with CNN feature extraction and an infrared 3D model. Sensors, 20.","DOI":"10.3390\/s20020543"},{"key":"ref_45","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). Tensorflow: A system for large-scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, Savannah, GA, USA."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Bergstra, J., Yamins, D., and Cox, D.D. (2013, January 24\u201329). Hyperopt: A Python library for optimizing the hyperparameters of machine learning algorithms. Proceedings of the 12th Python in Science Conference, Austin, TX, USA.","DOI":"10.25080\/Majora-8b375195-003"},{"key":"ref_47","unstructured":"R Core Team (2020). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing. Available online: https:\/\/www.R-project.org\/."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Grabska, E., Hostert, P., Pflugmacher, D., and Ostapowicz, K. (2019). Forest stand species mapping using the Sentinel-2 time series. Remote Sens., 11.","DOI":"10.3390\/rs11101197"},{"key":"ref_49","unstructured":"Chen, C., Liaw, A., and Breiman, L. (2021, April 22). Using Random Forest to Learn Imbalanced Data. Available online: https:\/\/statistics.berkeley.edu\/sites\/default\/files\/tech-reports\/666.pdf."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"6827","DOI":"10.5194\/bg-11-6827-2014","article-title":"Local spatial structure of forest biomass and its consequences for remote sensing of carbon stocks","volume":"11","author":"Detto","year":"2014","journal-title":"Biogeosciences"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1111\/j.1365-2745.2011.01935.x","article-title":"A forest structure model that determines crown layers and partitions growth and mortality rates for landscape-scale applications of tropical forests","volume":"100","author":"Bohlman","year":"2012","journal-title":"J. Ecol."},{"key":"ref_52","first-page":"102318","article-title":"Tree species classification using Sentinel-2 imagery and Bayesian inference","volume":"100","author":"Axelsson","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_53","first-page":"102376","article-title":"Mapping cropping intensity in Huaihe basin using phenology algorithm, all Sentinel-2 and Landsat images in Google Earth Engine","volume":"102","author":"Pan","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"175","DOI":"10.5589\/m05-004","article-title":"Issues in species classification of trees in old growth conifer stands","volume":"31","author":"Leckie","year":"2005","journal-title":"Can. J. Remote Sens."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1080\/2150704X.2016.1274443","article-title":"Urban landcover classification from multispectral image data using optimized adaboosted random forests","volume":"8","author":"Isaac","year":"2017","journal-title":"Remote Sens. Lett."},{"key":"ref_56","first-page":"1082","article-title":"Cascaded Random Forest for hyperspectral image classification","volume":"11","author":"Zhang","year":"2018","journal-title":"IEEE J. Sel. Top. Appl."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Ho\u015bci\u0142o, A., and Lewandowska, A. (2019). Mapping forest type and tree species on a regional scale using multi-temporal Sentinel-2 data. Remote Sens., 11.","DOI":"10.3390\/rs11080929"},{"key":"ref_58","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel."},{"key":"ref_59","unstructured":"Clevert, D.-A., Unterthiner, T., and Hochreiter, S. (2016). Fast and accurate deep network learning by exponential linear units (elus). arXiv."},{"key":"ref_60","unstructured":"Kingma, D.P., and Ba, J.L.B. (2015). ADAM: A Method for stochastic optimization. arXiv."},{"key":"ref_61","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_62","first-page":"26","article-title":"Lecture 6.5-Rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA Neural Netw. Mach. Learn."},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Lechevallier, Y., and Saporta, G. (2010). Large-scale machine learning with stochastic gradient descent. Proceedings of COMPSTAT\u20192010, Physica-Verlag HD.","DOI":"10.1007\/978-3-7908-2604-3"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Stat."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/21\/4297\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:23:46Z","timestamp":1760167426000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/21\/4297"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":64,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["rs13214297"],"URL":"https:\/\/doi.org\/10.3390\/rs13214297","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2021,10,26]]}}}