{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:17:05Z","timestamp":1760145425788,"version":"build-2065373602"},"reference-count":60,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"U.S. Geological Survey Earth Resources Observation and Science Center","award":["G19AS00001","80NSSC21K1962"],"award-info":[{"award-number":["G19AS00001","80NSSC21K1962"]}]},{"name":"NASA","award":["G19AS00001","80NSSC21K1962"],"award-info":[{"award-number":["G19AS00001","80NSSC21K1962"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Landsat data have been used to derive forest canopy structure, height, and volume using machine learning models, i.e., giving computers the ability to learn from data and make decisions and predictions without being explicitly programmed, with training data provided by ground measurement or airborne lidar. This study explored the potential use of Landsat reflectance and airborne lidar data as training data to estimate canopy heights in the Brazilian Amazon forest and examined the impacts of Landsat reflectance products at different process levels and sample spatial autocorrelation on random forest modeling. Specifically, this study assessed the accuracy of canopy height predictions from random forest regression models impacted by three different Landsat 8 reflectance product inputs (i.e., USGS level 1 top of atmosphere reflectance, USGS level 2 surface reflectance, and NASA nadir bidirectional reflectance distribution function (BRDF) adjusted reflectance (NBAR)), sample sizes, training\/test split strategies, and geographic coordinates. In the establishment of random forest regression models, the dependent variable (i.e., the response variable) was the dominant canopy heights at a 90 m resolution derived from airborne lidar data, while the independent variables (i.e., the predictor variables) were the temporal metrics extracted from each Landsat reflectance product. The results indicated that the choice of Landsat reflectance products had an impact on model accuracy, with NBAR data yielding more trustful results than the other products despite having higher RMSE values. Training and test split strategy also affected the derived model accuracy metrics, with the random sample split (randomly distributed training and test samples) showing inflated accuracy compared to the spatial split (training and test samples spatially set apart). Such inflation was induced by the spatial autocorrelation that existed between training and test data in the random split. The inclusion of geographic coordinates as independent variables improved model accuracy in the random split strategy but not in the spatial split, where training and test samples had different geographic coordinate ranges. The study highlighted the importance of data processing levels and the training and test split methods in random forest modeling of canopy height.<\/jats:p>","DOI":"10.3390\/rs16142571","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T12:44:36Z","timestamp":1721047476000},"page":"2571","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Estimating Brazilian Amazon Canopy Height Using Landsat Reflectance Products in a Random Forest Model with Lidar as Reference Data"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0656-8196","authenticated-orcid":false,"given":"Pedro V. C.","family":"Oliveira","sequence":"first","affiliation":[{"name":"Imaging Center, Image Processing Laboratory, South Dakota State University, Brookings, SD 57007, USA"},{"name":"Geospatial Sciences Center of Excellence, South Dakota State University, Brookings, SD 57007, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4470-3616","authenticated-orcid":false,"given":"Hankui K.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Geospatial Sciences Center of Excellence, South Dakota State University, Brookings, SD 57007, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8456-0547","authenticated-orcid":false,"given":"Xiaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Geospatial Sciences Center of Excellence, South Dakota State University, Brookings, SD 57007, USA"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"045023","DOI":"10.1088\/1748-9326\/2\/4\/045023","article-title":"Monitoring and Estimating Tropical Forest Carbon Stocks: Making REDD a Reality","volume":"2","author":"Gibbs","year":"2007","journal-title":"Environ. Res. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1007\/s10584-014-1058-7","article-title":"Amazon Forest Biomass Density Maps: Tackling the Uncertainty in Carbon Emission Estimates","volume":"124","author":"Ometto","year":"2014","journal-title":"Clim. Chang."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1038\/s41597-023-02575-4","article-title":"A biomass map of the Brazilian Amazon from multisource remote sensing","volume":"10","author":"Ometto","year":"2023","journal-title":"Sci. Data"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1038\/s41467-017-02771-y","article-title":"21st Century Drought-Related Fires Counteract the Decline of Amazon Deforestation Carbon Emissions","volume":"9","author":"Anderson","year":"2018","journal-title":"Nat. Commun."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1023\/A:1005336724350","article-title":"Greenhouse gases from deforestation in Brazilian Amazonia: Net committed emissions","volume":"35","author":"Fearnside","year":"1997","journal-title":"Clim. Chang."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1890\/1540-9295(2007)5[25:ARFDAL]2.0.CO;2","article-title":"Amazonia revealed: Forest degradation and loss of ecosystem goods and services in the Amazon Basin","volume":"5","author":"Foley","year":"2007","journal-title":"Front. Ecol. Environ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.1111\/gcb.12798","article-title":"Carbon Stock Loss from Deforestation through 2013 in Brazilian Amazonia","volume":"21","author":"Nogueira","year":"2015","journal-title":"Glob. Chang. Biol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3177","DOI":"10.1111\/gcb.12629","article-title":"Improved Allometric Models to Estimate the Aboveground Biomass of Tropical Trees","volume":"20","author":"Chave","year":"2014","journal-title":"Glob. Chang. Biol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1111\/gcb.13388","article-title":"Allometric equations for integrating remote sensing imagery into forest monitoring programmes","volume":"23","author":"Jucker","year":"2017","journal-title":"Glob. Chang. Biol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"20170048","DOI":"10.1098\/rsfs.2017.0048","article-title":"Weighing trees with lasers: Advances, challenges and opportunities","volume":"8","author":"Disney","year":"2018","journal-title":"Interface Focus"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"112845","DOI":"10.1016\/j.rse.2021.112845","article-title":"Aboveground Biomass Density Models for NASA\u2019s Global Ecosystem Dynamics Investigation (GEDI) Lidar Mission","volume":"270","author":"Duncanson","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"112234","DOI":"10.1016\/j.rse.2020.112234","article-title":"Fusing Simulated GEDI, ICESat-2 and NISAR Data for Regional Aboveground Biomass Mapping","volume":"253","author":"Silva","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"112760","DOI":"10.1016\/j.rse.2021.112760","article-title":"Global Canopy Height Regression and Uncertainty Estimation from GEDI LIDAR Waveforms with Deep Ensembles","volume":"268","author":"Lang","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"L15401","DOI":"10.1029\/2010GL043622","article-title":"A Global Forest Canopy Height Map from the Moderate Resolution Imaging Spectroradiometer and the Geoscience Laser Altimeter System","volume":"37","author":"Lefsky","year":"2010","journal-title":"Geophys. Res. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Simard, M., Pinto, N., Fisher, J.B., and Baccini, A. (2011). Mapping Forest Canopy Height Globally with Spaceborne Lidar. J. Geophys. Res. Biogeosci., 116.","DOI":"10.1029\/2011JG001708"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"413","DOI":"10.5194\/gmd-5-413-2012","article-title":"Vegetation Height and Cover Fraction between 60\u00b0 S and 60\u00b0 N from ICESat GLAS Data","volume":"5","author":"Los","year":"2012","journal-title":"Geosci. Model Dev."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"L21S01","DOI":"10.1029\/2005GL024009","article-title":"Overview of the ICESat Mission","volume":"32","author":"Schutz","year":"2005","journal-title":"Geophys. Res. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.isprsjprs.2014.11.007","article-title":"Characterizing Stand-Level Forest Canopy Cover and Height Using Landsat Time Series, Samples of Airborne LiDAR, and the Random Forest Algorithm","volume":"101","author":"Ahmed","year":"2015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.rse.2016.02.023","article-title":"Mapping Tree Height Distributions in Sub-Saharan Africa Using Landsat 7 and 8 Data","volume":"185","author":"Hansen","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"10750","DOI":"10.3390\/rs61110750","article-title":"Estimation of Airborne Lidar-Derived Tropical Forest Canopy Height Using Landsat Time Series in Cambodia","volume":"6","author":"Ota","year":"2014","journal-title":"Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.rse.2011.08.027","article-title":"Quantifying Forest Cover Loss in Democratic Republic of the Congo, 2000-2010, with Landsat ETM+ Data","volume":"122","author":"Potapov","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_22","unstructured":"Cliff, A.D., and Ord, J.K. (1981). Spatial Processes: Models & Applications, Pion."},{"key":"ref_23","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_24","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1111\/j.1600-0587.2000.tb00265.x","article-title":"Red-Shifts and Red Herrings in Geographical Ecology","volume":"23","author":"Lennon","year":"2000","journal-title":"Ecography"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mascaro, J., Asner, G.P., Knapp, D.E., Kennedy-Bowdoin, T., Martin, R.E., Anderson, C., Higgins, M., and Chadwick, K.D. (2014). A Tale of Two \u201cForests\u201d: Random Forest Machine Learning Aids Tropical Forest Carbon Mapping. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0085993"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s13021-016-0062-9","article-title":"Performance of Non-Parametric Algorithms for Spatial Mapping of Tropical Forest Structure","volume":"11","author":"Xu","year":"2016","journal-title":"Carbon Balance Manag."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2715","DOI":"10.1007\/s10994-021-05972-1","article-title":"Spatial Dependence between Training and Test Sets: Another Pitfall of Classification Accuracy Assessment in Remote Sensing","volume":"111","author":"Karasiak","year":"2022","journal-title":"Mach. Learn."},{"key":"ref_28","unstructured":"IBGE (2012). Manual T\u00e9cnico da Vegeta\u00e7\u00e3o Brasileira, IBGE. [2nd ed.]."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"E4","DOI":"10.1038\/nature16457","article-title":"Dry-season greening of Amazon forests","volume":"531","author":"Saleska","year":"2016","journal-title":"Nature"},{"key":"ref_30","unstructured":"Ometto, J.P., Gorgens, B.G., Assis, M., Cantinho, R.Z., Pereira, F.R.d.S., and Sato, L.Y. (2024, June 25). L3A\u2014Summary of Airborne LiDAR Transects Collected by EBA in the Brazilian Amazon (Version 20210616) [Data Set]. Zenodo 2021. Available online: https:\/\/zenodo.org\/records\/4968706."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"6762","DOI":"10.1364\/AO.45.006762","article-title":"Validation of a Vector Version of the 6S Radiative Transfer Code for Atmospheric Correction of Satellite Data. Part I: Path Radiance","volume":"45","author":"Kotchenova","year":"2006","journal-title":"Appl. Opt."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3855","DOI":"10.1080\/01431160010006926","article-title":"Cloud cover in Landsat observations of the Brazilian Amazon","volume":"22","author":"Asner","year":"2001","journal-title":"Int. J. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"100103","DOI":"10.1016\/j.srs.2023.100103","article-title":"The 50-Year Landsat Collection 2 Archive","volume":"8","author":"Crawford","year":"2023","journal-title":"Sci. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.rse.2016.01.023","article-title":"A General Method to Normalize Landsat Reflectance Data to Nadir BRDF Adjusted Reflectance","volume":"176","author":"Roy","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3591","DOI":"10.1109\/TGRS.2018.2885967","article-title":"Investigation of Sentinel-2 bidirectional reflectance hot-spot sensing conditions","volume":"57","author":"Li","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","unstructured":"Masek, J., Ju, J., Roger, J., Skakun, S., Vermote, E., Claverie, M., Dungan, J., Yin, Z., Freitag, B., and Justice, C. (2024, June 25). HLS Operational Land Imager Surface Reflectance and TOA Brightness Daily Global 30m (v2.0) [Data Set]. NASA EOSDIS Land Processes DAAC 2021, Available online: https:\/\/lpdaac.usgs.gov\/products\/hlsl30v002\/."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"111205","DOI":"10.1016\/j.rse.2019.05.024","article-title":"Fmask 4.0: Improved Cloud and Cloud Shadow Detection in Landsats 4\u20138 and Sentinel-2 Imagery","volume":"231","author":"Qiu","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/0034-4257(95)00142-5","article-title":"Global Discrimination of Land Cover Types from Metrics Derived from AVHRR Pathfinder Data","volume":"54","author":"DeFries","year":"1995","journal-title":"Remote Sens. Environ."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.rse.2017.05.024","article-title":"Using the 500 m MODIS land cover product to derive a consistent continental scale 30 m Landsat land cover classification","volume":"197","author":"Zhang","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_40","unstructured":"McGaughey, R.J. (2023). FUSION\/LDV: Software for LIDAR Data Analysis and Visualization v. 4.50."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/S0924-2716(98)00009-4","article-title":"Determination of Terrain Models in Wooded Areas with Airborne Laser Scanner Data","volume":"53","author":"Kraus","year":"1998","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/s00468-006-0119-6","article-title":"Estimating Canopy Structure of Douglas-Fir Forest Stands from Discrete-Return LiDAR","volume":"21","author":"Coops","year":"2007","journal-title":"Trees -Struct. Funct."},{"key":"ref_43","unstructured":"Cochran, W.G. (1977). Sampling Techniques, John Wiley & Sons. [3rd ed.]."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/S0034-4257(01)00295-4","article-title":"Status of Land Cover Classification Accuracy Assessment","volume":"80","author":"Foody","year":"2002","journal-title":"Remote Sens. Environ."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2272","DOI":"10.1016\/j.rse.2007.10.004","article-title":"Mapping Land-Cover Modifications over Large Areas: A Comparison of Machine Learning Algorithms","volume":"112","author":"Rogan","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1016\/j.rse.2014.11.024","article-title":"Improved Time Series Land Cover Classification by Missing-Observation-Adaptive Nonlinear Dimensionality Reduction","volume":"158","author":"Yan","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_47","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_48","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"ref_49","unstructured":"Legendre, P., and Legendre, L. (1998). Numerical Ecology, Elsevier. [3rd ed.]."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1046\/j.1466-822X.2003.00322.x","article-title":"Spatial Autocorrelation and Red Herrings in Geographical Ecology","volume":"12","author":"Bini","year":"2003","journal-title":"Glob. Ecol. Biogeogr."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.rse.2018.02.026","article-title":"A Comparison of Resampling Methods for Remote Sensing Classification and Accuracy Assessment","volume":"208","author":"Lyons","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.ecolmodel.2019.06.002","article-title":"Hyperparameter Tuning and Performance Assessment of Statistical and Machine-Learning Algorithms Using Spatial Data","volume":"406","author":"Schratz","year":"2019","journal-title":"Ecol. Modell."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.ecolmodel.2006.12.012","article-title":"Incorporating Spatial Dependence in Predictive Vegetation Models","volume":"202","author":"Miller","year":"2007","journal-title":"Ecol. Modell."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1111\/j.1538-4632.1992.tb00261.x","article-title":"The Analysis of Spatial Association by Use of Distance Statistics","volume":"24","author":"Getis","year":"1992","journal-title":"Geogr. Anal."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"2223","DOI":"10.1080\/014311698214983","article-title":"Local Spatial Autocorrelation Characteristics of Remotely Sensed Imagery Assessed with the Getis Statistic","volume":"19","author":"Wulder","year":"1998","journal-title":"Int. J. Remote Sens."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1080\/01431160903252327","article-title":"Contextual Land-Cover Classification: Incorporating Spatial Dependence in Land-Cover Classification Models Using Random Forests and the Getis Statistic","volume":"1","author":"Ghimire","year":"2010","journal-title":"Remote Sens. Lett."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/S0304-3800(01)00501-4","article-title":"All-Scale Spatial Analysis of Ecological Data by Means of Principal Coordinates of Neighbour Matrices","volume":"153","author":"Borcard","year":"2002","journal-title":"Ecol. Modell."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_59","first-page":"103938","article-title":"Status, advancements and prospects of deep learning methods applied in forest studies","volume":"131","author":"Yun","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1111\/gcb.15423","article-title":"Resource Availability and Disturbance Shape Maximum Tree Height across the Amazon","volume":"27","author":"Gorgens","year":"2021","journal-title":"Glob. Chang. Biol."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/14\/2571\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:16:21Z","timestamp":1760109381000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/14\/2571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":60,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["rs16142571"],"URL":"https:\/\/doi.org\/10.3390\/rs16142571","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2024,7,13]]}}}