Continental-scale mapping of forest tree density in North America using remote sensing and deep learning with uncertainty quantificationOA
Accurate,spatially consistent estimates of tree density remain elusive at continental scales,limiting our ability to assess forest structure,carbon stocks,and biodiversity.Existing global assessments have relied on simplified statistical models and sparse,heterogeneous ground data that are insufficient to capture nonlinear ecological interactions and spatial variability.To address these limitations,we integrated more than 600,000 harmonized ground-based forest inventory plots with satellite-derived vegetation indices,climate surfaces,soil properties,and topographic covariates to develop a deep learning framework for high-resolution mapping of tree density across North America.We evaluated four modeling approaches-generalized linear models(GLMs),ridge regression(RR),random forest(RF),and a feedforward neural network(FFNN).Among all models tested,the FFNN achieved the highest predictive accuracy(RMSE=344.8;R 2=39.53%),and was used to produce a wall-to-wall tree density map at 3 km resolution for the continent.We estimated that the total number of forest trees with diameter at breast height(DBH)≥10 cm across North America ranges from 339 to 514 billion,substantially lower than the widely cited estimate of 603 billion trees reported by Crowther et al.(2015).When smaller stems were included(no DBH threshold),totals more than doubled,reaching 738 billion to 1.12 trillion trees.We quantified uncertainty using Monte Carlo(MC)Dropout,generating pixel-level error estimates and confidence intervals.Spatial patterns reveal high tree densities in boreal and temperate forests,intermediate densities in mixed broadleaf regions,and relatively low densities in deserts,Mediterranean systems,and tundra.Compared to the global GLM-based benchmark by Crowther et al.(2015),our deep learning framework achieves markedly higher predictive accuracy,aligns more closely with national forest inventory statistics,and provides explicit uncertainty quantification,supporting applications in carbon accounting,biodiversity modeling,and ecosystem monitoring at scales through region specific calibration and validation.
Mustak Ahmad;Yun Tang;Andrew J.Lister;Javier G.P.Gamarra;William G.Powell;Nathan R.Beane;Wook Jin Choi;Ankita Mitra;Amit Kumar;Anibal Cuchietti;Alain Paquette;Eric Searle;Jiaxin Chen;Han Y.H.Chen;Frans Bongers;Jorge A.Meave;Mario Guevara;Aylin Barreras;Jose Armando Alanís de la Rosa;Rafael Mayorga Saucedo;Rubi Angélica Cuenca Lara;César Moreno García;Carlos Isaías Godínez Valdivia;Carina Edith Delgado Caballero;María de los Angeles Soriano Luna;Metzli Ileana Aldrete Leal;Sandra Liliana Medina Casillas;Johny Romero Correa;Sergio Armando Villela Gaytán;J.Javier Corral Rivas;Jose Daniel Vega-Nieva;Jaime Briseño-Reyes;Pablito Marcelo López-Serrano;Tom M.Fayle;Jan Altman;Daniel J.Johnson;Jingjing Liang
Forest Advanced Computing and Artificial Intelligence(FACAI),Department of Forestry and Natural Resources,Purdue University,USASamsung Research America,USANorthern Research Station,Forest Inventory and Analysis Unit,USDA Forest Service,USAForestry Division,Food and Agriculture Organization of the United Nations(FAO),ItalyU.S.Army Engineer Research and Development Center(ERDC),Environmental Laboratory,Forest Ecosystem Dynamics Team,USAU.S.Army Engineer Research and Development Center(ERDC),Environmental Laboratory,Forest Ecosystem Dynamics Team,USAForest Advanced Computing and Artificial Intelligence(FACAI),Department of Forestry and Natural Resources,Purdue University,USAForest Advanced Computing and Artificial Intelligence(FACAI),Department of Forestry and Natural Resources,Purdue University,USAForest Advanced Computing and Artificial Intelligence(FACAI),Department of Forestry and Natural Resources,Purdue University,USA Department of Geography,Institute of Science,Banaras Hindu University,Varanasi 221005,IndiaForestry Division,Food and Agriculture Organization of the United Nations(FAO),ItalyCentre for Forest Research,Universitédu QuébecàMontréal(UQAM),CanadaOntario Forest Research Institute(OFRI),Ministry of Natural Resources(MNR),CanadaOntario Forest Research Institute(OFRI),Ministry of Natural Resources(MNR),CanadaFaculty of Natural Resources Management,Lakehead University,Thunder Bay,Ontario P7B 5E1,Canada Institute for Global Change Biology,School for Environment and Sustainability,University of Michigan,Ann Arbor,MI,USAWageningen University&Research,NetherlandsDepartamento de Ecología,Facultad de Ciencias,UNAM,CDMX,MexicoInstituto de Geociencias,UNAM,Querétaro,MexicoForest and Rangeland Stewardship Department,Colorado State University,USAComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoComisión Nacional Forestal(CONAFOR),MexicoUniversidad Juárez del Estado de Durango(UJED),MexicoUniversidad Juárez del Estado de Durango(UJED),MexicoUniversidad Juárez del Estado de Durango(UJED),MexicoUniversidad Juárez del Estado de Durango(UJED),MexicoSchool of Biological and Behavioural Sciences,Queen Mary University of London,UK Biology Centre of the Czech Academy of Sciences,Institute of Entomology,Ceske Budejovice,Czech RepublicInstitute of Botany of the Czech Academy of Sciences,Zámek 1,Průhonice 25243,Czech Republic Faculty of Forestry and Wood Sciences,Czech University of Life Sciences Prague,Kamýcká129,Praha 6,Suchdol 16500,Czech RepublicSchool of Forest,Fisheries,and Geomatics Sciences,University of Florida,USAForest Advanced Computing and Artificial Intelligence(FACAI),Department of Forestry and Natural Resources,Purdue University,USA
农业科技
Tree density estimationFeedforward neural network(FFNN)Remote sensingDeep learningUncertainty quantificationMonte Carlo(MC)dropout
《Forest Ecosystems》 2026 (3)
P.757-776,20
评论