Spatial predictions of tree density and tree height across Mexico forests using ensemble learning and forest inventory data.

Autor: Barreras A; Department of Forest and Rangeland Stewardship Colorado State University Fort Collins Colorado USA.; Centro de Geociencias Universidad Nacional Autónoma de México Juriquilla Mexico., Alanís de la Rosa JA; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Mayorga R; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Cuenca R; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Moreno-G C; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Godínez C; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Delgado C; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Soriano-Luna MLÁ; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico.; US Forest Service, International Programs Washington District of Columbia USA., George S; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Aldrete-Leal MI; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Medina S; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Romero J; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Villela S; Comisión Nacional Forestal (CONAFOR) Zapopan Mexico., Lister A; US Forest Service, International Programs Washington District of Columbia USA., Sheridan R; US Forest Service, International Programs Washington District of Columbia USA., Flores R; US Forest Service, International Programs Washington District of Columbia USA., Crowther TW; Institute of Integrative Biology ETH Zurich Zürich Switzerland., Guevara M; Centro de Geociencias Universidad Nacional Autónoma de México Juriquilla Mexico.; Department of Environmental Sciences University of California Riverside California USA.; U.S. Salinity Laboratory, Agricultural Research Service United States Department of Agriculture Riverside California USA.
Jazyk: angličtina
Zdroj: Ecology and evolution [Ecol Evol] 2023 May 21; Vol. 13 (5), pp. e10090. Date of Electronic Publication: 2023 May 21 (Print Publication: 2023).
DOI: 10.1002/ece3.10090
Abstrakt: The National Forestry Commission of Mexico continuously monitors forest structure within the country's continental territory by the implementation of the National Forest and Soils Inventory (INFyS). Due to the challenges involved in collecting data exclusively from field surveys, there are spatial information gaps for important forest attributes. This can produce bias or increase uncertainty when generating estimates required to support forest management decisions. Our objective is to predict the spatial distribution of tree height and tree density in all Mexican forests. We performed wall-to-wall spatial predictions of both attributes in 1-km grids, using ensemble machine learning across each forest type in Mexico. Predictor variables include remote sensing imagery and other geospatial data (e.g., mean precipitation, surface temperature, canopy cover). Training data is from the 2009 to 2014 cycle ( n  > 26,000 sampling plots). Spatial cross validation suggested that the model had a better performance when predicting tree height r 2  = .35 [.12, .51] (mean [min, max]) than for tree density r 2  = .23 [.05, .42]. The best predictive performance when mapping tree height was for broadleaf and coniferous-broadleaf forests (model explained ~50% of variance). The best predictive performance when mapping tree density was for tropical forest (model explained ~40% of variance). Although most forests had relatively low uncertainty for tree height predictions, e.g., values <60%, arid and semiarid ecosystems had high uncertainty, e.g., values >80%. Uncertainty values for tree density predictions were >80% in most forests. The applied open science approach we present is easily replicable and scalable, thus it is helpful to assist in the decision-making and future of the National Forest and Soils Inventory. This work highlights the need for analytical tools that help us exploit the full potential of the Mexican forest inventory datasets.
Competing Interests: The authors declare that there is no conflict of interest.
(© 2023 The Authors. Ecology and Evolution published by John Wiley & Sons Ltd.)
Databáze: MEDLINE
Externí odkaz: