loading page

Spatial predictions of tree density and tree height across Mexico´s forests using ensemble learning and forest inventory data (2009-2014)
  • +15
  • Aylin Barreras,
  • José Alanís de la Rosa,
  • Rafael Mayorga,
  • Rubi Cuenca,
  • César Moreno-G,
  • Carlos Godinez,
  • Carina Delgado,
  • Maria de los Ángeles Soriano-Luna,
  • Stephanie George,
  • Sandra Medina,
  • Metzli Ileana Aldrete-Leal,
  • Johny Romero,
  • Sergio Villela,
  • Andrew Lister,
  • Rachel Sheridan,
  • Rafael Flores,
  • Tom Crowther,
  • Mario Guevara
Aylin Barreras
Universidad Nacional Autónoma de México Centro de Geociencias

Corresponding Author:[email protected]

Author Profile
José Alanís de la Rosa
Comisión Nacional Forestal
Author Profile
Rafael Mayorga
Comisión Nacional Forestal
Author Profile
Rubi Cuenca
Comisión Nacional Forestal
Author Profile
César Moreno-G
Comisión Nacional Forestal
Author Profile
Carlos Godinez
Comisión Nacional Forestal
Author Profile
Carina Delgado
Comisión Nacional Forestal
Author Profile
Maria de los Ángeles Soriano-Luna
Comisión Nacional Forestal
Author Profile
Stephanie George
Comisión Nacional Forestal
Author Profile
Sandra Medina
Comisión Nacional Forestal
Author Profile
Metzli Ileana Aldrete-Leal
Comisión Nacional Forestal
Author Profile
Johny Romero
Comisión Nacional Forestal
Author Profile
Sergio Villela
Comisión Nacional Forestal
Author Profile
Andrew Lister
US Forest Service International Programs
Author Profile
Rachel Sheridan
US Forest Service International Programs
Author Profile
Rafael Flores
US Forest Service International Programs
Author Profile
Tom Crowther
ETH Zurich
Author Profile
Mario Guevara
Universidad Nacional Autónoma de México Centro de Geociencias
Author Profile

Abstract

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., vegetation indexes, surface temperature). Training data is from the 2009-2014 cycle (n>26,000 sampling plots). Spatial cross validation suggested that the model had a better performance when predicting tree height r2=0.4 [0.15,0.55] (mean[min, max]) than for tree density r2=0.2[0.10,0.31]. Maximum values of tree height were for coniferous forests, coniferous-broadleaf forests and cloud mountain forest (~36 m, 30 m and 21 m, respectively). Tropical forests had maximum values of tree density (~1370 trees/ha), followed by tropical dry forest (1006 trees/ha) and coniferous forest (988 trees/ha). Although most forests had relatively low values of uncertainty, e.g., values <40%, arid and semiarid ecosystems had high uncertainty in both tree height and tree density predictions, e.g., values >60%. 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 technical capabilities aimed to use and resignify all the effort done by the Mexican Forestry Commission in implementing the INFyS.
07 Oct 2022Submission Checks Completed
07 Oct 2022Assigned to Editor
12 Oct 2022Reviewer(s) Assigned
19 Jan 2023Review(s) Completed, Editorial Evaluation Pending
20 Jan 2023Editorial Decision: Revise Minor
19 Mar 20231st Revision Received
22 Mar 2023Submission Checks Completed
22 Mar 2023Assigned to Editor
22 Mar 2023Review(s) Completed, Editorial Evaluation Pending
28 Apr 2023Editorial Decision: Accept