Dépôt numérique
RECHERCHER

Estimating species-specific leaf area index and basal area using optical and SAR remote sensing data in Acadian mixed spruce-fir forests, USA.

Bhattarai, Rajeev; Rahimzadeh-Bajgiran, Parinaz; Weiskittel, Aaron; Homayouni, Saeid ORCID logoORCID: https://orcid.org/0000-0002-0214-5356; Gara, Tawanda W. et Hanavan, Ryan P. (2022). Estimating species-specific leaf area index and basal area using optical and SAR remote sensing data in Acadian mixed spruce-fir forests, USA. International Journal of Applied Earth Observation and Geoinformation , vol. 108 . p. 102727. DOI: 10.1016/j.jag.2022.102727.

Ce document n'est pas hébergé sur EspaceINRS.

Résumé

This study combined Sentinel-1 synthetic aperture radar (SAR), Sentinel-2 multispectral, and site variable datasets to model leaf area index (LAI) and basal area per ha (BAPH) of two economically important tree species in Northeast, USA; red spruce (Picea rubens Sarg.; RS), and balsam fir (Abies balsamea (L.) Mill.; BF). We used Random Forest (RF), and Multi-Layer Perceptron (MLP) algorithms for LAI and BAPH modeling. The results showed that RF outperformed MLP by reducing the normalized root mean square error (nRMSE) by 0.01 and 0.06 for LAI and BAPH, respectively. The final variables selected for modeling of both LAI and BAPH indicated the superiority of Sentinel-2 variables over the Sentinel-1 SAR with minor contributions of site variables (mainly elevation). The red-edge spectral vegetation indices played a significant role in both LAI and BAPH estimation. We attained the lowest nRMSEs of 0.12, and 0.16 for the final LAI model of RS, and BF, respectively using Sentinel-2 and site variables. The lowest nRMSE for both RS and BF BAPH models was 0.12. As RS and BF are the primary host species for a cyclically occurring and most destructive pest of the region, eastern spruce budworm (Choristoneura fumiferana; SBW), these estimations will be useful to evaluate SBW dynamics in the region.

Type de document: Article
Mots-clés libres: forest inventory; red spruce; balsam fir; random forest; multi-layer; perceptron; remote sensing; Maine
Centre: Centre Eau Terre Environnement
Date de dépôt: 23 juin 2022 14:50
Dernière modification: 23 juin 2022 14:50
URI: https://espace.inrs.ca/id/eprint/12669

Gestion Actions (Identification requise)

Modifier la notice Modifier la notice