Détail de l'auteur
Auteur Jacob L. Strunk |
Documents disponibles écrits par cet auteur (2)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Effects of numbers of observations and predictors for various model types on the performance of forest inventory with airborne laser scanning / Diogo N. Cosenza in Canadian Journal of Forest Research, Vol 52 n° 3 (March 2022)
[article]
Titre : Effects of numbers of observations and predictors for various model types on the performance of forest inventory with airborne laser scanning Type de document : Article/Communication Auteurs : Diogo N. Cosenza, Auteur ; Petteri Packalen, Auteur ; Matti Maltamo, Auteur ; Petri Varvia, Auteur ; Janne Raty, Auteur ; Paola Soares, Auteur ; Margarida Tomé, Auteur ; Jacob L. Strunk, Auteur ; Lauri Korhonen, Auteur Année de publication : 2022 Article en page(s) : pp 385 - 395 Note générale : bibliographie Langues : Français (fre) Anglais (eng) Descripteur : [Termes IGN] forêt boréale
[Termes IGN] lasergrammétrie
[Vedettes matières IGN] Inventaire forestierRésumé : (auteur) Semi- and nonparametric models are popular in the area-based approach (ABA) using airborne laser scanning. It is unclear, however, how many predictors and training plots are needed to provide accurate predictions without overfitting. This work aims to explore these limits for various approaches: ordinary least squares regression (OLS), generalized additive models (GAM), least absolute shrinkage and selection operator (LASSO), random forest (RF), support vector machine (SVM), and Gaussian process regression (GPR). We modeled timber volume (m3·ha–1) for four boreal sites using ABA with 2–39 predictors and 20–500 training plots. OLS, GAM, LASSO, and SVM overfitted as the number of predictors approached the number of training plots. They required ≥15 plots per predictor to provide accurate predictions (RMSE ≤30%). GAM required ≥250 plots regardless of the number of predictors. The number of predictors only mildly affected RF and GPR, but they required ≥200 and ≥250 training plots, respectively. RF did not overfit in any circumstances, whereas GPR overfit even with 500 training plots. Overall, using up to 39 predictors did not generally result in overfit, and for most model types, it resulted in better accuracy for sufficiently large datasets (≥250 plots). Numéro de notice : A2022-948 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1139/cjfr-2021-0192 En ligne : https://doi.org/10.1139/cjfr-2021-0192 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100413
in Canadian Journal of Forest Research > Vol 52 n° 3 (March 2022) . - pp 385 - 395[article]An examination of diameter density prediction with k-NN and airborne lidar / Jacob L. Strunk in Forests, vol 8 n° 11 (November 2017)
[article]
Titre : An examination of diameter density prediction with k-NN and airborne lidar Type de document : Article/Communication Auteurs : Jacob L. Strunk, Auteur ; Peter J. Gould, Auteur ; Petteri Packalen, Auteur ; Krishna P. Poudel, Auteur ; Hans-Erik Andersen, Auteur ; Hailemariam Temesgen, Auteur Année de publication : 2017 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Caroline du Sud (Etats-Unis)
[Termes IGN] classification barycentrique
[Termes IGN] classification par la distance de Mahalanobis
[Termes IGN] diamètre des arbres
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] inventaire forestier (techniques et méthodes)
[Termes IGN] lasergrammétrie
[Vedettes matières IGN] Inventaire forestierRésumé : (Auteur) While lidar-based forest inventory methods have been widely demonstrated, performances of methods to predict tree diameters with airborne lidar (lidar) are not well understood. One cause for this is that the performance metrics typically used in studies for prediction of diameters can be difficult to interpret, and may not support comparative inferences between sampling designs and study areas. To help with this problem we propose two indices and use them to evaluate a variety of lidar and k nearest neighbor (k-NN) strategies for prediction of tree diameter distributions. The indices are based on the coefficient of determination (R2), and root mean square deviation (RMSD). Both of the indices are highly interpretable, and the RMSD-based index facilitates comparisons with alternative (non-lidar) inventory strategies, and with projects in other regions. K-NN diameter distribution prediction strategies were examined using auxiliary lidar for 190 training plots distribute across the 800 km2 Savannah River Site in South Carolina, USA. We evaluate the performance of k-NN with respect to distance metrics, number of neighbors, predictor sets, and response sets. K-NN and lidar explained 80% of variability in diameters, and Mahalanobis distance with k = 3 neighbors performed best according to a number of criteria Numéro de notice : A2017-877 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/f8110444 Date de publication en ligne : 16/11/2017 En ligne : https://doi.org/10.3390/f8110444 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91213
in Forests > vol 8 n° 11 (November 2017)[article]