Hopp til hovedinnholdet

Search

allprojectspublicationssubjectsemployeesserviceseventsnews

Publications

NIBIOs employees contribute to several hundred scientific articles and research reports every year. You can browse or search in our collection which contains references and links to these publications as well as other research and dissemination activities. The collection is continously updated with new and historical material.

2022

Authors

Inge Stupak Nicholas Clarke Andis Lazdins Iveta Kabasinskiene Diana Lukmine Dagnija Lazdina

Abstract

No abstract has been registered

To document

Authors

Jiunn Luh Tan Nina Trandem Jana Fránová Zhibo Hamborg Dag-Ragnar Blystad Rostislav Zemek

Abstract

No abstract has been registered

To document

Authors

Christina Hoerterer Jessica Petereit Gisela Lannig Johan Johansen Gabriella V. Pereira Luis E. C. Conceição Roberto Pastres Bela H. Buck

Abstract

No abstract has been registered

To document

Authors

Diogo N. Cosenza Petteri Packalén Matti Maltamo Petri Varvia Janne Räty Paula Soares Margarida Tomé Jacob L. Strunk Lauri Korhonen

Abstract

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).

To document

Authors

Paula Firmbach Hanna Burckhardt Daniel Dermitzel Wendy Fjellstad Sebastian Eiter

Abstract

No abstract has been registered

To document

Authors

Andreas Hagenbo Josu G. Alday Juan Martínez de Aragón Carles Castaño Sergio de-Miguel Jose Antonio Bonet

Abstract

No abstract has been registered

Authors

Vibeke Lind

Abstract

No abstract has been registered

To document

Authors

Daniel Rasse Simon Weldon Erik J. Joner Stephen Joseph Claudia I. Kammann Xiaoyu Liu Adam O'Toole Genxing Pan Nazli Pelin Kocatürk Schumacher

Abstract

No abstract has been registered

To document

Authors

Ilaria Piccoli Till Seehusen Jenny Bussell Olga Vizitu Irina Calciu Antonio Berti Gunnar Börjesson Holger Kirchmann Thomas Kätterer Felice Sartori Chris Stoate Felicity Crotty Ioanna S. Panagea Abdallah Alaoui Martin A. Bolinder

Abstract

No abstract has been registered

To document

Authors

Giovanna Ottaviani Aalmo Beniamino Gioli Divina Gracia P. Rodriguez Diana Tuomasjukka Hai-Ying Liu Maria Chiara Pastore Fabio Salbitano Peter Bogetoft Arne Sæbø Cecil Konijnendijk

Abstract

No abstract has been registered