Optimizing Field Data Collection for Individual Tree Attribute Predictions Using Active Learning Methods

• Published in: Remote sensing (Basel, Switzerland) Vol. 11; no. 8; p. 949
• Main Authors: Malek, Salim, Miglietta, Franco, Gobakken, Terje, Næsset, Erik, Gianelle, Damiano, Dalponte, Michele
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 19.04.2019
• Subjects: aboveground biomass; Active learning; Biomass; Boreal forests; Carbon; Classification; Data acquisition; Data collection; Datasets; diameter at breast height; Ecological monitoring; Ecosystems; Forest management; forestry; Forests; Independent variables; Learning; Lidar; Mapping; Optimization; Prediction models; Regression analysis; Remote sensing; Standard data; Support vector machines; support vector regression; Taiga; Trees; Vegetation; United States > US; Norway; Italy

Light detection and ranging (lidar) data are nowadays a standard data source in studies related to forest ecology and environmental mapping. Medium/high point density lidar data allow to automatically detect individual tree crowns (ITCs), and they provide useful information to predict stem diameter...