Projekter pr. år
Abstract
In order to fit population ecological models, e.g., plant competition models, to new droneaided image data, we need to develop statistical models that may take the new type of measurement uncertainty when applying machinelearning algorithms into account and quantify its importance for statistical inferences and ecological predictions. Here, it is proposed to quantify the uncertainty and bias of image predicted plant taxonomy and abundance in a hierarchical statistical model that is linked to groundtruth data obtained by the pinpoint method. It is critical that the error rate in the species identification process is minimized when the image data are fitted to the population ecological models, and several avenues for reaching this objective are discussed. The outlined method to statistically model known sources of uncertainty when applying machinelearning algorithms may be relevant for other applied scientific disciplines.
Originalsprog  Engelsk 

Artikelnummer  1161 
Tidsskrift  Remote Sensing 
Vol/bind  13 
Nummer  6 
Antal sider  7 
ISSN  20724292 
DOI  
Status  Udgivet  mar. 2021 
Fingeraftryk
Dyk ned i forskningsemnerne om 'Integrating hierarchical statistical models and machinelearning algorithms for groundtruthing drone images of the vegetation: taxonomy, abundance and population ecological models'. Sammen danner de et unikt fingeraftryk.


Drone Lab
Sørensen, P. B., Damgaard, C., Rasmussen, M. B. & Ovesen, N. B.
Projekter: Projekt › Forskning