Luis Andrés Guillén

TL;DR: In this paper, the authors surveyed a random selection of 100 papers from the remote sensing (RS) DL literature and found that RS DL studies have largely abandoned traditional RS accuracy assessment terminology, though some of the accuracy measures typically used in DL papers, most notably precision and recall, have direct equivalents in traditional RS terminology.

TL;DR: In this paper, the authors explore how trust influences the social relationships in a local context of Southern Swedish forestry and reveal large differences in owners' trust towards two major actors: the Swedish Forest Agency (SFA) and the forest owner association (FOA) Sodra.

TL;DR: In this article, a review of the accuracy assessment methods used in recently published geospatial and remote sensing (RS) studies, focusing on scene classification, object detection, semantic segmentation and instance segmentation, indicates that RS DL papers appear to follow an accuracy assessment approach that diverges from that of traditional RS studies.

TL;DR: In this article, a modified UNet semantic segmentation deep learning (DL) was used to detect surface mine disturbance features from topographic maps with a high level of accuracy (Dice coefficient = 0.902) and relatively balanced omission and commission error rates (Precision =0.891, Recall = 0.917).

TL;DR: In this paper, the authors used TLS data as an alternative approach to estimate the composite burn index (CBI) in the field, which is the most widely used field-based method used to calibrate satellite-based burn severity data but important limitations of this approach have yet to be resolved.