Search

Lichen mapping is vital for caribou management plans and sustainable land conservation. Previous studies have used random forest, dense neural network, and convolutional neural network models for mapping lichen coverage. However, to date, it is not clear how these models rank in this task. In this study, these machine learning models were evaluated on their ability to predict lichen percent coverage in Sentinel-2 imagery in Québec and Labrador, Canada. The models were trained on 10-m resolution lichen coverage (%) maps created from 20 drone surveys collected in July 2019 and 2022. The dense neural network achieved a higher accuracy than the other two, with a reported mean absolute error of 5.2% and an R2 of 0.76. By comparison, the random forest model returned a mean absolute error of 5.5% (R2: 0.74) and the convolutional neural network had a mean absolute error of 5.3% (R2: 0.74). A regional lichen map was created using the trained dense neural network and a Sentinel-2 imagery mosaic. There was greater uncertainty on land covers that the model was not exposed to in training, such as mines and deep lakes. While the dense neural network requires more computational effort to train than a random forest model, the 5.9% performance gain in the test pixel comparison renders it the most suitable for lichen mapping. This study represents progress toward determining the appropriate methodology for generating accurate lichen maps from satellite imagery for caribou conservation and sustainable land management., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Richardson et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Background: Improved survival has led to increasing numbers of children with life-limiting conditions transitioning to adult healthcare services. There are concerns that transition may lead to a reduction in care quality and increases in emergency care. This review explores evidence for differences in health or social care use post- versus pre-transition to adult services., Methods: MEDLINE, EMBASE, CINAHL, PsychINFO and Social Science Citation Index were searched. Studies published in English since 1990 including individuals with any life-limiting condition post- and pre-transition and reporting a health or social care use outcome were included. Data were extracted and quality assessed by one reviewer with 30% checked by an independent reviewer., Results: Nineteen papers (18 studies) met the inclusion criteria. There was evidence for both increases and decreases (post- versus pre-transition) in outpatient attendance, inpatient admissions, inpatient bed days and health service costs; for increases in Emergency Department visits and for decreases in individuals receiving physiotherapy., Conclusions: Evidence for changes in healthcare use post- versus pre-transition is mixed and conflicting, although there is evidence for an increase in Emergency Department visits and a reduction in access to physiotherapy. More high-quality research is needed to better link changes in care to the transition., Impact: Evidence for changes in healthcare use associated with transition to adult services is conflicting. Emergency Department visits increase and access to physiotherapy decreases at transition. There are marked differences between care patterns in the United States and Canada., (© 2021. The Author(s).)