Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311173829> ?p ?o ?g. }
- W4311173829 endingPage "286" @default.
- W4311173829 startingPage "269" @default.
- W4311173829 abstract "Monitoring and managing Earth’s forests in an informed manner is an important requirement for addressing challenges like biodiversity loss and climate change. While traditional in situ or aerial campaigns for forest assessments provide accurate data for analysis at regional level, scaling them to entire countries and beyond with high temporal resolution is hardly possible. In this work, we propose a method based on deep ensembles that densely estimates forest structure variables at country-scale with 10-m resolution, using freely available satellite imagery as input. Our method jointly transforms Sentinel-2 optical images and Sentinel-1 synthetic-aperture radar images into maps of five different forest structure variables: 95th height percentile, mean height, density, Gini coefficient, and fractional cover. We train and test our model on reference data from 41 airborne laser scanning missions across Norway and demonstrate that it is able to generalize to unseen test regions, achieving normalized mean absolute errors between 11% and 15%, depending on the variable. Our work is also the first to propose a variant of so-called Bayesian deep learning to densely predict multiple forest structure variables with well-calibrated uncertainty estimates from satellite imagery. The uncertainty information increases the trustworthiness of the model and its suitability for downstream tasks that require reliable confidence estimates as a basis for decision making. We present an extensive set of experiments to validate the accuracy of the predicted maps as well as the quality of the predicted uncertainties. To demonstrate scalability, we provide Norway-wide maps for the five forest structure variables." @default.
- W4311173829 created "2022-12-24" @default.
- W4311173829 creator A5005404030 @default.
- W4311173829 creator A5011434899 @default.
- W4311173829 creator A5023265715 @default.
- W4311173829 creator A5048243105 @default.
- W4311173829 creator A5053490540 @default.
- W4311173829 creator A5071121905 @default.
- W4311173829 date "2023-01-01" @default.
- W4311173829 modified "2023-10-05" @default.
- W4311173829 title "Country-wide retrieval of forest structure from optical and SAR satellite imagery with deep ensembles" @default.
- W4311173829 cites W1566741453 @default.
- W4311173829 cites W1903029394 @default.
- W4311173829 cites W1965597456 @default.
- W4311173829 cites W1981213426 @default.
- W4311173829 cites W1996263757 @default.
- W4311173829 cites W2014847057 @default.
- W4311173829 cites W2021793377 @default.
- W4311173829 cites W2031419936 @default.
- W4311173829 cites W2050635900 @default.
- W4311173829 cites W2100524057 @default.
- W4311173829 cites W2102605133 @default.
- W4311173829 cites W2113104361 @default.
- W4311173829 cites W2129987380 @default.
- W4311173829 cites W2156808278 @default.
- W4311173829 cites W2161746820 @default.
- W4311173829 cites W2194775991 @default.
- W4311173829 cites W2289402370 @default.
- W4311173829 cites W2319040573 @default.
- W4311173829 cites W2344727237 @default.
- W4311173829 cites W2537499819 @default.
- W4311173829 cites W2538404941 @default.
- W4311173829 cites W2549139847 @default.
- W4311173829 cites W2767594761 @default.
- W4311173829 cites W2782220608 @default.
- W4311173829 cites W2794252992 @default.
- W4311173829 cites W2810877939 @default.
- W4311173829 cites W2891248708 @default.
- W4311173829 cites W2899101283 @default.
- W4311173829 cites W2899336860 @default.
- W4311173829 cites W2900538159 @default.
- W4311173829 cites W2921568295 @default.
- W4311173829 cites W2944500670 @default.
- W4311173829 cites W2955331310 @default.
- W4311173829 cites W2962686771 @default.
- W4311173829 cites W2963037989 @default.
- W4311173829 cites W2963659230 @default.
- W4311173829 cites W2964194231 @default.
- W4311173829 cites W2964339591 @default.
- W4311173829 cites W2965918918 @default.
- W4311173829 cites W2967810856 @default.
- W4311173829 cites W2968347155 @default.
- W4311173829 cites W2981830988 @default.
- W4311173829 cites W2983286147 @default.
- W4311173829 cites W2990674770 @default.
- W4311173829 cites W3016329940 @default.
- W4311173829 cites W3025652605 @default.
- W4311173829 cites W3034792000 @default.
- W4311173829 cites W3035711539 @default.
- W4311173829 cites W3048260913 @default.
- W4311173829 cites W3088292472 @default.
- W4311173829 cites W3094643344 @default.
- W4311173829 cites W3101634875 @default.
- W4311173829 cites W3104839310 @default.
- W4311173829 cites W3134677142 @default.
- W4311173829 cites W3159553016 @default.
- W4311173829 cites W3164187405 @default.
- W4311173829 cites W3165336777 @default.
- W4311173829 cites W3173833413 @default.
- W4311173829 cites W3195841845 @default.
- W4311173829 cites W3203899159 @default.
- W4311173829 cites W3209176285 @default.
- W4311173829 doi "https://doi.org/10.1016/j.isprsjprs.2022.11.011" @default.
- W4311173829 hasPublicationYear "2023" @default.
- W4311173829 type Work @default.
- W4311173829 citedByCount "4" @default.
- W4311173829 countsByYear W43111738292023 @default.
- W4311173829 crossrefType "journal-article" @default.
- W4311173829 hasAuthorship W4311173829A5005404030 @default.
- W4311173829 hasAuthorship W4311173829A5011434899 @default.
- W4311173829 hasAuthorship W4311173829A5023265715 @default.
- W4311173829 hasAuthorship W4311173829A5048243105 @default.
- W4311173829 hasAuthorship W4311173829A5053490540 @default.
- W4311173829 hasAuthorship W4311173829A5071121905 @default.
- W4311173829 hasBestOaLocation W43111738291 @default.
- W4311173829 hasConcept C105795698 @default.
- W4311173829 hasConcept C127413603 @default.
- W4311173829 hasConcept C146978453 @default.
- W4311173829 hasConcept C154945302 @default.
- W4311173829 hasConcept C169258074 @default.
- W4311173829 hasConcept C19269812 @default.
- W4311173829 hasConcept C205649164 @default.
- W4311173829 hasConcept C22679943 @default.
- W4311173829 hasConcept C2778102629 @default.
- W4311173829 hasConcept C2778755073 @default.
- W4311173829 hasConcept C33923547 @default.
- W4311173829 hasConcept C39399123 @default.
- W4311173829 hasConcept C39432304 @default.