FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298007422> ?p ?o ?g. }

• W4298007422 endingPage "100843" @default.
• W4298007422 startingPage "100843" @default.
• W4298007422 abstract "The European Commission launch of the twin Sentinel-2 satellites provides new opportunities for land use and land cover (LULC) classification because of the ready availability of their data and their enhanced spatial, temporal and spectral resolutions. The rapid development of machine learning over the past decade led to data-driven models being at the forefront of high accuracy predictions of the physical world. However, the contribution of the driving variables behind these predictions cannot be explained beyond generalized metrics of overall performance. Here, we compared the performance of three shallow learners (support vector machines, random forest, and extreme gradient boosting) as well as two deep learners (a convolutional neural network and a residual network with 50 layers) in and around the city of Malmö in southern Sweden. Our complete analysis suite involved 141 input features, 85 scenarios, and 8 LULC classes. We explored the interpretability of the five learners using Shapley additive explanations to better understand feature importance at the level of individual LULC classes. The purpose of class-level feature importance was to identify the most parsimonious combination of features that could reasonably map a particular class and enhance overall map accuracy. We showed that not only do overall accuracies increase from shallow (mean = 84.64%) to deep learners (mean = 92.63%) but that the number of explanatory variables required to obtain maximum accuracy decreases along the same gradient. Furthermore, we demonstrated that class-level importance metrics can be successfully identified using Shapley additive explanations in both shallow and deep learners, which allows for a more detailed understanding of variable importance. We show that for certain LULC classes there is a convergence of variable importance across all the algorithms, which helps explain model predictions and aid the selection of more parsimonious models. The use of class-level feature importance metrics is still new in LULC classification, and this study provides important insight into the potential of more nuanced importance metrics." @default.
• W4298007422 created "2022-10-01" @default.
• W4298007422 creator A5001014249 @default.
• W4298007422 creator A5048111735 @default.
• W4298007422 creator A5088840349 @default.
• W4298007422 date "2022-11-01" @default.
• W4298007422 modified "2023-09-30" @default.
• W4298007422 title "Urban land use and land cover classification with interpretable machine learning – A case study using Sentinel-2 and auxiliary data" @default.
• W4298007422 cites W1678356000 @default.
• W4298007422 cites W1976029164 @default.
• W4298007422 cites W1987097445 @default.
• W4298007422 cites W2009514331 @default.
• W4298007422 cites W2014555541 @default.
• W4298007422 cites W2018707223 @default.
• W4298007422 cites W2029185882 @default.
• W4298007422 cites W2038951852 @default.
• W4298007422 cites W2044465660 @default.
• W4298007422 cites W2045085513 @default.
• W4298007422 cites W2053373080 @default.
• W4298007422 cites W2056435747 @default.
• W4298007422 cites W2059432853 @default.
• W4298007422 cites W2065800647 @default.
• W4298007422 cites W2069820899 @default.
• W4298007422 cites W2081991302 @default.
• W4298007422 cites W2083969383 @default.
• W4298007422 cites W2084413241 @default.
• W4298007422 cites W2094226036 @default.
• W4298007422 cites W2094677081 @default.
• W4298007422 cites W2098676252 @default.
• W4298007422 cites W2102636708 @default.
• W4298007422 cites W2110653042 @default.
• W4298007422 cites W2130121312 @default.
• W4298007422 cites W2138499468 @default.
• W4298007422 cites W2152640741 @default.
• W4298007422 cites W2155632266 @default.
• W4298007422 cites W2155695582 @default.
• W4298007422 cites W2168809519 @default.
• W4298007422 cites W2221744192 @default.
• W4298007422 cites W2261059368 @default.
• W4298007422 cites W2331319011 @default.
• W4298007422 cites W2331582811 @default.
• W4298007422 cites W2418853085 @default.
• W4298007422 cites W2538244214 @default.
• W4298007422 cites W2585014453 @default.
• W4298007422 cites W2604086375 @default.
• W4298007422 cites W2648242067 @default.
• W4298007422 cites W2733463659 @default.
• W4298007422 cites W2782522152 @default.
• W4298007422 cites W2793927960 @default.
• W4298007422 cites W2795840897 @default.
• W4298007422 cites W2801747952 @default.
• W4298007422 cites W2802758852 @default.
• W4298007422 cites W2809254203 @default.
• W4298007422 cites W2896998982 @default.
• W4298007422 cites W2903282641 @default.
• W4298007422 cites W2911964244 @default.
• W4298007422 cites W2919115771 @default.
• W4298007422 cites W2940726923 @default.
• W4298007422 cites W2959030086 @default.
• W4298007422 cites W2964287450 @default.
• W4298007422 cites W2969945043 @default.
• W4298007422 cites W2972170785 @default.
• W4298007422 cites W2976696463 @default.
• W4298007422 cites W2988576146 @default.
• W4298007422 cites W2995523160 @default.
• W4298007422 cites W2997519693 @default.
• W4298007422 cites W2999712229 @default.
• W4298007422 cites W3003421670 @default.
• W4298007422 cites W3013879714 @default.
• W4298007422 cites W3014372673 @default.
• W4298007422 cites W3041705624 @default.
• W4298007422 cites W3087408166 @default.
• W4298007422 cites W3093130013 @default.
• W4298007422 cites W3104341624 @default.
• W4298007422 cites W3140854437 @default.
• W4298007422 cites W3195079589 @default.
• W4298007422 cites W3203279891 @default.
• W4298007422 cites W3208751120 @default.
• W4298007422 cites W3217116165 @default.
• W4298007422 cites W4231109964 @default.
• W4298007422 cites W4239510810 @default.
• W4298007422 cites W4248710273 @default.
• W4298007422 doi "https://doi.org/10.1016/j.rsase.2022.100843" @default.
• W4298007422 hasPublicationYear "2022" @default.
• W4298007422 type Work @default.
• W4298007422 citedByCount "1" @default.
• W4298007422 countsByYear W42980074222023 @default.
• W4298007422 crossrefType "journal-article" @default.
• W4298007422 hasAuthorship W4298007422A5001014249 @default.
• W4298007422 hasAuthorship W4298007422A5048111735 @default.
• W4298007422 hasAuthorship W4298007422A5088840349 @default.
• W4298007422 hasBestOaLocation W42980074221 @default.
• W4298007422 hasConcept C108583219 @default.
• W4298007422 hasConcept C11413529 @default.
• W4298007422 hasConcept C119857082 @default.
• W4298007422 hasConcept C12267149 @default.
• W4298007422 hasConcept C127413603 @default.
• W4298007422 hasConcept C138885662 @default.

• next