Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229372223> ?p ?o ?g. }
- W4229372223 endingPage "2237" @default.
- W4229372223 startingPage "2237" @default.
- W4229372223 abstract "Automatic landslide mapping is crucial for a fast response in a disaster scenario and improving landslide susceptibility models. Recent studies highlighted the potential of deep learning methods for automatic landslide segmentation. However, only a few works discuss the generalization capacity of these models to segment landslides in areas that differ from the ones used to train the models. In this study, we evaluated three different locations to assess the generalization capacity of these models in areas with similar and different environmental aspects. The model training consisted of three distinct datasets created with RapidEye satellite images, Normalized Vegetation Index (NDVI), and a digital elevation model (DEM). Here, we show that larger patch sizes (128 × 128 and 256 × 256 pixels) favor the detection of landslides in areas similar to the training area, while models trained with smaller patch sizes (32 × 32 and 64 × 64 pixels) are better for landslide detection in areas with different environmental aspects. In addition, we found that the NDVI layer helped to balance the model’s results and that morphological post-processing operations are efficient for improving the segmentation precision results. Our research highlights the potential of deep learning models for segmenting landslides in different areas and is a starting point for more sophisticated investigations that evaluate model generalization in images from various sensors and resolutions." @default.
- W4229372223 created "2022-05-10" @default.
- W4229372223 creator A5014956576 @default.
- W4229372223 creator A5015104632 @default.
- W4229372223 creator A5053339757 @default.
- W4229372223 creator A5072925528 @default.
- W4229372223 date "2022-05-06" @default.
- W4229372223 modified "2023-10-14" @default.
- W4229372223 title "Landslide Segmentation with Deep Learning: Evaluating Model Generalization in Rainfall-Induced Landslides in Brazil" @default.
- W4229372223 cites W1572435444 @default.
- W4229372223 cites W1967174063 @default.
- W4229372223 cites W1969470658 @default.
- W4229372223 cites W1970331803 @default.
- W4229372223 cites W1975382649 @default.
- W4229372223 cites W1984792953 @default.
- W4229372223 cites W1985658177 @default.
- W4229372223 cites W1989078512 @default.
- W4229372223 cites W2001665101 @default.
- W4229372223 cites W2003381260 @default.
- W4229372223 cites W2004912142 @default.
- W4229372223 cites W2005227058 @default.
- W4229372223 cites W2012089683 @default.
- W4229372223 cites W2015159529 @default.
- W4229372223 cites W2017692381 @default.
- W4229372223 cites W2017920701 @default.
- W4229372223 cites W2020611012 @default.
- W4229372223 cites W2026492654 @default.
- W4229372223 cites W2033003794 @default.
- W4229372223 cites W2035385475 @default.
- W4229372223 cites W2037402385 @default.
- W4229372223 cites W2046048043 @default.
- W4229372223 cites W2046752082 @default.
- W4229372223 cites W2053536071 @default.
- W4229372223 cites W2058082754 @default.
- W4229372223 cites W2063623478 @default.
- W4229372223 cites W2070549879 @default.
- W4229372223 cites W2080134555 @default.
- W4229372223 cites W2081620141 @default.
- W4229372223 cites W2084744129 @default.
- W4229372223 cites W2091881089 @default.
- W4229372223 cites W2092680370 @default.
- W4229372223 cites W2094896089 @default.
- W4229372223 cites W2098057602 @default.
- W4229372223 cites W2103079830 @default.
- W4229372223 cites W2115548515 @default.
- W4229372223 cites W2145830077 @default.
- W4229372223 cites W2147555471 @default.
- W4229372223 cites W2162380055 @default.
- W4229372223 cites W2342016430 @default.
- W4229372223 cites W2463247229 @default.
- W4229372223 cites W2510250369 @default.
- W4229372223 cites W2604400741 @default.
- W4229372223 cites W2618530766 @default.
- W4229372223 cites W2624848721 @default.
- W4229372223 cites W2782522152 @default.
- W4229372223 cites W2792546905 @default.
- W4229372223 cites W2805627121 @default.
- W4229372223 cites W2883823848 @default.
- W4229372223 cites W2893932676 @default.
- W4229372223 cites W2912361013 @default.
- W4229372223 cites W2915254566 @default.
- W4229372223 cites W2930302290 @default.
- W4229372223 cites W2951991161 @default.
- W4229372223 cites W2954332586 @default.
- W4229372223 cites W2964194231 @default.
- W4229372223 cites W2966450079 @default.
- W4229372223 cites W2967019526 @default.
- W4229372223 cites W2980867860 @default.
- W4229372223 cites W2989839147 @default.
- W4229372223 cites W2989851051 @default.
- W4229372223 cites W2998709485 @default.
- W4229372223 cites W2999453777 @default.
- W4229372223 cites W3001525167 @default.
- W4229372223 cites W3005741980 @default.
- W4229372223 cites W3011881883 @default.
- W4229372223 cites W3047392236 @default.
- W4229372223 cites W3091852895 @default.
- W4229372223 cites W3105577662 @default.
- W4229372223 cites W3111915298 @default.
- W4229372223 cites W3158723639 @default.
- W4229372223 cites W4220849339 @default.
- W4229372223 doi "https://doi.org/10.3390/rs14092237" @default.
- W4229372223 hasPublicationYear "2022" @default.
- W4229372223 type Work @default.
- W4229372223 citedByCount "7" @default.
- W4229372223 countsByYear W42293722232022 @default.
- W4229372223 countsByYear W42293722232023 @default.
- W4229372223 crossrefType "journal-article" @default.
- W4229372223 hasAuthorship W4229372223A5014956576 @default.
- W4229372223 hasAuthorship W4229372223A5015104632 @default.
- W4229372223 hasAuthorship W4229372223A5053339757 @default.
- W4229372223 hasAuthorship W4229372223A5072925528 @default.
- W4229372223 hasBestOaLocation W42293722231 @default.
- W4229372223 hasConcept C108583219 @default.
- W4229372223 hasConcept C111368507 @default.
- W4229372223 hasConcept C114793014 @default.
- W4229372223 hasConcept C127313418 @default.
- W4229372223 hasConcept C132651083 @default.