Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385636629> ?p ?o ?g. }
- W4385636629 endingPage "3901" @default.
- W4385636629 startingPage "3901" @default.
- W4385636629 abstract "Landslides, the second largest geological hazard after earthquakes, result in significant loss of life and property. Extracting landslide information quickly and accurately is the basis of landslide disaster prevention. Fengjie County, Chongqing, China, is a typical landslide-prone area in the Three Gorges Reservoir Area. In this study, we newly integrate Shapley Additive Explanation (SHAP) and Optuna (OPT) hyperparameter tuning into four basic machine learning algorithms: Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Additive Boosting (AdaBoost). We construct four new models (SHAP-OPT-GBDT, SHAP-OPT-XGBoost, SHAP-OPT-LightGBM, and SHAP-OPT-AdaBoost) and apply the four new models to landslide extraction for the first time. Firstly, high-resolution remote sensing images were preprocessed, landslide and non-landslide samples were constructed, and an initial feature set with 48 features was built. Secondly, SHAP was used to select features with significant contributions, and the important features were selected. Finally, Optuna, the Bayesian optimization technique, was utilized to automatically select the basic models’ best hyperparameters. The experimental results show that the accuracy (ACC) of these four SHAP-OPT models was above 92% and the training time was less than 1.3 s using mediocre computational hardware. Furthermore, SHAP-OPT-XGBoost achieved the highest accuracy (96.26%). Landslide distribution information in Fengjie County from 2013 to 2020 can be extracted by SHAP-OPT-XGBoost accurately and quickly." @default.
- W4385636629 created "2023-08-08" @default.
- W4385636629 creator A5005929666 @default.
- W4385636629 creator A5006104793 @default.
- W4385636629 creator A5010066017 @default.
- W4385636629 creator A5030845235 @default.
- W4385636629 creator A5033732336 @default.
- W4385636629 creator A5043097022 @default.
- W4385636629 creator A5053573876 @default.
- W4385636629 creator A5063406632 @default.
- W4385636629 creator A5070480766 @default.
- W4385636629 creator A5078217440 @default.
- W4385636629 creator A5083878695 @default.
- W4385636629 date "2023-08-07" @default.
- W4385636629 modified "2023-10-17" @default.
- W4385636629 title "Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost" @default.
- W4385636629 cites W1678356000 @default.
- W4385636629 cites W1964262728 @default.
- W4385636629 cites W2077292227 @default.
- W4385636629 cites W2209410642 @default.
- W4385636629 cites W2567584640 @default.
- W4385636629 cites W2600926735 @default.
- W4385636629 cites W2734428930 @default.
- W4385636629 cites W2789555074 @default.
- W4385636629 cites W2790230321 @default.
- W4385636629 cites W2797908548 @default.
- W4385636629 cites W2918911087 @default.
- W4385636629 cites W2941125029 @default.
- W4385636629 cites W2989704899 @default.
- W4385636629 cites W2996089053 @default.
- W4385636629 cites W3008537971 @default.
- W4385636629 cites W3009636339 @default.
- W4385636629 cites W3010551242 @default.
- W4385636629 cites W3010757542 @default.
- W4385636629 cites W3023943971 @default.
- W4385636629 cites W3041870784 @default.
- W4385636629 cites W3081125651 @default.
- W4385636629 cites W3096207306 @default.
- W4385636629 cites W3102476541 @default.
- W4385636629 cites W3109885934 @default.
- W4385636629 cites W3128063649 @default.
- W4385636629 cites W3180662526 @default.
- W4385636629 cites W3202069230 @default.
- W4385636629 cites W3213078216 @default.
- W4385636629 cites W3216394249 @default.
- W4385636629 cites W4200490257 @default.
- W4385636629 cites W4205807395 @default.
- W4385636629 cites W4206715406 @default.
- W4385636629 cites W4224287576 @default.
- W4385636629 cites W4224294492 @default.
- W4385636629 cites W4228999611 @default.
- W4385636629 cites W4280513285 @default.
- W4385636629 cites W4282842090 @default.
- W4385636629 cites W4283163771 @default.
- W4385636629 cites W4283750094 @default.
- W4385636629 cites W4285037646 @default.
- W4385636629 cites W4289316013 @default.
- W4385636629 cites W4290729126 @default.
- W4385636629 cites W4294225093 @default.
- W4385636629 cites W4295122555 @default.
- W4385636629 cites W4309855153 @default.
- W4385636629 cites W4318683761 @default.
- W4385636629 cites W4318817650 @default.
- W4385636629 cites W4366827173 @default.
- W4385636629 cites W4377983245 @default.
- W4385636629 doi "https://doi.org/10.3390/rs15153901" @default.
- W4385636629 hasPublicationYear "2023" @default.
- W4385636629 type Work @default.
- W4385636629 citedByCount "0" @default.
- W4385636629 crossrefType "journal-article" @default.
- W4385636629 hasAuthorship W4385636629A5005929666 @default.
- W4385636629 hasAuthorship W4385636629A5006104793 @default.
- W4385636629 hasAuthorship W4385636629A5010066017 @default.
- W4385636629 hasAuthorship W4385636629A5030845235 @default.
- W4385636629 hasAuthorship W4385636629A5033732336 @default.
- W4385636629 hasAuthorship W4385636629A5043097022 @default.
- W4385636629 hasAuthorship W4385636629A5053573876 @default.
- W4385636629 hasAuthorship W4385636629A5063406632 @default.
- W4385636629 hasAuthorship W4385636629A5070480766 @default.
- W4385636629 hasAuthorship W4385636629A5078217440 @default.
- W4385636629 hasAuthorship W4385636629A5083878695 @default.
- W4385636629 hasBestOaLocation W43856366291 @default.
- W4385636629 hasConcept C12267149 @default.
- W4385636629 hasConcept C127313418 @default.
- W4385636629 hasConcept C141404830 @default.
- W4385636629 hasConcept C154945302 @default.
- W4385636629 hasConcept C165205528 @default.
- W4385636629 hasConcept C169258074 @default.
- W4385636629 hasConcept C186295008 @default.
- W4385636629 hasConcept C41008148 @default.
- W4385636629 hasConcept C46686674 @default.
- W4385636629 hasConcept C62649853 @default.
- W4385636629 hasConcept C70153297 @default.
- W4385636629 hasConcept C8642999 @default.
- W4385636629 hasConceptScore W4385636629C12267149 @default.
- W4385636629 hasConceptScore W4385636629C127313418 @default.
- W4385636629 hasConceptScore W4385636629C141404830 @default.
- W4385636629 hasConceptScore W4385636629C154945302 @default.