FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366281370> ?p ?o ?g. }

• W4366281370 endingPage "3866" @default.
• W4366281370 startingPage "3850" @default.
• W4366281370 abstract "Abstract Despite the importance of the prediction of land susceptibility to gully erosion, there is a lack of research studies adopting the deep‐learning approach. This study aimed to predict gully susceptibility hotspots using hybridized deep‐learning models and evaluate their efficiency. Field records of gully occurrences in a gully‐prone region, the Talwar watershed (6468 km 2 ), eastern Kurdistan province, Iran, were used to generate a gully inventory dataset. A total of 14 geomorphometric, environmental, and topo‐hydrological gully drivers were selected as predictor variables. The hybridized models were developed using convolutional neural network (NN C ) and metaheuristic procedures, including the gray wolf optimizer (GWO) and the imperialist competitive algorithm (ICA). The validity of the resulting outputs was investigated based on the area under the receiver operating characteristic (ROC) curve. Results revealed that the NN C ‐GWO had the highest efficiency in the validation step (AUC = 97.2%), whereas the NN C ‐ICA was the second‐best model (AUC = 95.1%). The standalone NN C model showed the lowest accuracy (AUC = 91.2%) in predicting gully susceptibility hotspots compared to NN C ‐GWO and NN C ‐ICA. Thus, both hybridized models had better predictive performance for identifying gully susceptibility in comparison with the standalone NN C model. Furthermore, according to the NN C ‐GWO model, about 0.2% (1294.8 ha) and 0.05% (235.2 ha) of the study area were identified as high and very high gully susceptibility classes. In addition, the application of the standalone NN C led to an overestimation of the susceptibility degree for gully initiation. This study supports researchers efforts to increase the model's performance when working in the land degradation domain." @default.
• W4366281370 created "2023-04-20" @default.
• W4366281370 creator A5007901876 @default.
• W4366281370 creator A5039567207 @default.
• W4366281370 creator A5085898850 @default.
• W4366281370 creator A5089143872 @default.
• W4366281370 date "2023-04-18" @default.
• W4366281370 modified "2023-09-29" @default.
• W4366281370 title "Scrutinizing gully erosion hotspots using hybridized deep‐learning analysis to avoid land degradation" @default.
• W4366281370 cites W194883109 @default.
• W4366281370 cites W1956284831 @default.
• W4366281370 cites W1964130720 @default.
• W4366281370 cites W1964529706 @default.
• W4366281370 cites W1974614011 @default.
• W4366281370 cites W1982623886 @default.
• W4366281370 cites W1984221745 @default.
• W4366281370 cites W2009040435 @default.
• W4366281370 cites W2014727276 @default.
• W4366281370 cites W2030908800 @default.
• W4366281370 cites W2055850772 @default.
• W4366281370 cites W2060775322 @default.
• W4366281370 cites W2061438946 @default.
• W4366281370 cites W2070663788 @default.
• W4366281370 cites W2080996603 @default.
• W4366281370 cites W2082507487 @default.
• W4366281370 cites W2083890125 @default.
• W4366281370 cites W2091455951 @default.
• W4366281370 cites W2122910451 @default.
• W4366281370 cites W2287935773 @default.
• W4366281370 cites W2611940228 @default.
• W4366281370 cites W2741517055 @default.
• W4366281370 cites W2757787785 @default.
• W4366281370 cites W2761962795 @default.
• W4366281370 cites W2768454628 @default.
• W4366281370 cites W2791822201 @default.
• W4366281370 cites W2800722845 @default.
• W4366281370 cites W2800900339 @default.
• W4366281370 cites W2801396930 @default.
• W4366281370 cites W2900784756 @default.
• W4366281370 cites W2903270499 @default.
• W4366281370 cites W2904064276 @default.
• W4366281370 cites W2909193898 @default.
• W4366281370 cites W2911688499 @default.
• W4366281370 cites W2911859703 @default.
• W4366281370 cites W2912153991 @default.
• W4366281370 cites W2913199049 @default.
• W4366281370 cites W2919115771 @default.
• W4366281370 cites W2920548804 @default.
• W4366281370 cites W2926701059 @default.
• W4366281370 cites W2940726923 @default.
• W4366281370 cites W2947478025 @default.
• W4366281370 cites W2957449316 @default.
• W4366281370 cites W2964393055 @default.
• W4366281370 cites W2966565127 @default.
• W4366281370 cites W2986126070 @default.
• W4366281370 cites W2990957379 @default.
• W4366281370 cites W2991562706 @default.
• W4366281370 cites W3003552281 @default.
• W4366281370 cites W3008439211 @default.
• W4366281370 cites W3009636339 @default.
• W4366281370 cites W3010444683 @default.
• W4366281370 cites W3013306393 @default.
• W4366281370 cites W3013673895 @default.
• W4366281370 cites W3014152650 @default.
• W4366281370 cites W3023488024 @default.
• W4366281370 cites W3032913569 @default.
• W4366281370 cites W3039523466 @default.
• W4366281370 cites W3047180133 @default.
• W4366281370 cites W3081658362 @default.
• W4366281370 cites W3087870633 @default.
• W4366281370 cites W3091980963 @default.
• W4366281370 cites W3093548899 @default.
• W4366281370 cites W3099819135 @default.
• W4366281370 cites W3103278630 @default.
• W4366281370 cites W3105134706 @default.
• W4366281370 cites W3106912735 @default.
• W4366281370 cites W3107569396 @default.
• W4366281370 cites W3126669490 @default.
• W4366281370 cites W3133244623 @default.
• W4366281370 cites W3134995590 @default.
• W4366281370 cites W3138339316 @default.
• W4366281370 cites W3140854437 @default.
• W4366281370 cites W3155739706 @default.
• W4366281370 cites W3156486246 @default.
• W4366281370 cites W3157775668 @default.
• W4366281370 cites W3159671785 @default.
• W4366281370 cites W3171502489 @default.
• W4366281370 cites W3172885010 @default.
• W4366281370 cites W3184968922 @default.
• W4366281370 cites W3190488053 @default.
• W4366281370 cites W3197756942 @default.
• W4366281370 cites W3199190751 @default.
• W4366281370 cites W3206829804 @default.
• W4366281370 cites W3209428055 @default.
• W4366281370 cites W3210614734 @default.
• W4366281370 cites W3212755948 @default.
• W4366281370 cites W4200108305 @default.
• W4366281370 cites W4200364514 @default.

• next