FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386575267> ?p ?o ?g. }

• W4386575267 endingPage "166960" @default.
• W4386575267 startingPage "166960" @default.
• W4386575267 abstract "Gully erosion possess a serious hazard to critical resources such as soil, water, and vegetation cover within watersheds. Therefore, spatial maps of gully erosion hazards can be instrumental in mitigating its negative consequences. Among the various methods used to explore and map gully erosion, advanced learning techniques, especially deep learning (DL) models, are highly capable of spatial mapping and can provide accurate predictions for generating spatial maps of gully erosion at different scales (e.g., local, regional, continental, and global). In this paper, we applied two DL models, namely a simple recurrent neural network (RNN) and a gated recurrent unit (GRU), to map land susceptibility to gully erosion in the Shamil-Minab plain, Hormozgan province, southern Iran. To address the inherent black box nature of DL models, we applied three novel interpretability methods consisting of SHaply Additive explanation (SHAP), ceteris paribus and partial dependence (CP-PD) profiles and permutation feature importance (PFI). Using the Boruta algorithm, we identified seven important features that control gully erosion: soil bulk density, clay content, elevation, land use type, vegetation cover, sand content, and silt content. These features, along with an inventory map of gully erosion (based on a 70 % training dataset and 30 % test dataset), were used to generate spatial maps of gully erosion using DL models. According to the Kolmogorov-Smirnov (KS) statistic performance assessment measure, the simple RNN model (with KS = 91.6) outperformed the GRU model (with KS = 66.6). Based on the results from the simple RNN model, 7.4 %, 14.5 %, 18.9 %, 31.2 % and 28 % of total area of the plain were classified as very-low, low, moderate, high and very-high hazard classes, respectively. According to SHAP plots, CP-PD profiles, and PFI measures, soil silt content, vegetation cover (NDVI) and land use type had the highest impact on the model's output. Overall, the DL modelling techniques and interpretation methods used in this study proved to be helpful in generating spatial maps of soil erosion hazard, especially gully erosion. Their interpretability can support watershed sustainable management." @default.
• W4386575267 created "2023-09-10" @default.
• W4386575267 creator A5026749912 @default.
• W4386575267 creator A5043499560 @default.
• W4386575267 creator A5054452914 @default.
• W4386575267 creator A5059040421 @default.
• W4386575267 creator A5073799902 @default.
• W4386575267 date "2023-12-01" @default.
• W4386575267 modified "2023-10-12" @default.
• W4386575267 title "Interpretability of simple RNN and GRU deep learning models used to map land susceptibility to gully erosion" @default.
• W4386575267 cites W1700449338 @default.
• W4386575267 cites W1967587709 @default.
• W4386575267 cites W1978110877 @default.
• W4386575267 cites W1992668584 @default.
• W4386575267 cites W2042490557 @default.
• W4386575267 cites W2066316400 @default.
• W4386575267 cites W2072866943 @default.
• W4386575267 cites W2075170979 @default.
• W4386575267 cites W2076063813 @default.
• W4386575267 cites W2129888542 @default.
• W4386575267 cites W2132993231 @default.
• W4386575267 cites W2156665896 @default.
• W4386575267 cites W2251365809 @default.
• W4386575267 cites W2551325035 @default.
• W4386575267 cites W2556566540 @default.
• W4386575267 cites W2766604911 @default.
• W4386575267 cites W2767547957 @default.
• W4386575267 cites W2786693279 @default.
• W4386575267 cites W2896326005 @default.
• W4386575267 cites W2900784756 @default.
• W4386575267 cites W2904031581 @default.
• W4386575267 cites W2905786035 @default.
• W4386575267 cites W2911964244 @default.
• W4386575267 cites W2972478446 @default.
• W4386575267 cites W2998204574 @default.
• W4386575267 cites W3010914732 @default.
• W4386575267 cites W3084863258 @default.
• W4386575267 cites W3102507711 @default.
• W4386575267 cites W3125555183 @default.
• W4386575267 cites W3126669490 @default.
• W4386575267 cites W3130073227 @default.
• W4386575267 cites W3135047428 @default.
• W4386575267 cites W3137389508 @default.
• W4386575267 cites W3143710874 @default.
• W4386575267 cites W3145933715 @default.
• W4386575267 cites W3156486246 @default.
• W4386575267 cites W3158138131 @default.
• W4386575267 cites W3159671785 @default.
• W4386575267 cites W3171502489 @default.
• W4386575267 cites W3193735541 @default.
• W4386575267 cites W3199795281 @default.
• W4386575267 cites W3208375681 @default.
• W4386575267 cites W3210455980 @default.
• W4386575267 cites W4210867509 @default.
• W4386575267 cites W4212781513 @default.
• W4386575267 cites W4283077289 @default.
• W4386575267 cites W4285045915 @default.
• W4386575267 cites W4288734556 @default.
• W4386575267 cites W4293707991 @default.
• W4386575267 cites W4294877645 @default.
• W4386575267 cites W4294970488 @default.
• W4386575267 cites W4308834975 @default.
• W4386575267 cites W4309046882 @default.
• W4386575267 cites W4309293946 @default.
• W4386575267 cites W4311435828 @default.
• W4386575267 cites W4313334125 @default.
• W4386575267 cites W4317745929 @default.
• W4386575267 cites W4319312238 @default.
• W4386575267 cites W4319870791 @default.
• W4386575267 cites W4321766156 @default.
• W4386575267 cites W4327975116 @default.
• W4386575267 cites W4360604571 @default.
• W4386575267 cites W4361000062 @default.
• W4386575267 cites W4366281370 @default.
• W4386575267 cites W4367298578 @default.
• W4386575267 cites W4375950737 @default.
• W4386575267 cites W4381929622 @default.
• W4386575267 cites W4383340034 @default.
• W4386575267 cites W4384459991 @default.
• W4386575267 cites W4385582638 @default.
• W4386575267 doi "https://doi.org/10.1016/j.scitotenv.2023.166960" @default.
• W4386575267 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37696396" @default.
• W4386575267 hasPublicationYear "2023" @default.
• W4386575267 type Work @default.
• W4386575267 citedByCount "0" @default.
• W4386575267 crossrefType "journal-article" @default.
• W4386575267 hasAuthorship W4386575267A5026749912 @default.
• W4386575267 hasAuthorship W4386575267A5043499560 @default.
• W4386575267 hasAuthorship W4386575267A5054452914 @default.
• W4386575267 hasAuthorship W4386575267A5059040421 @default.
• W4386575267 hasAuthorship W4386575267A5073799902 @default.
• W4386575267 hasConcept C114793014 @default.
• W4386575267 hasConcept C123157820 @default.
• W4386575267 hasConcept C127313418 @default.
• W4386575267 hasConcept C127413603 @default.
• W4386575267 hasConcept C138885662 @default.
• W4386575267 hasConcept C142724271 @default.
• W4386575267 hasConcept C147176958 @default.

• next