Machine learning strategies for lithostratigraphic classification based on geochemical sampling data: A case study in area of Chahanwusu River, Qinghai Province, China
Hits:
Release time:2021-07-06 Impact Factor:2.392 DOI number:10.1007/s11771-021-4707-9 Journal:Journal of Central South University Abstract:Based on the complex correlation between the geochemical element distribution patterns at the surface and the types of bedrock and the powerful capabilities in capturing subtle of machine learning algorithms, four machine learning algorithms, namely, decision tree (DT), random forest (RF), XGBoost (XGB), and LightGBM (LGBM), were implemented for the lithostratigraphic classification and lithostratigraphic prediction of a quaternary coverage area based on stream sediment geochemical sampling data in the Chahanwusu River of Dulan County, Qinghai Province, China. The local Moran’s I to represent the features of spatial autocorrelations, and terrain factors to represent the features of surface geological processes, were calculated as additional features. The accuracy, precision, recall, and F1 scores were chosen as the evaluation indices and Voronoi diagrams were applied for visualization. The results indicate that XGB and LGBM models both performed well. They not only obtained relatively satisfactory classification performance but also predicted lithostratigraphic types of the Quaternary coverage area that are essentially consistent with their neighborhoods which have the known types. It is feasible to classify the lithostratigraphic types through the concentrations of geochemical elements in the sediments, and the XGB and LGBM algorithms are recommended for lithostratigraphic classification. Note:Zhang, By., Li, My., Li, Wx. et al. Machine learning strategies for lithostratigraphic classification based on geochemical sampling data: A case study in area of Chahanwusu River, Qinghai Province, China. J. Cent. South Univ. 28, 1422–1447 (2021). https://doi.org/10.1007/s11771-021-4707-9 Co-author:Li, Man-yi, Li, Wei-xia, Jiang, Zheng-wen, Umair Khan, Wang, Li-fang, Wang, Fan-yun First Author:Zhang, Bao-yi Indexed by:Journal paper Volume:28 Issue:5 Page Number:1422-1447 Translation or Not:no Date of Publication:2021-05-31 Included Journals:SCI -
|
 Zip Code:c576f0c85848a14d10428d1b79269fc7d68bde9ba6ecb95648b168a03671c3821c778c2bedf0cae5d03c95a065c3a5efa4243241acb9eb6089885db6f9f3fa7f5b7491eb5af48e7ab43d253e29e0fa6991b0af260ac98903cc7fbca150cb2fc86cb6bd41d95f78a263ba3d6f6aa504ee56cdd8693f2e6f13b576940cee3633de Fax:2ea40a99ad3753f763b5113f1435c15eea64a48cf3566d2e3e20a1338a9d03f910c6c70c6840173adaa969926ae4e7628f5be3887f4156a2c4251fdc727f278ee1fb0e6453d4f9b3c6fd75fe86ee761adb0c0b99001c8f63a43339da07f9e9421816ae9972eccbc840442fd9c04ec03fbede3905bc3af0d0f7aacc8857b3b2d2 Postal Address:59aea379402a14c71b29fc90515ce0cb9fec7996949e526a85e2361f27334ab0b7d8b1264edfcd265f4fccd82834f53709b9e9158a7d646c7b9c3f16934cf6554da8628f32aee18c6f71793e004e8d1d8e1e0bf48b800dcec08890663130a6c7d0d62fb9b782bc0688161b546bd210f4f7bc75da4421801c2477a13d7f7e7f7f Office Phone:3b491e811b2b3f735815425e58b7c28d129673b93256854f3b3d4de544b44bc182beb6f6e7e4d7d6f266045a523116369c213927485c381c699ae8359f8cddc7cacee4f37abbc1150dfecd7f331866d50bf0c1853e3a8077ff84aa785e6f3f31f02859a398c8df32420b88a47af641a2ac0a713b312d8aa8f8b93d9af3325f3e Email:8111cd11bd75e3d2751915d667ba1d93a308f1bd7e7f5caa11ce07c22191b8e7004be628aa28b10a8d4f2331495fefbac1d9d355d3376abd3a51379a50ec57c65af30e7aac952d0d46172fcba9ab1766b031d4e7a21228e599637560e897b44d2d245b5a887c59798a8d2fbcaae6243c8b61c52ee26fb69271f736a95f0ea776
|
