Matches in SemOpenAlex for { <https://semopenalex.org/work/W4211061444> ?p ?o ?g. }
- W4211061444 endingPage "105075" @default.
- W4211061444 startingPage "105075" @default.
- W4211061444 abstract "The supervised deep learning methods applied in mineral prospectivity mapping usually need sufficient samples for training models. However, mineralization is a rare event. Insufficient known mineral deposits cannot meet the sample requirement of supervised learning methods, resulting in lower predictive accuracies and poor generalization abilities. For the purpose of solving this issue, this paper adopted a data augmentation method to make mineral prospectivity prediction of gold deposit in the Fengxian Region, China. This data augmentation method adopted cropping operations to generate sufficient training samples without changing spatial directions of geological data. Meanwhile, this paper utilized the continuous buffer distance method to quantify faults and anticline axes, overcoming the loss of geological information caused by using the discrete buffer distance mode. To prove the effectiveness of the data augmentation method, this paper utilized three different convolutional neural networks (LeNet, AlexNet, and VggNet) to extract relationships between multisource ore-indicating factors and mineral deposits. In addition, this paper discussed effects of different parameters on predictive performances. According to series of comparisons, the LeNet model outperformed other models, achieving superior values of accuracy (91.38%), Kappa coefficient (0.8119), and AUC (0.958). Moreover, the LeNet model successfully caught 81.8% of known gold deposits within 18.6% of the study area. The delineated high potential areas offer intuitive guides for exploring more gold deposits in the Fengxian region. The proposed data augmentation method is available for mineral prospectivity modeling by supervised deep learning methods for the areas of lower exploration degrees. For mineral prospectivity modeling based on convolutional neural networks, utilizing the continuous buffer distance to transform faults and anticline axes into predictor variables of the image form is conducive to improve the predictive performance than utilizing the discrete buffer distance. • To solve the issue of mineral prospectivity prediction in lower developed areas. • A cropping technology of data augmentation was used to expand training samples. • Continuous buffer distance retains more geological information on images for CNN. • Convolutional neural networks were utilized to build mineral prediction models. • The obtained model can catch more known deposits in smaller predicting areas." @default.
- W4211061444 created "2022-02-13" @default.
- W4211061444 creator A5013761158 @default.
- W4211061444 creator A5043680593 @default.
- W4211061444 creator A5080744347 @default.
- W4211061444 creator A5081541064 @default.
- W4211061444 date "2022-04-01" @default.
- W4211061444 modified "2023-09-27" @default.
- W4211061444 title "Applications of data augmentation in mineral prospectivity prediction based on convolutional neural networks" @default.
- W4211061444 cites W1544435011 @default.
- W4211061444 cites W1573373265 @default.
- W4211061444 cites W1801002936 @default.
- W4211061444 cites W1973237440 @default.
- W4211061444 cites W1973595880 @default.
- W4211061444 cites W1978053173 @default.
- W4211061444 cites W1978905539 @default.
- W4211061444 cites W1980789580 @default.
- W4211061444 cites W1982256854 @default.
- W4211061444 cites W1983865151 @default.
- W4211061444 cites W1988041076 @default.
- W4211061444 cites W2014823261 @default.
- W4211061444 cites W2018366608 @default.
- W4211061444 cites W2026953225 @default.
- W4211061444 cites W2027294097 @default.
- W4211061444 cites W2036956254 @default.
- W4211061444 cites W2048262994 @default.
- W4211061444 cites W2048708177 @default.
- W4211061444 cites W2061716532 @default.
- W4211061444 cites W2062540263 @default.
- W4211061444 cites W2072504176 @default.
- W4211061444 cites W2086999348 @default.
- W4211061444 cites W2089338675 @default.
- W4211061444 cites W2098397292 @default.
- W4211061444 cites W2112796928 @default.
- W4211061444 cites W2158698691 @default.
- W4211061444 cites W2159782581 @default.
- W4211061444 cites W2180178176 @default.
- W4211061444 cites W2201593588 @default.
- W4211061444 cites W2342740937 @default.
- W4211061444 cites W2461102141 @default.
- W4211061444 cites W2519414135 @default.
- W4211061444 cites W2564974494 @default.
- W4211061444 cites W2615492166 @default.
- W4211061444 cites W2618530766 @default.
- W4211061444 cites W2619107246 @default.
- W4211061444 cites W2761218489 @default.
- W4211061444 cites W2767155774 @default.
- W4211061444 cites W2767979165 @default.
- W4211061444 cites W2768818485 @default.
- W4211061444 cites W2896335697 @default.
- W4211061444 cites W2913600801 @default.
- W4211061444 cites W2920641855 @default.
- W4211061444 cites W2921482850 @default.
- W4211061444 cites W2936859456 @default.
- W4211061444 cites W2940433316 @default.
- W4211061444 cites W2943736627 @default.
- W4211061444 cites W2947060705 @default.
- W4211061444 cites W2954328919 @default.
- W4211061444 cites W2954339636 @default.
- W4211061444 cites W2959587919 @default.
- W4211061444 cites W2979128757 @default.
- W4211061444 cites W2988445804 @default.
- W4211061444 cites W3002325577 @default.
- W4211061444 cites W3014811513 @default.
- W4211061444 cites W3033765727 @default.
- W4211061444 cites W3048167958 @default.
- W4211061444 cites W3082511830 @default.
- W4211061444 cites W3086825826 @default.
- W4211061444 cites W3124465846 @default.
- W4211061444 cites W3129715495 @default.
- W4211061444 cites W3144613578 @default.
- W4211061444 cites W3154176209 @default.
- W4211061444 cites W3163225286 @default.
- W4211061444 cites W3164740228 @default.
- W4211061444 cites W3171799684 @default.
- W4211061444 cites W3171819295 @default.
- W4211061444 cites W3171942522 @default.
- W4211061444 cites W3172665323 @default.
- W4211061444 cites W3175535587 @default.
- W4211061444 cites W3177932121 @default.
- W4211061444 cites W3190438496 @default.
- W4211061444 cites W3194013069 @default.
- W4211061444 cites W3195687265 @default.
- W4211061444 cites W3216830627 @default.
- W4211061444 cites W576864993 @default.
- W4211061444 doi "https://doi.org/10.1016/j.cageo.2022.105075" @default.
- W4211061444 hasPublicationYear "2022" @default.
- W4211061444 type Work @default.
- W4211061444 citedByCount "17" @default.
- W4211061444 countsByYear W42110614442022 @default.
- W4211061444 countsByYear W42110614442023 @default.
- W4211061444 crossrefType "journal-article" @default.
- W4211061444 hasAuthorship W4211061444A5013761158 @default.
- W4211061444 hasAuthorship W4211061444A5043680593 @default.
- W4211061444 hasAuthorship W4211061444A5080744347 @default.
- W4211061444 hasAuthorship W4211061444A5081541064 @default.
- W4211061444 hasConcept C109007969 @default.
- W4211061444 hasConcept C114793014 @default.