Wide & deep learning for predicting relative mineral compositions of sediment cores solely based on XRF scans, a case study from Pleistocene Paleolake Olduvai, Tanzania  

作　　者：Gayantha R.L.Kodikara Lindsay J.McHenry Ian G.Stanistreet Harald Stollhofen Jackson K.Njau Nicholas Toth Kathy Schick 

机构地区：[1]Department of Geosciences,University of Wisconsin-Milwaukee,3209 N,Maryland Ave,Milwaukee,WI,53211,USA [2]Department of Earth,Ocean and Ecological Sciences,University of Liverpool,Brownlow Street,Liverpool,L693GP,UK [3]The Stone Age Institute,Bloomington,IN,47407-5097,USA [4]GeoZentrum Nordbayern,Friedrich-Alexander-University(FAU)Erlangen-Nümberg,Schloβgarten 5,91054,Erlangen,Germany [5]Department of Earth and Atmospheric Sciences,Indiana University,1001 East 10th Street,Bloomington,IN,47405-1405,USA

出　　处：《Artificial Intelligence in Geosciences》2024年第1期244-256,共13页地学人工智能（英文）

基　　金：supported by the National Science Foundation (BCS grant#1623884 to Njau and McHenry);Computational work was also supported by NASA SSW grant NNH20ZDA001N.

摘　　要：This study develops a method to use deep learning models to predict the mineral assemblages and their relative abundances in paleolake cores using high-resolution XRF core scan elemental data and X-ray diffraction(XRD)mineralogical results from the same core taken at coarser resolution.It uses the XRF core scan data along with published mineralogical information from the Olduvai Gorge Coring Project(OGCP)2014 sediment cores 1A,2A,and 3A from Paleolake Olduvai,Tanzania.Both regression and classification models were developed using a Keras deep learning framework to assess the predictability of mineral assemblages with their relative abundances(in regression models)or at least the mineral assemblages(in classification models)using XRF core scan data.Models were created using the Sequential class and Functional API with different model architectures.The correlation matrix of element ratios calculated from XRF element intensity records from the cores and XRD-derived mineralogical information was used to select the most useful features to train the models.1057 training data records were used for the models.Lithological classes were also used for some models using Wide&Deep neural networks since those combine the benefits of memorization and generalization for mineral prediction.The results were validated using 265 validation data records unseen by the model and discuss the accuracy of models using six test records.The optimized Deep Neural Network(DNN)classification model achieved over 86%binary accuracy while the regression models were also able to predict the relative mineral abundances of samples with high accuracies.Overall,the study shows the efficacy of a carefully crafted Deep Learning(DL)model for predicting mineral assemblages and abundances using high-resolution XRF core scan data.

关 键 词：Paleo PLEISTOCENE XRF 

分 类 号：P53[天文地球—古生物学与地层学]