There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.startPage | 140162 | - |
dc.citation.title | SCIENCE OF THE TOTAL ENVIRONMENT | - |
dc.citation.volume | 741 | - |
dc.contributor.author | Pyo, JongCheol | - |
dc.contributor.author | Hong, Seok Min | - |
dc.contributor.author | Kwon, Yong Sung | - |
dc.contributor.author | Kim, Moon Sung | - |
dc.contributor.author | Cho, Kyung Hwa | - |
dc.date.accessioned | 2023-12-21T16:45:10Z | - |
dc.date.available | 2023-12-21T16:45:10Z | - |
dc.date.created | 2020-10-07 | - |
dc.date.issued | 2020-11 | - |
dc.description.abstract | Heavy metal contamination in soil disturbs the chemical, biological, and physical soil conditions and adversely affects the health of living organisms. Visible and near-infrared spectroscopy (VNIRS) shows a potential feasibility for estimating heavy metal elements in soil. Moreover, deep learning models have been shown to successfully deal with complex multi-dimensional and multivariate nonlinear data. Thus, this study implemented a deep learning method on reflectance spectra of soil samples to estimate heavy metal concentrations. A convolutional neural network (CNN) was adopted to estimate arsenic (As), copper (Cu), and lead (Pb) concentrations using measured soil reflectance. In addition, a convolutional autoencoder was utilized as a joint method with the CNN for dimensionality reduction of the reflectance spectra. Furthermore, artificial neural network (ANN) and random forest regression (RFR) models were built for heavy metal estimation. Principal component analysis was utilized for dimensionality reduction of the ANN and RFR models. Among these models, the CNN model with convolutional autoencoder showed the highest accuracies for As, Cu, and Pb estimates, having R-2 values of 0.86, 0.74, and 0.82, respectively. The convolutional autoencoder disentangled the relevant features of multiple heavy metal elements and delivered robust features to the CNN model, thereby generating relatively accurate estimates. (c) 2020 Elsevier B.V. All rights reserved. | - |
dc.identifier.bibliographicCitation | SCIENCE OF THE TOTAL ENVIRONMENT, v.741, pp.140162 | - |
dc.identifier.doi | 10.1016/j.scitotenv.2020.140162 | - |
dc.identifier.issn | 0048-9697 | - |
dc.identifier.scopusid | 2-s2.0-85087414811 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/48271 | - |
dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S0048969720336834?via%3Dihub | - |
dc.identifier.wosid | 000568815900010 | - |
dc.language | 영어 | - |
dc.publisher | ELSEVIER | - |
dc.title | Estimation of heavy metals using deep neural network with visible and infrared spectroscopy of soil | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Environmental Sciences | - |
dc.relation.journalResearchArea | Environmental Sciences & Ecology | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Visible and near-infrared spectroscopy | - |
dc.subject.keywordAuthor | Soil heavy metal | - |
dc.subject.keywordAuthor | Convolutional neural network | - |
dc.subject.keywordAuthor | Regression | - |
dc.subject.keywordPlus | PRINCIPAL COMPONENT ANALYSIS | - |
dc.subject.keywordPlus | PARTIAL LEAST-SQUARES | - |
dc.subject.keywordPlus | REFLECTANCE SPECTROSCOPY | - |
dc.subject.keywordPlus | AGRICULTURAL SOILS | - |
dc.subject.keywordPlus | MINING AREA | - |
dc.subject.keywordPlus | DIMENSIONALITY REDUCTION | - |
dc.subject.keywordPlus | COMBINED GEOCHEMISTRY | - |
dc.subject.keywordPlus | FIELD SPECTROSCOPY | - |
dc.subject.keywordPlus | CONTAMINATION | - |
dc.subject.keywordPlus | REGRESSION | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.