본문 바로가기

Hyperspectral Remote Sensing of TiO2 Concentration in Cementitious Material Based on Machine Learning Approaches

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q1Scopus Q1
저널
REMOTE SENSING14(1) · 2022
피인용
Web of Science 2Scopus 2
FWCI (Scopus)
0.07
JCR IF
JCR 2021 5.349
ISSN
2072-4292

저자

  1. 오태민제1저자Pusan Natl Univ, Dept Civil & Environm Engn, Busan 46241, South Korea
  2. 백승일Pusan Natl Univ, Dept Civil & Environm Engn, Busan 46241, South Korea
  3. 공태현Pusan Natl Univ, Dept Civil & Environm Engn, Busan 46241, South Korea
  4. 고수윤Pusan Natl Univ, Dept Civil & Environm Engn, Busan 46241, South Korea
  5. 안재훈Pusan Natl Univ, Dept Civil & Environm Engn, Busan 46241, South Korea
  6. 김원국교신저자Pusan Natl Univ, Dept Civil & Environm Engn, Busan 46241, South Korea

초록

© 2022 by the authors. Licensee MDPI, Basel, Switzerland.Titanium dioxide (TiO2 ) is a photocatalyst that can be used to remove nitrogen oxide (NOx ). When applied to cementitious materials, it reacts with photons in sunlight or artificially generated light to reduce the concentration of particulate matter in the atmosphere. The concentration of TiO2 applied to the cementitious surface is difficult to quantify in a non-destructive manner after its application; however, knowledge of this residual amount is important for inspection and the evaluation of life expectancy. This study proposes a remote sensing technique that can estimate the concentration of TiO2 in the cementitious surface using a hyperspectral sensor. In the experiment, cement cores of varying TiO2 concentration and carbon contents were prepared and the surfaces were observed by TriOS RAMSES, a directional hyperspectral sensor. Machine-learning-based algorithms were then trained to estimate the TiO2 concentration under varying base material conditions. The results revealed that the best-performing algorithms produced TiO2 concentration estimates with a ~6% RMSE and a correlation close to 0.8. This study presents a robust machine learning model to estimate TiO2 and activated carbon concentration with high accuracy, which can be applied to abrasion monitoring of TiO2 and activated carbon in concrete structures.

키워드

Cementitious materialHyperspectral remote sensingMachine learningTiO2HARDENED CONCRETENOXEFFICIENCYABATEMENTSURFACE

식별자

Scopus EID
2-s2.0-85122072738
WoS UID
000751440400001