Sitemap Contact Us
닫기
Search
Advanced Search +
닫기
Quick links
Archives Most Cited Most Read Review My Read Go to E-submission

Research Paper

Split Viewer

Econ. Environ. Geol. 2024; 57(4): 353-362

Published online August 30, 2024

https://doi.org/10.9719/EEG.2024.57.4.353

© THE KOREAN SOCIETY OF ECONOMIC AND ENVIRONMENTAL GEOLOGY

Discussion on Detection of Sediment Moisture Content at Different Altitudes Employing UAV Hyperspectral Images

Kyoungeun Lee1, Jaehyung Yu1,2,*, Chanhyeok Park3, Trung Hieu Pham4

Author Info. +

1Department of Earth Environmental & Space Department of Earth, Environmental & Space Sciences Sciences, Chungnam National University
2Department of Geological Sciences, Chungnam National University
3Department of Astronomy, Space Science, & Geology, Chungnam National University
4Faculty of Geology, University of Science, Vietnam National University, Ho Chi Minh City (VNU-HCM)

Correspondence to : *jaeyu@cnu.ac.kr

Received: June 24, 2024; Revised: July 16, 2024; Accepted: August 7, 2024

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided original work is properly cited.

Abstract

This study examined the spectral characteristics of sediments according to moisture content using an unmanned aerial vehicle (UAV)-based hyperspectral sensor and evaluated the efficiency of moisture content detection at different flight altitudes. For this purpose, hyperspectral images in the 400-1000nm wavelength range were acquired and analyzed at altitudes of 40m and 80m for sediment samples with various moisture contents. The reflectance of the sediments generally showed a decreasing trend as the moisture content increased. Correlation analysis between moisture content and reflectance showed a strong negative correlation (r < -0.8) across the entire 400-900nm range.
The moisture content detection model constructed using the Random Forest technique showed detection accuracies of RMSE 2.6%, R2 0.92 at 40m altitude and RMSE 2.2%, R2 0.95 at 80m altitude, confirming that the difference in accuracy between altitudes was minimal. Variable importance analysis revealed that the 600-700nm band played a crucial role in moisture content detection. This study is expected to be utilized in efficient sediment moisture management and natural disaster prediction in the field of environmental monitoring in the future.

Keywords unmanned aerial vehicle (UAV), moisture content, hyperspectral, spectral analysis, machine learning

무인항공 초분광 영상을 기반으로 한 고도에 따른 퇴적물 함수율 탐지 고찰

이경은1 · 유재형1,2,* · 박찬혁3 · Trung Hieu Pham4

1충남대학교 지구환경·우주융합과학과
2충남대학교 지질환경과학과
3충남대학교 우주·지질학과
4Faculty of Geology, University of Science, VNU-HCM

요 약

본 연구는 무인항공기 기반 초분광 센서를 활용하여 퇴적물의 함수율에 따른 분광학적 반응 특성을 고찰하고, 비행 고도에 따른 함수율 탐지 효율성을 평가하였다. 이를 위해 다양한 함수율을 가진 퇴적물 시료를 대상으로 40m와 80m 고도에서 400~1000nm파장 대역의 초분광 영상을 획득하고 분석하였다. 퇴적물의 반사도는 함수율이 증가함에 따라 전반적으로 감소하는 경향을 보였다. 함수율과 반사도 사이의 상관관계 분석 결과, 400~900nm 전 영역에서 강한 음의 상관관계(r < -0.8)를 보였다. 랜덤포레스트 기법을 활용한 함수율 탐지모델 구축 결과, 40m와 80m 고도에서의 탐지 정확도는 각각 RMSE 2.6%, R2 0.92와 RMSE 2.2%, R2 0.95로 나타나 고도 간 정확도 차이가 미미함을 확인하였다. 변수 중요도 분석 결과, 600~700nm 대역이 함수율 탐지에 주요한 역할을 하는 것으로 나타났다. 본 연구는 향후 환경 모니터링 분야에서 효율적인 퇴적물의 수분 관리와 자연재해 예측에 활용될 수 있을 것으로 기대된다.

주요어 무인항공기, 함수율, 초분광, 분광분석, 기계학습

Article

Research Paper

Econ. Environ. Geol. 2024; 57(4): 353-362

Published online August 30, 2024 https://doi.org/10.9719/EEG.2024.57.4.353

Copyright © THE KOREAN SOCIETY OF ECONOMIC AND ENVIRONMENTAL GEOLOGY.

Discussion on Detection of Sediment Moisture Content at Different Altitudes Employing UAV Hyperspectral Images

Kyoungeun Lee1, Jaehyung Yu1,2,*, Chanhyeok Park3, Trung Hieu Pham4

1Department of Earth Environmental & Space Department of Earth, Environmental & Space Sciences Sciences, Chungnam National University
2Department of Geological Sciences, Chungnam National University
3Department of Astronomy, Space Science, & Geology, Chungnam National University
4Faculty of Geology, University of Science, Vietnam National University, Ho Chi Minh City (VNU-HCM)

Correspondence to:*jaeyu@cnu.ac.kr

Received: June 24, 2024; Revised: July 16, 2024; Accepted: August 7, 2024

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided original work is properly cited.

Abstract

This study examined the spectral characteristics of sediments according to moisture content using an unmanned aerial vehicle (UAV)-based hyperspectral sensor and evaluated the efficiency of moisture content detection at different flight altitudes. For this purpose, hyperspectral images in the 400-1000nm wavelength range were acquired and analyzed at altitudes of 40m and 80m for sediment samples with various moisture contents. The reflectance of the sediments generally showed a decreasing trend as the moisture content increased. Correlation analysis between moisture content and reflectance showed a strong negative correlation (r < -0.8) across the entire 400-900nm range.
The moisture content detection model constructed using the Random Forest technique showed detection accuracies of RMSE 2.6%, R2 0.92 at 40m altitude and RMSE 2.2%, R2 0.95 at 80m altitude, confirming that the difference in accuracy between altitudes was minimal. Variable importance analysis revealed that the 600-700nm band played a crucial role in moisture content detection. This study is expected to be utilized in efficient sediment moisture management and natural disaster prediction in the field of environmental monitoring in the future.

Keywords unmanned aerial vehicle (UAV), moisture content, hyperspectral, spectral analysis, machine learning

무인항공 초분광 영상을 기반으로 한 고도에 따른 퇴적물 함수율 탐지 고찰

이경은1 · 유재형1,2,* · 박찬혁3 · Trung Hieu Pham4

1충남대학교 지구환경·우주융합과학과
2충남대학교 지질환경과학과
3충남대학교 우주·지질학과
4Faculty of Geology, University of Science, VNU-HCM

Received: June 24, 2024; Revised: July 16, 2024; Accepted: August 7, 2024

요 약

본 연구는 무인항공기 기반 초분광 센서를 활용하여 퇴적물의 함수율에 따른 분광학적 반응 특성을 고찰하고, 비행 고도에 따른 함수율 탐지 효율성을 평가하였다. 이를 위해 다양한 함수율을 가진 퇴적물 시료를 대상으로 40m와 80m 고도에서 400~1000nm파장 대역의 초분광 영상을 획득하고 분석하였다. 퇴적물의 반사도는 함수율이 증가함에 따라 전반적으로 감소하는 경향을 보였다. 함수율과 반사도 사이의 상관관계 분석 결과, 400~900nm 전 영역에서 강한 음의 상관관계(r < -0.8)를 보였다. 랜덤포레스트 기법을 활용한 함수율 탐지모델 구축 결과, 40m와 80m 고도에서의 탐지 정확도는 각각 RMSE 2.6%, R2 0.92와 RMSE 2.2%, R2 0.95로 나타나 고도 간 정확도 차이가 미미함을 확인하였다. 변수 중요도 분석 결과, 600~700nm 대역이 함수율 탐지에 주요한 역할을 하는 것으로 나타났다. 본 연구는 향후 환경 모니터링 분야에서 효율적인 퇴적물의 수분 관리와 자연재해 예측에 활용될 수 있을 것으로 기대된다.

주요어 무인항공기, 함수율, 초분광, 분광분석, 기계학습

    Fig 1.

    Download
    Figure 1.Experiment setting for sediment moisture content measurement using UAV survey.
    Economic and Environmental Geology 2024; 57: 353-362https://doi.org/10.9719/EEG.2024.57.4.353

    Fig 2.

    Download
    Figure 2.UAV based-hyperspectral images for sediment samples at various moisture content acquired at altitude of 40 m (a) and 80 m(b) and ROI polygons(c and d), where the band combination is R : 641.92nm, G:549.75nm, and B:461.59nm.
    Economic and Environmental Geology 2024; 57: 353-362https://doi.org/10.9719/EEG.2024.57.4.353

    Fig 3.

    Download
    Figure 3.The mean reflectance spectra and hull quotient spectra of 6 different levels of moisture content in (a) 40m, (b) 80m.
    Economic and Environmental Geology 2024; 57: 353-362https://doi.org/10.9719/EEG.2024.57.4.353

    Fig 4.

    Download
    Figure 4.The correlogram based on correlation coefficient between moisture content and (c) reflectance spectra, (d) hull quotient spectra. Shaded area correspends to |r|<0.7.
    Economic and Environmental Geology 2024; 57: 353-362https://doi.org/10.9719/EEG.2024.57.4.353

    Fig 5.

    Download
    Figure 5.The importance values of spectral bands derived from the random forest(RF) method.
    Economic and Environmental Geology 2024; 57: 353-362https://doi.org/10.9719/EEG.2024.57.4.353

    Table 1 . The specification of hyperspectral sensor and UAV used for this study.


    Table 2 . The details of UAV survey conditions for data acquisition.

    Date (yyyy-mm-dd)Flight altitude (m)Ground resolution (cm/px)Mission time
    2022-09-2340m3.6711~12am
    80m7.33
    2022-10-0640m3.671~2pm
    80m7.33
    2022-10-2740m3.6711~12am
    80m7.33
    2022-10-2840m3.6711~12am
    80m7.33

    Table 3 . Accuracy assessment of random forest classification for detection of moisture content using hyperspectral images at 40m and 80m.

    AltitudeSpectral VariablesR2RMSE(%)
    40mReflectance0.922.6
    80mReflectance0.952.2

    KSEEG
    Aug 30, 2024 Vol.57 No.4, pp. 353~471
    Current Issue Archives

    Stats or Metrics

    Share this article on

    • kakao talk
    • line

    Related articles in KSEEG

    Economic and Environmental Geology

    pISSN 1225-7281
    eISSN 2288-7962
    qr-code Download