Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, Brazil

Visual inspection is essential to ensure the stability of earth-rock dams. Periodic visual assessment of this type of structure through vegetation cover analysis is an effective monitoring method. Recently, multispectral remote sensing data and machine learning techniques have been applied to develo...

Full description

Saved in:
Bibliographic Details
Main Authors: Carlos André de Mattos Teixeira, Thabatta Moreira Alves de Araujo, Evelin Cardoso, Marcos Antonio Costantin Filho, João Weyl Costa, Carlos Renato Lisboa Frances
Format: Article
Language:English
Published: PeerJ Inc. 2025-06-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2917.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422540952305664
author Carlos André de Mattos Teixeira
Thabatta Moreira Alves de Araujo
Evelin Cardoso
Marcos Antonio Costantin Filho
João Weyl Costa
Carlos Renato Lisboa Frances
author_facet Carlos André de Mattos Teixeira
Thabatta Moreira Alves de Araujo
Evelin Cardoso
Marcos Antonio Costantin Filho
João Weyl Costa
Carlos Renato Lisboa Frances
author_sort Carlos André de Mattos Teixeira
collection DOAJ
description Visual inspection is essential to ensure the stability of earth-rock dams. Periodic visual assessment of this type of structure through vegetation cover analysis is an effective monitoring method. Recently, multispectral remote sensing data and machine learning techniques have been applied to develop methodologies that enable automatic vegetation analysis and anomaly detection based on computer vision. As a first step toward this automation, this study introduces a methodology for land cover segmentation of earth-rock embankment dam structures within the Belo Monte Hydroelectric Complex, located in the state of Pará, northern Brazil. Random forest (RF) ensemble models were trained on manually annotated data captured by a multispectral sensor embedded in an uncrewed aerial vehicle (UAV). The main objectives of this study are to assess the classification performance of the algorithm in segmenting earth-rock dams and the contribution of non-visible band reflectance data to the overall model performance. A comprehensive feature engineering and ranking approach is presented to select the most descriptive features that represent the four dataset classes. Model performance was assessed using classical performance metrics derived from the confusion matrix, such as accuracy, Kappa coefficient, precision, recall, F1-score, and intersection over union (IoU). The final RF model achieved 90.9% mean IoU for binary segmentation and 91.1% mean IoU for multiclass segmentation. Post-processing techniques were applied to refine the predicted masks, enhancing the mean IoU to 93.2% and 91.9%, respectively. The flexible methodology presented in this work can be applied to different scenarios when treated as a framework for pixel-wise land cover classification, serving as a crucial step toward automating visual inspection processes. The implementation of automated monitoring solutions improves the visual inspection process and mitigates the catastrophic consequences resulting from dam failures.
format Article
id doaj-art-e4be0a2c09e049dbbbe5cb24ea218b14
institution Kabale University
issn 2376-5992
language English
publishDate 2025-06-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-e4be0a2c09e049dbbbe5cb24ea218b142025-08-20T03:31:02ZengPeerJ Inc.PeerJ Computer Science2376-59922025-06-0111e291710.7717/peerj-cs.2917Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, BrazilCarlos André de Mattos Teixeira0Thabatta Moreira Alves de Araujo1Evelin Cardoso2Marcos Antonio Costantin Filho3João Weyl Costa4Carlos Renato Lisboa Frances5Instituto de Tecnologia, Universidade Federal do Pará, Belém, Pará, BrazilDepartamento de Computação, Centro Federal de Educação Tecnológica de Minas Gerais, Divinópolis, Minas Gerais, BrazilInstituto de Tecnologia, Universidade Federal do Pará, Belém, Pará, BrazilNorte Energia S.A., Brasília, DF, BrazilInstituto de Tecnologia, Universidade Federal do Pará, Belém, Pará, BrazilInstituto de Tecnologia, Universidade Federal do Pará, Belém, Pará, BrazilVisual inspection is essential to ensure the stability of earth-rock dams. Periodic visual assessment of this type of structure through vegetation cover analysis is an effective monitoring method. Recently, multispectral remote sensing data and machine learning techniques have been applied to develop methodologies that enable automatic vegetation analysis and anomaly detection based on computer vision. As a first step toward this automation, this study introduces a methodology for land cover segmentation of earth-rock embankment dam structures within the Belo Monte Hydroelectric Complex, located in the state of Pará, northern Brazil. Random forest (RF) ensemble models were trained on manually annotated data captured by a multispectral sensor embedded in an uncrewed aerial vehicle (UAV). The main objectives of this study are to assess the classification performance of the algorithm in segmenting earth-rock dams and the contribution of non-visible band reflectance data to the overall model performance. A comprehensive feature engineering and ranking approach is presented to select the most descriptive features that represent the four dataset classes. Model performance was assessed using classical performance metrics derived from the confusion matrix, such as accuracy, Kappa coefficient, precision, recall, F1-score, and intersection over union (IoU). The final RF model achieved 90.9% mean IoU for binary segmentation and 91.1% mean IoU for multiclass segmentation. Post-processing techniques were applied to refine the predicted masks, enhancing the mean IoU to 93.2% and 91.9%, respectively. The flexible methodology presented in this work can be applied to different scenarios when treated as a framework for pixel-wise land cover classification, serving as a crucial step toward automating visual inspection processes. The implementation of automated monitoring solutions improves the visual inspection process and mitigates the catastrophic consequences resulting from dam failures.https://peerj.com/articles/cs-2917.pdfEmbankment damVegetationMultispectral imageryRemote sensingUAVSegmentation
spellingShingle Carlos André de Mattos Teixeira
Thabatta Moreira Alves de Araujo
Evelin Cardoso
Marcos Antonio Costantin Filho
João Weyl Costa
Carlos Renato Lisboa Frances
Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, Brazil
PeerJ Computer Science
Embankment dam
Vegetation
Multispectral imagery
Remote sensing
UAV
Segmentation
title Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, Brazil
title_full Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, Brazil
title_fullStr Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, Brazil
title_full_unstemmed Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, Brazil
title_short Aerial image segmentation of embankment dams based on multispectral remote sensing: a case study in the Belo Monte Hydroelectric Complex, Pará, Brazil
title_sort aerial image segmentation of embankment dams based on multispectral remote sensing a case study in the belo monte hydroelectric complex para brazil
topic Embankment dam
Vegetation
Multispectral imagery
Remote sensing
UAV
Segmentation
url https://peerj.com/articles/cs-2917.pdf
work_keys_str_mv AT carlosandredemattosteixeira aerialimagesegmentationofembankmentdamsbasedonmultispectralremotesensingacasestudyinthebelomontehydroelectriccomplexparabrazil
AT thabattamoreiraalvesdearaujo aerialimagesegmentationofembankmentdamsbasedonmultispectralremotesensingacasestudyinthebelomontehydroelectriccomplexparabrazil
AT evelincardoso aerialimagesegmentationofembankmentdamsbasedonmultispectralremotesensingacasestudyinthebelomontehydroelectriccomplexparabrazil
AT marcosantoniocostantinfilho aerialimagesegmentationofembankmentdamsbasedonmultispectralremotesensingacasestudyinthebelomontehydroelectriccomplexparabrazil
AT joaoweylcosta aerialimagesegmentationofembankmentdamsbasedonmultispectralremotesensingacasestudyinthebelomontehydroelectriccomplexparabrazil
AT carlosrenatolisboafrances aerialimagesegmentationofembankmentdamsbasedonmultispectralremotesensingacasestudyinthebelomontehydroelectriccomplexparabrazil