Enhancing the Prediction of Dam Deformations: A Novel Data-Driven Approach

Deformation monitoring is a critical task for dam operators to guarantee safe operation. Given an increasing number of extreme weather events caused by climate change, the precise prediction of dam deformations has become increasingly important. Traditionally, multiple linear regression models have...

Full description

Saved in:
Bibliographic Details
Main Authors: Jonas Ziemer, Gideon Stein, Carolin Wicker, Jannik Jänichen, Daniel Klöpper, Katja Last, Joachim Denzler, Christiane Schmullius, Maha Shadaydeh, Clémence Dubois
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/6/1026
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850087939651928064
author Jonas Ziemer
Gideon Stein
Carolin Wicker
Jannik Jänichen
Daniel Klöpper
Katja Last
Joachim Denzler
Christiane Schmullius
Maha Shadaydeh
Clémence Dubois
author_facet Jonas Ziemer
Gideon Stein
Carolin Wicker
Jannik Jänichen
Daniel Klöpper
Katja Last
Joachim Denzler
Christiane Schmullius
Maha Shadaydeh
Clémence Dubois
author_sort Jonas Ziemer
collection DOAJ
description Deformation monitoring is a critical task for dam operators to guarantee safe operation. Given an increasing number of extreme weather events caused by climate change, the precise prediction of dam deformations has become increasingly important. Traditionally, multiple linear regression models have been employed, utilizing in situ data from pendulum systems or trigonometric measurements. These methods sometimes suffer from sparse data, which typically represent deformations only at specific points on the dam, if such data are available at all. Technical advances in multi-temporal synthetic aperture radar interferometry (MT-InSAR), particularly Persistent Scatterer Interferometry (PSI), address these limitations by enabling monitoring in high spatial and temporal resolution, capturing dam deformations with millimeter precision, and providing extensive spatial coverage. This study advances traditional methods of dam monitoring by employing data-driven techniques and integrating Sentinel-1 C-band Persistent Scatterer (PS) time series alongside in situ data. Through a comprehensive evaluation of advanced data-driven approaches, we demonstrated considerable improvements in predicting dam deformations and evaluating their drivers. The analysis provided evidence for the following insights: First, the accuracy of current modeling approaches can be greatly improved by utilizing advanced feature engineering and data-driven model selection. The prediction performance of the pendulum data was improved by utilizing data-driven algorithms, reducing the mean absolute error from 0.51 mm in the baseline model (<i>R</i><sup>2</sup> = 0.92) to as low as 0.05 mm using the full model search space (<i>R</i><sup>2</sup> = 0.99). Although the model accuracy for the PS datasets (<i>MAE<sub>max</sub></i>: 0.81 mm) was about one order of magnitude lower than that for pendulum data, the mean absolute errors could be reduced by up to 0.25 mm. Second, by incorporating freely available PS time series into deformation prediction, dams can be monitored in higher spatial resolution, making PSI a valuable tool for dam operators. This requires adequate dataset filtering to eliminate noisy PS points. Third, extended representations of water level and temperature, including interaction effects, can improve model accuracy and reduce prediction errors. With these insights, we recommend incorporating the proposed methodology into the monitoring program of gravity dams to enhance the accuracy in predicting their expected deformations.
format Article
id doaj-art-e5bd58f341e54dc4869da4aeb974cd63
institution DOAJ
issn 2072-4292
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-e5bd58f341e54dc4869da4aeb974cd632025-08-20T02:43:06ZengMDPI AGRemote Sensing2072-42922025-03-01176102610.3390/rs17061026Enhancing the Prediction of Dam Deformations: A Novel Data-Driven ApproachJonas Ziemer0Gideon Stein1Carolin Wicker2Jannik Jänichen3Daniel Klöpper4Katja Last5Joachim Denzler6Christiane Schmullius7Maha Shadaydeh8Clémence Dubois9Department for Earth Observation, Friedrich-Schiller-University Jena, Leutragraben 1, 07743 Jena, GermanyComputer Vision Group, Friedrich-Schiller-University Jena, Ernst-Abbe-Platz 2, 07743 Jena, GermanyDepartment for Water Economy, Ruhrverband, Kronprinzenstraße 29, 45128 Essen, GermanyDepartment for Earth Observation, Friedrich-Schiller-University Jena, Leutragraben 1, 07743 Jena, GermanyDepartment for Water Economy, Ruhrverband, Kronprinzenstraße 29, 45128 Essen, GermanyDepartment for Water Economy, Ruhrverband, Kronprinzenstraße 29, 45128 Essen, GermanyComputer Vision Group, Friedrich-Schiller-University Jena, Ernst-Abbe-Platz 2, 07743 Jena, GermanyDepartment for Earth Observation, Friedrich-Schiller-University Jena, Leutragraben 1, 07743 Jena, GermanyComputer Vision Group, Friedrich-Schiller-University Jena, Ernst-Abbe-Platz 2, 07743 Jena, GermanyGerman Aerospace Center, Institute of Data Science, Mälzerstraße 3, 07743 Jena, GermanyDeformation monitoring is a critical task for dam operators to guarantee safe operation. Given an increasing number of extreme weather events caused by climate change, the precise prediction of dam deformations has become increasingly important. Traditionally, multiple linear regression models have been employed, utilizing in situ data from pendulum systems or trigonometric measurements. These methods sometimes suffer from sparse data, which typically represent deformations only at specific points on the dam, if such data are available at all. Technical advances in multi-temporal synthetic aperture radar interferometry (MT-InSAR), particularly Persistent Scatterer Interferometry (PSI), address these limitations by enabling monitoring in high spatial and temporal resolution, capturing dam deformations with millimeter precision, and providing extensive spatial coverage. This study advances traditional methods of dam monitoring by employing data-driven techniques and integrating Sentinel-1 C-band Persistent Scatterer (PS) time series alongside in situ data. Through a comprehensive evaluation of advanced data-driven approaches, we demonstrated considerable improvements in predicting dam deformations and evaluating their drivers. The analysis provided evidence for the following insights: First, the accuracy of current modeling approaches can be greatly improved by utilizing advanced feature engineering and data-driven model selection. The prediction performance of the pendulum data was improved by utilizing data-driven algorithms, reducing the mean absolute error from 0.51 mm in the baseline model (<i>R</i><sup>2</sup> = 0.92) to as low as 0.05 mm using the full model search space (<i>R</i><sup>2</sup> = 0.99). Although the model accuracy for the PS datasets (<i>MAE<sub>max</sub></i>: 0.81 mm) was about one order of magnitude lower than that for pendulum data, the mean absolute errors could be reduced by up to 0.25 mm. Second, by incorporating freely available PS time series into deformation prediction, dams can be monitored in higher spatial resolution, making PSI a valuable tool for dam operators. This requires adequate dataset filtering to eliminate noisy PS points. Third, extended representations of water level and temperature, including interaction effects, can improve model accuracy and reduce prediction errors. With these insights, we recommend incorporating the proposed methodology into the monitoring program of gravity dams to enhance the accuracy in predicting their expected deformations.https://www.mdpi.com/2072-4292/17/6/1026dam monitoringdata-driven algorithmsdeformation predictionPSISentinel-1
spellingShingle Jonas Ziemer
Gideon Stein
Carolin Wicker
Jannik Jänichen
Daniel Klöpper
Katja Last
Joachim Denzler
Christiane Schmullius
Maha Shadaydeh
Clémence Dubois
Enhancing the Prediction of Dam Deformations: A Novel Data-Driven Approach
Remote Sensing
dam monitoring
data-driven algorithms
deformation prediction
PSI
Sentinel-1
title Enhancing the Prediction of Dam Deformations: A Novel Data-Driven Approach
title_full Enhancing the Prediction of Dam Deformations: A Novel Data-Driven Approach
title_fullStr Enhancing the Prediction of Dam Deformations: A Novel Data-Driven Approach
title_full_unstemmed Enhancing the Prediction of Dam Deformations: A Novel Data-Driven Approach
title_short Enhancing the Prediction of Dam Deformations: A Novel Data-Driven Approach
title_sort enhancing the prediction of dam deformations a novel data driven approach
topic dam monitoring
data-driven algorithms
deformation prediction
PSI
Sentinel-1
url https://www.mdpi.com/2072-4292/17/6/1026
work_keys_str_mv AT jonasziemer enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT gideonstein enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT carolinwicker enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT jannikjanichen enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT danielklopper enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT katjalast enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT joachimdenzler enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT christianeschmullius enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT mahashadaydeh enhancingthepredictionofdamdeformationsanoveldatadrivenapproach
AT clemencedubois enhancingthepredictionofdamdeformationsanoveldatadrivenapproach