Toward Reliable Corrosion Forecasts in Waterway Infrastructure Using LSTM-Based Models and Synthetic Sequences under Sparse Data Conditions
Sarah Flohr (),
Svea Worms (),
Grit Behrens () and
Andreas Kahlfeld ()
Additional contact information
Sarah Flohr: University of Applied Sciences and Arts, Department of Applied Computer Science
Svea Worms: University of Applied Sciences and Arts, Department of Applied Computer Science
Grit Behrens: University of Applied Sciences and Arts, Department of Applied Computer Science
Andreas Kahlfeld: University of Applied Sciences and Arts, Department of Hydraulic and Transportation Engineering
A chapter in Advances and New Trends in Environmental Informatics, 2026, pp 21-37 from Springer
Abstract:
Abstract Reliable prediction of corrosion in hydraulic steel structures is crucial for maintenance planning and structural safety. However, practical inspection data are often sparse, irregular, and limited to a few time points per structure—challenging the applicability of conventional forecasting methods. This study presents a data-driven framework that enables long-term corrosion prediction under such constraints by combining domain-informed preprocessing, synthetic sequence generation, and deep learning. Starting from individual wall thickness measurements stored in the WaDiMe database, synthetic time series were constructed using interpolation and DTW Barycenter Averaging to simulate realistic corrosion progression. A CNN-BiLSTM model was trained on 14, 600 augmented sequences and evaluated using recursive forecasting strategies. The model reliably captured the general corrosion trend, including the characteristic exponential wall thickness loss, even with minimal input. Moreover, a transfer learning approach demonstrated successful model adaptation to new environments, such as canal structures, based on only a few additional time series. The framework thus offers a robust and generalizable solution for predictive maintenance in data-scarce settings.
Keywords: Corrosion Forecasting; Data-Driven Infrastructure Monitoring; Sparse Time Series; LSTM Networks; Synthetic Data; Transfer Learning (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:
There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:spr:prochp:978-3-032-22726-3_2
Ordering information: This item can be ordered from
http://www.springer.com/9783032227263
DOI: 10.1007/978-3-032-22726-3_2
Access Statistics for this chapter
More chapters in Progress in IS from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().