EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fine-Tuned Nonlinear Autoregressive Recurrent Neural Network Model for Dam Displacement Time Series Prediction

Vukašin Ćirović, Vesna Ranković, Nikola Milivojević, Vladimir Milivojević, Brankica Majkić-Dursun

Machine Learning and Knowledge Extraction · 05.04.2026 · 8 (4) · 90

DOI: 10.3390/make8040090 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 05.04.2026. Verfasst von Vukašin Ćirović und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dam monitoring data are nonlinear and nonstationary time series. Most existing data-driven dam displacement models are developed independently for each measuring point, disregarding the fact that a dam is a complex structure composed of various interconnected elements that form a unified whole. Regardless of the dam type, all points on the dam are exposed to the same external environmental influences. To account for the correlation between displacement time series at different points, this paper proposes a novel fine-tuned deep-learning nonlinear autoregressive (NAR) model based on a Long Short-Term Memory (LSTM) network for predicting dam tangential displacement, and a new method for generating source data to train the base model. The models for three measuring points were developed and tested on experimental data collected over a period of slightly more than twelve years. Compared with the model without fine-tuning, the proposed approach achieves an average mean square error (MSE) reduction of 80.68% on the training set and 65.79% on the test set, as well as an average mean absolute error (MAE) reduction of 51.05% and 52.62%, respectively. Furthermore, the proposed model outperforms Random Forest (RF), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP) models for dam displacement prediction.

Zitieren

APA

Ćirović, V., Ranković, V., Milivojević, N., Milivojević, V., & Majkić-Dursun, B. (2026). Fine-Tuned Nonlinear Autoregressive Recurrent Neural Network Model for Dam Displacement Time Series Prediction. Machine Learning and Knowledge Extraction, 8(4), 90. https://doi.org/10.3390/make8040090

Vancouver

Ćirović V, Ranković V, Milivojević N, Milivojević V, Majkić-Dursun B. Fine-Tuned Nonlinear Autoregressive Recurrent Neural Network Model for Dam Displacement Time Series Prediction. Machine Learning and Knowledge Extraction. 2026;8(4):90. doi:10.3390/make8040090

BibTeX
@article{irovi2026,
  author = {Ćirović, Vukašin and Ranković, Vesna and Milivojević, Nikola and Milivojević, Vladimir and Majkić-Dursun, Brankica},
  title = {Fine-Tuned Nonlinear Autoregressive Recurrent Neural Network Model for Dam Displacement Time Series Prediction},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {4},
  pages = {90},
  doi = {10.3390/make8040090}
}
Kostenlos starten →