Forecasting Fatal Construction Accidents Using an STL–BiGRU Hybrid Framework: A Multi-Scale Time Series Approach
Identification
- Public canonical key
- radar:r-2a3f40f9daa1481d89291c92401d32d1
- Authors
- Yuntao Cao · Rui Zhang · Ziyi Qu · Martin Skitmore · Xingguan Ma · J Wang
- Reported year
- 2026
- Reported language
- en
- Source type
- article
- First detected
- 2026-11-14T02:38:35.746162+00:00
- Last metadata observation
- 2026-11-14T02:38:35.746162+00:00
- Last HTTP verification
- Not checked
Institutions reported by the source
Shenyang Jianzhu University · Qingdao University of Technology · Bond University
Reported affiliation countries
AU · CN
Documentary abstract — original language
Accurate forecasting of fatal construction accidents is critical for proactive safety management; however, accident time series exhibit strong non-stationarity, nonlinear dynamics, and multi-scale temporal patterns that challenge conventional models. This study proposes a hybrid STL–BiGRU framework that integrates Seasonal–Trend decomposition using Loess (STL) with a Bidirectional Gated Recurrent Unit (BiGRU) network to deliver robust and interpretable forecasts tailored to construction safety needs. STL first decomposes the original monthly accident series (January 2012–December 2024, OSHA) into trend, seasonal, and residual components, reducing structural complexity and mitigating non-stationarity. Independent BiGRU models are then trained on each component to capture bidirectional temporal dependencies, and final forecasts are reconstructed through component aggregation. Comparative experiments against Gated Recurrent Units (GRUs), Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNNs), Support Vector Regression (SVR), Autoregressive Integrated Moving Average (ARIMA), and their STL-enhanced variants demonstrate that the proposed STL–BiGRU model achieves superior performance across both short-term and medium-term horizons. The model achieves the lowest error levels, with a short-term Root Mean Squared Error (RMSE) of 6.8522 and a medium-term RMSE of 7.0568, and shows consistent improvements in Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). Results indicate that multi-scale decomposition combined with bidirectional deep learning provides a practical, forward-looking tool. It helps regulators and contractors anticipate high-risk periods, optimize resource allocation, and reduce fatal accidents through targeted preventive measures.
Identifiers
- OPENALEX
- https://openalex.org/W7154395520
- DOI
- 10.3390/buildings16081539
Documentary context
- Documentary family
- article
- Source-reported types
- article
- Publishers
- Multidisciplinary Digital Publishing Institute
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Sources
OpenAlex · Record 1
Cite this reference
Yuntao Cao; Rui Zhang; Ziyi Qu; Martin Skitmore; Xingguan Ma; J Wang. Forecasting Fatal Construction Accidents Using an STL–BiGRU Hybrid Framework: A Multi-Scale Time Series Approach. 2026. https://doi.org/10.3390/buildings16081539
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Yuntao Cao; Rui Zhang; Ziyi Qu; Martin Skitmore; Xingguan Ma; J Wang. (2026). Forecasting Fatal Construction Accidents Using an STL–BiGRU Hybrid Framework: A Multi-Scale Time Series Approach. https://doi.org/10.3390/buildings16081539
- Chicago
- Yuntao Cao; Rui Zhang; Ziyi Qu; Martin Skitmore; Xingguan Ma; J Wang. Forecasting Fatal Construction Accidents Using an STL–BiGRU Hybrid Framework: A Multi-Scale Time Series Approach. 2026. https://doi.org/10.3390/buildings16081539
- ISO 690
- Yuntao Cao; Rui Zhang; Ziyi Qu; Martin Skitmore; Xingguan Ma; J Wang. Forecasting Fatal Construction Accidents Using an STL–BiGRU Hybrid Framework: A Multi-Scale Time Series Approach. 2026. https://doi.org/10.3390/buildings16081539
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. Forecasting Fatal Construction Accidents Using an STL–BiGRU Hybrid Framework: A Multi-Scale Time Series Approach. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-2a3f40f9daa1481d89291c92401d32d1/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://doi.org/10.3390/buildings16081539
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.