Advancing sustainable urban mobility has led to a surge of research in signalized intersection management, spanning adaptive signal control, short-horizon flow forecasting, emission modelling, and counterfactual scenario analysis. A common limitation across prior studies is that proposed methods are rarely benchmarked or benchmarked almost exclusively in simulation environments whose correspondence to physical reality is rarely evaluated according to industry standard. To address this, we construct a microscopic digital twin of a fully actuated intersection in Zürich, using the SUMO platform, grounded in a full 24-hour inductive loop detector occupancy and signal group state data collected at one-second resolution, comprising 86,400 observations. Calibration fidelity is assessed against two complementary industry standards: the Geoffrey E. Havers (GEH) criterion stipulated in DfT WebTAG M3.1 and the coefficient of determination threshold defined in NCHRP Report 765. Eight of nine loop detectors satisfy the GEH < 5.0 threshold, placing the aggregate pass rate at 89% and exceeding the minimum 85% acceptance criterion specified by the standard. Temporal agreement between simulated and observed per-period counts yields an R2 of 0.984 across all validated detectors, surpassing the NCHRP R2 > 0.90 acceptance threshold and confirming that ZuriTwinBench reproduces not only daily totals but the hour-by-hour demand profile with high fidelity.

ZuriTwinBench: A Calibrated Open Digital Twin of a Fully-actuated Urban Intersection as Enabling Infrastructure for Smart City Traffic Management Research / Idris, H.A., Cabri, G.. - (2026), pp. 1-6. (34rd IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE 2026 PARIS,FRANCE 2026) [10.1109/wetice70595.2026.11772342].

ZuriTwinBench: A Calibrated Open Digital Twin of a Fully-actuated Urban Intersection as Enabling Infrastructure for Smart City Traffic Management Research

Idris, Hussaini Aliyu;Cabri, Giacomo
2026

Abstract

Advancing sustainable urban mobility has led to a surge of research in signalized intersection management, spanning adaptive signal control, short-horizon flow forecasting, emission modelling, and counterfactual scenario analysis. A common limitation across prior studies is that proposed methods are rarely benchmarked or benchmarked almost exclusively in simulation environments whose correspondence to physical reality is rarely evaluated according to industry standard. To address this, we construct a microscopic digital twin of a fully actuated intersection in Zürich, using the SUMO platform, grounded in a full 24-hour inductive loop detector occupancy and signal group state data collected at one-second resolution, comprising 86,400 observations. Calibration fidelity is assessed against two complementary industry standards: the Geoffrey E. Havers (GEH) criterion stipulated in DfT WebTAG M3.1 and the coefficient of determination threshold defined in NCHRP Report 765. Eight of nine loop detectors satisfy the GEH < 5.0 threshold, placing the aggregate pass rate at 89% and exceeding the minimum 85% acceptance criterion specified by the standard. Temporal agreement between simulated and observed per-period counts yields an R2 of 0.984 across all validated detectors, surpassing the NCHRP R2 > 0.90 acceptance threshold and confirming that ZuriTwinBench reproduces not only daily totals but the hour-by-hour demand profile with high fidelity.
2026
34rd IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE 2026
PARIS,FRANCE
2026
1
6
Idris, Hussaini Aliyu; Cabri, Giacomo
ZuriTwinBench: A Calibrated Open Digital Twin of a Fully-actuated Urban Intersection as Enabling Infrastructure for Smart City Traffic Management Research / Idris, H.A., Cabri, G.. - (2026), pp. 1-6. (34rd IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises, WETICE 2026 PARIS,FRANCE 2026) [10.1109/wetice70595.2026.11772342].
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1425188
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex 0
social impact