Page 101 - Read Online

Page 16 of 23 Yu et al. Carbon Footprints 2025, 4, 17 https://dx.doi.org/10.20517/cf.2025.12

node attributes.

Overall evaluation
To facilitate a structured comparison, five representative data-driven emission models were evaluated across
five dimensions: Data Requirements, Accuracy, Complexity, Transparency, and Transferability. The scores
(1 = lowest, 5 = highest) are based on a synthesis of performance reports in the literature and prevailing
expert understanding of model behavior in emission estimation contexts. While these values are not derived
from uniform benchmarking experiments, they offer a qualitative overview of the trade-offs and design
considerations associated with each modeling approach.

Figure 5 presents a radar chart summarizing the evaluation results of these data-driven models: Random
Forest, LSTM, GCN, XGBoost, and a Hybrid Physics-Deep Learning approach. Among them, Random
Forest and XGBoost demonstrate relatively strong performance in terms of Data Requirements,
Complexity, and Transferability, highlighting their practical utility in diverse scenarios where data
availability and model generalization are critical. LSTM and the Hybrid Physics-DL models achieve the
highest scores in Accuracy, reflecting their ability to capture complex temporal dependencies and physical
relationships in emission dynamics. However, these models tend to be more complex and less transparent,
which may pose challenges in interpretability and computational demand. GCN, while offering moderate
accuracy and transferability, scores lower on data requirements and complexity, possibly due to the need for
structured graph data inputs and sophisticated model architectures. This qualitative assessment underscores
inherent trade-offs in selecting data-driven emission models: simpler models with lower data demands and
higher transparency may sacrifice some accuracy, while more complex models can better fit intricate
emission patterns but at the cost of interpretability and data needs.

RELATED APPLICATIONS
High-resolution spatiotemporal emission inventories
Decision support for traffic management departments is derived from smart traffic systems that incorporate
urban road traffic emission modules. The development of high-resolution emission inventories, featuring
fine-grained spatial (e.g., 1 × 1 km) and temporal (e.g., hourly) resolutions, enables detailed accounting of
both air pollutants and greenhouse gas emissions.

Current research typically achieves detailed emission calculations by integrating traditional emission models
with trajectory data or traffic variable data. Studies have found that the spatiotemporal heterogeneity of
emission inventories exhibits significant scale effects. At the spatial scale, emission hotspots show notable
regional clustering characteristics; for instance, emissions from trucks are concentrated around railway
stations. At the temporal scale, the emission intensity of freight vehicles on weekdays is higher than on
weekends, and at the hourly scale, both passenger and freight vehicles demonstrate a bimodal characteristic.
[49]
This confirms the necessity and feasibility of traffic operation management .

To improve the accuracy of models based on average speed or traffic conditions, localizing emission factor
databases is critical. Qiu et al. collected localized vehicle operating conditions in Shenzhen and matched
[86]
them with typical conditions from the European HBEFA database, identifying 4,500 emission factors under
various vehicle types, road conditions, and emission standards, thereby establishing a localized emission
factor database for Shenzhen.

Beyond trajectory and traffic variable data, the incorporation of automatic license plate recognition (LPR)
and vehicle registration data enables the construction of urban vehicle emission knowledge graphs. By