Page 100 - Read Online

Yu et al. Carbon Footprints 2025, 4, 17 https://dx.doi.org/10.20517/cf.2025.12 Page 15 of 23

Table 5. Representative spatiotemporal emission models at the traffic level
Reference Model Data source Input variables
[79] GCNNWR GPS, OBD, road network Driving behaviors (status, speed, speed variation), external
factors (weather)
[80] ST-GCN Remote CO sensor, PEMS, speed sensor, road Road network topology, traffic patterns, POIs, meteorological
2
network, POI patterns
[81] SAGE- Street view image, road network, taxi GPS data Street feature, graph structure, emission levels
GSAN
[78] GCNNWR Trajectory data, POI data, road network Number of POIs, road length
ST-GCN: Spatio-temporal graph convolutional network; SAGE-GSAN: graph sample and aggreGatE-graph spatial attention network; POI: point of
interest; GCNNWR: geographical convolutional neural network weighted regression; GPS: global positioning system; OBD: on-board diagnostics;
PEMS: portable emission measurement system.

Accuracy
The accuracy of data-driven emission models is influenced by multiple factors, including data quality,
preprocessing methods, feature engineering, model architecture, algorithm adaptability, and training
strategies such as hyperparameter optimization, making straightforward evaluation challenging .
[83]
Complexity
In data-driven machine learning approaches, traditional models such as linear regression and decision trees
offer high computational efficiency. Ensemble models (e.g., XGBoost and random forests), while requiring
careful feature selection and overfitting control, still exhibit significantly lower computational demands than
deep learning models. When applied to road network-level emission estimation, the strong spatiotemporal
dependencies inherent in vehicular emissions substantially increase model complexity. External factors such
as weather conditions, traffic patterns, and points of interest further compound this challenge. Due to the
involvement of graph convolution operations and spatiotemporal attention mechanisms, these models have
many parameters and require handling high-dimensional tensor operations during training, demanding
significant GPU memory and computational resources. This is particularly challenging in large-scale road
networks, where issues related to the storage and propagation efficiency of adjacency matrices may arise.
For instance, spatiotemporal GNNs typically scale quadratically with sequence length and the number of
links in the graph, hindering their application in large graphs and long time series .
[84]

Transparency
When a linear relationship exists between model inputs and emission outputs, the model tends to exhibit
higher transparency and interpretability [77,85] . However, machine learning methods such as neural networks
and deep learning are considered black-box models. Due to their complex internal structures and lack of
explicit analytical formulations, these models offer limited insight into the decision-making process. When
input data are noisy or uncertain, the opacity of such models may undermine confidence in the attribution
of emissions, posing challenges for traffic managers and policymakers seeking transparent and explainable
results.

Transferability
Regarding transferability, statistical regression-based emission models generally demonstrate strong
transferability. When the feature distribution of the target dataset closely resembles that of the training
dataset, these models can be directly transferred while maintaining high accuracy. Even in the presence of
differences, quick adaptation can be achieved through local feature recalibration. However, for neural
networks, the transferability of time series models is limited by vehicle type and driving behavior, while
spatiotemporal models face restrictions related to road network topology, necessitating the re-encoding of