| 1. |
- Zhang, Wei, et al.
(författare)
-
Coordination for heavy-duty vehicle platoon formation considering travel time variance
- 2015
-
Konferensbidrag (refereegranskat)abstract
- Forming a platoon has the potential to reduce the overall drag, providing economic and ecological benefitssuch as reduced energy consumption, increased safety and a more efficient utilization of roadinfrastructure. Previous research on platoon coordination has mainly focused on local control of platoonformation at highway on‐ramps and off‐ramps, or large‐network coordination strategy based on real‐timevehicle‐to‐vehicle communication. The platoon scheduling problem, however, has been barely explored.This study investigates the optimization of platoon scheduling problem, which is defined as theminimization of the total cost of all vehicles, including travel cost, early or late penalty and fuelconsumption. The travel cost is modelled as driver wage of certain travel time, which is comprised ofrecurrent travel time and non‐recurrent delay. Non‐recurrent delay is a random variable independent ofdeparture time. If the actual arrival time is earlier than the preferred arrival time, an early penalty isincurred. Otherwise a late penalty, which has a greater weight coefficient than early penalty, is incurred.Fuel consumption is a nonlinear function of travel time and platooning state. All vehicles in the platoonexcept the leader will experience an air‐drag reduction. The fuel cost caused by air drag only composes partof the total fuel consumption, from the perspective of energy conservation. For this nonlinear stochasticprogramming problem, a solution is proposed for the platoon‐or‐not‐platoon dilemma. Moreover, theoptimal departure time of the platoon is given when it is more beneficial to form a platoon than drivingindividually. Several numerical examples are presented to study the influences of different unit costparameters, together with various assumptions of the distribution of non‐recurrent delay, on the optimaldeparture time. The model enables the operator to predict the expected cost of platooning and scheduleadjustment and make a reasonable decision.
|
|
| 2. |
- Chi, Pengnan, et al.
(författare)
-
Difforecast : Image Generation Based Highway Traffic Forecasting with Diffusion Model
- 2023
-
Ingår i: Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 608-615
-
Konferensbidrag (refereegranskat)abstract
- Monitoring and forecasting of road traffic conditions is a common practice for real traffic information system, and is of vital importance to traffic management and control. While dynamic traffic patterns can be intuitively represented by space-time diagrams, this study proposes a new concept of space-time image (ST-image) to incorporate physical meanings of traffic state variables. We therefore transform the forecasting problem for time-series traffic states into a conditional image generation problem. We explore the inherent properties of the ST images from the perspectives of physical meaning and traffic dynamics. An innovative deep learning based architecture is designed to process the ST-image, and a diffusion model is trained to obtain traffic forecasts by generating the future ST-images based on the historical patterns.
|
|
| 3. |
- Chi, Pengnan, et al.
(författare)
-
Short-Term Traffic Prediction on Swedish Highways: A Deep Learning Approach with Knowledge Representation
- 2023
-
Konferensbidrag (refereegranskat)abstract
- Accurate prediction of highway traffic is of vital importance to proactive traffic monitoring, operation and controls. In the data mining of highway traffic, abstracting temporal knowledge is often prioritized than exploring topological relationship. In this study, we propose a deep learning model, called Knowledge-Sequence-to-Sequence (K-Seq2Seq), to solve the short-term highway traffic prediction problem in two stages: representing temporal knowledge and predicting future traffic. Through computational experiment in a road section of a Swedish motorway, we show that our model outperforms the conventional Seq2Seq model significantly, more than 20% when predicting information of longer time step.
|
|
| 4. |
- Ji, Qingyuan, et al.
(författare)
-
GraphPro : A Graph-based Proactive Prediction Approach for Link Speeds on Signalized Urban Traffic Network
- 2022
-
Ingår i: Conference Proceedings. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 339-346
-
Konferensbidrag (refereegranskat)abstract
- This paper proposes GraphPro, a short-term link speed prediction framework for signalized urban traffic networks. Different from other traditional approaches that adopt only reactive inputs (i.e., surrounding traffic data), GraphPro also accepts proactive inputs (i.e., traffic signal timing). This allows GraphPro to predict link speed more accurately, depending on whether or not there is a contextual change in traffic signal timing. A Wasserstein generative adversarial network (WGAN) structure, including a generator (prediction model) and a discriminator, is employed to incorporate unprecedented network traffic states and ensures a high level of generalizability for the prediction model. A hybrid graph block, comprised of a reactive cell and a proactive cell, is implemented into each neural layer of the generator. In order to jointly capture spatio-temporal influences and signal contextual information on traffic links, the two cells adopt several key neural network-based components, including graph convolutional network, recurrent neural architecture, and self-attention mechanism. The double-cell structure ensures GraphPro learns from proactive input only when required. The effectiveness and efficiency of GraphPro are tested on a short-term link speed prediction task using real-world traffic data. Due to the capabilities of learning from real data distribution and generating unseen samples, GraphPro offers a more reliable and robust prediction when compared with state-of-the-art data-driven models.
|
|
| 5. |
- Jin, J., et al.
(författare)
-
A GAN-Based Short-Term Link Traffic Prediction Approach for Urban Road Networks Under a Parallel Learning Framework
- 2022
-
Ingår i: IEEE transactions on intelligent transportation systems (Print). - : Institute of Electrical and Electronics Engineers (IEEE). - 1524-9050 .- 1558-0016. ; 23:9, s. 16185-16196
-
Tidskriftsartikel (refereegranskat)abstract
- Road link speed is often employed as an essential measure of traffic state in the operation of an urban traffic network. Not only real-time traffic demand but also signal timings and other local planning factors are major influential factors. This paper proposes a short-term traffic speed prediction approach, called PL-WGAN, for urban road networks, which is considered an important part of a novel parallel learning framework for traffic control and operation. The proposed method applies Wasserstein Generative Adversarial Nets (WGAN) for robust data-driven traffic modeling using a combination of generative neural network and discriminative neural network. The generative neural network models the road link features of the adjacent intersections and the control parameters of intersections using a hybrid graph block. In addition, the spatial-temporal relations are captured by stacking a graph convolutional network (GCN), a recurrent neural network (RNN), and an attention mechanism. A comprehensive computational experiment was carried out including comparing model prediction and computational performances with several state-of-the-art deep learning models. The proposed approach has been implemented and applied for predicting short-term link traffic speed in a large-scale urban road network in Hangzhou, China. The results suggest that it provides a scalable and effective traffic prediction solution for urban road networks.
|
|
| 6. |
- Jin, Junchen
(författare)
-
Advance Traffic Signal Control Systems with Emerging Technologies
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Nowadays, traffic congestion poses critical problems including the undermined mobility and sustainability efficiencies. Mitigating traffic congestions in urban areas is a crucial task for both research and in practice. With decades of experience in road traffic controls, there is still room for improving traffic control measures; especially with the emerging technologies, such as artificial intelligence (AI), the Internet of Things (IoT), and Big Data. The focus of this thesis lies in the development and implementation of enhanced traffic signal control systems, one of the most ubiquitous and challenging traffic control measures.This thesis makes the following major contributions. Firstly, a simulation-based optimization framework is proposed, which is inherently general in which various signal control types, and different simulation models and optimization methods can be integrated. Requiring heavy computing resources is a common issue of simulation-based optimization approaches, which is addressed by an advanced genetic algorithm and parallel traffic simulation in this study.The second contribution is an investigation of an intelligent local control system. The local signal control operation is formulated as a sequential decision-making process where each controller or control component is modeled as an intelligent agent. The agents make decisions based on traffic conditions and the deployed road infrastructure, as well as the implemented control scheme. A non-parametric state estimation method and an adaptive control scheme by reinforcement learning (RL) are introduced to facilitate such an intelligent system.The local intelligence is expanded to an arterial road using a decentralized design, which is enabled by a hierarchical framework. Then, a network of signalized intersections is operated under the cooperation of agents at different levels of hierarchy. An agent at a lower level is instructed by the agent at the next higher level toward a common operational goal. Agents at the same level can communicate with their neighbors and perform collective behaviors.Additionally, a multi-objective RL approach is in use to handle the potential conflict between agents at different hierarchical levels. Simulation experiments have been carried out, and the results verify the capabilities of the proposed methodologies in traffic signal control applications. Furthermore, this thesis demonstrates an opportunity to employ the systems in practice when the system is programmed on an intermediate hardware device. Such a device can receive streaming detection data from signal controller hardware or the simulation environment and override the controlled traffic lights in real time.
|
|
| 7. |
- Jin, Junchen, et al.
(författare)
-
PRECOM : A Parallel Recommendation Engine for Control, Operations, and Management on Congested Urban Traffic Networks
- 2021
-
Ingår i: IEEE transactions on intelligent transportation systems (Print). - : Institute of Electrical and Electronics Engineers (IEEE). - 1524-9050 .- 1558-0016. ; , s. 1-11
-
Tidskriftsartikel (refereegranskat)abstract
- This paper proposes a parallel recommendation engine, PRECOM, for traffic control operations to mitigate congestion of road traffic in the metropolitan area. The recommendation engine can provide, in real-time, effective and optimal control plans to traffic engineers, who are responsible for manually calibrating traffic signal plans especially when a road network suffers from heavy congestion due to disruptive events. With the idea of incorporating expert knowledge in the operation loop, the PRECOM system is designed to include three conceptual components: an artificial system model, a computational experiment module, and a parallel execution module. Meanwhile, three essential algorithmic steps are implemented in the recommendation engine: a candidate generator based on a graph model, a spatiotemporal ranker, and a context-aware re-ranker. The PRECOM system has been deployed in the city of Hangzhou, China, through both offline and online evaluation. The experimental results are promising, and prove that the recommendation system can provide effective support to the current human-in-the-loop control scheme in the practice of traffic control, operations, and management.
|
|
| 8. |
- Johansson, Ingrid
(författare)
-
Simulation Studies of Impact of Heavy-Duty Vehicle Platoons on Road Traffic and Fuel Consumption
- 2018
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The demand for road freight transport continues to grow with the growing economy, resulting in increased fossil fuel consumption and emissions. At the same time, the fossil fuel use needs to decrease substantially to counteract the ongoing global warming. One way to reduce fuel consumption is to utilize emerging intelligent transport system (ITS) technologies and introduce heavy-duty vehicle (HDV) platooning, i.e. HDVs driving with small inter-vehicle gaps enabled by the use of sensors and controllers. It is of importance for transport authorities and industries to investigate the effects of introducing HDV platooning. Previous studies have investigated the potential benefits, but the effects in real traffic, both for the platoons and for the surrounding vehicles, have barely been explored. To further utilize ITS and optimize the platoons, information about the traffic situation ahead can be used to optimize the vehicle trajectories for the platoons. Paper I presents a dynamic programming-based optimal speed control including information of the traffic situation ahead. The optimal control is applied to HDV platoons in a deceleration case and the potential fuel consumption reduction is evaluated by a microscopic traffic simulation study with HDV platoons driving in real traffic conditions. The effects for the surrounding traffic are also analysed. Paper II and Paper III present a simulation platform to assess the effects of HDV platooning in real traffic conditions. Through simulation studies, the potential fuel consumption reduction by adopting HDV platooning on a real highway stretch is evaluated, and the effects for the other vehicles in the network are investigated.
|
|
| 9. |
- Liang, Xinyue, et al.
(författare)
-
AVIATOR: fAst Visual Perception and Analytics for Drone-Based Traffic Operations
- 2023
-
Ingår i: 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 2959-2964
-
Konferensbidrag (refereegranskat)abstract
- Drone-based system is an emerging technology for advanced applications in Intelligent Transport Systems (ITS). This paper presents our latest developments of a visual perception and analysis system, called AVIATOR, for drone-based road traffic management. The system advances from the previous SeeFar system in several aspects. For visual perception, deep-learning based computer vision models still play the central role but the current system development focuses on fast and efficient detection and tracking performance during real-time image processing. To achieve that, YOLOv7 and ByteTrack models have replaced the previous perception modules to gain better computational performance. Meanwhile, a lane-based traffic steam detection module is added for recognizing detailed traffic flow per lane, enabling more detailed estimation of traffic flow patterns. The traffic analytics module has been modified to estimate traffic states using lane-based data collection. This includes detailed lane-based traffic flow counting as well as traffic density estimation according to vehicle arrival patterns per lane.
|
|
| 10. |
- Ma, Xiaoliang, Docent, et al.
(författare)
-
DigiWays: A Digitalisation Testbed for Sustainable Traffic Management on Swedish Motorways
- 2023
-
Ingår i: 2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023. - : Institute of Electrical and Electronics Engineers Inc..
-
Konferensbidrag (refereegranskat)abstract
- Motorway traffic management system plays important roles for modern Intelligent Transport Systems (ITS). The Swedish motorways near large cities such as Stockholm are equipped with a large number of sensors for traffic monitoring and advanced traffic management purposes. This paper introduces our recent experiments of digitalising motorway traffic system using vehicle-to-everything (V2X) communication and other sensors deployed for measuring road traffic and road-side air pollutants. In addition to the deployment of V2X testbed, a Cyber-Physical system (CPS) framework is presented to integrate the deployed sensors with the computational models for estimation and prediction of traffic and road-side environmental conditions. A digital twin of motorway traffic flow is established using traffic flow models of different levels. The computation in experiment of the cyber space shows that traffic states can be estimated using V2X sensing data by applying the model-based estimation approach.
|
|
| 11. |
- Ma, Xiaoliang, Docent, et al.
(författare)
-
METRIC : Toward a Drone-based Cyber-Physical Traffic Management System
- 2022
-
Ingår i: Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 3324-3329
-
Konferensbidrag (refereegranskat)abstract
- Drone-based system has a big potential to be applied for traffic monitoring and other advanced applications in Intelligent Transport Systems (ITS). This paper introduces our latest efforts of digitalising road traffic by various types of sensing systems, among which visual detection by drones provides a promising technical solution. A platform, called METRIC, is under recent development to carry out real-time traffic measurement and prediction using drone-based data collection. The current system is designed as a cyber-physical system (CPS) with essential functions aiming for visual traffic detection and analysis, real-time traffic estimation and prediction as well as decision supports based on simulation. In addition to the computer vision functions developed in the earlier stage, this paper also presents the CPS system architecture and the current implementation of the drone front-end system and a simulation-based system being used for further drone operations.
|
|
| 12. |
- Ma, Xiaoliang, Docent
(författare)
-
Multi-criteria evaluation of optimal signal strategies using traffic simulation and evolutionary algorithms
- 2012
-
Ingår i: iEMSs 2012 - Managing Resources of a Limited Planet. ; , s. 120-127
-
Konferensbidrag (refereegranskat)abstract
- As a result of the continuous increase of motor vehicles in city areas, sustainability of road traffic in terms of energy and emission has become, in addition to mobility, one important aspect in the planning and management of transportation. This paper introduces a computational framework to model traffic impacts and optimize traffic control measures by integrating microscopic traffic simulator with instantaneous emission model and multi-objective evolutionary algorithm. The approach is applied for evaluation and improvement of traffic management measures mainly traffic signal plans, concerning not only travel delay but also energy and environmental consequences. A case study is presented to show the Pareto frontiers estimated using different strategies, or combination of optimization objectives.
|
|
| 13. |
- Ning, Mang, et al.
(författare)
-
SeeFar : Vehicle Speed Estimation and Flow Analysis from a Moving UAV
- 2022
-
Ingår i: Image Analysis and Processing, ICIAP 2022, PT III. - Cham : Springer Nature. ; , s. 278-289
-
Konferensbidrag (refereegranskat)abstract
- Visual perception from drones has been largely investigated for Intelligent Traffic Monitoring System (ITMS) recently. In this paper, we introduce SeeFar to achieve vehicle speed estimation and traffic flow analysis based on YOLOv5 and DeepSORT from a moving drone. SeeFar differs from previous works in three key ways: the speed estimation and flow analysis components are integrated into a unified framework; our method of predicting car speed has the least constraints while maintaining a high accuracy; our flow analysor is direction-aware and outlier-aware. Specifically, we design the speed estimator only using the camera imaging geometry, where the transformation between world space and image space is completed by the variable Ground Sampling Distance. Besides, previous papers do not evaluate their speed estimators at scale due to the difficulty of obtaining the ground truth, we therefore propose a simple yet efficient approach to estimate the true speeds of vehicles via the prior size of the road signs. We evaluate SeeFar on our ten videos that contain 929 vehicle samples. Experiments on these sequences demonstrate the effectiveness of SeeFar by achieving 98.0% accuracy of speed estimation and 99.1% accuracy of traffic volume prediction, respectively.
|
|
| 14. |
- Sederlin, Michael, et al.
(författare)
-
A Hybrid Modelling Approach for Traffic State Estimation at Signalized Intersections
- 2021
-
Ingår i: 2021 IEEE Intelligent Transportation Systems Conference (ITSC). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 3604-3609
-
Konferensbidrag (refereegranskat)abstract
- Traffic state estimation is an important part of the traffic control process and aims to creates an accurate understanding of the current situation in traffic system. Bayesian Filtering is a statistical modelling framework that is useful in representing traffic state update as well as the relation between traffic state and detection data. This study develops a hybrid approach and uses non-parametric Gaussian Process (GP) to model the state-space transition of traffic system. Through representing the system models as either fully data-driven GP or as a hybrid model using a parametric mean function fusing the conventional principle of traffic flow with the data-driven approach, the requirement of an analytical model can be removed or relaxed. The computational results show that the proposed approach for lane based TSE can capture both short-term fluctuations and larger demand changes. In particular, the Bayesian nature of the GP models offer relative ease in quantifying the model uncertainties in combination with a conventional traffic flow model.
|
|
| 15. |
- Wang, Hao Luo, et al.
(författare)
-
A Data-driven Survival Modelling Approach for Predictive Maintenance of Battery Electric Trucks
- 2023
-
Konferensbidrag (refereegranskat)abstract
- Predictive Maintenance (PdM) aims to estimate the optimal moment when the maintenance of an industrial asset should be performed according to its actual health status. The goal is to minimize the costs, by finding the optimal point where the sum of the prevention and repair cost is at the lowest. Data-driven model may predict whether an asset is close to a real breakdown, therefore helping to build more cost-efficient maintenance strategies. This paper focuses on survival analysis based predictive maintenance applied to the operation of Battery Electric Trucks (BET). Cox Proportional Hazards and Random Survival Forests methods are adopted for modelling time-to-failure and the associated survival functions. Detailed telematics data from BET vehicles in real operations are used for modelling and analysis. The model performance is further improved by the feature selection and hyperparameter tuning processes.
|
|
| 16. |
- Yang, Can, 1990-
(författare)
-
Efficient Map Matching and Discovery of Frequent and Dominant Movement Patterns in GPS Trajectory Data
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The wide deployment of Global Positioning System (GPS) sensors for movement data collection has enabled a wide range of applications in transportation and urban planning. Frequent and dominant movement patterns embedded in GPS trajectory data provide valuable knowledge including the spatial and temporal distribution of frequent routes selected by the tracked objects and the regular movement behavior in certain regions. Discovering frequent and dominant movement patterns embedded in GPS trajectory data needs to address several tasks including (1) matching noisy trajectories to the road network (referred as map matching), (2) extracting frequent and dominant movement patterns, and (3) retrieving the distribution of these patterns over user-specified attribute (e.g., timestamp, travel mode, etc.). These tasks confront several challenges in observation error, efficiency and large pattern search space.To address those challenges, this thesis develops a set of algorithms and tools for efficient map matching and discovery of frequent and dominant movement patterns in GPS trajectory data. More specifically, two map matching algorithms are first developed, which improve the performance by precomputation and A-star search. Subsequently, a frequent route is extracted from map matched trajectories as a Contiguous Sequential Pattern (CSP). A novel CSP mining algorithm is developed by performing bidirectional pruning to efficiently search CSP and reduce redundancy in the result. After that, an efficient CSP comparison algorithm is developed to extend the bidirectional pruning to compare multiple sets of CSP. By comparing CSP mined from trajectories partitioned by a user-specified attribute, the distribution of frequent routes in the attribute space can be obtained. Finally, Regional Dominant Movement Pattern (RDMP) in trajectory data is discovered as regions where most of the objects follow a specific pattern. A novel movement feature descriptor called Directional Flow Image (DFI) is proposed to capture local directional movement information of trajectories in a multiple channel image and a convolutional neural network model is designed for DFI classification and RDMP detection.Comprehensive experiments on both real-world and synthetic GPS datasets demonstrate the efficiency of the proposed algorithms as well as their superiority over state-of-the-art methods. The two map matching algorithms achieve considerable performance in matching densely sampled GPS data to small scale network and sparsely sampled GPS data to large scale network respectively. The CSP mining and comparison algorithms significantly outperform their competitors and effectively retrieve both spatial and temporal distribution of frequent routes. The RDMP detection method can robustly discover ten classes of commonly encountered RDMP in real-world trajectory data. The proposed methods in this thesis collectively provide an effective solution for answering sophisticated queries concerning frequent and dominant movement patterns in GPS trajectory data.
|
|
| 17. |
- Zhang, Zhiguo, et al.
(författare)
-
A Meta-Graph Deep Learning Framework for Forecasting Air Pollutants in Stockholm
- 2023
-
Ingår i: 2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023. - : Institute of Electrical and Electronics Engineers Inc..
-
Konferensbidrag (refereegranskat)abstract
- Forecasting air pollution is an important activity for developing sustainable and smart cities. Generated by various sources, air pollutants distribute in the atmospheric environment due to the complex dispersion processes. The emerging sensor and data technologies have promoted the development of data-driven approaches to replace conventional physical models in urban air pollution forecasting. Nevertheless, it is still challenging to capture the intricate spatial and temporal patterns of air pollutant concentrations measured by heterogeneous sensors, especially for long-term prediction of the multi-variate time series data. This paper proposes a deep learning framework for longer-term forecast of air pollutants concentrations using air pollution sensing data, based on a conceptual framework of meta-graph deep learning. The key modules in the framework include meta-graph units and fusion layers, which are designed to learn temporal and spatial correlations respectively. A detailed case was formulated for forecasting air pollutants in Stockholm using air quality sensing data, meteorological data and so on. Experiments were conducted to evaluate the performance of the proposed modelling framework. The computational results show that it outperforms the baseline models and conventional deterministic dispersion models, demonstrating the potential of the framework to be deployed for the real air quality information systems in Stockholm.
|
|
| 18. |
- Zhang, Zhiguo, et al.
(författare)
-
Improving 3-day deterministic air pollution forecasts using machine learning algorithms
- 2024
-
Ingår i: Atmospheric Chemistry And Physics. - : Copernicus GmbH. - 1680-7316 .- 1680-7324. ; 24:2, s. 807-851
-
Tidskriftsartikel (refereegranskat)abstract
- As air pollution is regarded as the single largest environmental health risk in Europe it is important that communication to the public is up to date and accurate and provides means to avoid exposure to high air pollution levels. Long- and short-term exposure to outdoor air pollution is associated with increased risks of mortality and morbidity. Up-to-date information on present and coming days' air quality helps people avoid exposure during episodes with high levels of air pollution. Air quality forecasts can be based on deterministic dispersion modelling, but to be accurate this requires detailed information on future emissions, meteorological conditions and process-oriented dispersion modelling. In this paper, we apply different machine learning (ML) algorithms - random forest (RF), extreme gradient boosting (XGB), and long short-term memory (LSTM) - to improve 1, 2, and 3d deterministic forecasts of PM10, NOx, and O3 at different sites in Greater Stockholm, Sweden. It is shown that the deterministic forecasts can be significantly improved using the ML models but that the degree of improvement of the deterministic forecasts depends more on pollutant and site than on what ML algorithm is applied. Also, four feature importance methods, namely the mean decrease in impurity (MDI) method, permutation method, gradient-based method, and Shapley additive explanations (SHAP) method, are utilized to identify significant features that are common and robust across all models and methods for a pollutant. Deterministic forecasts of PM10 are improved by the ML models through the input of lagged measurements and Julian day partly reflecting seasonal variations not properly parameterized in the deterministic forecasts. A systematic discrepancy by the deterministic forecasts in the diurnal cycle of NOx is removed by the ML models considering lagged measurements and calendar data like hour and weekday, reflecting the influence of local traffic emissions. For O3 at the urban background site, the local photochemistry is not properly accounted for by the relatively coarse Copernicus Atmosphere Monitoring Service ensemble model (CAMS) used here for forecasting O3 but is compensated for using the ML models by taking lagged measurements into account. Through multiple repetitions of the training process, the resulting ML models achieved improvements for all sites and pollutants. For NOx at street canyon sites, mean squared error (MSE) decreased by up to 60%, and seven metrics, such as R2 and mean absolute percentage error (MAPE), exhibited consistent results. The prediction of PM10 is improved significantly at the urban background site, whereas the ML models at street sites have difficulty capturing more information. The prediction accuracy of O3 also modestly increased, with differences between metrics. Further work is needed to reduce deviations between model results and measurements for short periods with relatively high concentrations (peaks) at the street canyon sites. Such peaks can be due to a combination of non-typical emissions and unfavourable meteorological conditions, which are rather difficult to forecast. Furthermore, we show that general models trained using data from selected street sites can improve the deterministic forecasts of NOx at the station not involved in model training. For PM10 this was only possible using more complex LSTM models. An important aspect to consider when choosing ML algorithms is the computational requirements for training the models in the deployment of the system. Tree-based models (RF and XGB) require fewer computational resources and yield comparable performance in comparison to LSTM. Therefore, tree-based models are now implemented operationally in the forecasts of air pollution and health risks in Stockholm. Nevertheless, there is big potential to develop generic models using advanced ML to take into account not only local temporal variation but also spatial variation at different stations.
|
|
