A state of the art regarding urban air quality prediction models

Croitoru, Cristiana; Năstase, Ilinca

doi:10.1051/e3sconf/20183201010

Cited by 7 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Guarnaccia et al 15 reported that predicting air quality with high accuracy can be problematic. This issue is becoming increasingly important because it is a tool capable of providing complete information for helping to prevent critical pollution episodes and reduce human exposure to these contaminants 13 , 16 , 17 . However, there is a limited number of studies in the context of Lima, Peru, which is one of the cities with the highest pollution levels in South America 18 – 20 .…”

Section: Introductionmentioning

confidence: 99%

Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima-Peru

Cordova

Portocarrero

Salas

et al. 2021

Sci Rep

View full text Add to dashboard Cite

The prediction of air pollution is of great importance in highly populated areas because it directly impacts both the management of the city’s economic activity and the health of its inhabitants. This work evaluates and predicts the Spatio-temporal behavior of air quality in Metropolitan Lima, Peru, using artificial neural networks. The conventional feedforward backpropagation known as Multilayer Perceptron (MLP) and the Recurrent Artificial Neural network known as Long Short-Term Memory networks (LSTM) were implemented for the hourly prediction of $$\hbox {PM}_{10}$$ PM 10 based on the past values of this pollutant and three meteorological variables obtained from five monitoring stations. The models were validated using two schemes: The Hold-Out and the Blocked-Nested Cross-Validation (BNCV). The simulation results show that periods of moderate $$\hbox {PM}_{10}$$ PM 10 concentration are predicted with high precision. Whereas, for periods of high contamination, the performance of both models, the MLP and LSTM, were diminished. On the other hand, the prediction performance improved slightly when the models were trained and validated with the BNCV scheme. The simulation results showed that the models obtained a good performance for the CDM, CRB, and SMP monitoring stations, characterized by a moderate to low level of contamination. However, the results show the difficulty of predicting this contaminant in those stations that present critical contamination episodes, such as ATE and HCH. In conclusion, the LSTM recurrent artificial neural networks with BNCV adapt more precisely to critical pollution episodes and have better predictability performance for this type of environmental data.

show abstract

Section: Introductionmentioning

confidence: 99%

Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima-Peru

Cordova

Portocarrero

Salas

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…For numerical simplicity and efficiency, a static Smagorinsky subgrid model is used (Deardorff, 1970). Since the atmospheric model is operated in the limit of infinite Reynolds numbers, the principal purpose of the subgrid model is to dissipate enough energy at the shortest wavelengths to obtain a physically realistic energy cascade.…”

Section: Subgrid Modelmentioning

confidence: 99%

An urban large-eddy-simulation-based dispersion model for marginal grid resolutions: CAIRDIO v1.0

2021

View full text Add to dashboard Cite

Abstract. The ability to achieve high spatial resolutions is an important feature for numerical models to accurately represent the large spatial variability of urban air pollution. On the one hand, the well-established mesoscale chemistry transport models have their obvious shortcomings due to the extensive use of physical parameterizations. On the other hand, obstacle-resolving computational fluid dynamics (CFD) models, although accurate, are still often too computationally intensive to be applied regularly for entire cities. The major reason for the inflated computational costs is the required horizontal resolution to meaningfully apply obstacle discretization, which is mostly based on boundary-fitted grids, e.g., the marker-and-cell method. In this paper, we present the new City-scale AIR dispersion model with DIffuse Obstacles (CAIRDIO v1.0), in which the diffuse interface method, simplified for non-moving obstacles, is incorporated into the governing equations for incompressible large-eddy simulations. While the diffuse interface method is widely used in two-phase modeling, this method has not been used in urban boundary-layer modeling so far. It allows us to consistently represent buildings over a wide range of spatial resolutions, including grid spacings equal to or larger than typical building sizes. This way, the gray zone between obstacle-resolving microscale simulations and mesoscale simulations can be addressed. Orographic effects can be included by using terrain-following coordinates. The dynamic core is compared against a standard quality-assured wind-tunnel dataset for dispersion-model evaluation. It is shown that the model successfully reproduces dispersion patterns within a complex city morphology across a wide range of spatial resolutions tested. As a result of the diffuse obstacle approach, the accuracy test is also passed at a horizontal grid spacing of 40 m. Although individual flow features within individual street canyons are not resolved at the coarse-grid spacing, the building effect on the dispersion of the air pollution plume is preserved at a larger scale. Therefore, a very promising application of the CAIRDIO model lies in the realization of computationally feasible yet accurate air-quality simulations for entire cities.

show abstract

“…For instance, more than 50% of people live in cities in China [7]. Technological advances in urban air quality management in the context of simulations and monitoring are also essential for smart city development [8].…”

Section: Introductionmentioning

confidence: 99%

Application of a Machine Learning Method for Prediction of Urban Neighborhood-Scale Air Pollution

Wai

2023

IJERPH

View full text Add to dashboard Cite

Urban air pollution has aroused growing attention due to its associated adverse health effects. A model which could promptly predict urban air quality with considerable accuracy is, therefore, important and will benefit the development of smart cities. However, only a computational fluid dynamics (CFD) model could better resolve the dispersion behavior within an urban canyon layer. A machine learning (ML) model using the Artificial Neural Network (ANN) approach was formulated in the current study to investigate vehicle-derived airborne particulate (PM10) dispersion within a compact high-rise-built environment. Various measured meteorological parameters and PM10 concentrations were adopted as the model inputs to train the ANN model. A building-resolved CFD model under the same environmental settings was also set up to compare its model performance with the ANN model. Our results showed that the ANN model exhibited promising performance (r = 0.82, fractional bias = 0.002) when comparing the > 1000 h PM10 measurements. When comparing the diurnal hourly measured PM10 variations in a clear-sky day, both the ANN and CFD models performed well (r > 0.8). The good performance of the CFD model relied on the knowledge of the in situ diurnal traffic profile, the adoption of suitable mobile source emission factor(s) (e.g., from MOBILE 6 and COPERT4), and the use of urban thermal and dynamical variables to capture PM10 variations in both neutral and unstable atmospheric conditions. These requirements/constraints make it impractical for daily operation. On the contrary, the ML (ANN) model adopted here is free from these constraints and is fast (less than 0.1% computational time relative to the CFD model). These results demonstrate that the ANN model is a superior option for a smart city application.

show abstract

A state of the art regarding urban air quality prediction models

Cited by 7 publications

References 37 publications

Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima-Peru

Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima-Peru

An urban large-eddy-simulation-based dispersion model for marginal grid resolutions: CAIRDIO v1.0

Application of a Machine Learning Method for Prediction of Urban Neighborhood-Scale Air Pollution

Contact Info

Product

Resources

About