Related Experiment Video
Updated: Jun 13, 2026
12:44
Watershed Planning within a Quantitative Scenario Analysis Framework
Published on: July 24, 2016
8.0K
Predicting high-resolution air quality using machine learning: Integration of large eddy simulation and urban
Shibao Wang1, Jeremy McGibbon2, Yanxu Zhang1
1School of Atmospheric Sciences, Nanjing University, Nanjing, Jiangsu, China.
Environmental Pollution (Barking, Essex : 1987)
|January 24, 2024
Summary
This study introduces a convolutional neural network (CNN) for precise urban air quality prediction, outperforming traditional methods. The CNN model accurately forecasts carbon monoxide (CO) distribution, aiding urban air management.
Area of Science:
- Environmental Science
- Atmospheric Chemistry
- Urban Planning
Background:
- Accurate urban air pollutant prediction is vital for public health and environmental management.
- Traditional machine learning models struggle with accuracy and interpretability in complex urban environments.
- Existing methods often lack the spatial resolution needed for detailed urban air quality analysis.
Purpose of the Study:
- To develop and validate a novel convolutional neural network (CNN) model for high-resolution spatial prediction of carbon monoxide (CO) concentration.
- To integrate diverse urban factors including building height, topography, and emissions into the predictive model.
- To enhance the interpretability of air quality prediction models, revealing key influencing factors.
Main Methods:
- A convolutional neural network (CNN) model was developed to predict CO concentration at 10m resolution in Nanjing.
- The CNN was trained using data simulated by the Parallelized Large-Eddy Simulation (PALM) model across 48 varied scenarios.
- Model performance was rigorously evaluated using 10-fold and out-of-sample cross-validation, alongside application to a second city.
Main Results:
- The CNN model demonstrated strong consistency and high accuracy (R² > 0.8, low RMSE) when compared to PALM simulations.
- Weight contribution maps revealed that local buildings and emissions significantly influence CO concentration, highlighting neighborhood effects.
- The model showed robust generalization capabilities, achieving high prediction accuracy when applied to a different urban area.
Conclusions:
- The integrated CNN-PALM framework significantly improves the accuracy and interpretability of urban air quality predictions.
- The model provides valuable insights into the spatial distribution of CO, influenced by urban morphology and meteorological factors.
- This approach offers effective tools for urban air quality management and policy development.
Related Concept Videos
01:29Application of Linearization and Approximation
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
01:23Linear Approximations
For a differentiable function of two variables, linear approximation estimates values near a known point by replacing the curved surface with its tangent plane. Consider the function\begin{equation*}f(x,y)=x^2+3y^2\end{equation*}near the point (2, 1). The exact value at this point is f(2, 1) = 22 + 3(1)2 = 4 + 3 = 7.The linear approximation of f(x, y)) near (a, b) is\begin{equation*}L(x,y)=f(a,b)+f_x(a,b)(x-a)+f_y(a,b)(y-b)\end{equation*}First, compute the partial derivatives: fx(x, y) = 2x and...