Estimating Black Carbon Concentration from Urban Traffic Using Vision-Based Machine Learning

2025-12-06

AI Summary

Urban street-level black carbon (BC) concentration monitoring suffers from a lack of high spatiotemporal-resolution in situ data, hindering precise pollution mitigation. To address this, we propose a machine learning inversion method integrating traffic video analytics with meteorological data. For the first time, we leverage computer vision and deep learning to extract dynamic traffic features—including vehicle type, flow rate, speed, and congestion—from ubiquitous urban traffic surveillance videos. These features are coupled with meteorological variables to construct a spatiotemporally resolved, multi-source fusion model. The approach requires no additional hardware deployment, fully exploiting existing urban infrastructure. It achieves high-accuracy BC estimation at the street-segment scale (R² = 0.72, RMSE = 129.42 ng/m³). This work provides a low-cost, scalable solution for fine-grained pollution mapping, supporting environmental justice assessment and data-driven, hyperlocal municipal decision-making.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Multi-modal Vision
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Machine learning and data science for the Web
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Black carbon (BC) emissions in urban areas are primarily driven by traffic, with hotspots near major roads disproportionately affecting marginalized communities. Because BC monitoring is typically performed using costly and specialized instruments. there is little to no available data on BC from local traffic sources that could help inform policy interventions targeting local factors. By contrast, traffic monitoring systems are widely deployed in cities around the world, highlighting the imbalance between what we know about traffic conditions and what do not know about their environmental consequences. To bridge this gap, we propose a machine learning-driven system that extracts visual information from traffic video to capture vehicles behaviors and conditions. Combining these features with weather data, our model estimates BC at street level, achieving an R-squared value of 0.72 and RMSE of 129.42 ng/m3 (nanogram per cubic meter). From a sustainability perspective, this work leverages resources already supported by urban infrastructure and established modeling techniques to generate information relevant to traffic emission. Obtaining BC concentration data provides actionable insights to support pollution reduction, urban planning, public health, and environmental justice at the local municipal level.

Problem

• Estimates black carbon from urban traffic using vision-based machine learning.
• Bridges gap between traffic monitoring and environmental impact data.
• Provides actionable BC data for pollution reduction and urban planning.

Innovation

• Uses traffic video data for BC estimation
• Combines visual features with weather data
• Achieves high accuracy with R-squared 0.72