Summary of How to Predict On-road Air Pollution Based on Street View Images and Machine Learning: a Quantitative Analysis Of the Optimal Strategy, by Hui Zhong et al.
How to predict on-road air pollution based on street view images and machine learning: a quantitative analysis of the optimal strategy
by Hui Zhong, Di Chen, Pengqin Wang, Wenrui Wang, Shaojie Shen, Yonghong Liu, Meixin Zhu
First submitted to arxiv on: 19 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper presents a novel approach to predicting local air pollution using mobile monitoring data and street view images (SVIs). The authors collected data from 314 taxis that monitored four pollutants – NO, NO2, PM2.5, and PM10 – while simultaneously capturing SVIs at various angles and ranges. They developed a reliable strategy by extracting features from the SVIs and experimenting with three machine learning algorithms alongside linear land-used regression (LUR). The results show that machine learning methods outperform LUR for estimating the four pollutants, with random forest performing the best. The authors also identified four typical image quality issues and discussed their impact on estimation accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study aims to predict air pollution levels by combining mobile monitoring data with street view images (SVIs). To do this, researchers used 314 taxis that collected data while taking pictures of streets at different angles and distances. They then analyzed these images to develop a reliable method for predicting pollution levels. The results show that using special computer programs can better predict pollution levels than just using simple equations. The study also highlights the importance of considering image quality issues when analyzing SVIs. |
Keywords
» Artificial intelligence » Machine learning » Random forest » Regression
