Article complete

Using Satellite Imagery and GPS Data, AI Can Now Predict Accident Hotspots

The system makes bold predictions about which portions of a road network are likely to become accident hotspots, even when such locations have a zero-event history.

Using Satellite Imagery and GPS Data, AI Can Now Predict Accident Hotspots

Key takeaways

  • MIT's CSAIL and Qatar Center for AI have developed a system predicting traffic collisions before they occur.
  • The machine learning model generates detailed accident risk maps using historical data, satellite imagery, and GPS traces.
  • The system can identify potential accident hotspots, even in areas with no prior incidents reported.
  • Challenges include sparse data, making it difficult to detect subtle correlations without machine analytics.
  • Traditional prediction methods are limited, necessitating the new approach that examines similar road segments for risk assessment.

Takeaways drafted with AI from the article text.

MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Qatar Center for Artificial Intelligence researchers have built a machine learning system that predicts traffic collisions before they occur. The system makes bold predictions about which portions of a road network are likely to become accident hotspots, even when such locations have a zero-event history. The researchers created a deep learning model that forecasts extremely detailed accident risk maps. The risk maps, which are created using a combination of historical crash data, road maps, satellite imagery, and GPS traces, represent the projected number of crashes during a specified time period in the future, allowing for the identification of high-risk locations and the prediction of future crashes. 

Challenges with Sparse Data

The researchers' challenge is sparse data - while extremely high quantities of incidents would definitely be detected and addressed without the use of machine analytics, more subtle but potentially dangerous correlations are harder to spot. Existing accident prediction methods have relied on Monte Carlo estimation of historic accident data and are therefore incapable of providing an efficient prediction mechanism in the absence of this data. As a result, the new research examines road network segments with comparable traffic patterns, visual appearance, and structure, inferring an accident proclivity based on these features.

Contributing author Amin Sadeghi  stated that "By incorporating several clues from seemingly disparate data sources, our model can generalise from one place to another. This is a significant step toward general AI, as our model can forecast crash maps in previously undiscovered territory. The proposed model can infer a meaningful crash map in the absence of historical accident data, which could result in beneficial use for city planning and governance through comparison of hypothetical situations."

How is generalisation achieved?

Source: Architecture of the traffic prediction system

Model Validation

The model was validated using data from almost 7,500 kilometres of urban areas in Boston, Los Angeles, Chicago, and New York City. Additionally, the research makes use of 4.2 million records from the US Accidents dataset. Each record contains a timestamp and additional details. The first two years of historical data were fed into the model, while the latter two years were used for training and evaluation, allowing the researchers to quickly establish the system's accuracy over a two-year period.

The system was evaluated both with and without historical data and was found to accurately reflect the underlying risk distribution in all situations, significantly outperforming previous Kernel Density Estimation (KDE)-based techniques. Indeed, KDE has been used to show historical hotspots for traffic accidents but has been unable to forecast future accident locations.

Conclusion

The authors state that their approach may be deployed to other countries with minimal architectural adjustment, even in areas without accident data. Additionally, the authors suggest that their findings might be used to supplement urban planning design for new urban developments. According to lead scientist Songtao He, the research may be integrated into mainstream consumer GPS-based traffic tools and route planners.

Dataset 

Satellite imagery from MapBox. 

For further information, refer to the article.

Published

Spotted an error? Tell our editors. Read our editorial standards and corrections.

More in this story

AI (Artificial Intelligence) · 5 stories
  1. You are here: Using Satellite Imagery and GPS Data, AI Can Now Predict Accident Hotspots
  2. Relax, Automation ≠ Job Loss
  3. OpenAI Needs 158 Minds for Superintelligence
  4. AI Exposes the Flaws You’ve Been Ignoring. A Wake Up Call for Architects!
  5. AI’s Insatiable Appetite is Outpacing Data Centres, and Testing India's Momentum
About the author

Contributor

All stories
Belamy · Daily

The day’s AI news, before your first meeting.