A simple decision tree model was preferred over more complex regression and neural network models when predicting winter road weather conditions in Iowa.
The Iowa DOT is developing an approach to leverage the data already collected from assets and vehicles with a focus on the I-80 corridor to predict winter road conditions using artificial intelligence (AI).
Made Public Date
05/06/2019

740

Iowa
United States
TwitterLinkedInFacebook
Identifier
2019-00884

Can A.I. Take Over Winter Road Condition Reporting? (Presentation)

Background

Historical data collected from 2016 to 2018, including road condition, road-weather information stations, and automated weather observing systems are poured into an analytical environment powered by SAS software. In this environment, these data are analyzed to produce actionable information.

User acceptance testing with Iowa DOT staff was conducted in October 2018 to compare the accuracy and utility of three modeling tools used to predict road weather conditions.

Research and testing participants included:
  • 9 Maintenance field staff from around the state
  • 5 Central Office project team members
  • 2 Staff from Iowa State/CTRE

Several models were tested before the Decision Tree model was selected as the preferred approach over Regression and Neural Networks models based on the number of correctly predicted road conditions. Of approximately 242,000 road condition observations, about 237,000 were correctly classified by the decision tree model, a 97.8 percent accuracy rate. This high-accuracy model can help field maintenance staff plan more efficiently for winter road condition changes. The relative simplicity of the model compared to the other approaches was also viewed as an asset.

Lessons Learned

Data Governance is very important

  • Alongside the development of the algorithm, a user-interface was developed to communicate information produced by the algorithm. During testing, it was discovered that the data provided to SAS were incorrectly time-stamped, yielding some unexpected results in the visualizations that did not match real conditions at all. This experience illustrated the importance of carefully collecting, storing, and sharing data. Accurate data were then provided, which brought the results of both approaches in alignment.
  • Further exploration into historical data and mis-matches between the expected and actual outcomes are underway, as are efforts to improve the usability of the user interface.

Decision Tree model is best for modeling winter road condition

  • Three Model Building Methodologies were assessed: Decision Tree, Regression, and Neural Networks.
  • The decision tree is the best model based on the number of correctly predicted road conditions and that there are simpler and less variables without sacrificing accuracy.

Can A.I. Take Over Winter Road Condition Reporting? (Presentation)

Can A.I. Take Over Winter Road Condition Reporting? (Presentation)
Publication Sort Date
10/24/2018
Author
Stolle, Sinclair
Publisher
Iowa DOT

(Our website has many links to other organizations. While we offer these electronic linkages for your convenience in accessing transportation-related information, please be aware that when you exit our website, the privacy and accessibility policies stated on our website may not be the same as that on other websites.)

System Engineering Elements

Focus Areas Taxonomy: