Effectively Implementing Machine Learning with Office of Materials Technology [Research Summary]
Advanced Search
Select up to three search categories and corresponding keywords using the fields to the right. Refer to the Help section for more detailed instructions.

Search our Collections & Repository

For very narrow results

When looking for a specific result

Best used for discovery & interchangable words

Recommended to be used in conjunction with other fields

Dates

to

Document Data
Library
People
Clear All
Clear All

For additional assistance using the Custom Query please check out our Help Page

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.
i

Effectively Implementing Machine Learning with Office of Materials Technology [Research Summary]

Filetype[PDF-338.74 KB]


English

Details:

  • Creators:
  • Corporate Creators:
  • Subject/TRT Terms:
  • Resource Type:
  • Geographical Coverage:
  • Edition:
    Research Summary
  • Corporate Publisher:
  • Abstract:
    Machine learning models provide significant value for planning and asset management purposes by maximizing the usefulness of past data collection for decision-making and policy development. Newer and more powerful machine learning models not available in previous applications and research in highway transportation fields are investigated to address the challenging needs identified by OMT in design and construction, materials test data, management, operating optimization and field inspection. This research project is thus aimed to optimize and apply state-of-the-practice machine learning algorithms and application tools to address the emerging needs in the OMT needs for better operation and management of MD SHA assets. Specifically, machine learning models for landslide risk assessment, slope/embankment detection for geotechnical asset inventory, scarp line detection, concrete compressive strength test data modeling and prediction, pavement marking retroreflectivity data modeling and deterioration condition prediction, have been investigated in this project. There are many areas in the MDOT SHA Office of Materials Technology (OMT) that would greatly benefit from these valuable machine learning tools. Once the capability for model development is institutionalized, re-training by knowledgeable staff can enhance the models when datasets grow. Planning-level resources such as maps and estimated ranges of material properties, assist with preliminary engineering work. Phase II work is utilizing machine learning to support concrete strength predictions and geotechnical asset management efforts, including landslide risk, slope asset inventory development, and slope distress identification. As complex, structured data sets grow, accuracy will improve, along with increased reliance on machine learning analyses.
  • Format:
  • Collection(s):
  • Main Document Checksum:
  • Download URL:
  • File Type:

Supporting Files

  • No Additional Files
More +

Related Documents

You May Also Like

Checkout today's featured content at rosap.ntl.bts.gov