Skip to content
English
Contact us
  • There are no suggestions because the search field is empty.

Accelerating Carbon Assessments in ORIS open BIM Module with AI

This guide explains how AI Mapping works, how to prepare your model for optimal results, and how to validate its output to accelerate your Material Assessment workflow.

The accuracy of your carbon assessments in ORIS open BIM Module depends entirely on the quality and structure of your BIM data. The AI Mapping is designed to automate the linking of BIM elements to emission factors from the selected carbon database for construction materials, but it does not organise or categorise your model. It reads material properties and quantities exactly as they exist in the file and proposes matches to the materials existing within the selected carbon database.

AI Mapping: What It Does

Preparing BIM Data for AI Mapping

Running the AI Mapping Feature

Reviewing AI Suggestions

AI Mapping: What It Does

Once your model is uploaded into ORIS open BIM Module:

  • The AI Mapping reads the existing element properties and associated quantities, based on property-based categorisation you defined (up to two levels of grouping).
  • It also compares material descriptions, if you have added information through the selection of additional properties, to the selected carbon database of construction materials. 
  • Any conversion factors or assumptions applied during the matching process are highlighted, along with the AI’s confidence level, so you can decide whether to accept or reject the suggestions.
  • Once confirmed, the tool selects the appropriate quantity unit for each group of elements, generates material tables, and links materials to each group.

Important: AI Mapping does not infer categories or correct inconsistencies in your data. Structured categories, consistent quantities, and clear material data must be prepared before using the tool.

Preparing BIM Data for AI Mapping

AI Mapping relies on precise, descriptive material properties and consistent quantities:

  • Material Properties: Use clear, specific labels (e.g., “Concrete C40/50” rather than “Concrete”).
  • Quantities: Ensure each element exposes a usable, readable quantity (volume, mass, area, or length).
  • Consistency: Apply uniform naming conventions across similar elements that might be categorised within the same group. The richer and more structured the material data, the higher the AI confidence.

Bonus Tip:
Align your BIM material naming with the nomenclature used in the selected carbon database. Using similar terms increases the likelihood of a high-confidence match and reduces the need for manual corrections.

 

Tip: When a material specification is missing

In early design phases, material specifications are not always defined. When this is the case, apply conservative assumptions by selecting a material likely to overestimate rather than underestimate the carbon impact. This avoids underreporting emissions and can always be updated as the design develops.

To reduce this gap over time, consider building a set of typical material assumptions for common structural elements used in your projects, so your team has a consistent starting point when specifications are incomplete.

Running the AI Mapping Feature

Once your model is uploaded: 

  • Select the property sets used to group elements (maximum two levels of categorisation). These define how elements are consolidated into material rows. 
  • Choose the target carbon database (e.g. ORIS Global Database or country-specific databases).
  • Check the boxes next to the materials you wish to incorporate into your mapping.
  • Click AI Mapping.
  • Review the proposed matches before confirming.

The module will:

  • Match BIM material descriptions to entries in the selected carbon database using AI-based text comparison.
  • Consolidate quantities according to the predefined element groupings.
  • Detect unit inconsistencies and propose conversion factors where necessary (e.g. converting m³ to tonnes based on a default density assumption).
  • Generate a structured material table ready for use. 
  • Assign the matched materials from the table to the corresponding element groups (BoQ rows).
  • Provide a confidence score for each proposed match, indicating the strength of alignment between the BIM material description and the selected database entry.

Bonus Tip: To accelerate the process, users can accept materials that are close to the required ones and then modify them later in the Materials Table.

Reviewing AI Suggestions

The AI Mapping feature is an accelerator, not a replacement for technical review. Each suggested match should be validated:

  • Confirm that the correct material is selected.
  • Check unit conversions.
  • Adjust emission factors manually if project-specific data differ from database defaults in the Material section