Is Your BIM Model Ready for AI?

Introduction

A significant digital transition has been witnessed in theArchitecture, Engineering, and Construction (AEC) industry over the past 15years. During this period, Building Information Modelling (BIM) has proven tobe the most crucial component contributing to this advancement. BIM, whichstarted as a basic approach for 3D digital modelling, is now deeply rooted inthe industry. By means of BIM, stakeholders and professionals can now manageand share information seamlessly, ensuring overall project efficiency. BIMadoption in today’s industry represents a major breakthrough. Figures indicatethat 72.3% of industry experts have adopted it and 15.7% are in the process ofits implementation. This fact makes it evident that BIM is no longer a choicebut a necessity to excel and help shape the industry’s future.

As time progressed, BIM received mainstream acceptance in theconstruction industry. While doing so, another technology emerged and gainedthe spotlight, known as Artificial Intelligence (AI). Upon comparison of the2020 and 2023 stats, it can be stated that there was a profound change in AIutilisation by the construction industry in its daily routine. The stats show9% and 22%, respectively, which is a notable change. By 2025, the number roseto 42.5%, with 37.7% of the industry planning its adoption in the upcomingyears. When AI surged into view, many people were uncertain whether it was anexperimental or a work automation tool. However, later on, this chaoticsituation turned into certainty, and companies started focusing on HOW and WHENto adopt it rather than WHY. This is exactly what the figures show.

88.8% of experts affiliated with the construction industry state thatAI, within the coming two to three years, will have a significant impact andchange the way they work. However, the changes will be positive, such asimprovements in productivity (88.8%), increased safety (72.6%), support forsustainability efforts (69.3%), and increased project reliability (64.5%).

Tasks such as identifying design errors,predicting equipment maintenance, and generating design options alreadyincorporate AI, ultimately making this a practical tool of utmost importance.However, what makes its output stand out is actually the data it is trained on.Well-known AI tools such as ChatGPT (86.8%), Microsoft Copilot (57.9%), andGoogle Gemini (36.8%) are trained on high-quality data. They require good datafrom BIM models to produce reliable results. If this condition is not met andAI is trained on inconsistent standards and poor BIM models, AI will fail toproduce the expected results. In short, to acquire desired outcomes, it isnecessary for organisations to understand the importance of standardised,high-quality, data-rich BIM models.

Requirements for AI

Artificial Intelligence (AI) can perform to the best of its ability ascompared to humans, whether it is processing enormous amounts of information ordetecting minor errors and omissions. However, unlike humans, AI encounterssome constraints; that is, it works on logic and rules, which, in turn,increases the importance of organised data in a BIM model for seamless analysisand interpretation. Data should be structured into the following four coreelements.

1. Consistent Parameters

AI primarily operates on patternrecognition and cross-referencing. If the parameters lack these, AI will getconfused and it becomes overwhelming to produce precise results. So it isessential to ensure that information is stored in the same way everywhere usingconsistent parameters.

For instance, if an estimatorassigns AI the task of detecting and listing all wall materials, then it isimportant that the material is stored in a consistent parameter, which could beanything. However, the case should not be like the one below:

• Wall 1: Material
• Wall 2: Wall Type
• Wall 3: Material Info

The above parameter inconsistencies could leadto data not being recorded or becoming fragmented, which ultimately results inpoor outcomes. In short, there should only be one parameter, either Material orMaterial Info. Having two creates chaos.

2. Structured Data

Structured data means every parameter isconsistent, and the values in those fields are stored in a properly mappedformat. If the data is incorrectly listed in the fields, it may lead tomisinterpretation when analysed by AI. For instance,

• Wall 1: Height: 2m, Material: Concrete, Cost: 5000
• Wall 2: Height: 2m, Material: Conc, Cost: 5000

Even though both walls have the same height,material, and cost, if the material “Conc” is not mapped or defined properly,AI may interpret them as different materials. As a result, the walls may betreated as two separate material categories, which may lead to inaccurateanalysis.

3. Unified ClassificationSystems

Just like there is a history ofclassifying humans, plants, and animals based on their traits, this worksexactly the same way. However, this classification is done using codes to helpAI detect specific elements with a standardised coding system. That is why theUnified Classification System is the most trusted one in the industry comparedto the conventional Common Arrangement of Works Sections (CAWS) with apercentage comparison of 58.9% to 14.6%, respectively. For instance, the architect callsthe main door Main Entrance Door and the engineer refers to it as ExternalSteel Door. They both are right in their own context, but it is confusingfor AI to understand. This is where code classification sorts things out byassigning the Uniclass code = Pr_30_59_24 (Door systems example).

4. Metadata

The “data about data” is calledmetadata. Such data provides access to embedded information like materialorigin, composition, and carbon emissions beyond its geometric attributes. Itis then utilised by AI to perform intricate tasks such as evaluating embodiedcarbon, assessing environmental impacts over the product lifecycle, andverifying compliance with rules such as Digital Product Passports (DPPs). Whenelements from the BIM model include sophisticated metadata such asEnvironmental Product Declarations (EPDs) and material traceability, AI caninform stakeholders about the optimal environmental choice.

Constraints for AI

“Accuracy is the issue, the majority of the AI Hype Bubble at themoment is surrounding LLMs which hallucinate and generate inaccuracy but invery credible and believable ways (until someone checks the fine detail). Thishas to be resolved first before any AI really becomes of use within theConstruction Industry where accuracy is an absolute requirement.”

~ Technical Product Specialist

1. Poor Standards

 As we already know, logic is thekey principle on which AI operates. Therefore, it is very important not tobreak that principle, which is only achievable if we use proper standards suchas BS EN ISO 19650 in BIM model creation; if it is neglected, AI willconsequently struggle.

Simply put, the fact is that ifteams ignore standard practices, mix different modelling methodologies, or donot involve an active Common Data Environment (CDE), then results would beunreliable. Ultimately, this problem will eventually fall on humans forresolution, which is not our intended approach.

2. Inconsistent Naming

If, in a BIM model, there are variations inthe naming conventions, AI will encounter conflicts while analysing the data.Humans still have familiarity with such variations. However, AI treats them astwo different things.

For instance, if a modeller names a lightingfixture “Linear Light” and another calls it “Light-01”, thiscreates a contradiction that AI cannot deal with on its own. As a result,essential tasks such as clash detection and model checking become unreliabledue to the inconsistent naming of fixtures.

3. Fragmented Information

Fragmented information means information thatis scattered into pieces. It is also one of those issues AI struggles with. Dueto the absence of complete data in one place, as a unified system, AI cannotsee a holistic picture of the task that you want it to perform, leading toinaccurate outputs, often termed as “hallucinations”. For reliable results, AIrequires everything to be on a single platform for cross-referencing and toconclude things that sound precise.

BIM Readiness Checklist for AI Integration

Before assigning a BIM model to an AI for output, ensure you reviewthe checklist below in the model to achieve the expected results:

• Standard Alignment: Is the BIM model created using aproper standard such as BS EN ISO 19650?
• Unified Classification: Is the Uniclass classificationsystem being implemented across all disciplines?
• Nomenclature Verification: Is consistent naming beingadopted across the project?
• Parameter Mapping: Are parameters correctly mappedto the fields they belong to avoid inconsistencies?
• Manufacturer-Ready Content: Are you utilising propermanufacturer-provided BIM objects enriched with correct information.
• Metadata Completeness: Does each material have completemetadata providing information about carbon emissions and environmental impact?
• Model-Specification Integration: Is the model integrated seamlesslywith the specifications written in the properties to prevent datafragmentation?
• Single Source of Truth: Is the model data and updatesbeing stored in an active Common Data Environment (CDE) or not?
• Human Supervision: Is there a technical personoverseeing the workflow and approving AI results after ensuring everything iscorrect?

‍