The picture above is about how an App helps engineers identify structural issues. Photo courtesy: Build Change
AI used to examine construction following earthquakes
An open-source project hosted by the Linux Foundation with support from IBM and Call for Code will use machine learning to help inform quality assurance for construction in emerging nations.
A new open source machine learning tool has been developed to help inform quality assurance for construction in emerging nations.
Build Change, with support from IBM as part of the Call for Code initiative, created the Intelligent Supervision Assistant for Construction (ISAC-SIMO) tool to feedback on specific construction elements such as masonry walls and reinforced concrete columns.
The aim is to help engineers identify structural issues in masonry walls or concrete columns, especially in areas affected by disasters.
Users can choose a building element check and upload a photo from the site to receive a quick assessment.
“ISAC-SIMO has amazing potential to radically improve construction quality and ensure that homes are built or strengthened to a resilient standard, especially in areas affected by earthquakes, windstorms, and climate change,” said Dr Elizabeth Hausler, founder and CEO of Build Change.
“We’ve created a foundation from which the open source community can develop and contribute different models to enable this tool to reach its full potential. The Linux Foundation, building on the support of IBM over these past three years, will help us build this community.”
The ISAC-SIMO project, hosted by the Linux Foundation, was imagined as a solution to help bridge gaps in technical knowledge that were apparent in the field. It packages important construction quality assurance checks into a mobile app.
“ISAC-SIMO has amazing potential to radically improve construction quality and ensure that homes are built or strengthened to a resilient standard, especially in areas affected by earthquakes, windstorms, and climate change”
The app ensures that workmanship issues can be more easily identified by anyone with a phone, instead of solely relying on technical staff. It does this by comparing user-uploaded images against trained models to assess whether the work done is broadly acceptable (go) or not (no go) along with a specific score.
“Due to the pandemic, the project deliverables and target audience have evolved. Rather than sharing information and workflows between separate users within the app, the app has pivoted to provide tools for each user to perform their own checks based on their role and location,” added Daniel Krook, IBM chief technology officer for the Call for Code initiative.
“This has led to a general framework that is well-suited for plugging in models from the open source community, beyond Build Change’s original use case.”
According to Build Change, the project encourages new users to contribute and to deploy the software in new environments around the world. Priorities for short term updates include improvements in user interface, contributions to the image dataset for different construction elements, and support to automatically detect if the perspective of an image is flawed.
Build Change seeks to help save lives in earthquakes and windstorms. Its mission is to prevent housing loss caused by disasters by transforming the systems that regulate, finance, build, and improve houses around the world.