SewerAI's Technology Featured in Inaugural Issue of Purdue University Buried Assets Management Institute-International Journal
SewerAI's Eric Sullivan co-authors an article on AI-based computer vision for sewer rehab and asset management in the inaugural issue of the Purdue University-affiliated BAMI-I Journal.
SewerAI is proud to announce that Eric Sullivan, Director of Business Development, has co-authored a peer-reviewed article published in the inaugural issue of the BAMI-I (Buried Assets Management Institute-International) Journal — a prestigious academic publication affiliated with Purdue University. The article, titled AI-Based Computer Vision Provides Innovation to Optimize Sewer Rehab and Asset Management Decision Making, was co-written with Wei Liao and appears in the 2023 H1 issue of the journal.
A Milestone Publication for the Water Infrastructure Industry
The BAMI-I Journal represents a significant new forum for advancing knowledge in buried asset management, bringing together academic research and real-world industry practice. Being featured in its very first issue is a meaningful recognition of the work SewerAI is doing to push the boundaries of what is possible in sewer inspection and infrastructure asset management.
Purdue University's involvement lends the journal strong academic credibility, and the inaugural issue sets a high bar for the intersection of engineering research and applied technology. SewerAI's inclusion in this first issue underscores the company's position at the forefront of AI-driven innovation in the water and wastewater sector.
About the Article
The article explores how AI-based computer vision — specifically SewerAI's AutoCode™ platform — is transforming the way municipalities and engineers approach sewer rehabilitation planning and asset management decision-making. At its core, the piece examines how advanced machine learning models can be applied to CCTV inspection footage to automate the detection, identification, and classification of sewer defects at scale.
Key themes covered in the article include:
- Automated defect identification and classification: How AI computer vision processes CCTV footage to detect sewer defects faster and more consistently than manual review.
- NASSCO-compliant condition assessments: How AutoCode™ generates standardized, NASSCO-compliant condition data that integrates seamlessly into existing asset management workflows.
- Smarter rehabilitation prioritization: How AI-driven insights empower engineers and municipalities to make more informed, data-backed decisions about where and when to invest in sewer repairs.
- Infrastructure sustainability: The broader implications of AI-powered asset management for extending the life of aging sewer infrastructure and supporting long-term sustainability goals.
AutoCode™: AI-Powered Sewer Inspection at Scale
SewerAI's AutoCode™ is purpose-built to address one of the most time-consuming and error-prone aspects of sewer asset management: the manual review and coding of CCTV inspection footage. By leveraging deep learning and computer vision, AutoCode™ can process hours of inspection video in a fraction of the time it would take a human reviewer — while delivering consistent, auditable, and NASSCO-compliant results.
The technology doesn't just speed up the inspection process — it fundamentally improves the quality of the data that flows into rehabilitation planning. When engineers and asset managers have access to more accurate, comprehensive condition data, they can prioritize capital investments more effectively, reduce unnecessary spending, and extend the operational life of critical infrastructure.
The Broader Impact on Asset Management
The implications of AI-based computer vision extend well beyond individual inspection projects. As municipalities face growing pressure to maintain aging sewer networks with constrained budgets, the ability to generate high-quality condition data at scale becomes a strategic asset. The article argues that AI-driven tools like AutoCode™ are not simply efficiency gains — they represent a paradigm shift in how infrastructure owners understand and manage their buried assets.
By enabling more proactive, data-driven asset management, this technology supports broader sustainability objectives — helping communities reduce the risk of sewer failures, minimize environmental impacts, and make the most of every infrastructure dollar.
Read the Full Article
The 2023 H1 issue of the BAMI-I Journal, including Eric Sullivan and Wei Liao's article on AI-based computer vision for sewer asset management, is available now. We encourage engineers, asset managers, and infrastructure professionals to explore the full publication and discover how AI is reshaping the future of buried asset management.
