Leveraging AI, Cloud Technology, and Advanced Analytics for Sewer Condition Assessment and System Management

The use of Artificial Intelligence (AI), Machine Learning (ML), and other advanced analytical tools has already made a profound impact on the ability to collect condition data on gravity sewers and verify its integrity more cost effectively with elevated quality standards than traditional processing techniques. The most prominent tool utilized to date has been Automated Defect Recognition (ADR) which has enabled attaining increased quality in programmed SCA far more efficiently than traditional methods. Recent advancements in cloud computing enable the use of ADR at scale, drastically reducing the amount of time that lapses from CCTV inspection to utilize the data for informed business decisions even when presented with large volumes of data. When coupled with defect cluster analysis tooling, configured to match defect patterns to suggested rehabilitation techniques, the process directly results in relating observed condition to their capital cost ramifications. Intelligent use of ADR has also facilitated accessing large volumes of legacy data from programmed CCTV work with no coding to uncoded inspections from routine maintenance. The collection of sewer condition data in conjunction with age, era, and other readily available exposure data also allows the development of deterioration models that provide considerable insight into the manner and rate of degradation for various cohorts throughout the system. The combination of spatial and temporal knowledge enables the use of other advanced modeling tools, such as Genetic Algorithms, Monte Carlo Simulation, and other advanced analytical techniques to provide Asset Managers with consummate answers to relate how much is spent, on what, over what time frame, and what is the resulting benefit or risk involved.