Knowing the Likelihood of Failure
Increases the Likelihood of Success.


Fracta is a cloud-based solution employing Artificial Intelligence (AI) to assess the condition of drinking water distribution mains. The Fracta condition assessment solution calculates and visualizes the Likelihood of Failure (LOF) for every water main across your infrastructure.

The LOF score represents the mathematical probability of pipe failure. When you’re empowered with this information, decisions can be made based on accurate predictions quickly, confidently and far more efficiently.

Artificial Intelligence assesses large, complex data sets containing more variables than humans can process with current tools. Here are the different types of data we utilize:

Asset data – pipe ID, location, diameter, length, material, installation date

Historical data – break history

Geographical information – location, elevation, slope

Environmental data – soil, climate, water bodies, structures, population density, etc.

Solve complex
problems quickly.

Most water utilities have pipe, geographical data and break history. What’s more, federal, state and local organizations maintain stores of environmental data. There is no shortage of data needed to assess the condition of water main pipes.

It would be almost impossible for a human to comprehend all the possible relationships between these data. Fracta employs Artificial Intelligence models to collect, organize and make sense of it all. From there, volumes of data relating to water main pipes, their break history, geography and the environment (e.g., soils, climate) is fed into the Fracta solution identifying which pipes have the highest LOF.

The Fracta AI digital condition assessment solution delivers actionable results that can help your utility make better rehabilitation and replacement decisions in as little as 4-8 weeks.

Three step process

Determining which pipes to replace and which to save:

1. Wrangle and import utility data.

Fracta has developed a software-led approach to data cleaning and normalizing to aid in the challenge of using real-life data from city and community specific utilities that varies in its quality. Examples of varying data quality include missing pipe parameters like materials and install years, disparate data sets coming from different sources and sometimes just plain incorrect data values. The cleaned and normalized data set give an accurate picture of the current state of the asset and is the necessary foundation for the next phase of machine learning analysis. Once the water main asset data and break history has been normalized and imported, it can be easily analyzed and visualized.

2. Layer geodata and run machine learning algorithms.

Fracta uses its proprietary model to layer additional geospatial information about the environment the asset is in. The parameters include things like soil properties, proximities to transportation and many others. Using the utility data, Fracta trains and validates the machine learning algorithm. The machine learning algorithm then calculates the correlation between the parameters and historical failures and builds a model of the utility system. The output of the machine learning analysis is an accurate prediction for likelihood of water main failure for all the pipe segments of the utility.

3. Visualize vulnerabilities and apply LOF results.

Instead of building more than 52,000 different uncorrelated models, one for each drinking water utility, the Fracta algorithm considers all data from all utilities. This enables more accurate and precise predictions from the massive amounts of pipe, break history, geographical and environmental data. Armed with the LOF prediction and the consequence of failure risk, you can now focus on risk mitigation strategies. With these results, utilities and their consulting engineers can better understand which pipes are most likely to fail and decide which ones to replace to optimize capital expenditure.

Click here for a complimentary assessment of your current data set:


“Machine Learning is a field of Artificial Intelligence (AI) that allows computers to find hidden insights 'without being explicitly programmed where to look,"

– Arthur Samuel, 1959