Rezatec’s Geospatial AI platform uses artificial intelligence (AI) analytics and satellite data to help hydro owners detect changes in their assets, including remote structures and dams whose size makes them difficult to monitor in sufficient detail at scale. The Dam Monitoring product helps operators monitor those assets, manage risk, and prioritize maintenance before failures occur. In this interview, Camilla Braithwaite, the head of product at Rezatec, tells Hydro Leader about the benefits for hydro owners and operators of having a pair of eyes in the sky.
Hydro Leader: Please tell us about your background and how you came to be in your current position with Rezatec.
Camilla Braithwaite: I’ve been working in software for over 10 years. Before I started here, I worked with Diligent Corporation and eShare, helping legal clients to deal with the burden of regulation and compliance. This involved encouraging people to use software instead of paper and getting them comfortable with security, using technology, and changing the way they worked.
I joined Rezatec in 2020. My goal is to help the company understand how to use software with data and to take advantage of its huge observation and geospatial data capabilities. I’ve been helping Rezatec to package its capabilities to make them usable for customers. The original objective was to take the things we were doing for individual customers and make them into something that was valuable for a whole industry. We did extensive market research to understand the needs of the industries we were working in. Water was one area that had significant challenges and was therefore ripe for transformation. It was slowly changing, but it was still far behind other industries.
Fast forward to 2024, where we are launching a new Geospatial AI platform with significantly enhanced functionality and a totally refreshed Dam Monitoring product. We’ve evolved the solution to support risk-informed decisionmaking, something that many regulators, including the Federal Energy Regulatory Commission (FERC), are now encouraging hydro dam owners to engage in.
Hydro Leader: Please introduce Rezatec.
Camilla Braithwaite: We’re all about putting complex geospatial insights into the hands of water leaders so that they more easily can manage risk, prioritize resources, and maximize the value of their assets. Our Dam Monitoring platform tracks unusual changes in movement, seepage, vegetation, and downstream hazards. It provides a detailed view of failure modes and their consequences.
Rezatec started life in the forestry markets, analyzing inventory and carbon outputs for some of North America’s largest forestry companies. We quickly realized that water leaders had big challenges we could solve, especially monitoring the integrity of large assets such as dams and buried pipeline networks, where the change over time in factors contributing to deformation are difficult to see and predict.
It took the best part of 10 years to develop and refine our processing methodologies, machine learning, and AI algorithms. In fact, we’re still refining them now—I think that’s a continual process for us. We combine massive sets of satellite and other geospatial data with our customers’ data when appropriate. Our customers are now at the point at which they are comfortable with the technology, trust that it’s accurate, and see the value in using new insights they’ve never before had access to.
Hydro Leader: Please tell us more about how your Geospatial AI platform works.
Camilla Braithwaite: The Rezatec Geospatial AI platform fuses a huge number of data sets with AI to produce insights and visualizations. The platform powers products that we’ve specially tailored for each industry, such as dam operators and water utility leaders.
Geospatial data include location information, attribute information, and sometimes temporal information—information on things that change over time. AI or machine learning is about taking those large data sets and using what has happened in the past to predict the future.
We get our geospatial data from various places. We feed our model with sets of data on things such as soil pH and slope. Ground motion and vegetation data also give you an indication of what’s happening below the ground. What sets Rezatec apart is that we also use satellite data. The European Space Agency satellites provide a massive archive. We access those data for our customers and derive information about their assets from them.
The Geospatial AI platform incorporates customer information. For example, hydro customers upload visual inspections, emergency action plans (EAPs), water level data, piezometer data, geodetic data, and other survey data. This gives customers a comprehensive view of their structures, helping them to make more informed assessments.
Our patented machine learning and AI algorithms have been carefully developed over years of working with some of the largest—and smallest—dam operators and regulators. AI seems to be everywhere today. At Rezatec, we’re keen to uphold our mission around accuracy and trust. That’s why we consistently ground-truth our insights and predictions and test their precision in the field with our customers.
The outputs are powerful. For dam operators, we’re picking up errors they hadn’t noticed in instrumentation data, identifying movement over time that’s too fine to detect with the naked eye, spotting the development of potential wetlands that can threaten the ability to carry out maintenance work, and highlighting the requirement to reclassify dam hazard ratings. We’re also helping many operators to demonstrate that their structures are stable so that they can prioritize investment on more pressing maintenance issues, and we’re helping others to question the extent of deformation to better align repair costs.
Hydro Leader: What sorts of data do the satellites provide?
Camilla Braithwaite: There are two pairs of satellites. One pair gathers radar data. Radar is great because it’s not visual, so it works at night and in cloudy weather. We use that information to measure ground motion. The satellites with the radar sensor orbit every 6–12 days, which means you can compare one phase wave to another to detect small amounts of movement. Looking at the information over time, you can see trends and seasonal changes that help you understand your dam’s baseline signature better so you can spot problems. When you’ve got a large structure such as a dam that’s moving in a way that you can’t see visually—or that creates just a few cracks—you can use these data sets to get a precise measure of the millimetric movement over time.
The other pair of satellites has a sensor that collects visual multispectral data, including infrared and near-infrared, which we use to monitor vegetation. Looking at that information over time allows you to see the trends and seasonal changes in the greenness of the vegetation and the moisture level in the leaves and the top layer of the soil. Anything outside of what is seasonally expected can be an indication of a dam seeping or water leaking out of a pipe.
Hydro Leader: How do hydropower dam owners and operators use your platform?
Camilla Braithwaite: The Dam Monitoring product is powered by Rezatec’s geospatial AI platform. It looks not just at the dam itself but at the area around the dam. Many customers are thinking about monitoring risk. That requires doing a potential failure mode analysis to work out how a dam is likely to fail. The current way to monitor a dam for potential failure is to send someone to the site to do an annual or biannual survey. , but that is quite expensive, and you instrument the whole dam. As a result, the information that dam operators have is often patchy, either because they can’t instrument every inch of the dam or because they survey infrequently.
The first step in monitoring assets effectively is to digitize your data and pull them all into one place. Many of the dam operators we talk to tell us that their data are spread all over the place, sometimes including in filing cabinets. When you’re trying to get an understanding of a dam, especially if you’ve just recently bought it, you’re new to the job, or your regulator is asking questions you’re struggling to answer, you want everything in one place so that you can get a broader picture.
When a customer is looking at potential failure modes, we use satellite data to provide a more in-depth understanding of what’s happening. The satellites gather information by orbiting the earth every 6–12 days, and we use that to give customers movement information on the dam to understand what has happened over the last 3 years. That information indicates potential points of weakness. We gather data much more frequently and provide more data across the whole dam so that customers can understand where they need to focus their attention. For dams that have an embankment, vegetation is a relevant factor. Looking at the variation of the greenness and moisture of an embankment over 3 years gives you an understanding of its natural response to the seasons. If you start seeing behavior that doesn’t fit that pattern, it may signal a seepage issue or some other problem. Having more data helps inform your monitoring.
Hydro Leader: How much do dams move on average? For instance, is a movement of 3 inches a normal or a drastic shift?
Camilla Braithwaite: That’s a good question. Every dam is different. They’re built differently, and they sit in the landscape differently. They’re built out of different materials. They are affected differently by the climate—for example, concrete dams are more likely to move in hot weather due to thermal expansion, and embankment dams are affected more by water levels. Some dams are in areas where there is seismic activity. So on the face of it, you can’t say if a movement of 3 inches is perfectly normal or a potential disaster.
What’s unique about our Dam Monitoring solution is that it analyzes the historical movement of your dam going back 3 years. It understands the normal behavior of your structure over time and alerts you to anomalous movement. It provides detailed analysis of the movement of your dam, visualized on a map of the asset. So, if your dam moves by 3 inches, and that movement is perfectly normal for your structure at this time of year, all is good. If not, we’ll alert you, and you can take steps to investigate and mitigate any problem.
Hydro Leader: In addition to helping your customers manage their risk and liability, can your products help them fulfill their regulatory requirements?
Camilla Braithwaite: Demonstrating that they’re doing the right thing from a regulatory point of view is important. The satellite data help our customers with their dam monitoring and risk management by connecting those tasks to potential failure modes. When they’re looking to put a dam safety surveillance and monitoring report together, we help them to easily pull all the data into the report. One of the outputs of a risk-informed decisionmaking (RIDM) approach is often a risk matrix that details each of the potential failure modes, its likelihood, and the consequences of failure. Once the data from the RIDM risk matrix are loaded into our platform, it creates a dynamic risk matrix. As things change, you can alter the dynamic risk matrix. That capability allows everyone who’s involved with the dam to see its current state of risk, how the risk has changed over time, and what actions are being taken to mitigate or reduce the risk. Having that information front and center so that everyone can see what’s happening is a powerful change that makes use of the regulatory compliance work that our customers have done.
We also help high-hazard dam owners monitor habitation areas downstream for their EAPs. Currently, most dam operators use aerial imagery to try to assess the potential loss of life and economic effects in the flood zone of a dam breach. If a dam breaches, the floodwaters will follow the lay of the land and a wave will run quickly in a lot of different directions. Depending on the volume of water and the topography, the flood zone could cover a wide area. That means that using aerial imagery to assess the effects of a potential dam breach is tricky and takes a lot of time and effort. We realized that there’s a simple geospatial solution. Our product identifies your dam inundation zone and shows you the buildings in that zone. We pull the address data for those buildings, creating a list of addresses to feed into your EAP. We update that information for you each year by pulling those data again, comparing them, and showing you where there are new buildings. Using geospatial data and software to complete that task saves a massive amount of time.
Hydro Leader: Who are your U.S. hydropower customers?
Camilla Braithwaite: We have customers all over the United States, Canada, Europe, and Australasia. They include public utilities, cities, homeowners’ associations, and regulators. We have many hydropower customers, including the City of Spokane, the Grand River Dam Authority, Oglethorpe Power, and LS Power, all of which operate high-hazard dams. They have significant regulatory requirements for monitoring their dams. It is key for them to prove that they’re going above and beyond those requirements. We also have operators whose dams are difficult to get to normally or in bad weather. For example, one of our Australian customers, Hunter Water, has an embankment dam that it can’t get to during torrential rain. The company relies on our data to get routine information about the dam. That dam is 3 miles long, which is a large area to monitor. Hunter Water uses our data to give its ground staff directions about what areas to check. If something stands out to the ground staff, they go back to the data to see what’s been happening over the past 3 years.
Hydro Leader: Please tell us about how you incorporate customer feedback into your products.
Camilla Braithwaite: That’s the part of my job I love the most: talking to customers. The latest release of our Geospatial AI platform incorporates significant enhancements for our Dam Monitoring product, all of which have been built in response to our customers’ feedback on their challenges.
One example of those challenges is adopting RIDM, which FERC is now using to improve understanding of the safety and vulnerabilities of dams. The overall risk assessment meeting that is required as part of RIDM requires an entity to collate all its available data. If all available data are put into the Rezatec platform, they will be easier to access, analyze, and assess. That is more cost effective paying a dam consultant to look at loads of spreadsheets and to sort data. There’s a lot of potential for Rezatec as regulatory requirements evolve. We can do an enormous amount to help customers fill in gaps in their data, connect data to provide new insights, and manage data more effectively. This can help customers better prioritize the use of expensive resources like instrumentation and investigation technologies.
The new platform and product release gives customers the ability to upload their own data; boost it with our geospatial insights on ground motion, seepage, and vegetation; apply our AI algorithms; compare and visualize information to assess potential failure modes; and easily provide evidence and report on risk assessment to their regulator and other stakeholders.
Hydro Leader: What is your vision for the future?
Camilla Braithwaite: Rezatec’s vision to is take dam operators into the future and give them the tools that they need to adapt to the growing risks to the safety of their assets caused by climate change, aging infrastructure, and stretched resources. Although more federal funds are now available for dam rehabilitation, there is still a massive shortfall compared to what needs to be spent to keep dams in good repair. Using intelligence, data insights, and software to help dam operators mitigate these evolving risks is what our vision is all about.
Original article from Hydro Leader Magazine can be found at https://hydroleadermagazine.com/volume-5-issue-2-march/
Chief Dam Safety Engineer, City of Spokane
“We use Rezatec’s geospatial AI to evidence non-movement on the rip rap and embankments. The data really fits to solve the puzzles and gives us solid evidence that satisfies FERC’s questions.”
Dams Safety Engineer, Hunter Water
Rezatec’s analytics are very accurate and were able to detect movements associated with historical works that had taken place, that they had no knowledge of. We are also able to see trends of movement at more frequent intervals than would be practical with traditional survey techniques, all achieved with zero risk to on-site personnel.
Take a look at geospatial AI in action. Explore how satellite data can provide a view of your entire asset base across vast areas. Discover how analytics drill down to a level of detail you never knew existed.
