Joaquin Ramirez describes how advanced technology and on-the-ground expertise can help utilities proactively address wildfires.
In 1994, Joaquin Ramirez took a job with a wildland fire-fighting crew in his native Spain. That year, Spain saw some of the most destructive fires in its history, and Joaquin quickly realized he just wasn’t cut out to be a wildland firefighter.
He left the crew, but he kept thinking about the outdated maps his fellow firefighters had relied on, and wondering how better sensing and mapping technologies could make fighting wildfires safer and more effective. That curiosity led him to found Technosylva in 1998 to provide firefighters with advanced fire mapping and prediction tools. In 2007, the company expanded to the U.S.
This week on With Great Power, Joaquin tells Brad how Technosylva provides wildfire risk analysis services to utilities and fire agencies, and how incorporating AI into its wildfire risk forecasting tools can help utilities make more informed decisions in managing power infrastructure.
With Great Power is a co-production of GridX and Latitude Studios.
Subscribe on Apple, Spotify, or anywhere you get podcasts. For more reporting on the companies featured in this podcast, subscribe to Latitude Media's newsletter.
Credits: Hosted by Brad Langley. Produced by Erin Hardick and Mary Catherine O’Connor. Edited by Anne Bailey. Original music and engineering by Sean Marquand. Stephen Lacey is executive editor. The Grid X production team includes Jenni Barber, Samantha McCabe, and Brad Langley.
Brad Langley: In 1994, Joaquin Ramirez was 24 years old with a newly minted master's degree in forestry living in eastern Spain. He was fighting some of the most intense wildfires the country had ever seen.
Joaquin Ramirez: 1994 was the worst fire season ever in Spain where I come from.
Brad Langley: His shifts were brutal. He'd be on 24/7 for a week, then off for a week. Rinse and repeat. And to Joaquin, it felt like the worst firefights always happened during his on weeks. He just couldn't catch a break.
Joaquin Ramirez: Every week that I was on shift, all the bad fires were happening.
Brad Langley: But it's not that Joaquin had bad timing, it's just the job wasn't a good fit.
Joaquin Ramirez: I mean, that's a really demanding job facing really complex situations with a ton of skills that were not in my back pocket. Very soon I realized that I was useless as a firefighter.
Brad Langley: So he walked away, but he didn't go far. Joaquin took a job in forestry for a few years, but he kept thinking about the firefighting crews he had worked on and wondering if he could help fight fire in a different way.
Joaquin Ramirez: I realized that all these incredible challenges in front of this incredible personnel, they had to face all of this with very, very little intel, and that's when I saw, that I could help support firefighters behind the computer with the science, with good data.
Brad Langley: His goal was to modernize wildland firefighting because he knew from firsthand experience just how antiquated it was.
Joaquin Ramirez: We were using American aerial photographs that were used in Spain to create their air bases from the Air Force in the 50s. That was the intel that we were using and I was looking at that and said, incredible. I mean, we should do something about this.
Brad Langley: So in 1998, Joaquin founded Technosylva, a company that provides wildfire risk analysis tools for utilities. While building the company, he also earned his PhD at the University of León studying remote sensing and GIS – that's geographic information systems, basically a way to analyze and map data. All of this was enhancing his foundation in forestry.
Joaquin Ramirez: In forestry, we need a lot of information to take decisions on the landscape. Typically, we have to deal with hydrology, with soils, with weather and all of that. We look at the environment in a very holistic way, understanding the interaction between the people and the nature surrounding them, and all of that was a great background
Brad Langley: To build tools that could help predict wildfires and understand their behavior. He knew he’d need to leverage satellite and GPS data, both of which were becoming more widely accessible alongside advanced computing and data analytics tools. At Technosylva, Joaquin brought all of those elements together.
Joaquin Ramirez: No one was paying too much attention to this. In the wildfire industry, people were investing in more tools to suppress fire.
Brad Langley: Now, there were scientists focused on wildfires, but marrying that science with data analysis to build tools for firefighting crews was still largely an undeveloped space. Then in 2007 at an international wildfire conference in Seville, Joaquin met Russ Johnson, who at the time was a director of public safety at GIS mapping software provider Esri. But before that, Russ had spent decades fighting wildfires with the US Forest Service.
Joaquin Ramirez: He said, you know what, Joaquin, you have to come to the US. And I said, now what? No, no, you have to come to the US. You have to bring this science into these tools, into supercomputing and just show it there because we don't have what you are showing here.
Brad Langley: So later that year, Joaquin headed to California to set up a US arm of the company. Today, Technosylva has two main offices, one in Southern California and another in León, Spain. Three years later, in 2010, Technosylva started working with San Diego Gas and Electric to improve its fire prediction tools in the wake of the massive 2007 Witch Fire.
Joaquin Ramirez: They were looking for a system called the wildfire risk reduction model, so that way they could identify those hotspots where risk reduction was most valuable or more impactful.
Brad Langley: Fast forward to today and Technosylva works in 11 countries providing utilities, regulators, and fire agencies with tools designed to predict, prevent, and mitigate wildfires. Joaquin says the scale and scope of wildland fires has changed dramatically over the past 25 years.
Joaquin Ramirez: We have an environment that is more and more in collision with human activities, with our communities. We're living in a time of extremes now. Extreme is becoming the new normal. Our landscapes can burn, our houses can burn, and it's an all hands job. Many agencies, many communities are still being reactive and we're trying to help our customers to be proactive.
Brad Langley: This is With Great Power, a show about the people building the future grid. Today, I'm Brad Langley. Some people say utilities are slow to change, that they don't innovate fast enough, and while it might not always seem like the most cutting edge industry, there are lots of really smart people working really hard to make the grid cleaner, more reliable and customer centric. Today my guest is Joaquin Ramirez, founder and chief technology officer of Technosylva. We talk about how utilities are using the company's insights to better manage and communicate risk and how firefighters are using digital tools on the front lines and how since that first project in San Diego, Technosylva has worked closely with the country's largest state wildfire agency, Cal Fire, to improve the fire modeling system that is core to its products.
Joaquin Ramirez: They have incident commanders and fire behavioral analysts that have to face these extreme fires, and we've supported more than 70,000 incidents and counting. They give us the best feedback that we can get to improve our models.
Brad Langley: I asked Joaquin to give me some details on Technosylva's dynamic risk forecast model.
Joaquin Ramirez: Basically what we're trying to understand is any potential fire that could start in any part of the landscape for the next five days. What if a fire starts at any moment of those five days? What is going to be the potential impact of the fire? That's what we care about, how big it's going to be, how many people can be impacted? So we don't know where the fire is going to start. There are areas that tell you, well, there's more probability because of the history that there are people on this road or people in this community. There are more fires. To be honest, we don't care too much. We care about that for the mitigation, but for what is going to happen in the next five days, we just model everything and we create maps about the exposure of the power lines to potential fires, about the potential fires starting from the power lines and to be honest, for any fire that is starting in the landscape, we do that by integrating all the data that is needed to understand this phenomenon.
We need to integrate extreme weather data, data about the vegetation, data about how dry the vegetation is, how strong the fire season was, how productive the vegetation has been, how tall the grass is. We need to understand how extreme the wind gusts are. I mean, there are areas in the landscape that could be, you know what, these 70 miles per hour winds in Wyoming, we don't care too much, but 70 miles per hour winds in Georgia may be very bad. So we identify those conditions in the context of how vulnerable a territory is and then we run our models. Basically in the Western US we're running about half a billion simulations every day and we're expanding to the east. So we're very close to getting to a billion simulations every day. So once the forecasts are ready, when a utility manager is ready, they have a report every morning that says, you know what? These circuits or, this district, at this time of the day, you may have potential fires that are very impactful. There are many stakeholders, so we have to deliver the information that an engineer understands, but also that a C-level executive understands.
Brad Langley: The five day advance analysis that you guys do. I assume that plays a role in the public safety power shutoffs, which have become more prominent. They started in California, but you're seeing them more across the US. Maybe for those who aren't familiar with that concept, what are they and how should they be used in your mind?
Joaquin Ramirez: Yeah, so this is obviously one of the most important and powerful tools that the utilities have to be able to prevent potential impacts to their customers. That is something that was created in California, was developed initially in SDG&E. We worked from the very beginning with them to provide metrics to try to identify the conditions that are really extraordinary and the utilities are in the business to provide energy, not to remove the energy from the customers. It really drives into a really extremely complex scenario. So it's absolutely critical that it has to be done in an extremely surgical way, and we're talking about reducing the number of hours, the size of a PSPS at a minimum. We need to understand very granularly how the event that utility, those circuits are facing, how extraordinary it is, how concerned should be … the engineers that the utility are, should be in advance to be ready to do it when it's needed and only when it's needed for the minimum time that is needed.
Being able to communicate in advance, because at the end of the day, that's one of the reasons that we need those five days. We need to be able to be ready to communicate to the public in advance. Okay, maybe something that is extraordinary is going to happen, so you have to be ready. The utilities are doing an incredible job on communication and we see really tremendous great practices of how to communicate to the public in advance and how to be surgical. So our modeling tells them, okay, this specific circuit at this time of the day, considering 30 years of data, considering what we see right now with the weather stations, we feel that this event is over a 99.5 percentile of this historical dataset. It is really extreme. So the utilities have that information and use that information to set up those preparedness readiness levels, pre-PSPS conditions, and we provide that every day in advance, five days, very granular, and they can set up the conditions. Okay, well this is the threshold for me to be concerned in pre-alert mode, in full alert mode, in full PSPS mode.
Brad Langley: Well, and I assume you guys aren't just handing over a report and saying, here you go. I mean you're probably acting like advisors and I would think in these extreme fire situations, we know people on the front lines are working more than overtime putting their lives at risk. People in utilities are losing a lot of sleep in the command center. What's happening at Technosylva during these times? Do you guys have your own kind of command center where you're watching these things super closely? You're on the phone with the utility execs. I can imagine it's a very stressful and sleep-deprived time for yourselves. I'm not trying to overdramatize this, but what is that experience like for you guys, these extreme moments?
Joaquin Ramirez: Yeah, we talk about the data. We talk about the input data, the models, the tools and all of that. At the end of the day, the most important thing is the human factor and that human factor. We need to help the utilities face this new environment. We need to be able to provide the education needed to try to understand, so this is not a black box, to give them the power to discriminate from the information that they're getting because they're the ones that know the environment. They're the ones that know their grid. They're the ones that know their partners, even the partners at the customer level, at the agency level. What we try to do then is empower them, but also we do that. We have a campus, we do training with them. We have a really in-depth intel system for them to go through this path.
We facilitate workshops and collaboration with their utilities to build that trust so they can be champions internally. That's the first step. But then we have data scenarios and since 2019, I can tell you there's been not a quiet summer and it's been a busy fire season anywhere in the world the whole time. So for that, we put together an intel team in Technosylva. We created this kind of intel services team that is comprised by probably one of the best fire behavioral analysts in the nation. We've been lucky to be able to have on our team meteorologists, advanced fire behavioral analysts. This is a position on the incident command system that typically someone that has been an incident commander, operations chief has a deep understanding in the fire science and we have people that were the incident commander of the Dixie Fire, people with more than 40 years of experience. So that subject matter expertise and that being close to them when you're facing your first PSPS or when you're facing a simultaneous event in different areas at the same time.
Brad Langley: Do you think it's safe to say that all states now realize this is not just a California problem or do you think there is some denial still within the industry that fires won't come here? Is it widely accepted that everybody needs to be acting and preparing for these kinds of situations?
Joaquin Ramirez: At the beginning, as I mentioned, I think that the Lahaina fire just started to make everybody aware. Also, who is aware is the insurance market and all the Standard & Poors and all these people that are rating the companies and they say, okay, well you need to be ready for this because all these events could be catastrophic for you. And to be honest, it's an everywhere problem. I mean right now we're working in the east, we started to work, I mentioned at the beginning with wildfire agencies we've been working in, we are the company that is providing the services to Florida Forest Service, to Texas, to Virginia, to North Carolina. All those states in the south have been dealing with fire in a little less impactful way than others, but it doesn't need to be a 100,000-acre fire to be impactful when a fire or when an event is bigger than your capabilities or your capabilities to respond, that is impactful enough to hit your organization. And we've seen that in New Jersey. We see in Minnesota, we see in South Carolina and historically, we need to understand that the largest fire in the US was the Peshtigo fire. It was in Michigan, 1871, killed 1500 people. [Editor’s note: The Peshtigo Fire was in Wisconsin and Michigan.]
Brad Langley: Get out the crystal ball. Looking ahead, what technological innovations do you see reshaping wildfire intelligence in the next decade? And as somebody who has reshaped that as part of your company, Technosylva, you probably have good perspective on this. So if you were to look ahead, what's coming to continue this transformation in wildfire prevention?
Joaquin Ramirez: So first of all is what I'm excited that we are going to have more and more access to good data. At the end of the day, anything starts with good data to understand a phenomenon. So we're part of a team that is creating a constellation of satellites. We're getting information from the people on the field with different kinds of sensors. We're trying to capture information that is more integrated and hopefully, for example, a piece of information that is very important is the information coming from the utilities to understand how the utility grid reacts to the data to understand how the landscape and the conditions impact the grid, so outages, et cetera. So we need that kind of data and hopefully there's going to be better standards so we can capture that to understand the problem. On the other side, I think the innovations that are coming are in the direction of distilling all this complexity into actionable information.
And for that, it's obvious that we are going to have quite big changes and big opportunities coming from AI, right? I'm meeting with the chief data scientist at Microsoft, Juan Lavista, AI for Good. We have crazy ideas of how we can get that technology in the hands of the people that really need to understand the complexity, how to simplify the incredible amount of data. I've been talking about data, models and all that, but when we talk with our utility partners, they need to deal also with the grid information, with the customer's information, with historical production. The amount of information that they need to manage is just incredible. And I think that we have a great opportunity with what AI is bringing us to refine the amount of information that is needed to have more informed decisions. So I think that's very exciting.
Brad Langley: How about the fire crews themselves? How has their transition to using technology gone? Do they trust the models and the AI elements of what you're providing?
Joaquin Ramirez: Yeah, you'll be amazed because people think that the guys on the field, they don't trust technology. They trust their Pulaski tool, their McLeod or the ax, right? And that is not the reality. The reality is that we're living in a time, even more now, right? We spend probably a not healthy amount of time in front of our devices. They are becoming more and more reliable in terms of providing information. For example, all the tools that we have work on disconnected environments, work on mobile devices. When a crew, when a crew goes to an incident, we have a one-page assessment of what they're facing that works without connectivity. There's connectivity probably in their office and when they go to the field, they already can work. They have all the maps of the US locally and they can plan their activities. The adoption is very quick, but they don't adopt technology. What they want is tools. They don't want shiny objects. No, you have to do your job so they can have tools that they can rely on. And that is common everywhere. The apps that we build are very, very focused for the guys on the field. If it works for them, it will work anyone else because they need things that with two clicks, give relevant information and that's it.
Brad Langley: Alright. Last question for you. If you listen to the show, it's coming. We call this show With Great Power, which is a nod to the energy industry, it's also a famous Spiderman quote, “with great power comes great responsibility.” So Joaquin, what superpower do you bring to the energy transition?
Joaquin Ramirez: I think that my great responsibility probably is trying to turn uncertainty into readiness. When I see a map of our results, I don't see lines on the map or red to green. What I see is schools, hospitals, crews, families in the path of a fire. And that perspective really drives everything that we're doing. So yeah, so with great power comes great responsibility, and for me, well that means making sure that technology just doesn't predict the risk, but helps people to reduce it.
Brad Langley: Excellent. Well Joaquin, thank you so much for coming on the show. It's an incredibly important topic and I really do appreciate your time.
Joaquin Ramirez: Thank you very much.
Brad Langley: Joaquin Ramirez is the founder and CTO of Technosylva.
With Great Power is produced by GridX in partnership with Latitude Studios. Delivering on our clean energy future is complex. GridX exists to simplify the journey. GridX is the enterprise rate platform that modern utilities rely on to usher in our clean energy future. We design and implement emerging rate structures and we increase consumer investment in clean energy all while managing the complex billing needs of a distributed grid.
Our production team includes Erin Hardick and Mary Catherine O'Connor. Anne Bailey is our senior editor, Steven Lacey is our executive editor. Sean Marquand composed the original theme song and mixed the show. The GridX production team includes Jenni Barber, Samantha McCabe, and me, Brad Langley.
If this show is providing value for you and we really hope it is, we would love it if you could help us spread the word. You can rate or review this at Apple and Spotify, or you can share a link with a friend, colleague, or the energy nerd in your life. Thanks for listening as always. I'm Brad Langley.