With Laurent's segele end from London and Gerard Reed from Berlin. This is redefining Energy.
Today.
On Redefining Energy, we're going to talk about the weather.
Lauren, yes, job, it's September now, Simmer's gone for Lisa, Lisa in particular. As for it, I will sing a song that that's going to be at the conclusion. But first of all, from my partner.
A b Looco Energy is Europe's premier Lisa of ten foot container mobile batteries built in Europe with COTL best LFP cells. A Bloco Energy serves fourteen European countries, including France, Germany and the UK. A Bloco's batteries can be leased for any duration between six weeks and six years, and they are monitored by the Dutch award winning platform school a Bloco Energy. Make your life easier, make your business
more flexible. Back to the show, when you're going to sing the song like me, because nobody will listened to the podcast again if they hear my voice singing.
So actually, I just want to say. What we're not going to do is talk about the weather across Europe, which has been pretty crazy over the last few months.
But we're really going to talk about the importance I've been able to predict the weather for anybody that's running energy assets across the world. This is really becoming critical.
So there is this new sector called the weather forecasting service. It's a market to sizes about three billion a year and it's going extremely fast. Now. Of course, you've got sat de lights, new tech droans, new application, better granularity, use of AI, lots and lots of incredible innovation happening.
Which is why we sort of talked, listen, let's go and get an expert in. So we decided to invite Martin Fengler, who's the CEO and founder of meteo Matics, which is a Swiss based weather service company.
Yeah. Meteumatics is part of those ten ish startup which emerged in the past decade and competing, of course against the legacy public agency, but with a very different approach, very sharp. So yeah, it was a very interesting interview. One thing I need to say, it's very geeky. Surest Apron, Okay, let's listen to detail. Martin. Welcome to the show.
Thank you soon, watching me.
Great to have the weather man here. So I mean, what i'd like to do is maybe kick off by just asking just talk a little bit about the importance of the weather and the ability to predict the weather in the world of energy that were myself and RNA are living and working in every day well.
Weather Yes, of course a huge impact on the energy industry. So you have, for instance, demand forecasts that are typically related to temperature, maybe radiation and wind speed, which is
driving demand. But on the other hand, you have all these renewable energies like wind power, solar power, hydropower, and precise knowledge about the wind and the solar radiation, for instance, helps to predict the productions of those assets and ultimately helps you plan production much better with all the consequences or the different stakeholders in the energy sector.
You've been the weather forecasting business for quite some time. Can you talk about the recent technological innovation that we've seen the PUS say fifteen twenty years.
The weather industry has been actually quite old, so there have been players in the market for several decades. Especially national met services have been around for maybe on the years or even longer.
But all of.
Them have in common that they try to forecast weather. But it's a bottom line solving a really hard and challenging physical problem. So there are law of physics. Now, there are Stokes equations coup into feminodynamic equations, and it's really hard numerics that you've been in hands of National med Services. They had the budgets to purchase a supercompute power needed to run these models. But as we all know, the weather forecasts as we have them as if today
have their flaws. So if you think of forecasts low stratus or even storms, it's quite evident that there's something missing when it comes to quality, and when you have a close look to it, then you'll start to realize, Hey, models that are used typically and computations are just to cause to resolve these small scale phenomena, and often enough you don't have a clue how the weather is right now, which is for layman typically irritating because you can just
look out of the window and you see all the weather is outside. But of course the doesn't mean that the computer knows about it and knows exactly about the wind speed, wind direction and temperatures of force to do the weather forecast. And this is how matematics was born. We believe that it's time to do better and to do more high resolution weather forecasts and also to improve the initial state. And yeah, we have been working on this now for the last thirteen years by different means.
So Martin, maybe just to dig into exactly what you're doing differently than national weather agencies.
So national weather agencies are running their own models, but because it's their job from xpair is mainly to do it inside a specific country or to the country border. You rarely see them running really global models. There are only a few global models available and what we are doing is that we try to disrupt this. Next time we fly from Zurich to London, you need to recall that you're crossing maybe three different high resolution models from
three different national met services. And this is something that we do differently. So we run, for instance, a Pan European and US high resolution model, so that is all unique and the resolution is way higher than what you can get as today from the national met services. So that's one piece a larger domain, higher resolution, and you need to invest also a lot more in getting data
into your weather model that are currently not assimilated. Stimulated means that those weather information that you get from certain satellites, that you get from other measurement sources that might have also some proprietary nature, such as the meteor drones that we are working on whether whether the National met Service don't have access to and so you can improve the initial state, gets you closer to the current weather conditions and helps you also to forecast much better than the
National met Services can do.
Weather forecasting is the question of when and where. So when means how many days is the current state of the art, and compare with you a few years before? And where is how granular you can be from a geographical point of view? How do you compare?
In our services, we provide our customers for any arbitrary that long weather data from the service up to an altitude of maybe twenty five kilometers. And this is something often enough that relies on publicly available or commercially available data such as from the European Center of Medium Range Leather forecasts from the UK Met Office from and this helps us to harmonize the existing information and to provide for instance also seasonal forecasts, maybe even climate projections or
certain historical data. What Mediumatics is focusing on on top is that we run these high resolution models across Europe and yes, and for some if you other regions as well, but they are mainly focusing on the intra day day ahead and maybe three days ahead. So it's really more sort of a short term Betther model which helps us to address many applications that you come across in industry.
Can I ask you to dig into this idea resolution Because I'm managing a wind farm, all I want to know is how strong the wind is going to be all.
Over a period of time.
That is that not all that I'm interested in.
Someone who runs a wind turbine different aspects to it. So you have a rot or diameter that spands out, say fifty meters above the service to say one hundred and fifty meters, so it requires already wind information in different levels, but also temperature and air pressure that changes over time, and all of this is affecting the production of the wind speed. And it's quite obvious also the wind direction la role because of maybe shadowing or channelization
effects or sea breeze. With this example, you can already see how many aspects come into the game when it's about precisely forecasting what's happening at turbine level. And if you think of multiple turbines in the park then maybe neighboring wind turbines or affecting each other because of wake effects.
Okay, so this is this whole area of wind theft which we're beginning to hear in the offshore wind area. Right, Explain that to us and give us your view on this, because it seems to be a little bit strange. I go, well, I mean, it's your own fourth for wind turbines beside another wind turbine. Right, It's obvious if the wind comes in the west, you're going to steal it, or not steal it, you're going to change the weather pattern.
Right.
That What surprises me most is that people are surprised by it because the turbines are actually just doing what they've been designed to do, namely to collect energy out of the wind. So when you take the wind energy out of it, then now you have pretty calm winds behind on the lee of the such a wind farm. And we call these vake effects, and they can actually extend over large distances. So again layman might assume it's maybe just two hundred meters or one mile something like
this that has affected it. But depending on the weather conditions, those wake effects can effect downstream wind and weather patterns in twenty thirty forty kilometers distance. And if you think of some of the wind farms that have been already built in the North Sea, for instance, and look into the plants that say how they want your expanses to till say twenty to fifty, you will see lots of discussions and in your future around this topic. So the UK wind farms in the North Sea might be here
in favor because they're in Europe. We have often these westerly conditions and they getting the wind first. The others need to see what's left over.
So you're using somebody else satellite. So your expertise is to possess billions of data all the time and compare with the past and everything. And also you're using, and that's proprietory what you call your drones. So can you explain a bit what they are doing and what additional quality they bring to your results.
So satellites have been around and weather for maybe fifty years already, and here we are mainly typically in whether we discuss geostationary satellites. Satellites operating at an altitude of maybe thirty eight thousand kilometer distance to the airth surface and really well designed and well engineered instruments. And then you have also low earth orbiters typically operating in four
hundred kilometers distance. And again these are typically operated and owned by government entities such as humids such in Europe and in NOA in the US, and all of them haven't common that they typically use optical sensors in different spectral channels and this gives you some great pixel value. And this great pixel value that you detect can be related to some radiation input and after some calibration procedure, for instance, you can determine how a certain amount of water,
vapor or a cloud is then monitored with such an instrument. Now, the problem is these instruments is that they don't give you any direct measurements of the air temperature, the windspeed, in direction, air pressure, nothing even moisture is not directly measured. Therefore, those instruments are typically not that accurate. They give you a very strong signal and a super important for in the microather focus, so I'm not taking this into doubt.
But when it comes to very local phenomena, especially those that are triggered by air masses close to the air surface. So in the first say three or four kilometers, then these instruments are typically not that accurate, and this is why whether stations are still important. But of course also radio signs and some other remote sensing instruments or even aircraft data, they are all super relevant because they give
you direct measurement readings. And with our drones, we are actually replicating this and having a drone equipped with which logical sensors which gives us direct measurement readings.
Martin, can I ask you about the economic side of it, because what I'm trying to get my head of if I was an energy trader or as at the end of the day, what I'm trying to do is make as much money as possible for as little risk as possible. So how does it turned into economics? That's really weather prediction.
What we of course do is that we sell to energy and trading companies high resolution, high quality wind information and solar power information. Gives our customers some advantage that they can immediately leverage at the exchange. Now, coming back to the drone piece, for instance, it's not necessary that you have drones being installed on say every kilometer. It's absolutely not the case and the reason is, and this is where the secret source lies, is that you have
a four dimensional data simulation. This means that every single profile that you do now helps you also with the next model initialization that you do, even though the measurement is one hour old, but the information is advacted with the wind. It's transported with a wind. Simple example, if you do, for instance, and a profile in Zurich, and it takes about an hour on aver that this air mass is reaching sangaland that is about seventy kilometers to
the east of the ric. What it ultimately means, even if you do these soundings and a small amount of occasions, it helps you to make those sensings in many locations just because of the fact that the wind is transporting this information.
Maybe just to change topic as slide, but when I listen to you, I can hear very clearly the benefits in the energy space. But I also think that if benefits in other areas. I can imagine rescue missions, military missions. You can go through a whole pile of areas where accurate weather prediction is important.
Yeah, but that touches everything. I've been in this business now for nearly twenty years and I still learn at least once a week about the new use case. You have customers in the automotive industry such a Porsche may see this in w whatsoever. They all need weather for certain applications, save for entertainment in the car, for predictive maintenance, for autonomous driving. Just with these examples you already see how diverse weather applications can be. And this is just automotive.
Then you have maybe aviation, where we work with companies like air Bus, with Lockheed, with Tahlis and others. And again there might be about aircraft engine optimization. Again you need high altitude weather to do that. And you can continue with all of those industries and it's super fascinating how diverse weather applications is, and it goes far beyond what we typically have when we watch the BBC Weather, which shows just the UK map and then a few
items dropped on it. It's a lot more than what we typically look at.
If I look at your client least you have six on clients, and some extremely prestigious like NASA. Do you know the application they're doing or you're just giving them THATA and you don't really know what they do with those data. Is there a kind of collaboration, how does it work?
Often do you know about the application? In case of NASA, I can tell it's about supporting slide tests for some prototypes that they're looking at. And this is of course whether again it's affecting for instance, not just because of turbulence or maybe icing aircraft operations. But here, for instance,
it's about sound propagation. So you think of ultrasonic plane and aircraft, then you have this sonic boom and the boom propagation is affected by weather again and it's again it's not just wind, but it's the combination of temperature and moisture which creates sound bending sometimes sometimes not, and just just depends on the better.
How far away can you predict, because what's very very important in the energy business are mostly the dry and you know, not very windy winters versus the mild and windy winter, and that makes a lot of difference in you managed to get some long term you know, prediction when we arrive like in October, because this is really going to affect massively the all energy system for the coming months.
So for these long term predictions we rely also on other sources and MWF. The European center of a medium range of the forecasting is certainly the gold standard if it comes to forecasts into the front week, three weeks, four weeks, and maybe seasonal forecasts. We utilize the output and refine it. We're adding, for instance, downscaling techniques, combining their cost grid data with high resolution terraer data and find unit. But at the moment we as me teenetics.
We don't render the sort of long term forecasts. But of course our moonshot vision is to run a high resolution model, global one kilometer model one day, and we're making huge progress with this. We have been working on this for a couple of years now. When we start with it, people laughed at us. People told us, no one needs this, no one wants this. And now many
of our competitors stopped laughing. I believe we have delivered now on a pan European one calumeter model on the US one calummeter model, and it's just a matter of time that we are going to deploy also a global one klumeter model.
Martin, can I ask you something which is quite different, which is I'd really like to hear your opinion in and around what I call weather volatility, which is it seems that weather volatility is increasing. And listen, you've got all the data out there when you look at the weather, is our weather changing and if so, what does it mean for us?
I think because this always depends on the region and all of this, but what we definitely see in the data is that the weather becomes more pronounced, more extreme from time to time. Climate change is introducing more radiation and this leads to more higher temperatures. Higher temperatures often can often lead to an increased moisture transport, and then you often see much higher intensity when it comes to storms,
and there being some recent examples. I don't want to go that far and blame climate chain for that, but if you think of those extreme events that we just saw the other day in Texas or in Valencia, these are certainly extreme events that can be a consequence from this effect.
Martin, you are part of the coupe of startups who are competing again national weather services. How do you see the balance between the two services going forward?
We of course try to look into collaboration with National met Service wherever we can. But of course the natural question that let's call it the elephant in the room with National met Services whether the way how they operators of today is appropriate for the future. Meaning I envision that we see National met Services change over time and to become more like an authority like the Civil Aviation
Authority for instance, or like a Ministry of Defense. And this means in terms of betther that they are a rulemaking organization and still have some operative element to it, like reassuring severe weather warnings, but all the tools and services they need to render the operations will be acquired from the market, as if today it is just some sort of historical accident that you still have the agencies that are doing all the programming themselves. But frankly, there
is no reason to do so. If you can buy a fighter jet like an F thirty five through a bit process highly complex weapon systems in this case, when you can do this through a tenoring process, then frankly you can also purchase the weather model output from the market. You could also ask companies to run and operate weather station networks and just put some slas against it, and then you can actually buy all of this from the
private sector from the market. And this is maybe something we are not going to see to change in the near future, especially not in Central Europe, but I expect that we are going to see this already in other areas of the world, that these services will be purchased from the market.
Martin. When I look at the prediction, the market of weather forecasting is supposed to double the next ten years. So what technology do you have in mind and what type of result will we have in ten years that we don't have now?
What I strong believe is that all the modern AI techniques that are discussed will find their way also into weather. I'm here a bit cautious because that at the moment also a lot of noise in the market around that. But there are certainly areas where AI methods can contribute. If you think of satellite data assimulation, for instance, which has always been a huge challenge in whether or if
it comes to post processing. So for instance, if Jara is really interested in wind power output of a specific turbine civic location, then AI techniques helped to come up with even more precise focast because AI techniques can identify local phenomena that are not primetrized, not modeled, not reflected in another model. And this is where AI techniques can definitely add value.
Well, Martin was geeky but interesting. The whole point of being experts like you is just to realize that it's not because you read three articles on the internet that you become an immediate international expert. So thank you very much for sharing your expertise with us.
Thank you for having me here.
Yeah, it's good, Thank you very much, Martin.
Job. I found the conversation fascinating, and I'm glad we have this podcast so we can bring a real expert and not the Juninequgo expert like we are. Sometimes.
I'm totally with ch and I know it's a little bit nerdy and technical, but it's really really critical. And actually, do you know the funny thing is I use her app all the time now by the prediction now right, it's really good.
Okay, there was some part which I kind of knew, but learn more about wind theft which was really interesting, also about moisture and the impact of climate change on the events we have seen. Now, of course AI is going to be phenomenon, but the sentence that mark my mind is information is transported by the wind.
Yeah, very good, Okay, very good. So Lauren, I think I want to talk. Thank Martin again for coming on. The show was really great, and now I'm looking forward to you singing the song.
So this song is dedicated to Lisa. She knows she is and she said, Lauren, you know when you talk it's like nah, but when you sing, it's so beautiful. This one is for Lisa and it's about okay. So Maria's comment pass the enosun can never last wake me up when Septem burs.
My friend, Well, I've laughing because if I had a song that now, you would have just screamed laughing during the song.
No pretty good.
Hello, yeah, No, I know you are more a fan of Earth, Sween and Fire than gree Day, so you would have songs. Do you remember September? Okay? Joah?
Okay, my friend, you and speak next week, look forward to Thank you for listening to Redefining Energy. Don't forget to rate the show and subscribe on Apple, Podcast, Spotify, or the platform of your choice