You’re out of free articles.
Log in
To continue reading, log in to your account.
Create a Free Account
To unlock more free articles, please create a free account.
Sign In or Create an Account.
By continuing, you agree to the Terms of Service and acknowledge our Privacy Policy
Welcome to Heatmap
Thank you for registering with Heatmap. Climate change is one of the greatest challenges of our lives, a force reshaping our economy, our politics, and our culture. We hope to be your trusted, friendly, and insightful guide to that transformation. Please enjoy your free articles. You can check your profile here .
subscribe to get Unlimited access
Offer for a Heatmap News Unlimited Access subscription; please note that your subscription will renew automatically unless you cancel prior to renewal. Cancellation takes effect at the end of your current billing period. We will let you know in advance of any price changes. Taxes may apply. Offer terms are subject to change.
Subscribe to get unlimited Access
Hey, you are out of free articles but you are only a few clicks away from full access. Subscribe below and take advantage of our introductory offer.
subscribe to get Unlimited access
Offer for a Heatmap News Unlimited Access subscription; please note that your subscription will renew automatically unless you cancel prior to renewal. Cancellation takes effect at the end of your current billing period. We will let you know in advance of any price changes. Taxes may apply. Offer terms are subject to change.
Create Your Account
Please Enter Your Password
Forgot your password?
Please enter the email address you use for your account so we can send you a link to reset your password:

At a New York Mets game this weekend, I saw something I’m not used to seeing until late summer. No, not the inexplicable late-season implosion of a beloved local franchise — a neon-red setting sun.
West Coasters know this sun well. I call it the “Eye of Sauron” sun; others say it’s “blood-red.” In reality, the color is harder to describe, more like the red-orange-pink insides of a halved grapefruit. It feels unnatural and eerie, and is the effect of shorter wavelengths of light being filtered out of a sunrise or sunset by particles in the air caused by pollution, including wildfire smoke.
I immediately grabbed my phone to find the source of the haze, but a quick Google search of “Where is this smoke coming from?” didn’t turn up any immediate results. In fact, it can be frustratingly difficult to figure out the origin of wildfire smoke when you see or smell it. This only gets more difficult as fire season wears on; is the smoke you’re inhaling from a small nearby fire, or part of a bigger burn blowing in from somewhere else?
Unfortunately, there isn’t a handy app yet that will simply tell you “the smoke overhead is from the Canadian fires” — which, in the case of the pollution I was experiencing in Flushing Meadows, it actually was. But you can cobble together an answer about where smoke is coming from by using a few different methods.
When you climb a mountain, an inaccurate forecast can be the difference between life and death. I learned about the MyRadar app from an experienced mountaineering guide who swears it is the most accurate weather app on the market. It’s also become my go-to app for figuring out where the wildfire smoke I’m inhaling is coming from.
The app pulls data from the United States Geological Survey, InciWeb, and the United States Forest Service’s Risk Incident Information Management System to build its smoke and fire maps (it also received a wildfire detection grant from the National Oceanic and Atmospheric Administration last year). Hovering over my house at around 2 p.m. on Monday, the app clearly told me I was experiencing “moderate air quality” and “heavy smoke hazard.” Zooming out, it’s easy to guess based on the shape of the “heavy smoke hazard” cloud that the pollution is wrapping down from the massive fires burning in Alberta, Saskatchewan, and British Columbia. You can also overlay wind patterns on the app for further confirmation.

MyRadar’s visuals can get a little cluttered, though, and parsing this information still leaves you with an informed guess. But it’s one that can be easily cross-checked against the EPA’s AirNow app.
The EPA app is a little more straightforward: It gives users an upfront measurement of their air quality index, or AQI, which, with a click, can be broken down into “primary pollutants.” In the case of New York City on Monday, it was PM2.5, the expected particle from wildfire smoke (and also “the bad one” when it comes to your health). The app also shows a “forecast” of how the AQI is expected to develop over the coming hours; in New York’s case, it was going to get worse before it got better.
The AirNow app additionally has a “smoke” tab that shows a similar smoke plume overlay as MyRadar’s. By clicking on the globe in the upper left-hand corner, you can view additional fire information, including how far away the nearest burn is, and confirm if you’re under a smoke plume. Using these two pieces of information together, you can further deduce if the smoke you’re experiencing is blowing in from somewhere far away or nearby (some of New York’s smoke may be from the Cannon Ball 2 Fire to our northwest, in Passaic County, New Jersey, but the app shows me that fire is fairly small — 107 total acres — and so in this case, it is not the main culprit).

The BlueSky Canada Smoke Forecasting System (FireSmoke Canada) is run by the University of British Columbia, and while it has an emphasis on Canadian air quality, it is run in partnership with the United States Forest Service and includes U.S. data too. The FireSmoke Canada website specifically tracks PM2.5 smoke particles at ground level from wildfires across North America (“ground level” is an important distinction because sometimes smoke plumes will be too high in the atmosphere to actually affect your health). The FireSmoke Canada map throws in a time-lapse animation and for my purposes, it clearly showed that the smoke in New York was coming down from the Canadian fires.
The FireSmoke Canada map is also a great way to figure out the origin of local fire smoke too since it often shows plumes from even small blazes (though it has technical limitations too, which it details in its FAQ). Unfortunately, the service doesn’t allow users to click on a fire to learn more information about it, which means toggling back and forth between the AirNow or MyRadar app, or the FIRMS U.S./Canada website, to get a fuller picture of what is going on.

Other discrepancies between the apps can be frustrating; AirNow, for example, still shows the Great Lakes Wildfire as burning in North Carolina, though it’s not appearing on FireSmoke Canada’s tracker; MyRadar provides the most context, showing the containment at 90% and labeling its status as “minimal.” On the other hand, MyRadar and AirNow don’t show a fire near Hanford, Washington, while MySmoke Canada does.
Short of doing your own detective work with various wildfire tracking services, local media otherwise remain the best option for figuring out where smoke is coming from. The Hanford blaze that eluded MyRadar and AirNow, for example, is easily confirmed by the regional press; started by lightning, the fire reportedly burned around 1,000 acres and is now 100% contained.
Turns out, Googling “Why is it smoky outside” — while it might feel archaic — still might be one of the best options.
Log in
To continue reading, log in to your account.
Create a Free Account
To unlock more free articles, please create a free account.
Citrine Informatics has been applying machine learning to materials discovery for years. Now more advanced models are giving the tech a big boost.
When ChatGPT launched three years ago, it became abundantly clear that the power of generative artificial intelligence had the capacity to extend far beyond clever chatbots. Companies raised huge amounts of funding based on the idea that this new, more powerful AI could solve fundamental problems in science and medicine — design new proteins, discover breakthrough drugs, or invent new battery chemistries.
Citrine Informatics, however, has largely kept its head down. The startup was founded long before the AI boom, back in 2013, with the intention of using simple old machine learning to speed up the development of more advanced, sustainable materials. These days Citrine is doing the same thing, but with neural networks and transformers, the architecture that undergirds the generative AI revolution.
“The technology transition we’re going through right now is pretty massive,” Greg Mulholland, Citrine’s founder and CEO, told me. “But the core underlying goal of the company is still the same: help scientists identify the experiments that will get them to their material outcome as fast as possible.”
Rather than developing its own novel materials, Citrine operates on a software-as-a-service model, selling its platform to companies including Rolls-Royce, EMD Electronics, and chemicals giant LyondellBassell. While a SaaS product may be less glamorous than independently discovering a breakthrough compound that enables something like a room-temperature superconductor or an ultra-high-density battery, Citrine’s approach has already surfaced commercially relevant materials across a variety of sectors, while the boldest promises of generative AI for science remain distant dreams.
“You can think of it as science versus engineering,” Mulholland told me. “A lot of science is being done. Citrine is definitely the best in kind of taking it to the engineering level and coming to a product outcome rather than a scientific discovery.” Citrine has helped to develop everything from bio-based lotion ingredients to replace petrochemical-derived ones, to plastic-free detergents, to more sustainable fire-resistant home insulation, to PFAS-free food packaging, to UV-resistant paints.
On Wednesday, the company unveiled two new platform capabilities that it says will take its approach to the next level. The first is essentially an advanced LLM-powered filing system that organizes and structures unwieldy materials and chemicals datasets from across a company. The second is an AI framework informed by an extensive repository of chemistry, physics, and materials knowledge. It can ingest a company’s existing data, and, even if the overall volume is small, use it to create a list of hundreds of potential new materials optimized for factors such as sustainability, durability, weight, manufacturability, or whatever other outcomes the company is targeting.
The platform is neither purely generative nor purely predictive. Instead, Mulholland explained, companies can choose to use Citrine’s tools “in a more generative mode” if they want to explore broadly and open up the field of possible materials discoveries, or in a more “optimized” mode that stays narrowly focused on the parameters they set. “What we find is you need a healthy blend of the two,” he told me.
The novel compounds the model spits out still need to be synthesized and tested by humans. “What I tell people is, any plane made of materials designed exclusively by Citrine and never tested is not a plane I’m getting on,” Mulholland told me. The goal isn’t to achieve perfection right out of the lab, but rather to optimize the experiments companies end up having to do. “We still need to prove materials in the real world, because the real world will complicate it.”
Indeed it will. For one thing, while AI is capable of churning out millions of hypothetical materials — as a tool developed by Google DeepMind did in 2023 — materials scientists have since shown that many are just variants of known compounds, while others are unstable, unable to be synthesized, or otherwise irrelevant under real world conditions.
Such failures likely stem, in part, from another common limitation of AI models trained solely on publicly available materials and chemicals data: Academic research tends to report only successful outcomes, omitting data on what didn’t work and which compounds weren’t viable. That can lead models to be overly optimistic about the magnitude and potential of possible materials solutions and generate unrealistic “discoveries” that may have already been tested and rejected.
Because Citrine’s platform is deployed within customer organizations, it can largely sidestep this problem by tuning its model on niche, proprietary datasets. These datasets are small when compared with the vast public repositories used to train Citrine’s base model, but the granular information they contain about prior experiments — both successes and failures — has proven critical to bringing new discoveries to market.
While the holy grail for materials science may be a model trained on all the world’s relevant data — public and private, positive and negative — at this point that’s just a fantasy, one of Citrine’s investors, Mark Cupta of Prelude Ventures, told me over email. “It’s hard to get buy-in from the entire material development world to make an open-source model that pulls in data from across the field.”
Citrine’s last raise, which Prelude co-led, came at the very beginning of 2023, as the AI wave was still gathering momentum. But Mulholland said there’s no rush to raise additional capital — in fact, he expects Citrine to turn a profit in the next year or so.
That milestone would strongly validate the company’s strategy, which banks on steady revenue from its subscription-based model to compensate for the fact that it doesn’t own the intellectual property for the materials it helps develop. While Mulholland told me that many players in this space are trying to “invent new materials and patent them and try to sell them like drugs,” Citriene is able to “invent things much more quickly, in a more realistic way than the pie in the sky, hoping for a Nobel Prize [approach].”
Citrines is also careful to assure that its model accounts for real world constraints such as regulations and production bottlenecks. Say a materials company is creating an aluminum alloy for an automaker, Mulholland explained — it might be critical to stay within certain elemental bounds. If the company were to add in novel elements, the automaker would likely want to put its new compound through a rigorous testing process, which would be annoying if it’s looking to get to market as quickly as possible. Better, perhaps, to tinker around the edges of what’s well understood.
In fact, Mulholland told me it’s often these marginal improvements that initially bring customers into the fold, convincing them that this whole AI-for-materials thing is more than just hype. “The first project is almost always like, make the adhesive a little bit stickier — because that’s a good way to prove to these skeptical scientists that AI is real and here to stay,” he said. “And then they use that as justification to invest further and further back in their product development pipeline, such that their whole product portfolio can be optimized by AI.”
Overall, the company says that its new framework can speed up materials development by 80%. So while Mulholland and Citrine overall may not be going for the Nobel in Chemistry, don’t doubt for a second that they’re trying to lead a fundamental shift in the way consumer products are designed.
“I’m as bullish as I can possibly be on AI in science,” Mulholland told me. “It is the most exciting time to be a scientist since Newton. But I think that the gap between scientific discovery and realized business is much larger than a lot of AI folks think.”
Plus more insights from Heatmap’s latest event Washington, D.C.
At Heatmap’s event, “Supercharging the Grid,” two members of the House of Representatives — a California Democrat and a Colorado Republican — talked about their shared political fight to loosen implementation of the National Environmental Policy Act to accelerate energy deployment.
Representatives Gabe Evans and Scott Peters spoke with Heatmap’s Robinson Meyer at the Washington, D.C., gathering about how permitting reform is faring in Congress.
“The game in the 1970s was to stop things, but if you’re a climate activist now, the game is to build things,” said Peters, who worked as an environmental lawyer for many years. “My proposal is, get out of the way of everything and we win. Renewables win. And NEPA is a big delay.”
NEPA requires that the federal government review the environmental implications of its actions before finalizing them, permitting decisions included. The 50-year-old environmental law has already undergone several rounds of reform, including efforts under both Presidents Biden and Trump to remove redundancies and reduce the size and scope of environmental analyses conducted under the law. But bottlenecks remain — completing the highest level of review under the law still takes four-and-a-half years, on average. Just before Thanksgiving, the House Committee on Natural Resources advanced the SPEED Act, which aims to ease that congestion by creating shortcuts for environmental reviews, limiting judicial review of the final assessments, and preventing current and future presidents from arbitrarily rescinding permits, subject to certain exceptions.
Evans framed the problem in terms of keeping up with countries like China on building energy infrastructure. “I’ve seen how other parts of the world produce energy, produce other things,” said Evans. “We build things cleaner and more responsibly here than really anywhere else on the planet.”
Both representatives agreed that the SPEED Act on its own wouldn’t solve all the United States’ energy issues. Peters hinted at other permitting legislation in the works.
“We want to take that SPEED Act on the NEPA reform and marry it with specific energy reforms, including transmission,” said Peters.
Next, Neil Chatterjee, a former Commissioner of the Federal Energy Regulatory Commission, explained to Rob another regulatory change that could affect the pace of energy infrastructure buildout: a directive from the Department of Energy to FERC to come up with better ways of connecting large new sources of electricity demand — i.e. data centers — to the grid.
“This issue is all about data centers and AI, but it goes beyond data centers and AI,” said Chatterjee. “It deals with all of the pressures that we are seeing in terms of demand from the grid from cloud computing and quantum computing, streaming services, crypto and Bitcoin mining, reshoring of manufacturing, vehicle electrification, building electrification, semiconductor manufacturing.”
Chatterjee argued that navigating load growth to support AI data centers should be a bipartisan issue. He expressed hope that AI could help bridge the partisan divide.
“We have become mired in this politics of, if you’re for fossil fuels, you are of the political right. If you’re for clean energy and climate solutions, you’re the political left,” he said. “I think AI is going to be the thing that busts us out of it.”
Updating and upgrading the grid to accommodate data centers has grown more urgent in the face of drastically rising electricity demand projections.
Marsden Hanna, Google’s head of energy and dust policy, told Heatmap’s Jillian Goodman that the company is eyeing transmission technology to connect its own data centers to the grid faster.
“We looked at advanced transition technologies, high performance conductors,” said Hanna. “We see that really as just an incredibly rapid, no-brainer opportunity.”
Advanced transmission technologies, otherwise known as ATTs, could help expand the existing grid’s capacity, freeing up space for some of the load growth that economy-wide electrification and data centers would require. Building new transmission lines, however, requires permits — the central issue that panelists kept returning to throughout the event.
Devin Hartman, director of energy and environmental policy at the R Street Institute, told Jillian that investors are nervous that already-approved permits could be revoked — something the solar industry has struggled with under the Trump administration.
“Half the battle now is not just getting the permits on time and getting projects to break ground,” said Hartman. “It’s also permitting permanence.”
This event was made possible by the American Council on Renewable Energy’s Macro Grid Initiative.
On gas turbine backorders, Europe’s not-so-green deal, and Iranian cloud seeding
Current conditions: Up to 10 inches of rain in the Cascades threatens mudslides, particularly in areas where wildfires denuded the landscape of the trees whose roots once held soil in place • South Africa has issued extreme fire warnings for Northern Cape, Western Cape, and Eastern Cape • Still roiling from last week’s failed attempt at a military coup, Benin’s capital of Cotonou is in the midst of a streak of days with temperatures over 90 degrees Fahrenheit and no end in sight.

Exxon Mobil Corp. plans to cut planned spending on low-carbon projects by a third, joining much of the rest of its industry in refocusing on fossil fuels. The nation’s largest oil producer said it would increase its earnings and cash flow by $5 billion by 2030. The company projected earnings to grow by 13% each year without any increase in capital spending. But the upstream division, which includes exploration and production, is expected to bring in $14 billion in earnings growth compared to 2024. The key projects The Wall Street Journal listed in the Permian Basin, Guyana and at liquified natural gas sites would total $4 billion in earnings growth alone over the next five years. The announcement came a day before the Department of the Interior auctioned off $279 million of leases across 80 million acres of federal waters in the Gulf of Mexico.
Speaking of oil and water, early Wednesday U.S. armed forces seized an oil tanker off the coast of Venezuela in what The New York Times called “a dramatic escalation in President Trump’s pressure campaign against Nicolás Maduro.” When asked what would become of the vessel's oil, Trump said at the White House, “Well, we keep it, I guess.”
The Federal Reserve slashed its key benchmark interest rate for the third time this year. The 0.25 percentage point cut was meant to calibrate the borrowing costs to stay within a range between 3.5% and 3.75%. The 9-3 vote by the central bank’s board of governors amounted to what Wall Street calls a hawkish cut, a move to prop up a cooling labor market while signaling strong concerns about future downward adjustments that’s considered so rare CNBC previously questioned whether it could be real. But it’s good news for clean energy. As Heatmap’s Matthew Zeitlin wrote after the September rate cut, lower borrowing costs “may provide some relief to renewables developers and investors, who are especially sensitive to financing costs.” But it likely isn’t enough to wipe out the effects of Trump’s tariffs and tax credit phaseouts.
GE Vernova plans to increase its capacity to manufacture gas turbines by 20 gigawatts once assembly line expansions are completed in the middle of next year. But in a presentation to investors this week, the company said it’s already sold out of new gas turbines all the way through 2028, and has less than 10 gigawatts of equipment left to sell for 2029. It’s no wonder supersonic jet startups, as I wrote about in yesterday’s newsletter, are now eyeing a near-term windfall by getting into the gas turbine business.
Sign up to receive Heatmap AM in your inbox every morning:
The European Union will free more than 80% of the companies from environmental reporting rules under a deal struck this week. The agreement between EU institutions marks what Politico Europe called a “major legislative victory” for European Commission President Ursula von der Leyen, who has sought to make the bloc more economically self-sufficient by cutting red tape for business in her second term in office. The rollback is also a win for Trump, whose administration heavily criticized the EU’s green rules. It’s also a victory for the U.S. president’s far-right allies in Europe. The deal fractured the coalition that got the German politician reelected to the EU’s top job, forcing her center-right faction to team up with the far right to win enough votes for secure victory.
Ravaged by drought, Iran is carrying out cloud-seeding operations in a bid to increase rainfall amid what the Financial Times clocked as “the worst water crisis in six decades.” On Tuesday, Abbas Aliabadi, the energy minister, said the country had begun a fresh round of injecting crystals into clouds using planes, drones, and ground-based launchers. The country has even started developing drones specifically tailored to cloud seeding.
The effort comes just weeks after the Islamic Republic announced that it “no longer has a choice” but to move its capital city as ongoing strain on water supplies and land causes Tehran to sink by nearly one foot per year. As I wrote in this newsletter, Iranian President Masoud Pezeshkian called the situation a “catastrophe” and “a dark future.”
The end of suburban kids whiffing diesel exhaust in the back of stuffy, rumbling old yellow school buses is nigh. The battery-powered bus startup Highland Electric Fleets just raised $150 million in an equity round from Aiga Capital Partners to deploy its fleets of buses and trucks across the U.S., Axios reported. In a press release, the company said its vehicles would hit the streets by next year.