New research from the University of Georgia reveals that artificial intelligence can be used to find planets outside of our solar system. A recent study demonstrated that machine learning can be used to find exoplanets, information that could reshape how scientists detect and identify new planets very far from Earth.

“One of the novel things about this is analyzing environments where planets are still forming,” said Jason Terry, a doctoral student in the UGA Franklin College of Arts and Sciences department of physics and astronomy and lead author on the study. “Machine learning has rarely been applied to the type of data we’re using before, specifically looking at systems that are still actively forming planets.” 

The first exoplanet was found in 1992, and though more than 5,000 are known to exist, those have been among the easiest for scientists to find. Exoplanets at the formation stage are difficult to see for two primary reasons. They are too far away, often hundreds of light-years from Earth, and the discs where they form are thicker than the distance of the Earth to the sun. Data suggests the planets tend to be in the middle of these discs, conveying a signature of dust and gases kicked up by the planet.

The research showed that artificial intelligence can help scientists overcome these difficulties.

“This is a very exciting proof of concept,” said Cassandra Hall, assistant professor of astrophysics, principal investigator of the Exoplanet and Planet Formation Research Group, and co-author of the study. “The power here is that we used exclusively synthetic telescope data generated by computer simulations to train this AI, and then applied it to real telescope data. This has never been done before in our field, and paves the way for a deluge of discoveries as James Webb Telescope data rolls in.”

The James Webb Space Telescope, launched by NASA in 2021, has inaugurated a new level of infrared astronomy, bringing stunning new images and reams of data for scientists to analyze. It’s just the latest iteration of the agency’s quest to find exoplanets, scattered unevenly across the galaxy. The Nancy Grace Roman Observatory, a 2.4-meter survey telescope scheduled to launch in 2027 that will look for dark energy and exoplanets, will be the next major expansion in capability – and delivery of information and data – to comb through the universe for life.

The Webb telescope supplies the ability for scientists to look at exoplanetary systems in an exceptionally bright, high resolution, with the forming environments themselves a subject of great interest as they determine the resulting solar system.

“The potential for good data is exploding, so it’s a very exciting time for the field,” Terry said.

New analytical tools are essential 

Next-generation analytical tools are urgently needed to greet this high-quality data, so scientists can spend more time on theoretical interpretations rather than meticulously combing through the data and trying to find tiny little signatures. 

“In a sense, we’ve sort of just made a better person,” Terry said. “To a large extent the way we analyze this data is you have dozens, hundreds of images for a specific disc and you just look through and ask ‘is that a wiggle?’ then run a dozen simulations to see if that’s a wiggle and …  it’s easy to overlook them – they’re really tiny, and it depends on the cleaning, and so this method is one, really fast, and two, its accuracy gets planets that humans would miss.”

Terry says this is what machine learning can already accomplish – improve the human capacity to save time and money as well as efficiently guide scientific time, investments, and new proposals.

“There remains, within science and particularly astronomy in general, skepticism about machine learning and of AI, a valid criticism of it being this black box – where you have hundreds of millions of parameters and somehow you get out an answer. But we think we’ve demonstrated pretty strongly in this work that machine learning is up to the task. You can argue about interpretation. But in this case, we have very concrete results that demonstrate the power of this method.”

The research team’s work is designed to develop a concrete foundation for future applications on observational data, demonstrating the method’s effectiveness by using simulational observations.

Current climate policies including efforts like the Powering Past Coal Alliance will not add up to a global coal exit, a new study shows. Countries phasing coal out of the electricity sector need to broaden their policy strategy, or else they risk pushing the excess coal supply into other industries at home, like steel production. The scientists find that China has an opportunity to dominate the renewable energy technology market if it begins phasing down coal immediately. Otherwise, it could dangerously delay the renewable energy breakthrough worldwide.

“It’s really a make-or-break moment,” says Stephen Bi from the Potsdam Institute for Climate Impact Research (PIK) and Potsdam University in Potsdam, Germany, lead author of the study. “Our computer simulation of climate economics and policy making indicates that current policies lead the world to less than a 5 percent likelihood of phasing out coal by mid-century. This would leave minimal chances of reaching net-zero emissions by 2050 and limiting disastrous climate risks.”

“The most shocking result was that even though most countries decide to stop burning coal for electricity during the simulation, this has almost zero impact on total future coal use,” says Bi. “We then dug deeper into this perplexing result to identify what policymakers can do to actually achieve the coal exit.

Carbon pricing and coal mining phase-out would be effective policies

Investigating the Powering Past Coal Alliance, launched at the world climate summit COP23 in 2017, the scientists sought to understand whether these countries’ efforts to cut coal would make it easier or harder for other countries to follow suit. That is, the coalition may grow as member states work to modernize their electricity sectors, but it may also lead to a rebound in coal use globally. The latter effect often referred to as ‘leakage’, can arise due to market effects: if demand decreases in some places, so do prices, which in turn can increase demand elsewhere.

Interestingly, the scientists’ supercomputer simulation shows that the most concerning leakage effect, in this case, may actually arise within the Alliance itself rather than through international coal markets.  Although the Powering Past Coal Alliance is expected to grow, its pledge is limited to the electricity sector. This means that countries who join can actually increase their coal use in steel, cement, and chemicals production, greatly hindering the potential of this initiative.

“The greatest risk to the coal exit movement may actually come from free-riding sectors in coalition members. Unregulated industries can take advantage of falling coal prices at home and use more coal than they otherwise would have,” says co-author Nico Bauer, also from PIK.

The scientists conclude that additional strong policies are needed to avoid this effect. “The coal exit debate has to look beyond the power sector and also include the heavy industry. Carbon pricing would be the most efficient instrument to close loopholes in domestic regulations, while restrictions on coal mining and exports would go the furthest to deter free-riding abroad,” continues Bauer.

“A golden opportunity for China” – if it acts quickly

“China plays a special role since it produces and consumes more than half of all coal globally. The Chinese government must act swiftly to curtail the coal-driven Covid recovery,” says Bi. “The current coal plans jeopardize China’s recent promise to peak domestic emissions before 2030 and to achieve net-zero emissions by 2060. The computer simulation gives China roughly fifty-fifty odds of joining the Alliance, and it only falls on the right side of that line if it stops building coal plants by 2025.”

Further, the simulation shows that the Alliance only manages to boost solar and wind energy expansion if China decides to phase out coal. China would thus have “a golden opportunity to solidify its leading role in the renewable energy market and unleash sustainable development opportunities worldwide, but this requires a commitment to phasing out coal,” explains Bi. “If not, then it becomes less clear how we’ll achieve sufficient diffusion of renewables worldwide. China’s actions today can position it to either lead or impede the global energy transition.”

Innovative first real-world policy-making supercomputer simulation

These insights are substantially more robust than most previous analyses because the scientists used a data-driven approach for simulating real-world policy making, called Dynamic Policy Evaluation, for the first time. “Scientifically analyzing future emissions is subject to a large degree of uncertainties, not least policies. We were able to determine that coal-exit commitments often depend on certain domestic pre-conditions, which enabled us to remove some of the uncertainty on their emission impacts. Our new approach is thus the first to coherently simulate policy adoption in future scenarios which are also in line with historical evidence,” says co-author Jessica Jewell from the Chalmers University of Technology.

“The G20 has initiated the phase-out of international public finance for coal projects. We are now assessing how much political momentum this can potentially impart on the Powering Past Coal Alliance,” says PIK Director Ottmar Edenhofer. “Things are therefore looking somewhat more promising, but we must account for negative feedback alongside the positive for a balanced assessment of policy diffusion in our multipolar world. What remains clear is that governments must take a much much more active approach to phase out coal if they want to stay true to their climate promises.”