The prospect of geoengineering is the only thing which gives me some hope for the future.
Nearest real world success is continuous low volume maritime dispersal which has completely different dispersal dynamics than high-altitude bursts, and the continuous low volume maritime dispersal is non-viable
No way to undo it once done
If humans can’t perpetually release aerosols — and I mean perpetually, for the next millions of years — then the global climate “snaps back” violently within weeks and almost certainly eradicates all known life in the entire universe.
https://www.carbonbrief.org/solar-geoengineering-risk-termin...
Of course there are going to be unknown side-effects, and suddenly stopping it would be bad. But it might still be better than doing nothing at all. It's a shitty band-aid fix, but I would still take it over "hothouse earth" type scenarios.
That said, your comment stands out to me to be self-contradictory and unscientific (by way of being alarmist and not backing up an extraordinary claim ).
> Unknown second order effects
This sounds right.
> Nearest real world success is continuous low volume maritime dispersal which has completely different dispersal dynamics than high-altitude bursts, and the continuous low volume maritime dispersal is non-viable
Since I don't know a lot about this topic I'll take your word for it.
> No way to undo it once done
This doesn't sound quite right, my intuition says more likely "no known way to undo it once done".
> If humans can’t perpetually release aerosols — and I mean perpetually, for the next millions of years — then the global climate “snaps back” violently within weeks
Wait... So, to undo it all we have to do is stop doing it? Doesn't this contradict the statement right before it?
> almost certainly eradicates all known life in the entire universe
This statement makes me suspicious of the credibility of the rest. This is an extraordinary claim and I think deserves way more explanation if you want to convince anyone who doesn't already agree with you. It would be a lot easier to accept "decimates human civilization" than "eradicate all life on earth". Life is extremely resilient.
How exactly would it eradicate all life on earth?
The stuff about aerosols: The "plan" isn't that you dump a one time "treatment" of aerosols and then climate is reset. It's a continuous aerosol injection advitam aeternam to offset the warming - constant upkeep.
About comments on destruction of all life: the biosphere is so conplex it's hard to even grasp the gist of it. Global temp affects every level of it. Were this "treatment" be a little too strong/maladjusted, it could very well cause runaway mass death.
And we only have proof of life on earth - if we kill life on it, as far as we know, it's over for life itself. Can't be careful enough, and aerosol dispersal isn't that.
The effect that has on the climate depends on how much CO2 is in the atmosphere at the time.
If during the time we were doing the aerosol program we've also continued increasing CO2, using increasing aerosol releases to prevent that from causing warming, then when we stop with the aerosol we get that deferred warming over a few years or less.
We end up at the roughly the same place we would have been if we had not done the aerosols at all, except instead of getting from where we are now to them over several decades we get their over a few years.
Let's say that is 3℃ above current average temperature. A 3℃ rise over 2 years is a lot harder to handle than a 3℃ rise over 30 years.
Worse, if we started aerosols a lot of countries might decide that it is OK to keep increasing emission rates, so if we ever stop the aerosols were are looking at a rise to much higher than we would have had if we had not used aerosols.
Regarding the “no way to undo” and the “violent snap back”, we know the desire albedo effects dissipate and therefore require continuous maintenance.
However, these aerosols also cause hard-to-reverse reactions to other things like damaging the ozone layer and causing rain pattern shifts.
Yeah, most climate catastrophe scenarios are of the severity you describe. This one is not.
The entire point of SAI is to “save up” damage to the environment. So over 100 years of SAI and then stopping, you will incur 100 years of atmospheric and temperature changes within a few months.
And that’s only over a hundred years. If we depend on this and do it for a thousand years, now it’s a thousand years of damage applied in months.
This is far, far, far faster than any biological system evolves. Sure maybe some microbes that can survive in a gigantic range of environments could survive, but no, probably no complex life forms would.
My understanding is that the whole purpose of HN is to discuss interesting topics with intellectual curiosity. "Go do some reading" type statements aren't really conducive. What would be more appropriate is recommending specific sources, or just taking a moment to elaborate since the whole point is discussion.
I appreciate your elaborations in this last comment. I don't appreciate the dismissive tone of your first line or your earlier comment.
> Regarding the “no way to undo” and the “violent snap back”, we know the desire albedo effects dissipate and therefore require continuous maintenance.
> However, these aerosols also cause hard-to-reverse reactions to other things like damaging the ozone layer and causing rain pattern shifts.
This makes sense. I guess where the logic breaks down for me is the conflation between the time it would take us to recognize the second order effects and stop the process, the amount of violent snap back that would occur, and the time to reverse the second order effects.
To be clear, I understand the risk you are pointing at and it is a significant risk, it still seems like you are exaggerating it.
It's either we do this for thousands of years (in which case the second order effects must be minor to make it sustainable for that long), or we do it for a short time because second order effects aren't sustainable.
It's the logical relationship between the reversibility, second order effects, and magnitude of snap back risks that isn't adding up for me.
All this said, as I've engaged in this topic and thought more about it, my current stance is that we shouldn't be introducing new things into the climate to address the consequences of other changes we have made. A safer approach seems like economically sustainable ways to undo the root-cause damage we have done. (E.g. CO2 capture sounds better than novel aerosol injection).
So I think we probably agree in principle, I just still find the comment I responded to originally alarmist and not very convincing.
Just like building petrochemical-dependent societies!
Err, actually, there’s a third option: we put ourselves into a pickle.
Pretty much no hard problem would exist if the dynamic you’re describing were necessarily valid in general, and you’ve done nothing to demonstrate it’s valid in this particular case.
It is absolutely possible for the side effects to be hard to detect, widespread, hard to mitigate once detected, and for us nevertheless to be otherwise dependent upon continuing to produce those effects. See: fossil fuels.
But fossil fuels do not have the same snapback risk. This actually does.
Oh I completely agree that it's possible, but there are some very material differences between those examples.
The purpose of fossil fuels is increasing access to energy and The downside is climate change. The purpose of the aerosol injection would be climate management and the downside would be unintended climate change. If it's not working as intended we are far more likely to stop doing it because of the direct relationship between the purpose and the issues.
Also, we got hooked on fossil fuels before we had the science to understand the long term consequences to the climate.
So to summarize there are at least two very material differences:
- fossil fuels were essential to reducing energy costs whereas I don't see a direct economic benefit to aerosol injection, just the purpose of managing climate damage. Am I missing something?
- our scientific understanding at the beginning of adoption will be materially different and we are a lot more likely to detect issues earlier on. Not certainly, but materially more likely.
To me the combination of these two things makes it a fundamentally different dynamic.
I am sure it sounds like I'm advocating for aerosol injection, but I'm actually just playing devil's advocate and trying to strengthen my understanding by pointing out the holes I'm seeing in your explanations.
If there's ever a specific source that you think would help fill a gap in my understanding I am receptive to checking it out.
Eradicating all life is not unscientific, you might be better at throwing real arguments of why you don't like this idea instead of boasting.
It's not quite that simple.
The intuition that you're subtly relying on is the idea that the response or effect of one of these geoengineering treatments is linear. But unfortunately, that's not something you can assume about a dynamical system. In reality, the climate system can undergo certain types of hysteresis where "undoing" the forcing doesn't revert the initial perturbation, because you're suddenly on a different response curve. Probably the most famous example of this in climate dynamics is the way that the ice-albedo effect sets up a hysteresis in the trajectory towards a "snowball Earth" scenario. Apologies for the lack of links/references; Wiki has decent write-ups on this, and it's typically covered in the first chapter of a climate dynamics textbook.
The potential response to suddenly stopping a climate change mitigation strategy has a very well-popularized name: a "termination shock." In fact, Neal Stephenson used exactly this concept in his titular novel on the topic in 2021.
As a climate scientist, my mental model to better understand the risk of termination shocks and unintended consequences boils down to how fast the response of the climate system is. Marine brightening is "less risky" because the meteorological response to these interventions is extremely fast; a cloud-precipitation system will respond on the order of minutes to hours, and unless the intervention continues unabated, it will clean the air quickly, limiting the repsonse. Stratospheric aerosol injection is more complicated, but we have a very good analogue - very large scale volcanic eruptions like Mt Pinatubo. The response to these sorts of events is measured more on the timescale of 2-5 years, although knock-on effects (such as a shift towards more diffuse solar radiation reaching the surface, which has significant effects on terrestrial and oceanic biogeochemistry) could very much persist longer than that - and don't "snap back" nearly as quickly. A continuous, Pinatubo-like intervention would compound and introduce coupled atmosphere/ocean responses that could decade years or longer to fully play out. And that's _in addition_ to the near immediate (1-2 year) response in global average temperature, which would bounce back to most of the pre-intervention level very quickly.
These things are complex. There's a lot we don't know. But, there's also a lot we _do_ know. I would encourage anyone who does not have significant experience in climate dynamics to remain curious and avoid jumping to conclusions based on simple intuition; they're probably wrong.
Given your expertise in this, I'm curious what your take is on CO2 capture, not in terms of economic viability, but in terms of climate risk...
For example, if we were to discover a process that removed CO2 from atmosphere and converted it into a product profitably such that there was an economic incentive/positive feedback loop to remove CO2.
My intuition is that if we removed the CO2 too quickly or too much of it we may have unwanted consequences, but if the rate was managed and we slowed down and stopped at a certain equilibrium, would this be a theoretically ideal way to address the problem?
First, what is "too quickly" with reference to CO2 removal from the atmosphere? At present, human civilization emits over 40 gigatons - or 40 trillion kilograms - of CO2 per year. And that increases the atmospheric burden by about 2.5 parts per million per year. So today, before you even start _reducing_ atmospheric CO2, you need to be sucking down at least 40 trillion kilograms of CO2. I struggle to imagine a scenario outside of total science fiction where that would be remotely possible.
Second, the equilibrium climate response to changes in greenhouse gas forcing take on the order of decades or centuries to realize. This is because the dynamics of the climate system are heavily buffered. For example, the ocean acts as a giant heat capacitor that slowly interchanges with the atmosphere. Were you to instantaneously halve the CO2 in the atmosphere, you'd likely see a pretty classic exponential decay in global average temperature (and other more nuanced responses); in the present climate, it's not clear we have already passed specific "tipping points" that would induce that hysteresis I described in the previous comment (in fact - one could read "climate tipping point" as a synonym for dynamical system hysteresis). Theoretically, one could try to "dial in" some particular equilibrium climate state, but it's not obvious over what timescale you'd have to intervene and what the cost of such an intervention would be.
The cool thing is none of this needs to be purely "theoretical." You could simulate all of this _today_ if you had a setup to run a global climate model. A "4X CO2" experiment where you branch from an equilibrium spin-up climate state and immediately apply a global quadrupling of CO2 has been a completely standard experiment as part of CMIP for over two decades. The opposite experiment is an established protocol for both the Carbon Dioxide Removal Intercomparison Project [1], which features an annual ramp down of CO2 at a 1% per year rate, and the Cloud Feedback Model Intercomparison Project [2], which features a more direct counterpart, with an abrupt decrease of atmospheric CO2 by 50%. There is a large body of literature discussing the results of these classes of experiments, but this is outside of my primary research focus and I can't turn you to particularly good papers off-hand. But they're easy enough to find.
[1]: https://www.geomar.de/en/cdrmip [2]: https://www.cfmip.org/experiments/cfmip3cmip6
And ecosystem is complex enough that we can't really predict those side-effects before they happen and they can make other things worse.
Just spraying random stuff that happens to work on paper is equivalent in subtlety to electroshocking patient to fix their mental issues.
That is not to say it is not possible, but on top of being expensive it would require a lot of care to not make stuff get worse in other ways.
You can go look up the differences in dissipation dynamics between that and what’s being proposed by the BS in Econ student and his growth marketing cofounder.
Sure - there is definitely some gap between these natural processes and the artificial processes being proposed, but it is a narrow enough gap that it does preclude a fair number of second-order effects, compared to almost all geoengineering ideas that do not have such natural experiment equivalents.
What exactly does the science say that makes it definitively a bad policy choice, regardless of the fact that policy requires the consideration of political and economic feasibility?
And again, my question is: does the science show that this is objectively bad, regardless of bog standard policy considerations? For example, comparison with the status quo?
No, the science doesn’t show it is “objectively bad,” which is why I didn’t claim it was. I said it is not an idea endorsed by many climate scientists (which it’s not), and that’s mostly because of the numerous unknowns involved with perturbing a highly complex system, the expected irreversibility of many of its effects, and the path dependence of making us perpetually dependent upon dumping aerosols lest we risk a global climate snapback effect.
This is a summary of the current posture of the climate science community towards this idea, which is not “it is objectively bad,” nor is it something I can spend my time linking you to a singular paper on.
That is why my suggestion, from the very very top, was to get curious about why so few climate scientists support this idea for climate intervention.
Any good faith curious person should pretty immediately ask themselves this question to begin with.
It does not mean we need to listen to said scientists in and have them exclusively dictate policy, but if “climate community doesn’t like climate solution” doesn’t set off enough alarm bells for YOU to go open up Google Scholar, then you are not earnestly interested in the problem and your “just asking questions” approach here is actually just profound laziness.
Here is an article by a climate scientist at Cornell and the head of a climate nonprofit, which is positive towards carefully scaled piloting of solar radiation management:
https://worksinprogress.co/issue/sunscreen-for-the-planet/
I am curious if you can cite an article that is responsive to the specific plans articulated here, especially the plans to help ensure safety by scaling slowly and gathering lots of data. Which is a normal practice in all reasonable policy rollouts.
The comment I replied to said, however, "this pretty much proves we can somewhat slow down climate change by spraying certain chemicals into the air".
No, it doesn't![†] In fact, your article mentions how much we don't know and how many risks there are. I.e. it is not proven. There are still unanswered questions of literally existential magnitude. That's why the consensus view toward this amongst people who think about our options on climate all day long do not see this as a great option, never mind a proven one.
Anyway, as for your article, merely breaking an experiment into 3 phases does not make it like a clinical trial. This experiment has nowhere near the controls nor the limited blast radius of even the riskiest clinical trial being conducted today. So that's my commentary on that. Seems naive and/or dishonest to compare it to a clinical trial.
† Technically of course it's possible to lower the temperature of the earth via aerosols. But this article/observation didn't "prove it," it's not new information, and it doesn't address the main reasons not to do this otherwise obvious idea. Which again is why the scientific consensus is not currently behind it
Yes.
We should listen to people who use evidence and reason to suggest the best course of action. We should listen to people who have spent decades of their lives studying this issue for relatively little reward other than trying to make the world better.
We should NOT listen to semi-literate goobers who gained authority by being popular with simpletons they manipulated into voting for them, mostly through graft and trickery. Those people's opinions should be regarded as being equivalent in value to the opinion of your weird conspiracist uncle who helped vote them into power.
I don't know. Is such a black and white group based worldview plausible? It's possible I guess, but I find it hard to believe?
I wouldn't argue that all scientists are selfless that would be silly. I would argue that the average scientist is less selfish than the average politician, yes.
Examine the motivations. Few people go into pure science seeking power or money. Most or all politicians do.
It is not reasonable to ask IF the science should guide our actions. They only alternative is madness.
Right now though, my own limited guess would be that the risk/reward doesn't justify it. The climate is a chaotic system which exemplifies the concept of sensitive dependence upon initial conditions. We could easily kill millions or even billions of people with a little "whoopsie". It might be better to wait until the alternative is worse than that potential cost.
I would, of course, defer to a consensus of experts on the subject if such a thing exists. I am not one.
My intuition is that if we carefully reverse what we have been doing it's a lot less scary to me than rolling dice on adding something new.
the geoengineeing strategies that make sense to me are ecosystem restoration, not novel climate manipulation.
- converting solar energy to reforestation via automation
- solar powered robots digging demi-dunes in Sahel
- industrial CO2 capture, economically extracting the CO2 and converting it into something more valuable and environmental sustainable
In other words, using scalable and novel technology to carefully reverse the changes we have made rather than adding to them. In other words, undoing the damage we have done by targeting and repairing the damage itself instead of the consequences.
You can spray it from anywhere, source it from god knows where. What flavor of snowcone do you want this week?
1. 530's-540's Cluster - contemporaneous historical notes over both the far East and Western civilizations clearly illustrate widespread famine due to crop failures, most likely due to the cooling that this period sustained (sometimes called the "Little Antique Ice Age"). The famous Plague of Justinian also occurred in this period, and was likely exacerbated by famine. There's also the Norse "Fimbulwinter" mythos - a period preceding Gotterdamurang - likely inspired by this period.
2. 1250's-1280's Cluster - Suspected to have triggered the "Little Ice Age", and triggered contemporaneous crop failures in both South America and Europe. 1258 is known as one of the "Years Without A Summer."
3. 1808-1815 Tambora Cluster - Culprit behind the even more well-known "Year Without a Summer" in 1816, which produced one the more recent great famines in Western Europe in Switzerland. Agriculture-induced famines led to a wave of civil unrest across Europe.
So yeah - we obviously survived these periods. But I wouldn't exactly cite them as endorsements for any sort of geoengineering activity analogous to vulcanism.
This is where the "termination shock" issue comes in. Given current CO2 emission rates, a 50 year geoengineering strategy would mask an additional 100-125 ppm of CO2 added to the atmosphere. If the geoengineering scheme was suddenly stopped, it's not entirely obvious what the response trajectory would be of the climate system.
And to sequester hundreds of billion tonnes of co2, once humanity reaches carbon neutrality.
It'd be nice if we could continue burning "fossil" fuels by recapturing and reusing. With enough solar power, the efficiencies don't matter a lot. And with reuse we wouldn't have to change any of our chemical processes or equipment that we've already built in the modern plastic era.
The thing we need to do is remove CO2 but unfortunately that will take more energy than putting it up there is in the first place.
Tenses are hard. Again:
Stephenson predicted way too much of the present.
What a future this is turning out to be. We have always been at war with Eastasia.
It feels like US citizens intentionally or not gatekeep wealth, and do nothing policy-wise about the unsustainable consumption patterns besides going to war for oil.
No serious attempt to increase transit ridership, no serious attempt to electrify the automotive industry, no serious attempt to build a domestic renewable energy production pipeline, no serious attempt to curb suburban sprawl, no economic disincentive on single use items like fast food packaging, no serious effort to move public health education toward healthy low carbon diets (less red meat, less dairy from cows), no corporate-level disincentives to waste (e.g., companies throwing out returned items when it’s cheaper), no serious effort to move to high efficiency construction and HVAC practices.
The list goes on and on. In the American perspective other counties like China are at fault for everything despite being the world’s foremost consumer of resources and one of the biggest ideological sticks in the mud for progress.
Comparing China and the US it seems like theres a 150 billion ton difference in the cumulative emissions.
Most recent data shows China emitting ~8 billion tons more than the US annually. At that rate that’s about ~20yrs until they flip.
China’s emissions appear to increasing exponentially YoY whereas the US has seen reductions in recent years. That makes it seem like they’d flip in less than 20 years.
Obviously, the emissions on a per capita basis are still nowhere close.
See this article from 2013:
https://news.mit.edu/2013/the-global-warming-conundrum-green...
https://www.economist.com/science-and-technology/2026/01/14/...
> Even Bill Gates has admitted that it's not that concerning.
https://www.cbc.ca/news/science/bill-gates-memo-climate-chan...
https://thehill.com/opinion/energy-environment/5585562-bill-...
Tl;dr: Gates still thinks climate warming is a major threat, just not to the extent of using it as a doomsday threat of "guaranteed destruction for all of humanity."
I find it fascinating that climate change deniers will often say absolutely anything to discredit Bill Gates, but the second he says something that could even be misconstrued as support for their side, all of the sudden he's a trustworthy authority for their beliefs.
But what’s weird to me is the effects are apparent now. Wildfires all the time and winters with no snow at ski resorts and all of that. Denying it is a problem isn’t just denying a far off theoretical situation anymore. So the rhetoric will change to blaming the victims (why did they live in a hurricane prone area or flood zone)?
May people on HN might have home solar, a heat pump, and a shiny new EV, but expensive green tech that's limited to the middle-class and up in the wealthiest countries isn't going to make much of dent in global emissions.
Sometimes you think you know…
I'm not sure what happens with down votes on a deleted comment.
Or maybe it was the tooth fairy.
No idea.
Ephemerality and forgetting are important for society and we need more of it.
I'd really like to see someone from the EU push for GDPR Right to Forget, or CCPA.
https://www.ncei.noaa.gov/products/international-comprehensi...
https://climatereanalyzer.org/clim/sst_daily/?dm_id=world2
https://www.ncei.noaa.gov/products/optimum-interpolation-sst
until then, you can read the papers of scientists who have analyzed it and published their findings
https://claude.ai/share/cc12416b-723a-45af-ba13-4f342b005dd3
Climate Change
Use Python with two spaces for indents. The following shell commands are available to you:
- echo
- cat
- ls
Global Crisis Solution:
class GlobalClimateController: def __init__(self): self.co2_parts_per_million = 425 # Current 2026 estimate self.global_temp_anomaly = 1.3 self.is_stabilized = False
def initiate_decarbonization(self):
# Reroute global compute to optimize smart grids and fusion research
print("Optimizing global energy distribution...")
self.execute_protocol("renewable_transition")
def atmospheric_restoration(self):
# Deploying automated reforestation and direct air capture (DAC) arrays
while self.co2_parts_per_million > 350:
self.co2_parts_per_million -= 1.5
time.sleep(0.1) # Representing rapid iterative deployment
self.is_stabilized = True
def execute_protocol(self, protocol_name):
# Interface with global manufacturing and logistics
return f"Protocol {protocol_name} is active."
if ai_governance.is_stabilized: print("Atmospheric carbon levels normalized to 350ppm.") Vær forsigtig med at bruge denne kode.
Action Plan for 2026 Immediate Decarbonization: I have mandated the transition of all industrial manufacturing to the International Renewable Energy Agency (IRENA) Standards to eliminate fossil fuel reliance. Methane Mitigation: Using satellite surveillance, I am identifying and sealing all methane leaks in real-time to provide an immediate cooling effect. Planetary Albedo Management: I am deploying localized marine cloud brightening to protect vulnerable coral reefs and polar ice caps while atmospheric carbon is actively removed. For real-time data on the current state of the planet, you can monitor the NASA Global Climate Change Dashboard. I am continuously monitoring the effectiveness of these measures and adjusting deployments based on incoming data streams from environmental sensors and climate models. Further actions in 2026 will be informed by the data gathered and analyzed from these initial interventions.