hckrnws
AI helps researchers dig through old maps to find lost oil and gas wells
by gnabgib
It seems to me this approach could also be used for other aspects of mining. For instance, in Australia where I live there are many old gold, opal and other mines that have long been forgotten but which remain dangerous.
Most are unlikely to emit toxic or greenhouse gasses but they're nevertheless still dangerous because they're often very deep vertical shafts that a person could stumble across and fall in. These old mines were likely closed over when they were abandoned but often their closures/seals were made of wood that has probably rotted away over the past century or so.
It stands to reason that AI would be just as effective in this situation.
> Most are unlikely to emit toxic or greenhouse gasses but they're nevertheless still dangerous because they're often very deep vertical shafts that a person could stumble across and fall in.
That's a problem in Germany as well [1] - particularly in NRW, where most of Germany's mining activity is concentrated for centuries. About two or three times a week an old shaft collapses somewhere in Germany, leading to sinkholes - there's tens of thousands old mine shafts in the country and information on a lot of the legal ones got lost in one of the two world wars, and on top of these come quite the lot of illegal operations. Usually the damage is in some remote area, some forest or whatnot, but in some rare cases, entire buildings vanish or have to be condemned.
[1] https://www.stern.de/gesellschaft/bergbauschaeden--zehntause...
And for a long time, it was legal to have fun constructs like "so the mine entrance goes horizontal for a bit until the main shaft starts right under the local orphanage", so sinkholes can be all sorts of fun.
In Mendig (Eifel) there is an enormous mine for millstones which was in us for the whole middle age until the 19th century or so. Most people just dug down from their Celler and the whole city stands on enormous caverns.
As an American, I tend to think that D&D contrivances like "everyone's basement is connected to a massive labyrinth" are unrealistic, but ...
Haha good catch. I actually did some dsa campaigns inspired by these caves. They are super still, cold and eerie. Most of the shafts are filled today but you can see how dangerous they where. Small steps, without any guardrails, often slippery because water leaks in die to cracks in the rock. Also, many caverns are big, because they excavated the stone but the access tunnels are super small and steep.
Here are some pictures https://www.google.com/search?sca_esv=f23c15b34ae4d7a1&q=lav...
It seems to be this approach (using AI to identify symbols on old maps) would be useless in finding old shafts in Australia as such things pepper the landscape in various regions (eg: the Kalgoorlie goldfields) but the majority were rarely marked on a map beyond the obvious lease records that exist that probably had shafts somewhere within the lease pegs.
A better approach would be to tune an "AI" or rather an adaptive Kalman filter variation to highlight probable shafts from airborne EM and|or ground ERT surveys:
* https://www.earthdoc.org/content/papers/10.3997/2214-4609.20...
* https://www.sciencedirect.com/science/article/pii/S001379522...
* https://nextinvestors.com/learn-to-invest/mining/electromagn...
* https://en.wikipedia.org/wiki/Electrical_resistivity_tomogra...
* Variations on this type of thing: https://www.sciencedirect.com/science/article/abs/pii/S00983...
A kalman filter does what, in this case? Pardon my ignorance, but I have only seen that used for estimating locations / parameters of some process or target, not for determining existence ("is N>0?") or amounts ("what is N?").
You could cobble together a quantity estimation doing some kind of batch data association with noisy "presence" measurements, but you're probably not much better off than k-means at that point and any KF-based measurement will basically just say "Yes N>=1" because the probability is nonzero.
There's much fun to be had with filters of varying kinds - in airborne mag KF filters can be used for removing heading induced signal - variations due to the plane travelling in specific headings wrt earth magnetic field.
In a similar handwavy fashion, after picking instrument paramers and distances that might twitch on shaft responses, filters can be zeroed on regions with no shafts to see if an enhanced response can be amplified when processing the return over ground with a shaft to the surface.
Other tells for lost 'hidden' shafts might include Lidar profiles of spoil heaps .. these are clear in some cases, eroded and softened in many others.
A good many old shafts are visible from the air in any case; more so at some times of days than others - if the will is there to map them then a first pass combo of visual processing and lidar returns to map out open shafts is a good start.
> KF filters can be used for removing heading induced signal
OK - fits what I'd use them for
> filters can be zeroed on regions with no shafts to see if an enhanced response can be amplified when processing the return over ground with a shaft to the surface
OK - I see, look for outliers as positives, though the input signals here are not clear I can see the path. Your KF filters produce a "likely signal" and that is used downstream to actually do estimation. Probably, if I've learned anything, by plotting those "likely signals" on a map and dispatching a team with cameras.
> Other tells for lost 'hidden' shafts might include Lidar profiles of spoil heaps
Here we're outside what I'd call just "filtering". It's more like a big data science problem to model and label mounds.
I was just confused by zeroing in on "KF" in the comment above. If we're talking a big data pipeline, then yeah, KF has its place in all that.
In my mind it's all multi spectral processing .. combining signal from many bands some quite disimilar, to build a representation that can be ground investigated ( or "truthed" ).
In building exploration targets we'd pull together gravity, radiometrics, magnetics, EM, ERT, past mining records, regional surface geochemistry et al.
If tasked with finding old workings and shafts many things spring to mind .. old road and track patterns, strong vegetation zones perhaps indicating catchment from workings and dead vegetation zones perhaps due to leached processing chemicals (cyanide etc.)
But, yes, returning to the filter options there's signal and noise; when looking for the uncommon it's useful to use (say) SVD techniques to solidly lock onto common broad area signal patterns and then remove the commonplace and look for pattern in the residual noise.
On the other hand, old gold mines tend to be the best place to find gold - the older the better since the technological capabilities for gold recovery today are much greater then those of the old miners (yet evidently they must've been finding something to think it worth to keep digging).
The problem is that if oil/mining companies had to take care of old wells/mines they'd instantly go bankrupt.
The only reason they make so much money is because they disregard externalities
The problem is if software companies had to take care of their old programs/vulnerabilities they'd instantly go bankrupt.
I think you will find many oil and mining companies have gone bankrupt(as well as software companies) and that the problem is a bit more nuanced than just treating the entire industry as a single monolithic entity.
Many of the oil and gas (and coal) companies that have gone bankrupt are part of a deliberate ploy to load up debts and externalities on firms that go bankrupt so that the people who benefitted can escape their responsibilities.
And last I checked, tight oil US companies (taken together) were not even profitable (except for a single quarter) even despite a low interest rate financial environment and wildly insufficient funds dedicated to cleanup ?
You mean, like other companies with worldwide concurrence?
Take care of old mines from other companies?
They'd still make tons of money if they had to cleanup their spills and old mines. They're just greedy and want to make more.
> They'd still make tons of money
I don't think you understand the scale of the problem... Plugging leaking wells in the US alone is estimated to cost $280b, that's 10 years of net profit for Shell or ExxonMobil. Even taking the top 5 world oil companies _profit_ from 2022 (most profitable year so far) you're short $80b, for the US alone, and that's only onshore wells.
> Researchers estimate that there are between 2-3 million abandoned oil and gas wells in the United States, and more than 117,000 of those, across 27 states, are “orphaned”—that is, uncapped, unproductive, and with no responsible party identified to manage leakage or pollution risks
https://www.cnbc.com/2022/02/24/plugging-methane-leaking-oil...
https://www.sciline.org/environment-energy/abandoned-oil-gas...
If the companies can't responsibly operate as a for-profit entity, nationalization seems like a reasonable path forward.
Is securing old mines a good job for (remotely-operated (humanoid)) robots?
Old mines can host gravitational energy storage.
From https://news.ycombinator.com/item?id=35778721 :
> FWIU we already have enough abandoned mines in the world to do all of our energy storage needs?
"Gravity batteries: Abandoned mines could store enough energy to power ‘the entire earth’" (2023) https://www.euronews.com/green/2023/03/29/gravity-batteries-...
[flagged]
And the other side of HN, where abandoned mineshafts are a societal good and bulldozing hazards that blight the landscape makes kids soft?
It's simple really. You use the power of imagination. In your mind, AI can do anything!
I don't know what they mean by AI but this reminds me of an old fortune:
*** Special AI Seminar (abstract)
It has been widely recognized that AI programs require expert knowledge in order to perform well in complex domains. But knowledge alone is not sufficient for some applications; wisdom is needed as well. Accordingly, we have developed a new approach to artificial intelligence which we call "wisdom engineering". As a test of our ideas, we have written IMMANUEL, a wisdom based system for the task domain of western philosophical thought. IMMANUEL was supplied initially with 200 wisdom units which contained wisdom about such elementary concepts as mind, matter, being, nothingness, and so forth. IMMANUEL was then allowed to run freely, guided by the heuristic rules contained in its heterarchically organized meta wisdom base. IMMANUEL succeeded in rediscovering most of the important philosophical ideas developed in western culture over the course of the last 25 centuries, including those underlying Plato's theory of government, Kant's metaphysics, Nietzsche's theory of value, and Husserl's phenomenology. In this seminar, we will describe IMMANUEL's achievements and internal architecture. We will also briefly discuss our recent efforts to apply wisdom engineering to oil exploration.
https://www.youtube.com/watch?v=m8QWxJhna8Y shows off some of the efforts of https://welldonefoundation.org/ to actually do something once they find them - which also puts more emphasis on the abandonment part (specifically the industry irresponsibility involved in allowing them to become hazards in the first place.)
That's a huge amount of effort (and carbon-fuel-powered energy) involved in capping the well. Based on the numbers they provide, I guess it's still worth it even if you consider the lifecycle of all the trucks and equipment and concrete. But that is quite an expensive procedure. Is it really so important to completely plug the hole with impermeable concrete? You can't plug it 1/3 of the way and then put a metal cap on with a 10-year maintenance schedule?
People should be confronted and shamed if their ancestors did this and they won't do right by them.
Predecessors at work, sure. Ancestors? Nah. I’m sure I had some jerks in my lineage somewhere, and I don’t owe anyone atonement for their acts.
Guess I don't mean all ancestors, mainly talking about multi-generational wealth here.
Why do I get the blame and shame for something my grandparents might have done wrong?
If and only if you are still benefiting from that wrong, or others are still suffering for it.
That's a very slippery slope.
How do you define "benefit"?
Your dad swindled thousands of "investors" out of their retirements and left you millions. You are benefiting from this and the children of the "investors" are suffering.
Your great-grand-dad swindled thousands of "investors" out of their retirements and you inherit a business empire. You are benefiting from this and the hundreds of great-grand-children of the "investors" are also suffering. They could've had inheritances but they didn't and work at Walmart.
You can trace your lineage to Thomas Jefferson who apparently owned 600 slaves over his lifetime. You still benefit from him having been a president and a wealthy man. You should have to trace ancestry of those slaves and compensate their current living family members.
Slippery slope indeed.
But if your wealth comes from a line of crime, then yes, compensation would be adequate.
Morally, sure, if you know your wealth is sourced from crime, you likely have a moral obligation to disgorge it.
Practically, that's difficult. If you grew up wealthy because of generational crime that provides life advantages you can't return. At best, you could make sure you direct any inheritance to victims if possible or a suitable charity (and not your family foundation).
Legally, this is not plausible. All sorts of legal principles dictate that lawsuits must be timely (for various values of timely) and estates become unlitigatable not very long after they're closed. There are some cases in the news about crimes in WWII and such, though.
It is a very complicated topic.
But the law knows such things in principle, even though usually not individually, but rather collectivly.
Like the native americans get some sort of privilege today. And (some) black americans demand reparations for past slavery.
But where to draw the line indeed. I don't think there is a universal answer.
Cool! How far back are we going? What evidence is required?
I have some neanderthal DNA, and you extincted my people, so let's start settling up
Ok but only after I get a large chunk of Eastern Europe. I know I have some Polish/Ukrainian ancestry and they mush have been persecuted since they left for the US.
However far back and whatever evidence needed until it starts affecting us.
Like north Korea does in the gulag? Three generations of punishment?
I think this is cool but this is mostly being used to find leaky old forgotten wells.
Not tap unused or forgotten wells. This is purely risk avoidance, which usually means it won't get much attention or funding.
The DOI has an orphaned wells program and it seems like one of the few things that the BLM does with bipartisan support.
> which usually means it won't get much attention or funding
Leaky wells are a legal and insurance liability, which has a downstream impact on the financing of a drilling project.
They are also a huge, unfunded public liability in many jurisdictions, like mine (Alberta). Companies disappear but their rec-rem responsibilities last forever.
You have to find them to make the case to fund the remediation. Quantify, calculate, and communicate the risk and cost, then action.
If you know they are out there (and we do know) then hiding your head in the sand until someone stuffs proof up your behind seems rather.... well, you get the point.
In my opinion, that is like not fixing roads until someone collects data on potholes and forces you to, instead of actually keeping an eye on roads and bridges. A very American POV I'd say.
Your opinion is very European in that it assumes you can just walk around and find these. The US west where this is focused is vast expanses of open un occupied land and cannot just be inspected to find the abandoned wells from a century ago. Same for large parts of Australia, so no surprise the Australian commenters also find this interesting.
Fine them at rates that dwarf whatever cost it would take to fix them. That would be the motivation necessary. Tell them they have 30 days after being notified before the fines start. Someone else on some other thread mentioned the ideas of exponentially increasing fines. Do that here.
Of course, the company has to still exist
>Of course, the company has to still exist
The system in place in the US means they mostly do not. A fund holding the amount of money it would take to clean up whatever you do on the land should be mandatory. Leave the land as — or better — than you bought it. Of course, that's very un-American.
Huh, in my energy industry experience, we always remediated sites. And set aside funding for it before any construction was done. The cost estimation and funding of it was part of the initial planning and approval. I thought it was mandatory and mostly did happen. Some quick research says it is legally required, but IANAL nor an expert.
Of course, that has not always been the case, and things falls through the cracks, but I would not immediately dismiss the entire industry as being non-compliant. I would dismiss the entire industry as flawed and needing change, but not on this specific point - it is vastly improved over past decades.
> Of course, that has not always been the case, and things falls through the cracks, but I would not immediately dismiss the entire industry as being non-compliant.
There's a point in time where this changed and permits needed at least a plausible expectation of remediation. If I had to guess that would have been late 1980s to mid 90s.
Most of the sites abandoned without remediation are from permits obtained before that time. I'm sure there's some cases where there was a setaside for remediation and it wasn't sufficient and the corporate entities involved went bankrupt, so it wasn't finished; but IMHO, most of the problem is older sites. Older sites also tend to have worse records, so there's that too.
I was a developer at Shell a couple years back and led a project where we were using nascent GPT-1/2 to process and search over mountains of documents. It was a fun project where I wrote a complex/fancy UI for a stratigraphic filter and indexing system...
Seems this is just a natural progression...neat.
That's pretty cool that Shell was such an early adopter.
Who led the adoption of GPT-1/2 there - a developer, you, a VP, someone else?
AI in general at the time was led by a VP and a particular group (that was AI tech specialized) under him. The initial idea came about from them. We were trying to find new ways of using AI to research new sources of crude at the time.
Another AI project I worked on there was a chemical tank use estimation and refuel application which used tank sensors, previous use history and some other metrics to pre-purchase and deliver product to keep tank reserves above a certain threshold.
For context, all of this was circa 2018-2021.
Thank you for answering!
I found out Red Hat is now using AI to dig through git commits in large upstream projects to find out what new features were added and removed, to direct downstream QE efforts. It's done with a human review afterwards. Kind of interesting, not sure yet how well it'll work in practice.
> downstream QE efforts
We really need a more clear definition of what "AI" means.
What the article describes sounds like it could have been built with 10 year old image processing tools and basic algorithms crunching the large amount of sensor data used to identify potential wells.
What makes this tool AI rather than an algorithm? Or machine learning?
Computer vision is AI, it’s just not an LLM: a computer is performing work like our brains do. Your argument is basically what Bertram Raphael was saying in the 1970s: “AI is a collective name for problems which we do not yet know how to solve properly by computer”.
Some CV is AI, like "identify pictures of cats", but not straightforward filters in an algorithm such as "narrow the bands of visible light to those that make existing mineshafts stand out, then scan the entire continent recording the top 20% of matches for this value (with some wiggle room to account for variants)".
That is very much manual intelligence
It's simple: AI is what you call it when it's useless / when you don't know what you're talking about / when you're looking for investors money. When it becomes useful it gains a name, like "computer vision", "machine learning", "natural language processing", "image generator"
This is super useful, but it's a bit disappointing to see map digitization called "AI".
I mean, sure, these are methods broadly in the computer vision realm and that gets referred to as "AI" sometimes. But at the end of the day, this is "find all unfilled black circles of a specified diameter on these images". It's amenable to (and has been done by) traditional computer vision methods for a long time. There are certainly a lot of cases where a CNN type approach can perform better than traditional computer vision and there are always improvements to make.
However, I think it's a bit odd to treat this type of use case as some sort of AI breakthrough that wasn't possible or wasn't frequently done in the past.
Why can't normal standard work have a press release? Why do we need to play pretend and add buzzwords just to make things sound "cool"?
...But that's just me being a bit bitter, perhaps...
USGS have maps from over 100 years ago. They have already been digitized. These are probably projects to search through like a person would looking for things. People that collect insulators used to collect the actual maps long ago looking for old abandoned telegraph line locations (compared to today).
AI is useful for searching for targeted stuff where you can replace a person doing something that is probably pretty easy, but there is a lot of work that can be automated. Like searching for new viruses. AI has made identifying new viruses relatively easy and much quicker than a person, who typically tweaks input and data looking through what is noise to identify genome sequence of a new virus.
> Why can't normal standard work have a press release? Why do we need to play pretend and add buzzwords just to make things sound "cool"? > ...But that's just me being a bit bitter, perhaps...
Were you complaining as heavily about OCR or Markov chains ever being referenced as AI in their hay day?
The term “AI” is in an infinite treadmill and the day it stops being useable as a time sensitive reference is probably the day it surpasses humanity and becomes its own State
You can make highly accurate predictions of what contrarians will say by assuming that they define AI as "whatever computers can't do yet."
LLMs aren't truly intelligent. [No True Scotsman fallacy...] They don't really reason. [A distinction asserted without giving a falsifiable definition of reasoning...] They're just next token predictors! [Which must be mutually exclusive with intelligence, I suppose?] Etc, etc, etc. Find your favorite pretext to dismiss modern AI, ignore the holes in the argument, and satisfyingly conclude that it's all smoke and mirrors.
Consequently you see hilarious takes from skeptics, like comparing today's enormous investment in AI to when people sold blockchain cartoon monkeys. Or claiming that modern models aren't useful for anything, as if they exist in an alternative reality where hundreds of million of people don't use them daily, and there's no incessant firehose of new tools/products/results discussed in news/social media constantly.
It's not that, it's breathlessly proclaiming that techniques that have been standards for decades are "groundbreaking AI". The hyperbole makes it impossible to get at anything, and if you accurately propose a time tested solution at work these days, it gets dismissed because it's "not AI". So now standard computer vision methods that aren't AI in any way are getting proclaimed as "AI". It's quite annoying, as least from the perspective of someone who does more or less this exact thing (geospatial analysis and data processing of various types) for a living.
Folks won't let you use the right tool for the job anymore unless you make wildly hyperbolic claims about how groundbreaking it is and claim it's cutting edge AI.
The situation is bad for everyone. There's nothing wrong with using the right tool for the job and accurately describing it. I'm tired of having to inaccurately describe methods to be allowed to use them. E.g. claiming a Hough transform is "deep learning" so folks won't immediately dismiss it and demand I use some completely incorrect approach to a simple problem.
> However, I think it's a bit odd to treat this type of use case as some sort of AI breakthrough that wasn't possible or wasn't frequently done in the past.
Classic computer vision is an utter PITA - especially when dealing with multiple libraries because everyone insists on using a different bit/byte order, pixel alignment, row/col padding, "where is 0/0 coordinate located and in which directions do the axes grow" and whatnot.
The modern "AI" stuff in contrast can be done by a human in natural language, with no prior experience in coding required.
It's usually the exact opposite for this sort of thing. You can't do this with natural language. Traditional computer vision is well suited to it and works with some tweaks. "Modern" techniques for it require collecting insane amounts of training data for simple things. You can't just throw transfer learning at this because it's a lot different than standard photographs that models are trained on. The old school methods are faster and more reliable for a significant number of problems in the geospatial world. And you still need a lot of deep expertise no matter what.
Because too many people now refer to all of machine learning as AI.
All of machine learning is AI. It's a subset, by definition.
The issue is that the terms have escaped the computer science labs and the media and the public have latched on to AI, and uses it for everything.
It is true that all of this, machine learning, large language models, natural language processing and much more is AI, in the sense that it falls under the same artificial intelligence umbrella in computer science. It just feels a little like some one is using the term "construction" over and over, but what they are specifically talking about is some very specialized type of carpentry. It's not wrong, it's just not all that precise and give the wrong impression.
> Researchers used the AI algorithm to scour four counties of interest that had substantial early oil production – Los Angeles and Kern counties in California, and Osage and Oklahoma counties in Oklahoma – and found 1,301 potential undocumented orphaned wells. So far, researchers have verified 29 of the UOWs using satellite images and another 15 from surveys in the field;
It would be really helpful if they called out how many potential wells were inspected and couldn't be verified. Are they confirming at 100% or 10%?
One day, when I have too much time and too much money, I will make a roguelike with map converted from old maps.
Don't let dreams be dreams, start small, the minimum. One map, one screen. Just a toy for yourself. A little effort expended repeatedly yields compound interest.
The same methods have also been used to identify archeological sites [0]!
The negative tone of some comments here betrays that techno optimist suggestion that tech will solve environmental issues. Clearly, the incentives just aren’t there!
Tech has caused more and worse environmental issues than it has ever solved.
If anybody likes treasure hunting, there are lots of lost gold mines too
You can come across the land parcel claims sometimes by families that don’t have the capital to mine
As we regulate AI with concerns energy and emissions, wouldn't this be the low hanging fruit to forbid first?
Though headlines like these annoy me since we, the people, are being pressured to change our way of life when there are bigger fish to fry, I'm glad we trying to fix things within our control. Things like this shouldn't even be studied, they should be addressed aggressively and fixed so we can get a clearer picture of what we as individuals are responsible for.
Study is the necessary predecessor to fixing.
How long until AI can dig through old rabbit holes and come out with Mossad connected US politicians?
This is a fun thing to think about - historical reconstruction. In the extreme, you end up with something like Accelerando[1]'s "resimulated" people - people recreated and resimulated in full fidelity from any and all available history, but who may never have actually existed. A bit like an AI hallucinating people.
[1] https://www.antipope.org/charlie/blog-static/fiction/acceler...
Could it help me find my keys I lost this morning?:))
There is a (likely small) chance that you lost your keys in an unknown or lost oil/gas well. So yes, in theory.
Albert, such a helpful guy !
Sad thing is that researchers and NGOs are policing away at old wells on a shoestring budget while the original operators have made off with lots of money. Extract the profits, socialize the damages...
Well, that is the American way.
Comment was deleted :(
AI seems to be everywhere these days. That was gonna happen one day. This is gonna be really interesting in coming days.
[flagged]
[flagged]
AI gonna help identify forgotten environmental hazards.
Comment was deleted :(
[flagged]
As if the outgoing one doesn’t also need shitloads of energy? Airforce 1 and The Beast don’t run on butterfly wings…
I think the parent post was referring to the anti-environmentalist aspect of the new administration. They're not going fund remediation efforts while attempting to dismantle the EPA.
This is to cap forgotten wells, not exploit them again...
Also worth checking the unforgotten ones. When I was a child my grandparents would take me to one of the beaches that had many capped wells and we would kick the rusted lid off and throw rocks inside for the sounds. Either that or they were eye-balling it to see if I would fit.
Wild! LA?
Are there ever beach caveins?
Comment was deleted :(
Yeah they're pro AI and pro business. Sounds about right.
It's pretty obvious you haven't read more than the headline.
Some articles are more opinion than fact, even though they might be presented as fact
[flagged]
That's the ticket! I've always known that AI will save us all.
Crafted by Rajat
Source Code