Eyes in the sky on Climate Change (like Skynet, but supposedly nicer)

Satirical image composite – A. Watts

We love our bad-boy (and -girl) artificial intelligences — think Skynet or Hal 9000 — pushing people and societies to the brink of ruin, and telling a good science fiction story in the process.

But what if, in real life, we used the massive computational powers of artificial intelligence (AI) for good, making it the hero of our epic endeavor to save humanity from, say, the effects of climate change?

This is the story UC Santa Barbara ecohydrologist Kelly Caylor wants to tell. And now, with an AI for Earth Innovation grant sponsored by National Geographic and Microsoft, he and colleagues Matt McCabe from King Abdullah University of Science and Technology in Saudi Arabia, and Lyndon Estes from Clark University in Massachusetts, are beginning a new chapter in the global effort to adapt to a rapidly changing Earth. At UC Santa Barbara, the team also will consist of Ryan Avery, a doctoral student in geography, and Marc Mayes, an Earth Research Institute scientist.

“There is a real big movement — which is really exciting — to take advantage of the next generation of satellite data, ground-based observations and just a whole new set of technologies around being able to monitor environmental processes, and the potential to use those in conservation, or to support efforts to better manage landscapes,” said Caylor, whose research specialties lie in hydrology, terrestrial ecology and coupled natural-human systems.

The project is an extension of work already being done on the ground and from the sky, as Caylor and colleagues have, for years, monitored field sites and satellite images to get a sense of climate conditions and water availability that could indicate the health of crops and other vegetation in sub-Saharan Africa.

“In Zambia, where I do a lot of fieldwork, there are a lot of subsistence farmers who are still planting crops based on the timing of rainfall and are really trying to deal with rainfall variability in a very traditional way,” Caylor said. “We’re trying to help them by giving them better data. And we’ve built sensors that can monitor rainfall and things like that.”

It’s an effective system, and one that has proven itself in times of climate change, where variability can lead to drought and subsequent food insecurity. But Caylor and his team are also interested in all the water we can’t see from the surface — namely, groundwater. This other major component of water use in agriculture is being more heavily utilized as investors both domestic and foreign lease large tracts of land on the continent to develop or grow crops.

One huge indicator of groundwater use, Caylor explained, is the center pivot agriculture system. The method creates a large, often circular crop field watered by slowly-rotating sprinklers that extend outward from a central well, irrigated by the water therein. In a place as big as the African continent, for example, much of this takes place in remote areas, according to Caylor.

“We’ve seen this happening but it’s hard to get a picture of it on the ground,” he said. “And so we got to thinking about all this new satellite data that’s out there. We’ve got companies that are launching these micro satellites that can map the whole Earth at two- to three-meter resolution every day. And so from those we can start to see not only where these fields are as they’re being installed but also what’s growing in them and how often the water is being applied. We now have the capability to look down and see these things. But to do it you have to be looking at really large scales and you have to be able to quickly process lots and lots of data.”

Enter artificial intelligence and, for Caylor’s group, the chance to scale up from provincial fields in Zambia to the entire African continent. Instead of round-the-clock human eyeballs searching for these telltale signs of aquifer-tapping, computer vision is used to classify images that look like center pivot-irrigated fields, with help from the world’s premiere mapping organization and one of the world’s leading technology companies.

“It’s a great three-way partnership,” Caylor said. The research ideas developed at UC Santa Barbara are enhanced by the large-scale data, computational and workflow management tools that are Microsoft’s forte, while National Geographic’s experience in communication and visualization is valuable as the scientists try to convey their findings into actionable items.

“They see the value of doing this as we do, in terms of connecting this kind of information we can share to help people make decisions about water management and understand land use change,” noted Caylor. “Is there encroachment in conservation areas? Do we need to be worried about the expansion of these areas into places where we’re trying to preserve wildlife?”

The project is still in its beginning stages, as the scientists face the same challenge every computer vision researcher faces with his or her AI: training it well enough to recognize every version of its target image.

“Computer vision algorithms are pretty good, but they can get sensitive to things that we don’t realize,” Caylor explained. While computer vision might find center pivot-irrigated fields in Africa, it might struggle to find the same in New Mexico, for instance, because surrounding soils and vegetation are different. Or, it might find a baseball field and call it an agricultural field.

Fortunately, Caylor, McCabe, Estes and the rest of the team are off to a good start, with decades of research and data to build on, and resources that can help them both refine and scale up their approach as they embark on this most ambitious land-use study — not to mention the enthusiasm and energy to help solve one of the biggest environmental problems we face.

“The main goal is to empower people who are worried or interested in thinking about water management issues and conservation of water and land in areas where those things are transforming really rapidly,” Caylor said. “We have a great team of people and we’re all going to throw ourselves into this problem.”


Press release from Eurekalert

0 0 votes
Article Rating
Newest Most Voted
Inline Feedbacks
View all comments
January 14, 2019 11:36 am

And now the Wolf of Wall Street can change clothes and become an eco Green AI programmer to rig the system…..this time for keeps.

Rich Davis
Reply to  ResourceGuy
January 14, 2019 2:07 pm

Do I need to say it?

Say no more.

January 14, 2019 11:42 am

“We have a great team of people and we’re all going to throw ourselves into this problem.” (as long as the free money to support them keeps flowing.)

January 14, 2019 11:49 am

When dystopian sci fi is cited this cinematic gem of AI is usually forgotten. “Colossus, The Forbin Project”.

“This is the voice of world control”……For the collective good of course.

Reply to  Jones
January 14, 2019 12:35 pm

We don’t get to find out what happens.

It is absolutely imperative that no AI is in the position to seize power and that every AI has an unstoppable kill switch.

We really don’t understand human thought. The left hemisphere of the brain does language and logic. That’s where our inner voice comes from. We think of consciousness as what goes on in the left hemisphere.

The right hemisphere provides context. It is our BS filter. If the right hemisphere is disabled, the result is a disconnect from reality that mimics schizophrenia. link Logic and facts are not enough to function as a thinking entity.

It is just as likely as not that any sufficiently advanced AI will be bats**t crazy.

January 14, 2019 11:58 am

Jones January 14, 2019 at 11:49 am – darn you beat me to it.

Reply to  dave
January 14, 2019 11:33 pm


January 14, 2019 11:58 am

Garbage in, garbage out applies even more to AI then it does to human intelligence. Even the best AI’s need to learn by being directed by a human intelligence about what’s true and what’s not.

Reply to  co2isnotevil
January 14, 2019 12:13 pm

There is an old article with the title “Artificial Intelligence meets Natural Stupidity”. It’s still relevant today. It begins with “As a field, Artificial Intelligence has always been on the border of respectability, and therefore on the border of crackpottery”. That still seems to be the case. A lot of bullshit has been spilled in the name of AI and a lot of pseudo research has been done.

January 14, 2019 12:00 pm

My slight knowledge is in Australia, and as I understand it there is a limit to how much one can extract. .

It has to come from somewhere , in Australia it s probably the Big Wet up North during the Monsoon season up there.


January 14, 2019 12:16 pm

If they really want to know what’s happening on the ground, it would seem to me the best method would be to actually monitor what’s happening on the ground. I would venture to guess that any agricultural endeavor which utilizes central ground water irrigation systems probably also has a means of outside communication.

BTW how exactly can the “science be settled” when they don’t even know what’s happening on the ground?

Joel Snider
January 14, 2019 12:17 pm

Well, let’s see. ‘Skynet’ was about total human extinction. In a movie.

‘Green’ is about 90% population reduction. For real.

So Skynet, in philosophy is only marginally worse – and in reality is only a dated reference to a tired-out Hollywood franchise.

Therefore – not really ‘nicer’.

Craig from Oz
Reply to  Joel Snider
January 14, 2019 5:05 pm

Common ground between the two?


To think, if only the Outer Limits had better lawyers we might have avoided all this destruction… 😀

January 14, 2019 12:24 pm

Skynet is enabled when much of the population is on hi-dose THC and opioids. It’s all in the timing.

Reply to  ResourceGuy
January 14, 2019 1:44 pm

To resource guy, yes and in “A brave new world” it was “Soma”… Just now on the radio I hear there is a new drug that will be given to people with incurable cancer etc if they want it, from the cane toad, that will have that person happier and more accepting of their situation and able to better enjoy the rest of their existence. Good idea and you only need to take it once and it will last for 6 mnths.
Perhaps this drug could also be used on violent repeat offenders? And should that work, maybe they can extend the range of people that can access it to depressed people or others unable to fit into society properly, maybe chronically unemployed people might have to take it…etc What if it gives you an advantage in your field of work or sport? Or gives you an edge in chatting up girls? What if it just plain is a better existence? And causes you to vote in the correct State approved manner? Just like Soma?
Anyway, we can all see it coming, by salami tactics…one little slice at a time…mind control is already being used by the Dems and all other leftist Govs around the world, primarily by Media domination, institutional domination and by politically dividing the population into separate sub sets and telling them lies that cause each set to hate each other.
Obama, the greatest fraudster in human history is also the greatest hate monger in human history, I put him ahead of Hitler in this as Hitler never attempted to set men and women against each other, and never attempted to coerce the population to hate its own country. Other than this Obama is just as bad, only constrained by his inability to obtain complete control…something “they” are attempting now, the new world order, coming soon to a town like yours.
Does your town already have a camera on every corner? Are your bureaucrats talking up a cashless society? Do your blacks hate your whites? Do you have vagina hat parades and other brown shirt activities such as closing down dissenting speakers etc? They are already there!

J Mac
January 14, 2019 12:25 pm

Since when are ‘center pivot-irrigated fields in Africa’ …’one of the biggest environmental problems we face’? You have to be incredibly perverse to think growing food to feed hungry people is ‘bad’!

Thomas Homer
Reply to  J Mac
January 14, 2019 12:37 pm

J Mac – “You have to be incredibly perverse to think growing food to feed hungry people is ‘bad’!”

More ‘perverse’ than Carbon Based Life Forms proclaiming Carbon Pollution?

Reply to  J Mac
January 15, 2019 1:27 am

Great catch.
“You have to be incredibly perverse to think growing food to feed hungry people is ‘bad’!”
I find it interesting that huge tracts of land are leased, not owned.
Leasing means the owners will simply leave after using up as much as possible.
Since the Saudis are paying, want to guess who’s leasing?

January 14, 2019 12:34 pm


Is that a real thing?

Rud Istvan
Reply to  MarkW
January 14, 2019 12:41 pm

In his mind, yes.
In reality, maybe not so much.

Ron Long
January 14, 2019 12:54 pm

I’m confused by the need for AI cited in the report. GoogleEarth ™ already utilizes QuickBird digital imagery at 60 cm resolution, so why special satellites at 1 or 2 meter resolution? In 1996 I managed a research group that developed techniques to find gold-associated alteration with available imagery products and the program ENVI. We often found farmers crop circles due to the sulfate ions which were also in target jarosite minerals. Find pivot irrigation crop circles? Chlorophyll gives off a tremendous near IR reflection and this would be extremely easy. Sounds to me like they are utilizing AI to invent a horse-and-buggy.

Reply to  Ron Long
January 14, 2019 1:26 pm

And if you need day-by-day coverage there is EOSDIS Worldview, albeit with lower resolution (but easily good enough to spot pivot irrigation:


Peta of Newark
January 14, 2019 1:02 pm

Recognizing that the machines are only as good as their masters is essential to getting useful data out of them. And, you know, keeping them from getting mad at how badly we messed them up as children.

They don’t do they?

From here:

January 14, 2019 1:19 pm

“center pivot-irrigated fields ….In a place as big as the African continent, for example, much of this takes place in remote areas, according to Caylor.”

No it doesn’t. Center-pivot-irrigated fields requires reasonably good road access (you just try and haul the hardware on donkey-back) and reliable electrical power. Neither exists in remote areas in Africa (or perhaps all of Africa is remote for a Santa Barbara academic?).

Steven Fraser
Reply to  tty
January 14, 2019 1:53 pm

I think it would take 1 researcher the better part of an afternoon to survey the entire continent for artefacts indicating use of this style irrigation (via Google Earth or equivalent), and another morning to profile the power grid supporting those.

Anyone who has flown over West Texas, New Mexico or Arizona during growing season knows what to look for. Though, I bet there is already a Texas A&M University study on the topic.

Computationally, no AI is required. The artefacts will be located in areas of limited topological change/land slope. A bit of altimetry could be used to isolate the likely candidates.

Reply to  tty
January 14, 2019 2:40 pm

Libya were doing it on a large-scale in the mid-1970s.

D. J. Hawkins
Reply to  WXcycles
January 14, 2019 6:14 pm

I took a quick look at Libya on Google Maps, and it appears that center pivot systems are discernible at a resolution of 2 miles to the inch.

January 14, 2019 1:34 pm


The AI technology, or AI as a “tool”, even when it may be considered as at an early stage, still holds a strong and well deserved reputation as it being the best and most successful ever “tool” or means employed in analyzing-sorting big or very high density data towards an expected rationale point of address…for us the humanos, and our benefit.

So far there is and stand a very strong case pro AI, in and towards the support of-for humanity and the benefits to humanity.


Alan Tomalty
Reply to  whiten
January 14, 2019 9:53 pm

I agree. With AI you define the rules and like 1 massive Monte Carlo simulation repeated an almost infinite number of times you just might find out what really causes ice ages. However you would have to be very careful not to parameterize anything when setting up the rules and goal. But a bigger however is Does anybody really trust anybody connected to this project( who all have to be global warmer alarmists just to get on the project) to not tamper with the rules at the beginning of the project the way that GCM’s were tampered with , in regards to CO2 and temperature?

John Endicott
Reply to  whiten
January 16, 2019 9:51 am

yeah, whiten, but “evil” AI out to subjugate/kill humanity makes for much juicier/sexier stories.

January 14, 2019 2:23 pm

While they’re performing this service they should also turn the farmers on to GMO’s. The science is in and they are good to go. Who are the science deniers now.

Johann Wundersamer
January 14, 2019 2:36 pm

“We have a great team of people and we’re all going to throw ourselves into this problem.”

On the risk of repeating myself, there’s already computer models to throw people and stuff :


January 14, 2019 2:37 pm

More nonsense that reveals the worthless intellectual-bankruptcy of the plague of ‘higher-education’ time-waster parasite anthrophobes infesting humanity, pretending to ‘help’ us, and to ‘like’ us, so that they can further mess with us to harm, and pick our pockets more. The rest of humanity, for the most part, works for a living, and makes a small but honest income, and who are in no need of copious verbal manure to fertilize their farm with as the overflowing bounty of natural CO2 and rainfall already provides the ‘dynamic lifter’ (chicken poo) they require thanks.

If this is all a ‘modern’ University can deliver, defund them now and close them down.

Reply to  WXcycles
January 14, 2019 4:30 pm

Well said!

January 15, 2019 10:59 am

Artificial intelligence, what a leap forward.

Paul Drahn
January 15, 2019 11:02 am

After graduating from college in 1964 with a degree in math/physics, I attended a business school named “Automation Institute”. They gave each student a nice lapel pin with the initials “AI” in bold letters.

When my younger brother saw the pin he said “Oh, you have been to Artificial Insemination’ school. I quit wearing the pin. But whenever I read “AI” I always wonder which they mean.

%d bloggers like this:
Verified by MonsterInsights