Slashdot Mirror
Satellite Images Can Map Poverty (bbc.com)
A new study using satellite images and machine learning plans to map poverty from space in an effort to "fix the world's problems." Satellite imagery can be less dangerous, slow and expensive than gathering the data on the ground. BBC reports: "A team from Stanford University were able to train a computer system to identify impoverished areas from satellite and survey data in five African countries. The latest study looked at daylight images that capture features such as paved roads and metal roofs -- markers that can help distinguish different levels of economic wellbeing in developing countries. They then used a sophisticated computer model to categorize the various indicators in daytime satellite images of Nigeria, Tanzania, Uganda, Rwanda and Malawi. 'If you give a computer enough data it can figure out what to look for. We trained a computer model to find things in imagery that are predictive of poverty,' said Dr Burke. 'It finds things like roads, like urban areas, like farmland, it finds waterways -- those are things we recognize. It also finds things we don't recognize. It finds patterns in imagery that to you or I don't really look like anything... but it's something the computer has figured out is predictive of where poor people are.' The researchers used imagery from countries for which survey data were available to validate the computer model's findings." The results of the study are published in the journal Science.
It's the only way to be sure
You can also tell poverty by satellite images by looking at the amount of light in a area at night or the dryness of the land. Except for Dubai, Las Vegas and various palaces around the middle east where the oil barons live, people living in the desert are in poverty too simply because theres barely anything for them to exploit.
I don't have one.
They are expensive.
Altho, I didn't think i was living in poverty.
_ _ _ Go for the eyes Boo! GO FOR THE EYES!
Spend money on satellites to stare at poor people instead of giving them food.
BBC reports on Stanford study.
US? Just sham election and what celebrity is disgruntled about a candidate.
...mapping something does not fix it. It just quantifies the problem. Quantifying is very laudable, but to actually fix the problem will require things that the affected countries may not be willing to do. First, let's tackle the issue of corruption. Then tackle the problem of people/organization only giving the important jobs to friends/family/religious group (i.e. NOT giving jobs to people who are actually qualified for that job). THEN lets see if the people in charge actually work for the betterment of the country and not for themselves. And all these things are doubly true in a third world country like Africa.
...already knew that. And it's not quite as hard as they make out.
Irony: Agile development has too much intertia to be abandoned now.
Do these satellites see into basements to find the permanently unemployed underclass of poor people who lost their jobs as soon as Obama was elected and have been unable to find work since? Of course not. Do these satellites see into garages where poor people who have no economic prospects spend their idle hours working on hobbyist projects that will never be funded? Of course not. Do these satellites see into coffee shops where poor people linger to get out of the house during the day because they have nowhere else to go and nothing to do? Of course not.
This imaging project has nothing to do with fixing poverty and everything to do with surveying real estate to find opportunities to make the rich even richer.
What's the opposite of *follow the money*?
“He’s not deformed, he’s just drunk!”
Our totally scientific satellite imaging methods found some more coders to recruit! Cheapest coders! Get em here!
What money? usdebtclock.org
Why would you distance yourself up in space, then try to work out poverty from outside the earths atmosphere by satellite photographs? Is poverty contagious? Why on earth would you assign poverty to GPS locations? That would represent an average poverty/richness in that zone and be totally useless when dishing out welfare.
Take any Google map and you'll see supermarkets, restaurants, hospitals, AND slums intermixed. The slums are there because the jobs and money are there. The jobs and money are there because there are richer people there. It's NOT A FUNCTION GPS LOCATION.
You would not decide on welfare based on a course GPS cell map.
"The assistant professor at the University of California, Berkeley, wrote: "For social welfare programmes, some of which already use satellite imagery to identify eligible recipients, higher-fidelity estimates of poverty can help to ensure that resources get to those with the greatest need.""
Ahh, OK, professor wants to play with satellites and computers and make the world a better place..... from a distance....without getting his hands dirty. Plus they don't have decent Latte Maciato in Africa.... do they?... they have lions and tigers and mud huts.... he researched that on discovery channel.... but no Starbucks.
Waste of resources. We already have this data. All you have to do is find any place for which Google Maps doesn't store full-resolution pictures.
If it is really helpful to identify the Poor from those countries it is good....
Remember the constant "profiling is racist" and constant complaints in media right after 2001 about profiling...
Waiting for the campus sjw's to have something new to embarrass themselves with protesting :-P
Just map the number of cars up on blocks per square mile and you'll get near perfect correlation to poverty. The greater number of cars the greater the poverty. The old metric of satellite dish per square mile (the more the poorer) is unfortunately no longer relevant.
Couldn't similar technology be used to seek out hungry people and launch guided bananas at them?
Its a great one and also a beautifully crafted one. looking forward for more from this website.I read all of article of the site the article was very nice go and check it out!
birthdaywisheszone
Its a great one and also a beautifully crafted one. looking forward for more from this website.I read all of article of the site the article was very nice go and check it out!
birthdaywisheszone
I always thought the GIS community was still too unfamiliar with remote sensing. Apparently it also is the case the other way round. They have made a spatial analysis of a classified remote sensing image. This has been done in a lot of fields. Geologists, hydrologists and other experts have been making maps using remote sensing images for some time. In this case they mapped the parameter "poverty".
Thought not. RACE is the number one predictor of poverty, but this article (and most of the cretins on Slashdot) appear to believe that LAND MASSES magically make one group of people more intelligent than another. LOL.
So we know who to build walls around to keep them out.
Can easily identify poverty here in the U.S. All you need to see is a liquor store, family dollar, a title pawn and at least one place that sells nothing but 22" rims.
This has fuck nothing to do about helping a systemic social problem. There a plenty of homeless people living under bridges, in all major cities, that those satellite won't see. People that do see them, don't want to, or are emotionally blind anyway.
Damn hard to find on the ground ...
"Consensus" in science is _always_ a political construct.
I would think locating poverty isn't the problem. Do we really not know where the poor people are? The article is all about some huge international agency making a determination where best to send aid. I'll go out on a limb and say satellite imagery isn't going to make any of those more effective.
This posting is provided 'AS IS' without warranty of any kind, implied or otherwise.
https://xkcd.com/1138/
If something is so important that you feel the need to post it on the internet... It probably isn't that important.
Once we have found the poor what is the next step? Drone Strike?
Repeal the 17th Amendment TODAY! Also Please Read http://www.gnu.org/philosophy/right-to-read.html
I don't know why this is news. Givedirectly.org has been doing this for years. (https://www.givedirectly.org/operating-model)
Given the absolute poverty that overwhelmingly covers the Continent, it would be better to map areas WITHOUT poverty as they are few and far between (even Libya has a 33% poverty rate).
Browsing at +1 - no ACs, I ignore their posts. So refreshing!
I guess ivory towers are outdated.
Politics; n. : A religion whereby man is god.
I think the BBC needs to look in a dictionary for the difference between "predictive" and "indicative".
Satellite imagery can be less dangerous, slow and expensive than gathering the data on the ground.
The opposite of less dangerous, slow and expensive is not the same as safer, faster and cheaper... although I think that is what you meant.
Phrasing things in the positive is usually not as less unclear.