Paleontologists turning to neural networks to find new dig sites

November 9, 2011 by Bob Yirka, report

( -- For hundreds, if not thousands of years, researchers of one kind or another have dug into the earth in search of clues to help explain our past. In so doing they have found evidence of ancient peoples that roamed around in an environment that we can only vaguely imagine. Such evidence is generally composed of remnants of dwellings, clothing, tools and most especially bones. Traditionally, such relics have been found either by accident or by serious-minded teams of professional scientists scanning likely terrain and having at it with small axes and shovels.

Now however, is helping such teams better their chances. , for instance can highlight certain types of geographical regions that are similar to others that have been found to contain fossils, thus reducing the amount of ground that paleontologists must cover. But even that can only reduce the work so much. Enter Bob Anemone, a and his team from Western Michigan University; they’ve developed a computer system that can scan satellite images for them and highlight the areas that are most likely to contain fossils, thus increasing the chances of finding fossils while doing far less work. They have published their findings in Evolutionary Anthropology.

To create their system, the team turned to neural networking technology, which essentially means creating computer software to mimic how the human brain works. It’s all about pattern matching and learning from what has been learned already. To apply neural networking to the science of finding, the team fed the system satellite images which were analyzed to separate out different light wavelengths corresponding to different types of terrain. Then the system was “taught” to look for certain patterns by showing it places that were already known to contain fossils. After that, images taken of virgin territory were entered into the system and it highlighted areas that matched what it had learned from existing sites. With that information in hand, the team can then head out into the wilds with far more confidence of finding something worthwhile.

So far, the whole idea is mostly theory, though the system did correctly find known fossil sites that it wasn’t told about beforehand 79% of the time in testing. And of those very small areas that it flagged as especially likely, it was right 99% of the time. Interesting in the lab, but the team won’t find out just how well the system really works till they actually travel next summer to a target they’ve picked out, the Great Divide Basin in Wyoming, and start digging.

Explore further: Study: Mentoring can build great leaders - if they can handle the truth

More information: Finding fossils in new ways: An artificial neural network approach to predicting the location of productive fossil localities, Evolutionary Anthropology, Volume 20, Issue 5, pages 169–180, September/October 2011 DOI: 10.1002/evan.20324

Chance and serendipity have long played a role in the location of productive fossil localities by vertebrate paleontologists and paleoanthropologists. We offer an alternative approach, informed by methods borrowed from the geographic information sciences and using recent advances in computer science, to more efficiently predict where fossil localities might be found. Our model uses an artificial neural network (ANN) that is trained to recognize the spectral characteristics of known productive localities and other land cover classes, such as forest, wetlands, and scrubland, within a study area based on the analysis of remotely sensed (RS) imagery. Using these spectral signatures, the model then classifies other pixels throughout the study area. The results of the neural network classification can be examined and further manipulated within a geographic information systems (GIS) software package. While we have developed and tested this model on fossil mammal localities in deposits of Paleocene and Eocene age in the Great Divide Basin of southwestern Wyoming, a similar analytical approach can be easily applied to fossil-bearing sedimentary deposits of any age in any part of the world. We suggest that new analytical tools and methods of the geographic sciences, including remote sensing and geographic information systems, are poised to greatly enrich paleoanthropological investigations, and that these new methods should be embraced by field workers in the search for, and geospatial analysis of, fossil primates and hominins.

Related Stories

Smart materials that get bone to heal

November 4, 2011

Bone tissue is very good at self-healing, but in many situations the natural healing process is not sufficient. In a dissertation at Uppsala University, Sonya Piskounova shows how functional materials that she and her colleagues ...

Cool roofs really can be cool

November 4, 2011

A recent Journal of Climate paper by Stanford’s Mark Jacobson and John Ten Hoeve (2011) on urban heat islands and cool roofs is a useful contribution to the literature. However, their results regarding white roofs are ...

Tally for violence 'shocking'

November 8, 2011

The economic costs for women who leave an abusive partner do not end once they walk out the door. In fact, the ongoing costs in Canada equal a staggering $6.9 billion annually.

New Duqu virus linked to Microsoft Word Documents

November 4, 2011

I new virus has cropped up in various countries across the world and its target appears to be corporate networks. The Duqu virus, first noted last month by a laboratory at Budapest University, has now been spotted in several ...

Recommended for you

Study sheds new light on ancient human-turkey relationship

January 17, 2018

For the first time, research has uncovered the origins of the earliest domestic turkeys in ancient Mexico. The study also suggests turkeys weren't only prized for their meat—with demand for the birds soaring with the Mayans ...


Adjust slider to filter visible comments by rank

Display comments: newest first

1 / 5 (5) Nov 09, 2011
For hundreds, if not thousands of years, researchers of one kind or another have dug into the earth in search of clues to help explain our past . . . They have published their findings in Evolutionary Anthropology.

a.) Life is in a state of continuous evolution

b.) Because Earth's climate has always been changing

c.) Because Earth's heat source - the Sun - is unstable

d.) The remains of the supernova that gave birth to the Solar System five billion years (5 Gyr) ago, and

e.) Still changes every day as Earth orbits around the pulsar that is hidden from view by a glowing sphere of waste products (91% H and 9% He) that is called the photosphere.

Review of Observations:

"Neutron Repulsion", The APEIRON Journal, in press (2011)

Today's news:
5 / 5 (3) Nov 09, 2011
Man, you are really far gone. This is about paleeontology (look it up before posting) - not your loony/unsubstantiated theories on star formation.

Quit spamming the forum unless you have something to say about the article or in response to someone else.

And what is your spamming supposed to accomplish, anyways? You just make yourself look ever more ridiculous by trying to sell it in off topic sections. What are people supposed to say:
"Whoa...this has nothing to do with the subject, but the author has some neat points in his publications"?

What do YOU think someone will say if you can't even stick to the subject at hand when posting? More likely:
"Whoa...he is so delusional as to think his theory fits here somehow. What a crackpot."

5 / 5 (3) Nov 09, 2011
@omatumr, "Neutron Repulsion" has nothing to do with the application of neural networks to Evolutionary Anthropology, you sad, pathetic, old man. I would encourage you to spend more time with your family instead of this "Neutron Repulsion" foolishness but you've already done enough damage to your own children:
1 / 5 (2) Nov 09, 2011
One more example of nonsense.
whilst "antialias physorg" is correct in his criticism he should look at the end of the first line of his third paragraph.
The word is anyway, not anyways.
There is no plural for anyway.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.