Dinosaur Revolution Episodes III & IV on tonight on Discovery Science

Just a quick note, for those looking forward to the last two episodes.  They will be showing tonight on Discovery Science at 9 and 10pm (check local listings).

Reign of the Dinosaur Revolution

Copyright the Discovery Channel

One of the projects I've worked on the last two years was Dinosaur Revolution - although for most of that time it had the working name "Reign of the Dinosaurs" - which is still how I think of it in my head.  I'm sure I'll get over it.

Two of the episodes aired this last Sunday(September 4th) and the last two air this Sunday (Sep 11th).  (Note! The airing of episodes III  & IV have been postponed, as Discovery felt that the show wasn't appropriate for September 11th.  Thanks to Tom Holtz for point that out!)  I'm sure there will be other showings.  Anatomically-speaking, the dinosaurs will be the best to yet reach the screen (although there will be a few recent discoveries that couldn't get worked in on time).  The artists working to create these dinosaurs were about as good as it gets when you need to combine talent and knowledge of dinosaurs into one package.  The "story" in the episodes is more ambitious, attempting to hook viewers with no narration (although some minimal narration did get added late in production).  How well it works for you is probably a matter of opinion, although I enjoyed it.  Regardless, the show is well worth your time.

The reason I bring this up is over my long association with the project I've developed a new appreciation for how difficult it is to get anything on TV, let along maintain a specific scientific or artistic vision.  That might actually make for a good post or two.  But first I want to open this up for discussion.

So, who saw it, and what did you think?  Some of you commented on Google+ - feel free to cut and paste your response over here if you want (or else come up with something even snazzier to say).  I'll talk more about the experience, and the challenges, in the days to come.

Mike Habib's Great Flying Skeletals: Perspectives from Pterosaurs

Today we get the second guest post on pterosaurs.  In addition to his extensive background in biomechanics, Mike has started a blog with Justin Hall on biomechanics - you should check it out.  Now, one with the main programming...

Great Flying Skeletals: Perspectives from Pterosaurs

Scott has graciously invited me to do a little guest post from the perspective of a biomechanist.  While Skeletal Drawing focuses primarily on dinosaurs, I am going to depart a bit on this occasion and use pterosaurs to highlight some of the biomechanics issues that can occur with skeletal poses.

The Case of Running Pterosaurs

Many of you have probably seen pterosaurs reconstructed in the popular standard pose (particularly preferred by Greg Paul) where they are in mid-sprint, like so:

From here.  Copyright Gregory S. Paul.

It's an impressive pose for a flying animal.  A lot of people really like the look, and it lines up nicely with the same pose in birds, to which pterosaurs are often compared.  There's just one (big) problem with it: pterosaurs probably never sprinted around on their hindlimbs like the reconstructions show.

In the case of pterosaurs, the "standard running pose" is typically presented as a launch pose.  However, in the late 90's, Jim Cunningham made a strong case for quadrupedal launching in Quetzalcoatlus at a series of presentations for both engineers and biologists.  In 2008, I published a manuscript on a sizable comparative study I ran on bone structural strength estimates in the forelimb and hindlimb, which demonstrated that most pterosaurs probably launched quadrupedally rather than bipedally.

Now, I know you're thinking "Oh c'mon, Mike, you just don't like those bipedal running pterosaurs because they conflict with your personal results.  You're biased!"  I may be biased in some sense, but actually, that's not the problem.  I would not mind bipedal, sprinting pterosaurs if another study had used different data to support the idea.  But the reality is that no analysis has ever produced support for bipedal launching in pterosaurs.  In fact, so far as I am aware, my paper was the first attempt at testing between the two modes of launch.  There have not been a great number of biomechanical analyses run on pterosaurs, but there were a handful back in the 1970's and again in the early 2000's.  A few of these considered their performance during takeoff, and the authors all assumed a bipedal launch mechanism, as in birds.  The key word there is assumed - those studies asked the question "if pterosaurs launched like birds, then how would it work out?", but they never actually tested if a bipedal run was likely. I think the first lesson here is this: 

Don't reconstruct skeletal images in poses the animal was not known to reach, unless you are specifically trying to argue the plausibility in conjunction with the pose, with appropriate empirical data present.

Most viewers of a skeletal reconstruction will assume that the animal could (and did) the action shown by the skeletal pose.  More discriminating viewers may consider the issue more thoroughly, but either way this gets in the way of the point of a typical reconstruction. 

A typical skeletal is supposed to show off the anatomy.  If the paper you are illustrating happens to be arguing for a specific dynamic action, then it makes sense to show the animal in that pose.  If there is a dynamic pose that others have shown to be plausible, then that's fine, too - but not as a standard pose, because there will nearly always be some animal that you come across later that can't do it.  Nearly all terrestrial vertebrates can manage a slow walk, but only some can sprint - so choosing sprinting as your standard is risky.  Inevitably, something is going to end up sprinting in your illustrations that never did so in life. 

We can make an animal do anything we want in an illustration.  Scott made an Allosaurus do a handstand.  We could make Quetzalcoatlus launch by vaulting on its beak.  These extreme examples are obvious, but less extreme cases can be difficult to detect.  The ability to render a good illustration is powerful, because it can make the action or anatomy suggested by the image seem plausible, even if it's completely false or fabricated.  If you're an illustrator, use your powers wisely.

Where Does that Wing Go?

One really tricky issue with pterosaurs is the wings - we don't know for certain where the wings attached in most species, and even if we pick a particular attachment point, there are a range of potential resulting wing shapes (if you want to read more about this issue, check out the section on flight over at pterosaur.net).

(Image from David Hone's blog.)

Of course, the soft tissue extent need not affect a skeletal reconstruction, but the typical methodology for skeletal illustrations is to include a black body outline.  Usually this can made relatively conservative and follow typical muscle contours for vertebrates, but there is still a certain amount of conjecture there.  When there is a major soft tissue structure involved, like the wing of a pterosaur, this can get very tricky.  Any wing profile you show will be taken much the same as a pose: the viewer will assume you are explicitly supporting that particular wing shape.

One way to get around this issue is to leave off the wing membrane.  A simple black muscle contour can be drawn around the wing spar and then the wing itself can be left out.  This is, from my perspective, probably the best option if one is trying to simply show pterosaur skeletal anatomy in a neutral manner.  However, if your illustration is for wide audience, then be forewarned that you will probably need to make a note that the wing is left out somewhere in the caption, or else non-specialists will be very confused.

This same problem can arise with other taxa, of course, especially swimmers - flukes and fins tend to be largely soft tissue, and sometimes there is no exact match to a bony contour (look at the tails of cetaceans, for example).  In those cases, leaving off the fin or fluke might be especially confusing, so some sort of estimate might be required - but again, there is a danger of extrapolation.  I do not know what the best option in that case would be, though half-tone might be an option for showing speculative components.

Up and Away?

The last major challenge for pterosaur skeletal illustration is probably choosing whether to show them flying or walking.  As already discussed, bipedal sprinting is not likely, but pterosaurs certainly walked around (quadrupedally, as it turns out, based on the trackways), so one could easily show them walking, which would tend to match other skeletal reconstructions and work well for the standardization aspect.  However, it can be difficult to show off pterosaur anatomy well with a walking pose, because the folded wing gets in the way.  Some illustrators may also prefer to remind the viewer that the reconstructed critter was a flying animal.  As such, there are some good arguments for a flying pose.  As a biomechanist, I tend to be happy seeing either or both options, but this does bring one final consideration for skeletal standardization, which is that any given illustrator will inevitably need multiple standards.  You can't really show a mosasaur walking, for example.  As such, it may be that a separate standard is needed for each major mode of locomotion - flyers, swimmers, and walkers, as it were. 

There are additional concerns that could be raised for pterosaurs, and for biomechanics interests, but those three general issues (plausible posing, soft tissue suggestion, and multi-modal animals) are some of the factors that speak most quickly to biomechanists like myself.  Happy reading!  Thanks again to Scott for the guest slot.

--

Mike Habib

John Conway's Note from Pterosaur-land: End the Lateral Tyranny!

Today we have the first of two guest posts that look at skeletal reconstructions from a more pterosaur-centric point of view.  I feel these posts (and there will be some more guest posts on other subjects in the not-too-distant-future) are really important.  First, it helps break the stranglehold that dinosaurs have had on the subject matter thus far on SD Blog.  And second it diversifies the voices heard on the issues that impact the science behind reconstructing extinct animals.  And finally, they mean I can get by while doing less work.

First up is a message from John Conway, pterosaur skeletal drawing-er extraordinaire (all images belong to John), who also contributes to Pterosaur.net:

A Note from Pterosaur-land: End the Lateral Tyranny!

When I first started to draw skeletals, I still very much wanted to be Greg Paul when I grew up. But even so, I was not entirely happy with the sprinting pose he uses, I felt then, as I still do, that it’s too extreme, too hypothesis-laden, and unsuitable for many animals.

I tried walking poses and static poses, but never really settled on a standard. But its wasn’t until I started my first serious skeletals of pterosaurs that I really gave the matter of posing serious consideration. I gave it serious consideration because I had to: the running launch pose that Greg Paul was using is biologically inaccurate, and most walking poses for pterosaurs seriously obscure their anatomy.

Greg Paul notes that he ignores the slight foreshortening that would be apparent because of the bow in dinosaur legs. And that’s fine for dinosaurs, because the effect is tiny. Not so for pterosaurs, as their semi-erect stance would foreshorten the humerus (possibly) and the femur significantly, meaning lateral-view skeletals give misleading information about pterosaur proportions. I was still interested in a standards pose for all the animals I was interested in, but I just couldn’t think of one. So I gave up, and just went with something that would best elucidate pterosaur anatomy: a three-view skeletal with the limbs arranged in the only biologically plausible, non-foreshortened way I could think of.

As time goes by, I’ve come thing think I made a good decision. Every single time a sit down to do a skeletal, I find that the doing three or more views requires me to correct errors that I would have missed if I were just doing lateral or dorsal views. It works for just about any vertebrate (be it a sprawler, a strider, a hopper, or what ever)

However, I will admit that these skeletals aren’t exactly the most space efficient things in the world, and they may be a little dry for some contexts. However:

Gentlemen, We Can Repose Him, We Have the Technology!

Most people these days are using vector drawing programs like Illustrator to create skeletals (and if they aren’t, they should be). It is trivially easy to move these skeletals into just about any pose we like.

When I’m making a skeletal, usually it’s for my own reference, as a base for a life-reconstruction. For this purpose, multiple views are critical, posing much less so. Posing may be more important when we are trying to make a biomechanical point, or in popular works were we are trying to get across more information about the biology of the animal. Different contexts lend themselves to different poses, and perhaps we should be working with that, not against it.

So to end, I think it very doubtful that we will be able to come up with a standard pose that works for all vertebrates—and nor, perhaps, should we. Perhaps it is good enough to aim for clearly and accurately elucidating anatomy, posing depending on context.

-

John Conway

Neutral Poses & Elmerfuddasaurus

Here's a quick look at another kind of pose: the neutral pose, which is more or less the equivalent of the standard anatomical poses used for extant animals.  I'm actually quite fond of the unassuming aesthetic of this type of pose, but alas I suspect it isn't a good candidate for a pose to standardize on.  To see why let's take a quick look at the strengths and weaknesses of the approach:

Strengths:

Better shows off the center of gravity (full-tilt running poses always look unstable...because of course they are).  A reduced burden for the author/illustrator to get a biomechanically plausible gait (although there would still be the need to get a realistic stance).  A pose like this is possibly better for some artists (e.g. 3D artists).  Certainly there's no distraction created by the pose.

Weaknesses:

 Some people might find this pose dull, although scientifically speaking that's not much of a criticism.  I suppose when used for education or popular media that could be a drawback, although arguably there's good reason for people to see dinosaurs portrayed as animals, rather than stylized carnage-machines, so the argument could be made both ways.

The biggest drawback to a pose like this is it shows off less of the anatomy, since the limbs from the far side are obscured.  It's easy-enough to fix that, by arbitrarily moving the limbs like this:

You can even show off some other pose (in this case the finders are lightly flexed), perhaps the other wrist could also demonstrate the degree of pronation that is possible (in the case of Archaeoceratops it more or less already is), which would then pack in a bit more information.  Of course if you move the other hind leg then you are pretty much back to putting the animal in a walk.

Of course you don't have to put the feet on the ground - if we're looking for poses that are more neutral about locomotion we could instead illustrate as if the animal were lying on a virtual dissection table:

Unfortunately, even if this were explicitly labeled, I suspect someone somewhere would take it as intending to show off biomechanical behavior.  Jumping.  Or dancing.  Or maybe sneaking along, saying "Be vewy vewy quiet, I'm hunting wabbits.":

So it seems to me that you probably can't have it both ways - to get the benefits of the neutral pose we'd have to sacrifice showing off as much morphological data.

Conclusions:

Neutral poses have a couple of advantages - they may benefit some types of artists, they reduce the amount of biomechanical inference that is required, and their lack of "visual excess" means they won't distract from the anatomy.  Unfortunately they also obscure more of the anatomy, and trying to correct this by moving the limbs around quickly sacrifices the very things that were an advantage to the neutral pose.

For this reason I think neutral poses may have limited appeal - and if that's the case, it probably isn't an ideal candidate for a new standard.

Skeletal Poses: Do they matter?

Ok, first stop chortling.  Then take a good look at the handstand allosaur up there.  In several respects it's scientifically accurate - the bone outlines reflect the actual morphology of the fossils, and the proportions are correct, so it's a "realistic" skeletal reconstruction.  The pose is certainly unusual, but none of the joints are disarticulated.  In these respects it's better than many of the skeletals that appear in peer-reviewed journals.  Yet I think it's safe to say that most researchers would consider that allosaur to be in a biologically implausible position.

Do skeletal poses matter?

 Is this pose just as good as any other, or are in fact some choices more useful?  After the break I'll try to make the case that choosing a pose is an important part of making a skeletal reconstruction, rather than a random after-thought.

I shouldn't have to say this, but just to be clear: I don't think Allosaurus could do a handstand.  Even attempting it would probably lead to a dramatic reduction in life expectancy. Yet if all a skeletal reconstruction is supposed to do is to show off the bones, then the only real complaint in the image above is that the left leg obscures the pelvis more than necessary.

So why not use this pose?  Certainly it would be easy to build up a "brand" around such a pose.  Yet I'd submit to you that skeletal reconstructions with inaccurate biomechanics undercut the value of a skeletal by virtue of the added theoretical "baggage". Mike Habib, clever gentleman that he is, anticipated this point in his comment on the previous article, which I'll quote below:

"...it is distracting from the point of the reconstruction if the viewer spends time trying to work out if the pose is realistic. Ideally, a "standard" pose should be a 'no-brainer' for most taxa, so that viewers can focus on, you know, the *skeleton*."

In addition to distraction, poses that are not feasible (or even just unlikely) create other problems; some authors will avoid such skeletals (perhaps even choosing a reconstruction that is otherwise less accurate).  There will inevitably be well-intentioned artists that introduce incorrect poses into their work.  And of course other scientific illustrators may be scared off of using the same pose, making comparisons between bodies of work more difficult.

If we only dealt with ludicrous poses, this may seem like a straw man argument.  So let's consider a less overt example:

That's Silesaurus, from the original description in JVP.  The shapes of the bones generally reflect the individual elements described in the manuscript, and the proportions are quite good; clearly it's intended as a realistic skeletal reconstruction. The pose is certainly not wrong in some over-the-top manner, yet there are several problems with it.  Some differences are due to different interpretations of rib orientation and pectoral girdle positioning (but that's another post...), while others are not so easily categorized.

The vertebral column in general is problematic; the flex in the base of the neck and the overly-straight back are positions that may be possible, but would not be terribly common for the animal.  The forearms are pronated to a degree that is unlikely in such a  primitive dinosauromorph.  Even more clear-cut is the position of the right forelimb.  The right humerus (the upper arm bone) is so far forward it would be completely dislocated from the shoulder socket.  Moreover, given the position of the visible part of the humerus the proximal part would be articulating with the center of the coracoid, rather than the glenoid fossa (the shoulder joint).

If the only thing you care about is the bones, then I admit that how distracting these issues are depends on how closely you pay attention to biomechanics.  But the pose isn't without repercussions; a quick image search shows that several derivative skeletal drawings have been produced that perpetuate the same errors, and a decent number of life reconstructions also exhibit those errors.

(Image from here; artist unattributed.)

To some degree this is where we get to the crux of disagreements - people are often quick to criticize as outlandish the problems that appear at the macroscopic level (Allosaurus can't do a handstand!) while ignoring the problems that are less obvious, or at least the ones that fall out of their area of expertise.  As a result I'd be willing to bet cold hard cash that the handstand allosaur at the top would not make it past the same reviewers that gave a pass to the Silesaurus paper, even though the skeletal in that paper is a less biologically plausible pose than the allosaur.

If people really want to present just the bones, and not make any statement about functional anatomy at all, perhaps researchers should consider exploded diagrams:

Exploded diagrams have a proud tradition in technical illustration, and can be done without making any statement what so ever on functional morphology.  I should note that the above diagram is a butchered version of my Styracosaurus skeletal; in a diagram prepared from the start to be an exploded diagram I would expect the limb bones and possibly even the vertebrae to not be connected as in life.  Providing all of the bones scaled (and revealing only the preserved portions) would accomplish the purely descriptive goals of a traditional skeletal (perhaps even be superior, since nothing is hidden by the limbs) and completely relieves authors/illustrators from making explicit claims about how the animal went together.

So in conclusion, the point I want to make is this:

People do not have to put realistic skeletal poses in their papers.  They can use schematic diagrams (which partially relieves the burden) or use exploded diagrams (which completely removes it).  The exploded diagram in particular conveys more morphological evidence then a traditional skeletal drawing, while being 100% agnostic about biomechanics.

If authors/illustrators do choose to do a realistic skeletal reconstruction, then they should accept the need to place them in biomechanically sound poses.  Inaccurate poses can distract from the other purposes of a skeletal diagram, and may mislead paleoartists.  Down the line if such diagrams get incorporated into educational diagrams they also play a role in confusing students and consumers of popular scientific media...but that, two, is another post.

In the mean time, remember: Poses are important!

The Great Skeletal Repose of 2011

As many of you are no doubt aware, earlier this year paleontologist and scientific illustrator Greg Paul made a fairly public hubbub when (among other demands) he requested that all other illustrators stop using the skeletal poses he popularized the last several decades.  There was quite a bit of consternation over the issues he raised, filled with both sympathy (it's hard to make a living from paleoart) and skepticism (most people don't believe Greg has any legal basis to try and lay claim to an anatomical pose - I suspect those people are correct).

None the less, on March 8th of this year I wrote:

Allowing Greg (Paul) to establish a branding around the poses he popularized is a request I'm inclined to grant; after corresponding briefly with Greg I've decided to embark on the process of reposing my 100+ skeletal reconstructions.

That lead to a lot of questions.  I will be examining in greater detail skeletal poses and how we can make them as useful as possible, but first I wanted to address some of the common questions that came up from this.  Namely...

What was I thinking???

This is the main question I get.  While it's been phrased several different ways, the crux of it is some people are concerned whether the (substantial) time investment in changing the pose in all of my skeletals is worth it.  Of which the most substantive question is:

Will they will be less useful in another pose?

Several workers wrote to me with this concern - that by altering the pose it would make my skeletals less useful, since they would be more difficult to compare directly with Greg's.  I am a strong supporter of standards in science, so I'm sympathetic to this claim.  That said, due to the aforementioned hubbub the utility of those poses as a standard is rapidly eroding as several artists are now altering their poses, or actively advocating for everyone to use their own unique pose.  Since artists are frequently somewhat conflict-averse, I expect this exodus to continue, regardless of legal standing.

Given this larger perspective, I feel that we'd be better served to find a new pose to standardize on, perhaps one that can still be compared effectively with Greg's body of work.  An open standard by design, so that other researchers/illustrators can feel free to adopt it without fear upsetting someone else who uses it.  And by starting again we have an opportunity to "reboot" the standard skeletal pose, perhaps producing something even more useful then the original.

One obvious example: the "Greg Paul" pose for theropods, though iconic, is held back by its theoretical baggage.  The pushing off the left foot while dashing around at a full sprint pose is not something that all researchers agree is possible in all theropods.  Several times while providing a skeletal for another researchers publication I've been asked to alter the pose for this reason.  I've done this a couple of times due to my own incredulity; for example I illustrated Majungasaurus in a walking pose, since I'm skeptical that it could sprint:

So by undertaking this project we can take advantage of hindsight to create a standard that is both open and potentially solves some of the largest criticisms of Greg Paul's poses.

So what, you're just going to pick the new "standard"?

I do need to pick a new pose.  Or rather several (for various groups of dinosaurs).  But it won't be much of a standard if I am the only one using it.  Instead, I'm hoping to crowd-source this discussion, involving any individuals who have a stake and wish to participate.  To that effect I'm working on a series of articles on such subjects as: Do skeletal poses even matter?  And if they do, what is the best way to go about creating a pose?  Who are we serving with these poses?  And how can we balance the sometimes conflicting needs of the "consumers" of skeletal reconstructions?

I'm actively communicating with some people, and hope to engage others to pick up the torch.  I hope to get a wide range of responses on the blog, and perhaps to inspire others to create articles on the subject.  The best results can only be achieved if we get generate a robust conversation on the subject.  I hope you'll participate!

By the way, if for some reason you'd rather share an opinion privately, feel free to email me and I can incorporate your concerns into a future discussions anonymously.