I.O.Yutyrannus

Hey, it's not every day that a completely fuzzy, nearly 30-foot long meat-eating dinosaur is described, now is it? I'm afraid my current schedule won't allow for a full skeletal of this critter for several more weeks, so consider the skull a down payment.

First, I should say that I'm not going to retread much of the excellent writing that has already been done onYutyrannus. If you'd like more in depth coverage, I highly recommend David Hone's excellent write-up on his blog Archosaur Musings. For more coverage and some reasons to question whetherYutyrannus is a actually a tyrannosauroid, check out Darren Naish's coverage on his Scientific American TetZoo blog. I'd also be remiss to not mention Brian Switek's article over at the Smithsonian website.

Photograph by Roberto Appiani 

What I will cover are some of the difficulties I've already observed in restoring Yutyrannus. The reconstruction above is based on one of the beautifully preserved skulls (there are 3!); like everything else found in the Yixian Formation, the specimens have been squashed flat. Relatively robust bones like a femur hold up fairly well, but skulls really don't. They tend to be highly three-dimensional in shape, and are made out of relatively thin elements. In particular, on theropod skulls the top and rear of the skull tend to fold upward as the head undergoes the pancake treatment of diagenesis

.Small dinosaurs with larger eyes and brains (like the juvenile Scipionyx above seen at right) exaggerate the problem even more, and unsuspecting artists can restore the skulls as having huge domes over the eyes if they don't know better. In Yutyrannus I suspect we are seeing something similar, which probably exaggerates the apparent size of the nasals (especially as you move closer to the eyes), as well as the top of the skull at the back.

If you check out the beautiful photograph of the head of juvenile specimen ELDM V1001 in David Hone's blog (the same one I've restored above), you can probably see what I'm getting at.

The skull restoration at the beginning of this article takes those things into account, attempting to return a 3-dimensional shape to the steam-rolled remains of the skull (by the way, the mandible is largely a place holder for now, the surangular is actually a fairly different shape). Below I've included a comparison of the the skull with and without those "corrections". Because there are three skulls, and because they have likely been subject to distortion from somewhat different angles, I should be able to double check this with greater precision once I get around to doing the full skeletal.

For those of you investing the time to study the comparison image, the top one is the restored version, while the bottom one treats the outline more literally. In both cases I've re-articulated the lacrimal (the bone in front of the eye) with the jugal (the bone underneath the orbit). In both cases the lower jaw is (as mentioned above) just a generic placeholder that is the correct size, but doesn't take the information from other specimens into account.

That's all the time I have to put into a new skeletal on my own whim for the moment. Until I get a chance to do the whole thing enjoy this Yutyrannus I.O.U.

When journalists attack!

As recently reported on several apparently legitimate news sources, a new interpretation of dinosaur biology has been proposed that is "so revolutionary it stands the whole world of palaeontology on its head." What is this landmark new idea that has set paleontologists agog? It's being termed the "Aquatic Dinosaur" hypothesis, and as the name implies it suggests that the Charles Knight painting you see above isn't out of date, it was just ahead of its time. And not just for sauropods, but all large dinosaurs.

If something smells fishy to you, it's not just the swamp water; something is very wrong here. First, to be clear, there is no such controversy, or even an idea that you need to take seriously. To be sure, some guy wrote an article in Laboratory News, so I've listed the evidence below in a handy tabulated format:

Literally, no data was provided in the article. The author makes references to "calculations" that were run, but they never make it into print. The article is mostly long-winded hyperbole, filled with such gems as "Dinosaurs look more convincing in water, and the physics stands up more soundly."

So the author's main point appears to be "See??! They look better in the water, so it must be true! Also, I have some secret calculations I won't bother to share with you support my aesthetic preference!"  The fact that it was in the April edition might give us pause to wonder if this isn't a big joke, but alas there are reasons to suspect otherwise (see below).

 Two general claims seem to permeate the article, that dinosaurs were just really big so water would help, and that dinosaur footprints aren't as deep as you'd expect from such big animals. Of course how deep a footprint sinks is only partially related to the mass of an animal. The surface area of the foot must be taken into account, as smaller feet concentrate the weight while large feet spread it out. That's why a woman in high heels can dent substrates that elephants won't. And of course the substrate itself matters - no animals leave tracks on concrete, while people easily get bogged down in viscous mud.

The "they're just so big" meme is also painfully wrong; there's an entire literature of biomechanics that shows that dinosaur limbs are strong enough to support terrestrial locomotion. And of course dinosaurs lack the aquatic features seen in animals such as hippos or crocodiles, which actually spend most of their time in water. Running your mouth off (err, running your text editor off?) without even bothering to read the literature is one of those "the stupid, it hurts!" sorts of moments.

From xkcd

Ok, enough ragging on "professor" Ford; he's either a crank or a practical joker (perhaps those aren't mutually exclusive?), but he's not the first person to have a loony idea and not support it with any evidence. Heck, the internet is littered with such people.

The real problem here is that his personal speculation somehow got reported as news by the mainstream press. First, if this isn't an April Fools prank, it calls the editorial judgement of Laboratory News into serious question (and if it IS somehow a prank, why was it allowed to be spread pre- and post-April 1st to other media outlets?). Amusingly, on page 17 of the same issue of Laboratory News there is an article lamenting the state of science reporting in the news (seriously, I couldn't make this stuff up if I tried).

If you or your lab has a subscriptions to Lab News, I'd seriously consider making inquiries, or simply dropping it. If they allow this sort of thing to happen, how can you trust the rest of their articles?

More importantly, why on Earth was this story picked up and repeated by serious news outlets? Does BBC Radio 4 do any sort of review at all before they put someone on the air? Have journalistic standards sunk that low at the British Broadcasting Company? A quick listen to the audio shows the show starting out as mildly skeptical, but concluding by comparing Ford to Galileo freakin' Galilei!

W. T. F.?!!

Galileo, you may recall, did actual science and was being silenced by non-scientists due to the (presumed) theological implications of his findings. Mr. Ford (who the BBC charitably refers to as a "cell biologist" despite being more of a media gadfly and author of popular books and articles, not a publishing scientist) is not doing science - he in fact seems intent on ignoring science at all costs - and was simply being refuted by an actual, you know, paleontologist. Yet they whipped out the Galileo reference!

Which honestly begs the question of whether anyone should bother listening to BBC Radio 4. To be fair, actual paleontology has been covered on Radio 4 and it seems to otherwise have solid programming, but the BBC should move swiftly to clear this up if they don't want a permanent stain on their credibility.

Most of the web and print articles are based on the BBC interview, but that doesn't exonerate them; not a single one of them bothered to inquire as to whether there was any real science here, and when they did contact paleontologists, they presented it as another "side" in a debate, rather than the debunking of junk Science.

Regular readers have already seen that sources like Scientific American can get even basic anatomical facts wrong, but this goes well beyond an incorrect fact in an otherwise solid story; it's misleading through and through. In a follow up article the Telegraph directly compares the aquatic dinosaur nonsense with actual research, in the process repeatedly mutilating the concept of a scientific theory.

This stuff really matters. We live in a world where huge swaths of people don't understand basic scientific concepts, and this sort of nonsense just makes it harder to teach. Worse, listeners that were sympathetic to the reporting will become disillusioned when they find out the reality of the situation, possibly making them view all science more cynically (or simply avoiding science altogether).

We deserve better science reporting than this. The BBC and everyone else who carried this story should be ashamed. Perhaps the best way to sum this up is in grand internet fashion:

Carnotaurus - delving into self-parody?

This is Carnotaurus sastrei, a theropod that seems to be little more than a mouth with a set of legs to carry it around. Carnotaurus belongs to an aberrant group of theropods called abelisaurs, which dominated much of the southern hemisphere during the Cretaceous. While all abelisaurs appear odd to our tetanuran-biased eyes, it seems like Carnotaurus is striving for weirdness as a means to its own end; as if it were making some sort of meta-commentary on abelisaur diversity.

I should take a moment to make a public service announcement: I apologize for my absence from blogging and other social media that last several weeks - I've been producing more than a few new skeletals (on a schedule), so time has become a scarce resource. On the upshot, several of the new skeletals address blog-worthy topics, so I'm going to produce some shorter posts that examine them.

One of the questions raised in the comments of a previous post involved the hyoid bones - the bones that support several muscles, including in dinosaurs the tongue musculature. Being long, slender bones that don't directly articulate to other bones, hyoids are often not found (and other times are probably not collected or m-identified). Even when they are found, their lack of a direct connection to other bones makes restoring them problematic. In Carnotaurus this wasn't a problem, as they were found in direct association with the underside of the mandible, apparently in their life position. The fact that extensive skin impressions were found with Carnotaurus reinforces the likelihood that the soft tissue holding the hyoid in place had not been disturbed.

In the skeletal above you can see part of the hyoid sticking out from under the bottom-rear part of the jaw. Part of the hyoid is obscured, but there's not much I can do about that. Having the hyoid is actually pretty useful - the trachea and esophagus have to pass through it (or above it), so having a properly positioned hyoid constrains the throat tissue. 

Carnotaurus is also striking due to its advanced arm reduction - in side view the arms almost disappear, as they don't even extend past the stomach. What on Earth could such arms be used for? Hold on to that thought, as I'm not ready to go public with my thoughts on that just yet. But it sure reinforces the "legs carrying a head" image.

Finally, for those of you paleo-artists out there considering Carnotaurus as your next paleo-subject, I wanted to point out something not obvious in side view: Carnotaurus is really flat on top. The transverse processes on the tail actually stick up in a V-shape that reaches just about to the level of the neural spine. Persons & Currie recently described how this impacts the tail muscles (TL;DR version is the tail is very wide at the base, and quite flat on top).

From Person's & Currie

The back and neck also have osteological structures that raise up to, or above the level of the neural spine. So most of the animal should be restored as having a remarkably flat top. Given how narrow the head is, this must have produced a really strange life appearance. 

A final note on the skeletal itself: while Carnotaurus is a wonderfully complete specimen, the lower legs and much of the tail is missing, so those elements were restored after its close cousin Aucasaurus.

The evolution of (my) Acrocanthosaurus

WithSpinosaurus temporarily out of the way, we're going to take a closer look at Acrocanthosaurus. This series is going to include a post on what we know and don't know about Acrocanthosaurus, how to restore the skeletal in multiple views, and how to restore the muscles. At the end of that series I'll also comment on some areas of soft-tissue variation that artists should keep in mind when they envision "their" Acrocanthosaurus.

First though, I wanted to take a moment to look at how my own reconstruction of Acrocanthosaurus has changed over the last decade. With any luck some of my earlier errors in methodology might help others who want to do skeletals. Also I hope to provide some insight to how I update skeletals over time, and the importance of revising your work as new data is published.

Although Acrocanthosaurus is hardly the best known theropod, it provides more than its share of challenges when attempting to reconstruct it. In my case, I attempted the original skeletals during what I'd call a methodological nexus - it was one of the first skeletals I attempted within an entirely digital environment, and to some degree the initial reconstruction suffered as a result. I had developed many techniques when I executed skeletals in pen and ink, and most of those translated fairly well during the years (roughly 2000-2004) when I used a hybrid method of digital and ink work. Alas, attempting to work entirely inside a computer forced me to rediscover how to accomplish the same things inside of Photoshop, and as a result the first couple of attempts were actually a step backward in some ways. Luckily I stuck with it, and the results are now far better then anything I accomplished in the "analog" world.

In the beginning...

Acrocanthosaurus itself is not a new dinosaur. It was described in 1950, and it was noted at the time that the specimen was a carnosaur with enlarged neural spines on the back. What really brought Acrocanthosaurus to my attention, however, was the reconstruction of NCSM 14345, the "Fran" specimen, which was prepared, molded, and mounted by Black Hills in the 1990s. One of those specimens became part of a travelling display that I contributed to, and I was inspired by the fully restored mount, as well as my ability to take lots of photographs of the mount.

Alas, that was in the "olden days" when cameras captured light on sheets impregnated with silver nitrate rather than CCDs, and I never did scan in those photos. I still had them in 2003, but they appear to be one of many casualties of moving around frequently.

I was also attending the University of Wyoming, and their Geology library had supplied valuable gifts: descriptions of Acrocanthosaurus specimens by Jerry Harris (1998), and Currie & Carpenter (2000). Armed with proto-pdfs (read: xeroxed copies), lots of photos, and an abundance of enthusiasm I sat down to create my first all-digital skeletal reconstruction.

The tomb of the unknown skeletal...

Directly above, what you don't see is my first Acrocanthosaurus skeletal. I'm not being shy, I just didn't back up the original very carefully, and eventually the hard drive it was on suffered a systemic failure. Cloud storage was a pie-in-the-sky dream at the time, so I've lost several "original" skeletal files during the course of computer failures over the years. Luckily I've been anal retentive enough to keep current versions of skeletal files on multiple hard drives, so I haven't totally lost a reconstruction (at least, not a digital one).

What I can say is that in many ways my first attempt was an unmitigated failure. For starters, I didn't actually have the papers I mentioned above in their entirety. I'd read them in Laramie, but at the end of the semester I only photocopied the parts I thought I'd need (hey, it took time and money to copy texts in those days!). And of course the photocopies didn't always do justice to the original figures.

Instead I had to rely strongly on the photographs I had taken of the Fran mount. Even that was fraught with uncertainty, as I hadn't been able to take orthographic photos of the mount. Also, there were errors in the fully restored mount, but without all of the text from Currie & Carpenter I didn't always recall what was restored and what was cast from original bone. The results were predictably poor.

You don't  have to take my word for it though. I posted that first attempt to the Dinosaur Mailing List in early July of 2003. Jaimie Headden and Waylon Rowley made quick and (deservedly) pointed replies. I had missed several characteristic parts of the tail and neck vertebrae, and a bunch of other minor details had simply been missed.

What happened? For one thing I really didn't have enough data on hand. But more importantly, I was distracted by having to solve the technical problems of a new medium. Digital skeletal reconstructions have many advantages, but at the time they were lost on me as I struggled to figure out how to simply do the things I'd taken for granted in the "analog world".

The Acro strikes back

With a bit of work, I quickly produced the skeletal above, which addressed some of the basics. It wasn't a horrible attempt - it accurately captures almost all of the proportions, and many of the changes since have been either due to newer research getting published, or on changing interpretations in soft tissue reconstruction.

One thing mistake in this earlier version is that the neural spines were too tall - I had based their height on the mount of the Fran specimen, but it turned out that neural spines were not complete in that specimen (at least not the ones in the back, sacrum, or the front part of the tail). A review of other specimens ruled out such a grandiose neural spine height, and that also has implications for paleoartists wondering how to illustrate the back.

Two important papers were published on Acrocanthosaurus after that early skeletal. One was on the forearm, which showed that the arm couldn't actually reach as far forward as I'd illustrated it (and also clarified details of the size and shape of all the elements). Another paper was published in the last year that updated our understanding of the skull of Acrocanthosaurus. When I was asked if I could supply the skeletal to an upcoming book, it was clear that I had to revamp the skeletal before sending it along...

Back to the future

Which brings us back to my current skeletal. In addition to the new skull and arm data, the newfangled Acrocanthosaur naturally sports my new skeletal pose. So how crazy different is it? In some ways it's pretty similar - the overall dimensions really didn't change, and that's a good thing. A bunch of more subtle soft-tissue changes took place (at least some of which will get to star in their own post in the future), but a couple of obvious ones involve the tail and the neck.

The tail in the newer one has a heavier base, reflecting the research by Persons and Currie on tyrannosaur tails that I wrote about last year. The tail also is a bit less bouncy. The current skeletal is moving at a more sedate pace, and its tail is no longer bouncing along like a dropped garden hose. The neural spines on the tail have also been updated, with the spines on the front of the tail (near the hips) shorter to reflect other specimens, and the ones in the middle a bit taller, again based on other specimens.

Looking at the neck, the silhouette is no longer shrink-wrapped as tightly to the skeleton. I will probably address the "why" part of that in a later post, but suffice it to say that the newer Acro would have an easier time wolfing down large pieces of meat it tore off a carcass.

A final set of changes were made in the pectoral girdle (the shoulder region). I added a furcula which, while not found in Acrocanthosaurus, now appear to be a primitive feature found in all theropods. Additionally, I used to illustrate a large cartilaginous presternum that split the coracoids apart (you can see it poking out the bottom and front of the chest area on the older skeletal).

Reflecting the articulated chest regions of other non-maniraptoran theropods, I changed it to a smaller presternum, that would have ended sooner and allowed the coracoids to almost contact one another along the midline. This slightly changes the outline in side view, but in front or top view has the effect of narrowing the front of the torso across the shoulders.  Now if only someone would produce multiple-angle skeletals of Acrocanthosaurus to show this off...

Dawn Thief

A quick post (and a new skeletal) today, while I apply a bit more polish to the Acrocanthosaurus series. To satisfy all of your skeletal-drawing-based-amusement needs I give you Eoraptor lunensis, one of the most primitive dinosaurs yet discovered.

How primitive? So primitive that we can't actually answer that question with any certainty right now. Eoraptor is one of those taxa that bounces around a lot in different studies. When it was originally describe, it was thought to be one of the most primitive theropods known. Other studies suggested it might be more primitive than the split between theropods and sauropods. Recently, some have even found it to be on the line leading to sauropods!

All three positions have shown up in recent studies, so for now at least the answer is "we're not sure". Why all the trouble figuring out who is Eoraptor's closest relative? Basically what it boils down to is that Eoraptor is so primitive that this is what the common ancestor of theropods and sauropodomorphs would look like. No matter where Eoraptor ends up on the dinosaur family tree, the difference between it and animals at the other position will be very small indeed.

If you compare Eoraptor to Panphagia (which I examined in this post), which is a well-supported basal sauropodomorph, you can see just how similar the two are. The problem is sort of like being handed photographs of all of the Kennedy's when they were two years old and being asked which one was closest in age to JFK - there's a correct answer, but it's awfully hard to tell from the information you have.

As for the skeletal reconstruction, Eoraptor didn't present nearly as many challenges as some other taxa do. For one, it's know from fairly complete remains. It would have been nice to have a more detail description of the animal in print (the original papers leave something to be desired along those lines), but luckily the specimen is available in detailed orthographic photos, which do a nice job of supplementing the published data.

That's all for now!

The Great Skeletal Repose of 2011: A Retrospective

Well, it's 2012, so the Great Skeletal Repose of 2011 must officially come to an end. Most of the bipedal skeletals in my collection have been reposed much like this Velociraptor. I had plenty of things to say, and we saw some great discussion by guest writers, but when it comes right down to it, the issue feels incomplete without some sort of summary as to how I got here, and what's left to do. So let's take a quick look at where things stand now...

To some degree, the walking pose shown above was selected by acclimation. When I started to show off different types of poses, by far the most popular was the walking pose you see above. And I want this pose to be one that other scientific illustrators can feel free to adopt, so widespread can only enhance that proposition. But it wasn't just a popularity contest - there are several practical reasons why this walking pose became the winner:

The Good

1) Utility - Greg Paul of course will continue to use his pose, and a number of previously published skeletals by other authors (including all of mine up until last year) had adopted the same pose. By selecting the walking pose the retracted left leg remains unchanged, allowing for a easy comparison of the proportions. This was probably the biggest factor.

2) Functional Aesthetics - The old pose of animals sprinting along at a lively clip tended to impose a specific hypothesis of activity on the animals. While in some cases dashing along may have been quite likely, it still required that a research who wanted to use the skeletals to swallow that hypothesis, whether they agreed with it or not. With Velociraptor that wasn't unlikely, but with larger theropods it became needlessly controversial, and with graviportal taxa like therizinosaurs the results could be laughable.

3) Laziness - I prefer "efficient" over "lazy", but no matter what label you place on it, this pose required a minimal amount of alteration to my existing skeletals. And the stark reality is that when you have to repose hundreds of technical illustrations that time adds up. Quickly. Of course this reason would not have been sufficient if it weren't for the more important points 1 & 2, but it sure was a nice bonus.

Does that mean I'm thrilled with the outcome?

Yes and no. Since I'm starting with a blank slate, it would have been fun to come up with something truly distinctive. Yet the allure of the new wasn't worth sacrificing how useful the skeletals were for comparative purposes. Also, thanks to lots (and lots) of time spent pondering the issue, and to the extra stimulus provided by Mike Habib and Jon Conway's excellent guest posts, I've come to some unsettling questions that are still unresolved.

The Bad

1) Whither goest utility? - As I wrote way back in the halcyon days of...spring 2011, after I announced that I would relinquish the old pose and select a new one I got many requests that I refrain from this. Almost all of them were concerned with losing the ability to easily contrast my skeletals to others after the repose. I was (and am) sympathetic to that plight, and selected a pose that minimized the "damage". 

Yet I also had a disconcerting realization: Both Greg Paul and myself had been varying the pose of the forelimbs for years and no one ever bothered to complain about the loss of utility. Sometimes we've both illustrated maniraptorans with the arms flexed into their folded-wing pose, sometimes not. Less advanced theropods obviously never adopted such a pose, so their arms often hang listlessly. My tyrannosaurs went from a similar "hanging out" pose to one that reflected the work done by Lipkin and Carpenter. Why was the issue never broached? Are forelimbs less important for comparative purposes than hind limbs? Or do we naturally gravitate towards the larger structure because of how our visual cortex's work? I don't know, but I'm unsatisfied by the discrepancy.

2) Is variety the spice of life? - Jon Conway also brought up a good point in his guest article, that there isn't a single pose that best serves every need. This is certainly true, and while I still feel that within groups making poses similar is useful, I also have to admit that in some ways the job has just begun.

3) That job has just begun - Oh yeah, and another thing. Turns out there are quadrupedal dinosaurs too. Who'd have thunk it, eh? Despite the obvious and objective superiority of theropods, prosauropods, and basal ornithiscians, there's still a lot of four-footed critters in my skeletal collection, and I'm going to have to come up with a pose for them as well. Two actually, since the graviportal species will need a pose that is different from the quadrupeds with flexed limbs. Ah well, that just means that 2012 will also need to have a Great Skeletal Repose as well.

An end and a beginning

So we've come full circle. I've adopted a pose for the bipedal dinosaurs, but still have to come up with (two!) new poses for quadrupeds. I still am very much interested in soliciting outside opinions on the subject, but I also want the blog to move back to posts about anatomy and reconstruction, rather than a continuing series of posts on the technical issues behind selecting a pose. So expect to see the occasional progress report on the quadrupeds, but don't expect it to dominate space on the blog this year.

If you have a strong opinion on the subject, don't hesitate to email me (or use that Gchat thing). In the mean time, I really do have a series of upcoming posts on Acrocanthosaurus and Spinosaurus anatomy, as well as the trials and tribulations of reconstructing skeletals in multiple views.

Stick around, won't you? 2012 should be an interesting year.

Revisiting the Fisher King

I know, I know, my last post promised a series on reconstructing Acrocanthosaurus in multiple views - bear with me, as this is actually part of that series. Remember that both animals have stuff sticking up on their backs, so I want to be able to compare and contrast those elongated neural spines...and how those differences should impact reconstructions of the animals. But to do that I had to update this skeletal, as new information had rendered the older one no longer tenable.

Besides, Spinosaurus is cool! For one, it's the only dinosaur in the Jurassic Park series to tangle with a T. rex and emerge victorious (no matter how unlikely that outcome was). It's probably the longest theropod we know of, and may have been the heaviest as well. Yet counter-intuitively it shows specialization for piscivory (fish-eating)...maybe in JP3 the spinosaur mistook the T. rex for a really large lung-fish?

Tongue firmly out of cheek now, Spinosaurus has lit up imaginations partially due to its size, but also because there was so much you had to imagine to try and reconstruct the animal. Until the last decade or two it was sort of a theropod Rorschach test where you could project any sort of oversized monster theropod onto its scant (and now lost) remains. This brings a thrilling "Sherlock Holmes" quality when trying to imagine the living animal, but for most of the last century serious attempts to reconstruct Spinosaurus have been more frustrating than titillating.

Darren Naish has an excellent write up of the history (and tragedy) of of the type specimen of Spinosaurus, which I won't duplicate here. The long and short of it is that WWII claimed the fossils as another victim of the conflict. The already-meager remains lost, paleontologists were stuck with the original description and some somewhat uninspired sketches as the only link to the past.

A series of fortunate events occurred in the latter half of the 20th century that allowed for a more accurate interpretation of Spinosaurus to emerge. For one, other spinosaurids were found. Baryonyx from the U.K., and Nigerian Suchomimus, started to paint a more complete picture of what these animals were like. They had bizarrely long snouts that seemed to resemble a gharial as much as a traditional theropod. Suchomimus even had a smaller version of the enlarged neural spines on the back:

The amusingly-named Irritator from South America further clarified the relationships and anatomy of spinosaurids. But the real breakthrough was the re-discovery of several photographic plates of the original material. While Spinosaurus wasn't the most complete specimen, having photographs at least made it possible to ensure that what was found is incorporated accurately into a reconstruction.

Among other details, the image also shows what had been the basis of attempts to restore the shape of the elongate sail or hump on the back: Stromer's original interpretation for the position of the elongated neural spines. In particular, notice that the tallest one is set directly in front of the sacrum here, while the only associated tail vertebra (at the far left of the picture) has a very short spine. That has lead most people to infer that the spine started quickly after the neck, grew to ridiculous heights over the pelvis, and then quickly dropped off again. Indeed, this is the interpretation that I used in my first attempt, and has been widely seen in such disparate and reputable scientific endeavors as Jurassic Park 3, the Carnegie Collection of "museum quality replicas", and Greg Paul's reconstruction in his Princeton Field Guide to Dinosaurs.

And they're in excellent company (whereby I arbitrarily define myself as "excellent company"). I had been concerned with Stromer's original interpretation for the placement of the tallest neural spinse - no vertebral body (centrum) was preserved, but the change in the angle of the spine seemed pretty extreme compared to the previous dorsals, especially right in front of the sacrum. My solution was to assume it was a sacral neural spine. This largely preserved the traditional appearance of the "sail", but provided a bit of breathing room for the change in orientation.

Luckily for us, Andre Cau and Jamie Headden were busy mulling over this specific issue, and came to a much more likely conclusion, that the backward-oriented neural spine was actually an anterior caudal. Looking at a host of dinosaurs with elongate neural spines, they noted that in general you never seen backward-canted spines in front of the hips, you always see them after it. There is a bit more detail to the argument (which I encourage you to read on their blogs), but in essence they make a very compelling case.

And so it was back to the virtual drawing board. I made some other corrections from my previous attempt - there had been some scaling issues with the neck vertebrae that had given my reconstruction a thinner Baryonyx-like profile in the neck. Also, it appears that the necks of these animal don't have as much of the traditional theropod S-curve, so that was changed as well (although I still don't buy the extreme hang-dog look that Greg Paul has started to restore his spinosaurs with). The results are a stockier animal, with a more elongate sail (or hump):

Looking at the rigorous reconstruction, it's clear that there's still quite a bit of uncertainty in the skeleton, although not all of the missing parts are created equal. Much of the pelvic girdle is known from Irritator, as is the back of the skull. Also, some unpublished specimens shed light on this, even if they aren't documented well enough to be official parts of the reconstruction. Still, there's a bit of ambiguity about the exact limb proportions, the length of the tail, and the exact shape of the sail.

Speaking of which, how should those tall neural spines be restored by artists doing life reconstructions? Is it a sail, was it supporting a hump of tissue like a bison, or was it simply a muscular ridge? We'll get back to that subject in a bit, after looking at Acrocanthosaurus.

Until then, best wishes to one and all for a wonderful 2012!