Sep 292023
 

OK, not exactly a surprising result but still, a fantastic experimental achievement: Yes, Virginia, antimatter falls downward.

Why is this important? Well, we kind of knew that it was inevitable. I mean, if antimatter were to fall upward, it’d have meant that our entire understanding of gravitation is wrong. That even our understanding of special relativity is probably wrong.

So it was a rather safe bet that antimatter follows the same geodesics as normal matter and falls downward.

But physics, lest we forget it, is ultimately not about erudite speculation. It is about experiment and observation.

And this amazing experiment achieved the almost impossible: it observed antihydrogen atoms in a vertical vacuum chamber at cryogenic temperatures and, as expected, most of those hydrogen atoms ended up at the bottom.

 Posted by at 12:33 am
Sep 162023
 

My friend John Moffat has a finite quantum field theory that, I think, deserves more attention than it gets.

The theory is nonlocal (then again, so is quantum physics to begin with). However, it does not violate causality. So its nonlocality is a mathematical curiosity, not a physical impossibility.

The essence of the theory is present in the form of its “nonlocal field operator”. Given, e.g., a scalar field in the form \(\phi(x),\) the field is transformed as

$$\tilde\phi(x)=\int d^4x’f(x-x’)\phi(x’).$$

Now if we just used the Dirac delta-function \(f(x-x’)=\delta^4(x-x’),\) we’d get back \(\phi(x).\) But what if we use some other function, the only restriction being that \(f(x)\) must be an entire function, which is to say, unambiguously defined without poles or singularities over the entire complex plane?

Well, then, assuming again that \(f(x)\) is an entire function, we can integrate iteratively in parts, until we arrive at an expression in the form,

$$\tilde\phi(x)={\cal F}(\partial_x)\phi(x),$$

where \({\cal F}(\partial_x)\) is a derivative operator, typically some power series in the form \(\lambda_i\partial_x^i\), acting on \(\phi(x).\)

Why is this good for us? Because this field redefinition can suppress high-energy divergences in the theory, essentially doing away with the need for renormalization, which, of course, is a Big Claim indeed but I think John’s theory works.

John’s first substantive papers on this topic were titled Finite quantum field theory based on superspin fields (J. W. Moffat, Phys. Rev. D 39, 12 (1989)) and Finite nonlocal gauge field theory (J. W. Moffat, Phys. Rev. D 41, 4 (1990)). Unfortunately these papers predate arxiv.org so only the paywalled versions are available. They are beautiful papers that deserve more recognition. More recently, John wrote another paper on the subject, collaborating with a student. One of these days, I’m hoping to spend some time myself working a bit on John’s theory because I believe it has merit: The theory appears to remain causal despite the nonlocal operator, and by doing away with the need for renormalization, it makes canonical quantization almost trivially possible. I keep wondering if there is, perhaps, a catch after all, but if that’s the case, I have yet to find it.

 Posted by at 1:37 pm
Sep 122023
 

I gave a talk on the Solar Gravitational Lens in Montreal back in July, using the above title.

Video of the talk is now available online, courtesy of the Interstellar Research Group.

I just listened to it myself and I didn’t cringe too much hearing my own voice or watching myself, which is probably a good sign?

 Posted by at 12:31 am
Aug 232023
 

Chandrayaan-3 landed safely on the Moon, cementing India’s position as a space superpower.

What can I say? Congratulations! Not sure who the gentleman is in this image that I saw on Twitter, but he certainly looks happy.

 Posted by at 12:48 pm
Aug 212023
 

Russia’s first probe to the Moon in nearly half a century, Luna-25, has crashed.

It would be easy to react to the news with glee, with schadenfreude. We are, after all, talking about a crash that denied a propaganda opportunity to Putin’s Evil Empire (maybe not quite as evil as Stalin’s regime but more evil, to be sure, than the USSR ever was in my lifetime).

But space exploration transcends, always transcended, national boundaries. Our petty squabbles look pretty… well, petty from the Moon. Chances are, if human beings are still around with an advanced technical civilization a millennium from now (or, if our machine descendants are still around) they’re far more likely to remember Armstrong’s first step on the Moon than Russia’s attack on Ukraine, the Cold War, or even WW2.

So this crash is sad news, Putin or no Putin. I hope India’s probe, Chandrayaan-3, is more successful. Fingers crossed. Things are looking good for now but it has yet to accomplish a tricky landing.

 Posted by at 11:57 pm
Aug 182023
 

And then there is this. The rate of increase in atmospheric methane has been rising since the mid-2000s. The curve is becoming ever steeper.

Surprisingly perhaps, it’s not from natural gas producers, industry, or vehicles. Not even cow farts.

It’s apparently in large part coming from tropical wetlands. Climate change is still indirectly responsible as it is the changing climate that changes the vegetation that, in turn, results in more methane production. But the consequences of this rise in methane levels can dwarf anything CO2 will do. A “termination-level” event, they call it, which sounds alarming and it should be: even though it does not mean our immediate termination, it may mark the termination of an epoch, just as in the past, when similar rises in methane events marked the end of the ice ages. Except that there’s no ice age at present.

 Posted by at 5:47 pm
Aug 182023
 

Yellowknife is not a large city by Ontario standards, but it is the capital city and the largest community in the Northwest Territories of Canada, with over 20,000 inhabitants.

And it is about to be evacuated entirely today, because of the imminent wildfire threat.

Yes, it’s a faraway place but it is still incredibly scary that tens of thousands of Canadians are uprooted, some taking their cars, some boarding evacuation buses or flights, fleeing their homes, traveling through landscapes that are like warzones, with burned buildings and burnt-out vehicles often in sight.

No, I won’t rant about climate change. There can be other contributing reasons behind this unprecedented wildfire season, though I bet climate change is by far the most significant contributor.

I wonder what prompted N.W.T. authorities to take this drastic step. I may be wrong but I have a feeling that the devastation in Maui was a wake-up call, and they wanted to avoid a similar disaster. Having said that, I sincerely hope that Yellowknife will be spared and its inhabitants can return in a few days.

 Posted by at 2:43 am
Aug 112023
 

Here’s a sunflower, which grew in a large planter right here on our driveway, as photographed by my beautiful wife just the other day (before Ottawa got an incredible deluge of rain):

If you look closely, there’s a bumblebee in the flower. May there be more! I keep reading about the crisis pollinating insects face worldwide, sometimes accompanied by tragic images of entire beehives, dead. Pollinating insects play an essential role in nature, including our food supply. And they seem to be in serious trouble. Climate change, habitat loss, reckless use of insecticides, whatever the reason, it might be a good idea to take this problem seriously before it is too late. (Just don’t turn it into politics please. It’s a real crisis, not fodder for virtue-signaling by wannabe liberals or progressive-bashing by wannabe conservatives.)

 Posted by at 5:38 pm
Aug 062023
 

I don’t usually like climate panicmongering but this chart that I came across today is… Well, see for yourself.

These are ocean temperatures, by the way. Oceans are supposed to be large, stable reservoirs of heat. Which they probably are, except that surface temperatures also reflect changing patterns like changing ocean currents.

This massive deviation from the 20+ year average (more than four sigmas!) is difficult to comprehend. What it says about the changing climate, I have no idea, but it is unlikely to be good news.

If only we stopped making this political. OK, well, it is of course political in the sense that we need to make collective, i.e., political decisions on how we manage Spaceship Earth. But it should not be political in the sense that the facts are not political, and the proposed solutions should be weighed by their feasibility, efficacy and social impact, not political palatability.

And for heaven’s sake, stop the dumbed down oversimplifications. Next time I hear about someone emitting “carbon”, I’ll scream. Carbon is solid at room temperature. Carbon is not carbon dioxide, just as hydrogen is not dihydrogen oxide. I have yet to see anyone drinking liquid hydrogen… or emitting carbon. Perhaps the first step to take is to give people a more decent education in the sciences so that they actually understand what carbon dioxide is, what it does in the atmosphere, what “four sigma” means, and what things like heat reservoirs are in a climate system? Is that really too much to ask? Am I being a silly elitist or something?

 Posted by at 7:59 pm
Jun 262023
 

The next time (it happens often) I hear someone complain about scientific ‘orthodoxy’ that is used to ‘stop innovation’ and prevent ‘new entrants from entering’ the field (or equivalent words), I’ll remind them that these were exactly the words used by Stockton Rush, defending the design of his ill-fated submersible Titan.

Of course the consequences are far less deadly when the subject is purely theoretical, like fundamental particle physics or general relativity. But that does not validate nonsensical arguments.

Orthodoxy is adherence to tradition or faith. Science and engineering are about testable and tested knowledge, which is the exact opposite. What folks like Stockton describe as orthodoxy is simply knowledge that they do not possess (maybe because it takes too much of an effort to learn) or knowledge they purposefully ignore because it contradicts their preconceptions or expectations.

My condolences to the families of Rush and his passengers on Titan. But foolishness has its consequences. Sometimes deadly ones.

 Posted by at 10:33 am
May 312023
 

I just finished uploading the latest release, 5.47.0, of our beautiful Maxima project.

It was a harder battle than I anticipated, lots of little build issues I had to fix before it was ready to go.

Maxima remains one of the three major computer algebra systems. Perhaps a bit (but only a bit!) less elegant-looking than Mathematica, and perhaps a bit (but only a bit!) less capable on some friends (exotic integrals, differential equations) than Maple, yet significantly more capable on other fronts (especially I believe abstract index tensor algebra and calculus), it also has a unique property: it’s free and open source.

It is also one of the oldest pieces of major software that remains in continuous use. Its roots go back to the 1960s. I occasionally edit 50-year old code in its LISP code base.

And it works. I use it every day. It is “finger memory”, my “go to” calculator, and of course there’s that tensor algebra bit.

Maxima also has a beautiful graphical interface, which I admit I don’t use much though. You might say that I am “old school” given my preference for the text UI, but that’s really not it: the main reason is that once you know what you’re doing, the text UI is simply more efficient.

I hope folks will welcome this latest release.

 Posted by at 8:54 pm
May 232023
 

In the last several years, we worked out most of the details about the Solar Gravitational Lens. How it forms images. How its optical qualities are affected by the inherent spherical aberration of a gravitational lens. How the images are further blurred by deviations of the lens from perfect spherical symmetry. How the solar corona contributes huge amounts of noise and how it can be controlled when the image is reconstructed. How the observing spacecraft would need to be navigated in order to maintain precise positions within the image projected by the SGL.

But one problem remained unaddressed: The target itself. Specifically, the fact that the target planet that we might be observing is not standing still. If it is like the Earth, it spins around its axis once every so many hours. And as it orbits its host star, its illumination changes as a result.

In other words, this is not what we are up against, much as we’d prefer the exoplanet to play nice and remain motionless and fully illuminated at all times.

Rather, what we are against is this:

Imaging such a moving target is hard. Integration times must be short in order to avoid motion blur. And image reconstruction must take into account how specific surface features are mapped onto the image plane. An image plane that, as we recall, we sample one “pixel” at a time, as the projected image of the exoplanet is several kilometers wide. It is traversed by the observing spacecraft that, looking back at the Sun, measures the brightness of the Einstein ring surrounding the Sun, and reconstructs the image from this information.

This is a hard problem. I think it is doable, but this may be the toughest challenge yet.

Oh, and did I mention that (not shown in the simulation) the exoplanet may also have varying cloud cover? Not to mention that, unlike this visual simulation, a real exoplanet may not be a Lambertian reflector, but rather, different parts (oceans vs. continents, mountain ranges vs. plains, deserts vs. forests) may have very different optical properties, varying values of specularity or even more complex optical behavior?

 Posted by at 12:06 am
May 052023
 

I got sent a link about an interesting, newly published book on the memoirs of Charles-Augustin de Coulomb. He was, of course, the French officer, engineer and physicist most famous for the Coulomb law that characterizes the electrostatic interaction.

As I occasionally receive e-mails from strangers about their self-published tomes or tomes published through vanity publishers of questionable credibility, I have come to the habit of dismissing such e-mails without paying them much attention. I am glad I paid more attention this time because this book is interesting, valuable, and genuine.

It is available as a matter of fact as a free PDF download from the authors but hey, I just bought the paperback. It was for some reason deeply discounted on Amazon Canada, so with free Prime shipping, all I am paying is the princely sum of $3.15. These days when even “cheap” paperback novels often cost 20 bucks if not more, how could I resist?

Of course it also helped that I looked at the PDF. I am sure the book has flaws (all books do) but it looks like a serious scholarly publication delivering real value to physicists and science historians both.

In fact, it is fascinating to see how modern, how advanced scientific thinking was already evident more than a quarter millennium ago. It makes me appreciate even more just how much of our collective human effort was needed to get from these early experiments to the present era of ubiquitous computer networks running amazing software that now mimics human intelligence, all powered by the same electricity that Coulomb was exploring.

 Posted by at 9:46 pm
May 022023
 

Not exactly the greatest discovery, I know, but GPT-4 still managed to offer an impressive demonstration of its understanding of gravitational physics when I asked it to build a Newtonian homogeneous universe:

What distinguishes GPT-4 from its predecessor is not that its training dataset is larger, but that it has significantly improved reasoning capabilities, which is well demonstrated by this answer. GPT 3.5 and Claude have the same knowledge. But they cannot put the pieces together quite like this (although they, too, can do impressive things with appropriate human guidance, one step at a time.)

 Posted by at 12:37 pm
Apr 202023
 

Another paper of ours, in all its 36-page glory, was accepted by Physical Review D and I am delighted.

One of the things we do in this paper is the use of symmetric trace-free tensors (STF) that allow us, among other things, to effect a rotation of spherical harmonic coefficients. This approach likely has many uses as a bit of practical math, beyond modeling gravitational fields.

 Posted by at 7:13 pm
Apr 202023
 

I just asked GPT-4 using my freshly developed UI about Starship.

In the background, GPT-4 correctly utilized a facility to perform Google searches and make use of the resulting snippets (I’m sure I’ll find a way to prevent it from referencing those snippets, which are not visible to the user, in the actual answer). Here is the critical part of the conversation that took place in the background:

User: What happened to Starship this morning?

GPT: SEARCH(Starship event on 2023/04/20)

System: Snippet 1: 3 hours ago … The rocket got off the launchpad before exploding above the Gulf of Mexico. This segment airs on April 20, 2023. Audio will be available after …
Snippet 2: UPCOMING. April 19, 2023. STARLINK MISSION · April 20, 2023. Starship Flight Test.
Snippet 3: 6 hours ago … April 20, 2023 … SpaceX launches the inaugural test flight of the integrated Starship and Super Heavy rocket from the company’s Starbase …
Snippet 4: 5 hours ago … April 20, 2023. Elon Musk has called it the “holy grail” for space technology. Starship, a new SpaceX rocket system that launched for the …
Snippet 5: ATCSCC ADVZY 007 DCC 04/20/2023 OPERATIONS PLAN. MESSAGE: EVENT TIME: 20/0200 – AND LATER … THE SPACEX STARSHIP SUPER HEAVY LAUNCH FROM BOCA CHICA, …

GPT: This morning, SpaceX launched the inaugural test flight of the integrated Starship and Super Heavy rocket from the company’s Starbase. Unfortunately, the rocket got off the launchpad but exploded above the Gulf of Mexico during the flight test (Snippet 1, Snippet 3).

In case you are wondering, yes, it knows the current date, too, thanks to the way my UI sets it up.

And yes, Starship blew up. But it blew up after the job of the first stage was nearly complete, at separation, at an altitude of some 40 km. Which means that despite the spectacular RUD (rapid unscheduled disassembly) event, this launch is still a huge success.

Now if we could only convince Elon to spend more time building rockets and less time honing his skills at corporate value destruction at Twitter, pardon me, X Corp…

 Posted by at 3:22 pm
Apr 132023
 

Once again, we have summer in April.

This picture shows the melting pile of dirty snow in our visitor parking area, photographed from our upstairs bedroom window.

The date and the temperature widget speak for themselves. (Yes, I still use Windows widgets, through a third-party tool. What can I say? I like them.)

 Posted by at 5:14 pm
Apr 032023
 

We all know that GPT is very competent, very knowledgeable. So let me go ahead and ask a technical question. It’s not trivial but not terribly complicated either; any student studying general relativity should be able to show the correct derivation. Here is my question:

Derive the geodesic equations for \(d\tau^2=Bdt^2-Adr^2-r^2d\theta^2-r^2\sin^2\theta d\phi^2\), where \(A\) and \(B\) are functions of \(r\) only.

Let’s see how GPT3.5 responds:

The geodesic equations for the given metric are given by:

$$\frac{d^2x^\alpha}{d\tau^2}+\Gamma^\alpha_{\mu\nu}\frac{dx^\mu}{d\tau}\frac{dx^\nu}{d\tau}=0$$

where \(\tau\) is the proper time, \(x^\alpha\) are the coordinates \((t,r,\theta,\phi)\), and \(\Gamma^\alpha_{\mu\nu}\) are the Christoffel symbols of the second kind, given by:

$$\Gamma^\alpha_{\mu\nu}=\frac{1}{2}g^{\alpha\beta}(\partial_\mu g_{\beta\nu}+\partial_\nu g_{\beta\mu}-\partial_\beta g_{\mu\nu})$$

where \(g_{\alpha\beta}\) is the metric tensor.

For the given metric, the non-zero Christoffel symbols are:

\begin{align*}
\Gamma^t_{rr}&=\frac{1}{2}B’\\
\Gamma^t_{tt}&=\frac{1}{2}B\frac{A’}{B}\\
\Gamma^r_{rt}&=\frac{1}{2}\frac{A’}{B}\\
\Gamma^r_{rr}&=-\frac{1}{2}\frac{A’}{B}\\
\Gamma^\theta_{r\theta}&=\frac{1}{r}\\
\Gamma^\theta_{\theta\phi}&=-\sin\theta\cos\theta\\
\Gamma^\phi_{r\phi}&=\frac{1}{r}\\
\Gamma^\phi_{\theta\phi}&=\cot\theta
\end{align*}

where a prime denotes differentiation with respect to \(r\).

Using these, we can write down the geodesic equations explicitly:

\begin{align*}
\frac{d^2t}{d\tau^2}+\frac{B’}{2B}\left(\frac{dt}{d\tau}\right)^2+\frac{A’}{2B}\left(\frac{dr}{d\tau}\right)\left(\frac{dt}{d\tau}\right)&=0\\
\frac{d^2r}{d\tau^2}-\frac{A’}{2B}\left(\frac{dt}{d\tau}\right)^2+\frac{A’}{2B}\left(\frac{dr}{d\tau}\right)^2+r\left(\left(\frac{d\theta}{d\tau}\right)^2+\sin^2\theta\left(\frac{d\phi}{d\tau}\right)^2\right)&=0\\
\frac{d^2\theta}{d\tau^2}+2\frac{dr}{d\tau}\frac{d\theta}{d\tau}-\sin\theta\cos\theta\left(\frac{d\phi}{d\tau}\right)^2&=0\\
\frac{d^2\phi}{d\tau^2}+2\frac{dr}{d\tau}\frac{d\phi}{d\tau}+2\cot\theta\frac{d\theta}{d\tau}\frac{d\phi}{d\tau}&=0
\end{align*}

Hmmm… sounds eminently knowledgeable, does it not?

Well… maybe not. How about we ask an actual computer algebra system:

(%i1) load(ctensor)$
(%i2) derivabbrev:true$
(%i3) ct_coords:[t,r,u,v]$
(%i4) depends([A,B],[r])$
(%i5) lg:matrix([B,0,0,0],[0,-A,0,0],[0,0,-r^2,0],[0,0,0,-r^2*sin(u)^2])$
(%i6) cmetric(false)$
(%i7) christof(mcs)$
                                            B
                                             r
(%t7)                          mcs        = ---
                                  1, 1, 2   2 A

                                            B
                                             r
(%t8)                          mcs        = ---
                                  1, 2, 1   2 B

                                            A
                                             r
(%t9)                          mcs        = ---
                                  2, 2, 2   2 A

                                             1
(%t10)                          mcs        = -
                                   2, 3, 3   r

                                             1
(%t11)                          mcs        = -
                                   2, 4, 4   r

                                              r
(%t12)                         mcs        = - -
                                  3, 3, 2     A

                                           cos(u)
(%t13)                        mcs        = ------
                                 3, 4, 4   sin(u)

                                               2
                                          r sin (u)
(%t14)                     mcs        = - ---------
                              4, 4, 2         A

(%t15)                   mcs        = - cos(u) sin(u)
                            4, 4, 3

(%i16) geod:[0,0,0,0]$
(%i17) cgeodesic(true)$
                                   B t    + B  r  t
                                      s s    r  s  s
(%t17)                     geod  = -----------------
                               1           B

                        2        2           2          2                     2
                 2 r sin (u) (v )  + 2 r (u )  - B  (t )  - 2 A r    - A  (r )
                               s           s      r   s          s s    r   s
(%t18) geod  = - --------------------------------------------------------------
           2                                  2 A

                                            2
                        r cos(u) sin(u) (v )  - r u    - 2 r  u
                                          s        s s      s  s
(%t19)        geod  = - ----------------------------------------
                  3                        r

                   r sin(u) v    + 2 r cos(u) u  v  + 2 r  sin(u) v
                             s s               s  s      s         s
(%t20)     geod  = -------------------------------------------------
               4                       r sin(u)

Looks different, doesn’t it. And no, I don’t mean LaTeX vs. the fixed pitch character representations of equations in a text terminal. Rather, the content.

The thing is, what GPT produces looks plausible. It has the right idea. The equations seem to make sense. Unless you know what to expect, you are likely to accept the result as correct, since it appears correct. But GPT sucks at math. It gets easily confused. It is a text model that is optimized to write equations that look right… but only has a superficial understanding of what it produces. Kind of like a student who is trying hard to remember, produces something that resembles the right thing, but without a perfect memory (and keep in mind, trained neural nets are not like any other software we are used to using, as they have no perfect memory!) and without in-depth understanding, fails.

I am sure over time this will improve. GPT-4 is already better at it than 3.5 (which was used to produce this outcome). And future versions may likely interface with computer algebra subsystems (among other things) to augment the neural net with specific capabilities. But for now, perhaps I can be forgiven for asking GPT’s cousin, DALL-E, to draw me a cat, exasperated by the bad math GPT produces:

 Posted by at 2:06 pm
Mar 222023
 

Students at the California State University, Northridge, are currently working on a short documentary film about our work on the Solar Gravitational Lens.

The project hopes to attract modest crowdfunding. They also produced a teaser trailer.

Of course I hope they succeed; our SGL work could use some good publicity.

 Posted by at 9:39 pm
Feb 272023
 

More than 20 years ago, I wrote a program that showed what Mars would look like if it had oceans.

I wrote it originally in C++, but then ported it to Java and turned it into a Web application.

That was a long time ago. Unfortunately, browsers no longer support Java applets for security reasons. So my beautiful applet was not working anymore.

Today, I finally spent some time reimplementing the applet in plain JavaScript. It’s working again! (Apart from some minor cosmetics.) And it has data sets for Mars, Earth, Venus and the Moon as well.

 Posted by at 2:47 am