Geophysics is a challenging endeavor — one part geology as historical evidence and the other part current measurements revealing how the forces of nature are continuously shaping the behavior of the Earth. Yet, how much faith can we place on any one interpretation, or on any past consensus?
This goes double for the study of geophysical fluid dynamics — volumes and forces so large that controlled experiments are impossible. So that when a semi-controlled impulse comes about, say from the calving of a glacier, the empirical results may be surprising:
The subsequent mega-tsunami — one of the highest in recent history — set off a wave which became trapped in the bendy, narrow fjord for more than a week, sloshing back and forth every 90 seconds.
The phenomenon, called a “seiche,” refers to the rhythmic movement of a wave in an enclosed space, similar to water splashing backwards and forwards in a bathtub or cup. One of the scientists even tried (and failed) to recreate the impact in their own bathtub.
While seiches are well-known, scientists previously had no idea they could last so long.
“Had I suggested a year ago that a seiche could persist for nine days, people would shake their heads and say that’s impossible,” said Svennevig, who likened the discovery to suddenly finding a new colour in a rainbow. — http://www.msn.com/en-in/news/techandscience/what-caused-the-mysterious-9-day-earth-vibration-scientists-point-to-650-ft-mega-tsunami-that-rocked-greenland/ar-AA1qwIqk
This took place in a large Greenland fjord — massive but not as massive as the ocean. And that’s where massive geophysical forces also take place, such as from tidal pull.
So what about the Atlantic Multidecadal Oscillation (AMO)? The Mt long-period tide is an interference between the Mf nodal tidal cycle (13.66 days) and the Mm anomalistic tidal cycle (27.55 days). When this is synchronized to an annual impulse, a multidecadal response results.
It is much too easy to model the 50-60 year AMO cycle via nonlinear triad frequency-doubling mechanisms, and also simulate the faster cycling from the predominate Mf and Mm interactions with the annual cycle. This is essentially a sloshing behavior operating on the ocean’s thermocline as described in Chapter 12 of Mathematical Geoenergy, applying the nonlinear geophysical dynamics embedded within Laplace’s Tidal Equations.
New colors of the rainbow are waiting to be revealed. No excuse for others to reproduce the tidal forcing models as described and perform cross-validated model fits to replicate the results above. Work smart not hard.
Susan Anderson said:
“I worry about supercomputing’s vast use of energy”
It’s a fact of life now. Even for the use of supercomputers for solving climate/MET models it’s a fact. It’s also sad that there’s a Green(!!!) 500 list of energy efficient supercomputers – https://en.wikipedia.org/wiki/Green500 . The most efficient ones on the list around 1 Exaflops https://en.wikipedia.org/wiki/Frontier_(supercomputer) are still comparable to the power consumption of a Boeing 737 flying at altitude, and that’s considering the extrinsic factor of cooling the systems with water while running non-stop for maximum utilization. Hopefully they use the waste heat for the buildings. Just think about the number of electrons traveling through all those chips with nothing accomplished but colliding with lattice defects, phonons, etc to dissipate that kind of energy through heat!
That’s why I have adopted as my recent crusade to advertise working smart and not hard in solving climate models. There’s absolutely no excuse for researchers to not cross-check model results that can potentially capture ocean cycles by computations running on a laptop. https://geoenergymath.com/2024/09/23/amo-and-the-mt-tide/
OK, so what if this model doesn’t pan out? How much energy is wasted? Is it the equivalent of fleets of 737’s running around the clock while not making any progress in explaining what caused the 2023 temperature or being unable to predict an El Nino beyond a year?
Face it. If nothing else, these natural climate patterns will be found out by a machine learning experiment run by Google or NVIDIA. And like what happened with the most recent physics and chemistry Nobel prizes, it won’t go to a traditional physicist or chemist but to someone applying AI.
Just think if someone the equivalent of Susan’s father https://en.wikipedia.org/wiki/Philip_W._Anderson will no longer receive Nobel physics awards at the expense of machines? Let’s get the recognition before that plays out 😉
====
At 62.86 gigaflops/watt how much power does 1.1 exaflops use? ChatGPT
To calculate the power consumption for 1.1 exaflops at 62.86 gigaflops per watt, you can use the following steps:
1.1 exaflops=1.1×109 gigaflops1.1 , text{exaflops} = 1.1 times 10^9 , text{gigaflops}1.1exaflops=1.1×109gigaflops
Power consumption=1.1×109 gigaflops62.86 gigaflops/watttext{Power consumption} = frac{1.1 times 10^9 , text{gigaflops}}{62.86 , text{gigaflops/watt}}Power consumption=62.86gigaflops/watt1.1×109gigaflops
Now, let’s calculate:Power consumption=1.1×10962.86≈17,500,159.1 wattstext{Power consumption} = frac{1.1 times 10^9}{62.86} approx 17,500,159.1 , text{watts}Power consumption=62.861.1×109≈17,500,159.1watts
Converting this to megawatts:Power consumption≈17.5 megawattstext{Power consumption} approx 17.5 , text{megawatts}Power consumption≈17.5megawatts
So, a system running at 1.1 exaflops with an efficiency of 62.86 gigaflops per watt would consume approximately 17.5 megawatts of power.
How about an average jet-liner used more for frequent short domestic routes?
ChatGPT
For an average jetliner commonly used for short domestic routes, such as a Boeing 737 or Airbus A320, the fuel consumption and power usage are significantly lower compared to a Boeing 747, since these planes are smaller and more fuel-efficient.Step 1: Estimate fuel consumption
A typical narrow-body jet like a Boeing 737 or Airbus A320 consumes around 2.5 to 3 tons of fuel per hour while cruising at altitude. We’ll use 2.75 tons per hour for this calculation.2.75 tons/hour=2750 kg/hour2.75 , text{tons/hour} = 2750 , text{kg/hour}2.75tons/hour=2750kg/hourStep 2: Calculate energy consumption per hour
Using the same energy content for jet fuel (43 MJ/kg):Energy/hour=2750 kg/hour×43 MJ/kg=118,250 MJ/hourtext{Energy/hour} = 2750 , text{kg/hour} times 43 , text{MJ/kg} = 118,250 , text{MJ/hour}Energy/hour=2750kg/hour×43MJ/kg=118,250MJ/hourStep 3: Convert energy per hour to watts
Converting to watts (joules per second):Power (watts)=118,250×106 joules3600 seconds≈32,847,222 wattstext{Power (watts)} = frac{118,250 times 10^6 , text{joules}}{3600 , text{seconds}} approx 32,847,222 , text{watts}Power (watts)=3600seconds118,250×106joules≈32,847,222wattsStep 4: Convert to megawatts
Power≈32.85 megawattstext{Power} approx 32.85 , text{megawatts}Power≈32.85megawatts
Thus, a typical jetliner used for frequent short domestic routes, such as a Boeing 737 or Airbus A320, consumes approximately 33 megawatts of power while cruising at altitude.