Hurricane predictions

[GregLocock]

Abstract

Every year, tropical hurricanes affect North and Central American wildlife and people. The ability to forecast hurricanes is essential in order to minimize the risks and vulnerabilities in North and Central America. Machine learning is a newly tool that has been applied to make predictions about different phenomena. We present an original framework utilizing Machine Learning with the purpose of developing models that give insights into the complex relationship between the land–atmosphere–ocean system and tropical hurricanes. We study the activity variations in each Atlantic hurricane category as tabulated and classified by NOAA from 1950 to 2021. By applying wavelet analysis, we find that category 2–4 hurricanes formed during the positive phase of the quasi-quinquennial oscillation. In addition, our wavelet analyses show that super Atlantic hurricanes of category 5 strength were formed only during the positive phase of the decadal oscillation. The patterns obtained for each Atlantic hurricane category, clustered historical hurricane records in high and null tropical hurricane activity seasons. Using the observational patterns obtained by wavelet analysis, we created a long-term probabilistic Bayesian Machine Learning forecast for each of the Atlantic hurricane categories. Our results imply that if all such natural activity patterns and the tendencies for Atlantic hurricanes continue and persist, the next groups of hurricanes over the Atlantic basin will begin between 2023 ± 1 and 2025 ± 1, 2023 ± 1 and 2025 ± 1, 2025 ± 1 and 2028 ± 1, 2026 ± 2 and 2031 ± 3, for hurricane strength categories 2 to 5, respectively. Our results further point out that in the case of the super hurricanes of the Atlantic of category 5, they develop in five geographic areas with hot deep waters that are rather very well defined: (I) the east coast of the United States, (II) the Northeast of Mexico, (III) the Caribbean Sea, (IV) the Central American coast, and (V) the north of the Greater Antilles.

https://www.mdpi.com/2073-4433/13/5/707

It's good to see quantified predictions. OTOH I hate(?- Ok strongly dislike) non physics based climate modelling. This one uses the usual suspects in numerical analysis, Bayes, which is great fun, and wavelets, which I used to use all the time at work.

The generic problem with stats based climate modelling is that correlation is not causation.



Cheers

Greg Locock


New here? Try reading these, they might help FAQ731-376

http://eng-tips.com/market.cfm?

 

[dik]

I did a bunch of heuristic progamming about 50 years back (pre PC, on IBM 360), but not for climate. I have no idea of what the current state of the art for equipment or models is. I think weather is one of the most difficult things to model. Lorenz 'butterfly effect' comes to mind.

Rather than think climate change and the corona virus as science, think of it as the wrath of God. Do you feel any better?

-Dik

 

[TugboatEng]

I thought it was interesting that the SR-71 Blackbird used a camera that could track stars in daylight to locate the aircraft so that a pre-recorded cassette tape, based on predicted weather conditions, could vary the altitude of the aircraft to prevent con-trailing as well as position the inlet cones on the engines. In one instance an incorrect tape was used leading to multiple unstarts of the engines on the aircraft. That's some pretty good weather predictions dating back to the late 1950's.

 

[PNachtwey]

I would like to know. I am thinking of retiring to one of the Caribbean islands. Hurricanes cause lots of destruction there.


Peter Nachtwey
Delta Computer Systems

http://www.deltamotion.com

http://forum.deltamotion.com/

IFPE Hall of Fame Member

 

[itsmoked]

Well Peter..

I'd make sure I had:

A hurricane proof house.
Hurricane surge proof location.
A 20 inches of rain in one day proof house.
Two weeks of drinking water storage.
Enough water to minimally bath and wash dishes with for two weeks.
My own independent solar off-grid system that would allow me to easily remove and store the panels pending a cane, and could run the place for 4 days without solar.
One or two months of those high quality good tasting pre-packaged meals.

What did I forget? Starlink?

I believe this is all totally possible as long as you shop for a place with each item in mind. Or build from scratch on the correct piece of dirt.

Keith Cress
kcress -

http://www.flaminsystems.com

 

[JoshPlumSE]

Here is my idea of what a "hurricane proof" house would be, since that is not a real term.

1) Designed so that the living areas are above the storm surge levels. You can have a garage or basement type level on the lower floor. But, it should be made with materials that can be completely submerged in water without being ruined.... Typically reinforced concrete.

2) Upper level construction should have lots of hold downs and such so that the roof doesn't pull off. Generally, there are requirements for this in ASCE-7. But, I imagine the construction "standard of practice" in the Caribbean doesn't live up to these standards.

3) Also, remember that it's considered a success when the building is still standing, even if it's damaged. And, a complete success if the structure is undamaged, but the stuff inside (furnishings, dry wall, etc) is complete flooded / ruined / soaked).

Just want to make sure you understand the concept of "hurricane proof".... as we structural people define it.

Anyone else have points to add....

 

Alternatively, don't live where hurricanes are. In the hierarchy of mitigation that is the lowest hanging fruit.

South Florida is basically one big sand bar that would not be inhabited if it were not for air conditioning.

"Everyone is entitled to their own opinions, but they are not entitled to their own facts."

 

[JoshPlumSE]

South Florida is basically one big sand bar that would not be inhabited if it were not for air conditioning.

Let's say "sparsely" inhabited if not for air conditioning. Anywhere with a supply of wild game, arable land, and fresh water would be inhabited. Honestly, I find it amazing how many inhospitable locations had a good sized native population. Alaska?! It's surprising that these folks didn't just keep moving south until they got to an easier place to survive.

 

[rb1957]

I think human settlement is like most natural mechanisms ... where there's a niche there's something to fill it. I suspect the earliest Intuit figured it was easier to survive (and prosper) in the high Artic than move the current residents off the land they settled (further south).

another day in paradise, or is paradise one day closer ?

 

[SuperSalad]

I'd say it is all about food and water. Once you find a place that has relatively abundant food and water, the rest of the necessary comforts humanity craves can be created and adapted for. The Inuit found areas where there was clean water and lots of food if you knew how to obtain it. Sure it's cold, but cold issues can be circumnavigated where water and food cannot.

- Andrew

 

[rb1957]

sure, but I don't think it would've been their first choice. I think they bumped into some more warlike people, and the easiest course of action was to go around, or head East rather than South, and not conflict with this "superior" people.

another day in paradise, or is paradise one day closer ?

 

[SuperSalad]

Or they did both. Maybe some stayed where they knew they could survive and some moved onto prospective "greener pastures". A separation of peoples by risk/reward tolerance.

- Andrew

 

Must be spring, the engineering pedantry is in full bloom.

In future I will commit to qualifying every comment to the nth degree, so as not to provoke tangents due to minute shortfalls in absolute precision.

"Everyone is entitled to their own opinions, but they are not entitled to their own facts."

 

[JoshPlumSE]

Must be spring, the engineering pedantry is in full bloom.

My apologies.... Some days, I just can't help myself. Let's interpret my post as "playfully pedantic" this time. Without the intent to nit pick or annoy.

 

[rb1957]

"Alternatively, don't live where hurricanes are. In the hierarchy of mitigation that is the lowest hanging fruit."

Only one group of people can grab that fruit ! The next group of people will either take to take it from them, or pick the next lowest.

But, in this case, the OP has said ... "I want to live where there are hurricanes" and is looking for mitigation.
High ground is likely to be expensive, low ground cheap.
Insurance is either unobtainable or expensive.
A storm proof building will be expensive and of limited value.

But everywhere (well, all over the place) people live with the risk of floods and the cost of cleaning up afterwards (including my nephews in Brisbane).

It's "just" the cost of doing business.

another day in paradise, or is paradise one day closer ?

 

[LionelHutz]

It wasn't the OP and I still do know what "I would like to know." refers to exactly.

Like to know about the ability to accurately forecast hurricanes?