Meriturvallisuus saa potkua ennustavan tekoälyanalyysin avulla roggenuolten ennustamiseen

This week marks a major milestone in oceanic studies and maritime safety after a team of engineers published a study demonstrating how AI neural networks could help to forecast and warn about rogue waves. Notably, these massive events were once seen as unpredictable and have led to major losses for centuries. Here’s what you need to know.

Roggenuolat

Roggenuoloja kutsutaan monilla nimillä, kuten tappajiksi, hirviöiksi ja ääriaalloiksi. Nämä aallot ovat kaksinkertaisen korkeita normaaleihin merellisiin olosuhteisiin verrattuna ja voivat ilmestyä tyhjästä, asettaen niiden tielle tulevat suureen vaaraan. Historian saatossa roggenuolat ovat olleet merimatkustajien kansantarua, jotka epäilemättä ovat kuulleet legendoja näistä massiivisista aalloista, jotka vievät merimiehiä syvyyksiin. Nykyäänkin nämä aallot aiheuttavat merkittävän uhan.
Notably, these rare oceanic events are similar to tsunamis in their size and destructive power. However, unlike their well-understood counterparts, Rogue waves can appear without any major noticeable event, such as an earthquake. As such, these large and unpredictable waves pose great danger to offshore infrastructure, travelers, and other equipment.

Miten roggenuolat muodostuvat

Until recently, there wasn’t enough data and computational power to create reliable rogue wave formation mechanisms. As such, the majority of science regarding the formation of these elusive events was based on observational data collection following events. This info has led researchers to determine the three most prominent ways that rogue waves form.

Hitaasti kertymä

Interestingly, a rogue wave can begin to form and build up without the need to combine with other waves. Strong currents like the Gulf Stream can resonate and expand to create a massive sea anomaly. Scientists studying this phenomenon often employ a method called Benjamin-Feir instability to explain the single-wave train’s expansion. This is one of the rarest forms of rogue waves captured by researchers.

Useita aaltoja

The most widely understood formation of rogue waves occurs due to multiple wave interference meeting at the perfect time to amplify the magnitude. When waves build up and resonate, they can magnify and intensify the current and ferocity of the wave. You can think of this like a snowball effect in that each wave becomes absorbed into the greater momentum creating a massive wall ready to destroy anything in its path.

Nykyiset roggenuolojen määrittämistavat

There are no reliable rogue wave forecast systems in place globally, even though these events have the potential to wreak billions in damage yearly. The most common methods used to determine these events rely on real-time ocean data that can only be predicted as the event occurs, notifying scientists of the increase in sea level. This strategy leaves much to be desired in terms of early warning and safety precautions.

Roggenuolojen tutkimus

The “Ennuste poikkeuksellisista aalloista kelluksimittauksilla” study seeks to shed light on these unique ocean events. The researchers set out to create an AI neural network capable of predicting the chances of a rogue wave occurring based on the current ocean state. As part of this approach, researchers sought to determine what pre-factors occurred before the formation of rogue waves.
This approach was meant to demonstrate the functional relationship between the previous waves and the final rogue event using field measurement devices and advanced neural networks. More importantly, the team wanted to capture and document the phases of synchronization between the individual waves needed to create rogue waves.

Testausvaihe

The testing began with the creation of a neural network. The team decided to use a long short-term memory network (LSTM) AI algorithm. These AI systems were created to streamline the functional relationship between input data and output data. As such, they are ideal for creating data-driven forecasts of complex systems.

Meren kellukat

The researchers gathered data from 172 buoys located off the east coast of the US and Pacific islands with depths ranging from 20 meters to +4000m. Two types of buoys were used in the test. The Datawell directional wave rider MkIII with a 1.28 Hz sampling rate and Datawell directional wave rider MkIII with a 2.56 Hz rate. These units are well-tested and offer reliable data, including accelerators that monitor vertical displacement.

Lähde – MATLAB

Aineisto

The neural network was programmed using a sample size equivalent to 880 years of consecutive data regarding pre-rogue wave conditions. In particular,  14 million 30-minute sea surface elevation measurements were combined with 40,000 sea surface elevation measurements from the same buoys. This data was then scanned to check for abnormalities. The data was then fed back into the algorithm to better train it how to spot these factors.

Relevantti merellisiin olosuhteisiin

The researchers were keen to try to make the rogue wave samples few and far between in the testing phase to ensure that data was closer to real-world scenarios. The samples were then broken into the non-rogue wave and rogue wave categories that were reinforced. Notably, the initial data was obtained via the Coastal Data Information Program (CDIP) in conjunction with Scripps Institution of Oceanography.

Skannattu roggenuoloja varten

The researchers scanned the wave sample data using the University of Maryland supercomputing resources. This access enabled them to leverage an NVIDIA (NVDA ) A100 GPU in conjunction with a local NVIDIA Quadro P1000 GPU to enhance their AI performance, training times, and accuracy.

Tulokset

The results of this study could have a resounding effect on the way engineers and researchers view rogue waves moving forward. These once nearly impossible-to-determine events were able to be singled out with 75% accuracy using the AI systems. Specifically, 75% of rogue waves were predicted within 1 minute of their appearance. The rate only dropped to 73% when the time was expanded to 5 minutes of warning.
In total, the AI successfully predicted close to 3k rogue waves accurately. Only 855 events managed to slip past the AI detection, leaving the system with a 23% accuracy rating. Considering many researchers believed it was impossible to determine these events, these results opened the door for new and more effective prediction systems to be introduced.

Hyödyt

This study could bring many benefits to the market. For one, it’s the first reliable rogue wave forecast system concept. It takes the idea of these events being too complex to predict and instead, introduces a very reliable and cost-effective solution that could provide valuable advanced warning to ships and offshore platforms when needed.

Käyttää nykyistä kellukadataa

Another major benefit of this approach to determining the probability of rogue waves is that there is no need to install new sensors or systems. Buoys have already been deployed and tested for decades. As such, they provide a reliable and proven data source that has a trackable history.  This AI prediction upgrade is software. As such, it can leverage the millions of hours of data provided by these devices to improve and enhance future performance.

Yleinen soveltuvuus

One of the most interesting aspects of their AI training is that the model was able to be applied to locations outside the original buoy data set with success. The team was able to predict with high probability the rogue wave risk for two off-site buoys. They tested their theory on Buoy 132, located near Jacksonville, Florida, and Buoy 067 near San Nicolas Island off the coast of Los Angeles. The results showed that the algorithm could be applied to other locations with success.

Itseparantava

One of the biggest benefits of this style of AI algorithm is that it can continually improve its data set, reinforcing its understanding and improving performance. These systems will improve as the data gets refined. As such, this method provides a low-cost and efficient way to enhance operations.

Tutkijat

Thomas Breunung and Balakumar Balachandran were the lead researchers in the study. They achieved their goal of demonstrating a way to determine rogue waves with high accuracy globally. Notably,  The University of Maryland provided supercomputing resources and support for the team, which now seeks to improve its results by introducing more data to its model including wind speed, location, and depth. All of these factors could help to improve detection times and even provide a way to determine the height of the event.

Yritykset, jotka voivat ottaa tämän teknologian käyttöön tänään

Many firms could gain immediate benefits from this study. There are currently billions in offshore infrastructure and shipping vessels traversing the ocean. These firms are sure to invest in any technology that can help prevent catastrophic losses and death.

1. Diamond Offshore Drilling Inc.

Diamond Offshore Drilling Inc. on merkittävä öljy‑ ja kaasuporautusyritys, joka sijaitsee Katyssa, Texasissa. Yritys tuli markkinoille vuonna 1987 Diamond M Drilling -yrityksenä ennen useita brändimuutoksia. Tällä hetkellä sillä on 44 offshore‑porauslauttaa, mukaan lukien 32 puolialustaa ja 5 porialusta.
Diamond Offshore Drilling Inc.:lla on sopimuksia monien maailman suurimpien öljy‑ ja kaasuyritysten kanssa, kuten Hess Corporation , Petrobras, BP ja Occidental Petroleum (OXY ). Sen asema ja fossiilisten polttoaineiden kysyntä tekevät tästä osakkeesta vahvan “hold.” Huomattavaa on, että se on kokenut joitakin haittoja vihreän energian tulon myötä markkinoille, mutta analyytikot ennustavat tulevia voittoja, kun konfliktit ja muut tekijät nostavat kaasun hintoja.

2. Sable Offshore Corp

SOC Hintakaavio

Sable Offshore Corp (SOC ) on toinen porausyritys, joka voisi hyödyntää roggenuola‑ennustejärjestelmää suojellakseen offshore‑lauttojaan ja porausasemiaan. Yritys perustettiin vuonna 2020 nimellä Flame Acquisition Corp , ennen kuin se muutti nimensä Sableksi. Sablella on offshore‑toimintaa Kalifornian rannikolla liittovaltion vesillä. Se omistaa myös 76 000 hehtaaria merenalaisia vuokrasopimuksia, jotka mahdollistavat raakaöljyn ja maakaasun putkittamisen.
Yrityksellä on useita strategisia kumppanuuksia alan johtajien kanssa, kuten ExxonMobil (XOM ), Canada Ltd, Imperial Oil (IMO ) Resources Limited ja Pengrowth Energy Corporation, luetteloon sisältyen. Yrityksen osake on kärsinyt viime aikoina markkinoiden heilahteluista. Kuitenkin Kaliforniassa on kasvava kysyntä näille palveluille, mikä asettaa Sable Offshore Corpin johtavaksi paikalliseksi energian tarjoajaksi.

Roggenuolojen ennustamisen tulevaisuus

This study sheds light on the elusive world of rogue waves. These events are no longer sailor tales but are now predictable events. In the future, these systems will be integrated across the maritime economy to mitigate risk and improve efficiency.  Notably, these systems will get much better and more accurate as they obtain additional reinforced data.
You can expect to see this style of prediction coupled with systems such as blockchain networks that provide real-time monitoring of massive data across the globe soon. This improvement would enable these systems to record and track real-time occurrences across the ocean in an immutable manner. This data could then be used to improve scientists understanding of these elusive occurrences.

Roggenuolat ovat ongelma, jonka havaitseminen voi ratkaista

There’s no way to stop rogue waves from forming as of yet. However, the first step to preventing major losses is determining when and what makes these events occur. These engineers have taken the first steps and laid the groundwork for future research that could save lives. For now, their efforts are making “waves” across multiple industries.
Learn about other cool AI projects nyt.