Connect with us

Science

AI is changing sea ice melting climate projections

Published

on

AI is changing sea ice melting climate projections

The tremendous melting of sea ice at the poles is one of the most urgent problems facing planet as it warms up so quickly. These delicate ecosystems, whose survival depends so heavily on floating ice, have a difficult and uncertain future.

As a result, climate scientists are using AI more and more to transform our knowledge of this vital habitat and the actions that can be taken to preserve it.

Determining the precise date at which the Arctic will become ice-free is one of the most urgent problems that must be addressed in order to develop mitigation and preservation strategies. A step toward this, according to Princeton University research scientist William Gregory, is to lower the uncertainty in climate models to produce these kinds of forecasts.

“This study was inspired by the need to improve climate model predictions of sea ice at the polar regions, as well as increase our confidence in future sea ice projections,” said Gregory.

Arctic sea ice is a major factor in the acceleration of global climate change because it cools the planet overall by reflecting solar radiation back into space. But because of climate change brought on by our reliance on gas, oil, and coal, the polar regions are warming considerably faster than the rest of the world. When the sea is too warm for ice to form, more solar radiation is absorbed by the Earth’s surface, which warms the climate even more and reduces the amount of ice that forms.

Because of this, polar sea ice is extremely important even outside of the poles. The Arctic Ocean will probably eventually have no sea ice in the summer, which will intensify global warming’s effects on the rest of the world.

AI coming to the rescue

Predictions of the atmosphere, land, sea ice, and ocean are consistently biased as a result of errors in climate models, such as missing physics and numerical approximations. Gregory and his colleagues decided to use a kind of deep learning algorithm known as a convolutional neural network for the first time in order to get around these inherent problems with sea ice models.

“We often need to approximate certain physical laws in order to save on [computational] time,” wrote the team in their study. “Therefore, we often use a process called data assimilation to combine our climate model predictions together with observations, to produce our ‘best guess’ of the climate system. The difference between best-guess-models and original predictions provides clues as to how wrong our original climate model is.”

The team aims to show a computer algorithm  “lots of examples of sea ice, atmosphere and ocean climate model predictions, and see if it can learn its own inherent sea ice errors” according to their study published in JAMES.

Gregory explained that the neural network “can predict how wrong the climate model’s sea ice conditions are, without actually needing to see any sea ice observations,” which means that once it learns the features of the observed sea ice, it can correct the model on its own.

They achieved this by using climate model-simulated variables such as sea ice velocity, salinity, and ocean temperature. In the model, each of these factors adds to the overall representation of the Earth’s climate.

“Model state variables are simply physical fields which are represented by the climate model,” explained Gregory. “For example, sea-surface temperature is a model state variable and corresponds to the temperature in the top two meters of the ocean.

“We initially selected state variables based on those which we thought a-priori are likely to have an impact on sea ice conditions within the model. We then confirmed which state variables were important by evaluating their impact on the prediction skill of the [neural network],” explained Gregory.

In this instance, the most important input variables were found to be surface temperature and sea ice concentration—much fewer than what most climate models require to replicate sea ice. In order to fix the model prediction errors, the team then trained the neural network on decades’ worth of observed sea ice maps.

An “increment” is an additional value that indicates how much the neural network was able to enhance the model simulation. It is the difference between the initial prediction made by the model without AI and the corrected model state.

A revolution in progress

Though it is still in its early stages, artificial intelligence is becoming more and more used in climate science. According to Gregory, he and his colleagues are currently investigating whether their neural network can be applied to scenarios other than sea ice.

“The results show that it is possible to use deep learning models to predict the systematic [model biases] from data assimilation increments, and […] reduce sea ice bias and improve model simulations,” said Feiyu Lu, project scientist at UCAR and NOAA/GFDL, and involved in the same project that funded this study.

“Since this is a very new area of active research, there are definitely some limitations, which also makes it exciting,” Lu added. “It will be interesting and challenging to figure out how to apply such deep learning models in the full climate models for climate predictions.”  

Continue Reading
Advertisement

Science

Astronauts Confront Vision Challenges in Space with Upcoming Dragon Mission

Published

on

The primary priorities for the Expedition 72 crew on board the ISS on Tuesday were preparing cargo for a future voyage and safeguarding astronauts’ eyesight to maintain their health.

Microgravity Eye Health

Body fluids rise toward an astronaut’s head in the weightless atmosphere of space. This fluid movement puts pressure on the eyes, which may have an impact on vision and eye anatomy. NASA astronauts Commander Suni Williams and Flight Engineer Butch Wilmore tried a modified thigh cuff that stops these headward fluid movements in order to combat this. As NASA and its international partners prepare for lengthier journeys farther into space, researchers are keeping a careful eye on these changes to create strategies to safeguard eye health.

Getting Ready for Resupply

On Earth, the SpaceX Dragon cargo spaceship is preparing for the next resupply mission to the space station, which is scheduled to launch next week. NASA Flight Engineers Nick Hague and Don Pettit got ready for Dragon’s arrival, which will include a delivery of new station hardware and scientific equipment. After docking and then returning to Earth, Pettit started packing and arranging the goods that would be stored aboard Dragon. Hague received training on how to use instruments that will monitor Dragon’s autonomous approach and docking procedure.

Spacecraft Docking and Manoeuvre

However, Hague will take Williams, Wilmore, and Roscosmos astronaut Aleksandr Gorbunov on a brief ride onboard the SpaceX Dragon Freedom spacecraft to a new docking site prior to the supply mission blasting out toward the space station. On Sunday, November 3, the four will board Dragon. They will undock from the forward port of the Harmony module at 6:35 a.m. EDT and then navigate the spaceship to Harmony’s space-facing port for a docking at 7:18 a.m. The Dragon cargo mission’s forward port is made available by the relocation.

Earth Observations and Maintenance at Night

Gorbunov installed and turned on equipment to observe Earth’s nighttime atmosphere in near-ultraviolet wavelengths following a training session on the exercise cycle of the Destiny laboratory module at the start of his shift. Ivan Vagner and Alexey Ovchinin, two of his fellow cosmonauts, collaborated on inspection and maintenance tasks in the Zvezda service module’s aft end.

Continue Reading

Science

SpaceX launches the year’s 99th operational flight

Published

on

On Friday night, SpaceX successfully completed its 99th flight of the year with a Starlink mission from Cape Canaveral, Florida.

At 7:31 p.m. Eastern time, a Falcon 9 carrying 20 Starlink satellites blasted out from Canaveral’s Space Launch Complex 40.

The Just Read the Instructions droneship’s first-stage rocket completed a downrange recovery touchdown in the Atlantic on its seventeenth flight.

It was the 71st flight from the Space Coast in 2024, just one less than the record-breaking 72 launches in 2023. United Launch Alliance has launched the remaining ones, while SpaceX has flown all but five of those.

There have only been two Falcon Heavy missions this year, with the remainder being Falcon 9 launches.

Along with the other 18 from KSC, this was the 53rd launch from Cape Canaveral.

Together with the two Falcon Heavy missions, SpaceX has performed 33 missions from Vandenberg Space Force Base in California this year, for a total of 97 Falcon 9 launches, including this one.

From its Starbase test site in Boca Chica, Texas, it has also launched three test flights of its in-development Starship and Super Heavy rocket, all of which have reached orbit.

Adding to the success of the March and June missions, last Sunday’s launch included the first on-target controlled landing of the second stage in the Indian Ocean and the first land capture of the Super Heavy booster back at the launch tower.

In 2023, SpaceX completed 98 operational missions, including 91 Falcon 9 and 5 Falcon Heavy missions. The company also attempted two Starship test flights, both of which ended explosively before reaching orbit, though one of them managed to reach space for a brief period of time before being destroyed by its flight termination system.

Officials from the business stated at the beginning of 2024 that it could reach 144 launches for the year, or 12 launches per month. However, weather and the three different groundings of its Falcon 9 rocket due to various problems have caused some obstacles to that pace.

This launch is only the sixth of October thus far. It flew nine times in September, eleven times in August, six times in July, ten times in June, thirteen times in May, twelve times in April, eleven times in March, nine times in February, and ten times in January.

Most of them have been for Starlink, which has launched over 7,100 versions since the first functional versions were sent up in 2019.

This marked SpaceX’s 67th Starlink launch in 2024.

Continue Reading

Science

20 Starlink internet satellites are launched by SpaceX from Florida

Published

on

According to a summary of the SpaceX mission, it was the booster’s seventeenth launch and landing.

Meanwhile, the Starlink satellites were still being transported to low Earth orbit by the upper stage of the Falcon 9. If all goes as planned, it will deploy them there approximately 64 minutes after liftoff.SpaceX launched a new set of Starlink broadband satellites into orbit this evening, October 18.

At 7:31 p.m. EDT (2331 GMT) tonight, a Falcon 9 rocket carrying 20 Starlink spacecraft—13 of which were equipped with direct-to-cell capability—blasted out from Florida’s Cape Canaveral Space Force Station.

About 8.5 minutes after takeoff, the first stage of the Falcon 9 returned to Earth as scheduled, landing on the SpaceX drone ship “Just Read the Instructions” in the Atlantic Ocean.

According to astronomer and satellite tracker Jonathan McDowell, the new group will join the massive and constantly expanding Starlink megaconstellation, which presently comprises of over 6,400 active spacecraft. Of those satellites, about 230 are direct-to-cell vehicles.

Two-thirds of SpaceX’s 96 Falcon 9 flights flown in 2024 have been devoted to expanding the Starlink network. This year, the corporation has also launched three test flights of its Starship megarocket and two Falcon Heavy missions.

Continue Reading

Trending

error: Content is protected !!