How AI Upscaling Improves Weather Forecasts

preview_player
Показать описание

A paper last year demonstrated that machine learning techniques similar to image upscaling can improve the forecast of the weather, in particular notoriously difficult-to-predict precipitation. In this video I talk to two of the paper's authors about their Generative Adversarial Network (GAN) approach and how they adapted it to the chaotic system of the atmosphere.

---------- II ----------

---------- II ----------

Some stock footage courtesy of Getty.
Edited by Luke Negus.

How is the weather predicted? Why are weather forecasts wrong? How to predict rain accurately? Can you use machine learning to predict the weatehr? This video is about a scientific paper that blends machine learning techniques with weather prediction, using a generative adversarial network to upscale (downsample) predictions of rainfall over the UK. If you like videos from Jordan Harrod, Veritasium, or Real Engineering you will enjoy this science video about predicting the weather.

Huge thanks to my supporters on Patreon:
Mark Moore, Philipp Legner, Zoey O'Neill, Veronica Castello-Vooght, Jan Krüger, Heijde, Liat Khitman, Michael Parmenter, Matthew Powell, Stormchaser007 , Daan Sneep, Abou El-Ela the Physics Boi, Cody VanZandt, bitreign33 , Andy Hartley, Lachlan Woods.
Chaotic Brain Person, Simon H., Julian Mendiola, Woufff, Ben Cooper, Mark Injerd, dryfrog, Justin Warren, Jack Grimm, Angela Flierman, Alipasha Sadri, Calum Storey, Mattophobia, Riz, The Confusled, Conor Safbom, Paul H and Linda L, Simon Stelling, Gabriele Siino, Bjorn Bakker, Ieuan Williams, Candace H, Tom Malcolm, Leonard Neamtu, Brady Johnston, Kent & Krista Halloran, Rapssack, Kevin O'Connor, Timo Kerremans, Thomas Rintoul, Lars Hubacher, Ashley Wilkins, Samuel Baumgartner, Dan Sherman, ST0RMW1NG 1, Adrian Sand, Morten Engsvang, Farsight101, Haris Karimjee, K.L, fourthdwarf, Felix Freiberger, Chris Field, ChemMentat, Kolbrandr, , Sebastain Graf, Dan Nelson, Shane O'Brien, Alex, Fujia Li, Jesper Koed, Jonathan Craske, Albrecht Striffler, Igor Francetic, Jack Troup, HandsomeCaveman, Sven Ebel, Sean Richards, Kedar , Omar Miranda, Alastair Fortune, Mat Allen, Rafaela Corrêa Pereira, Colin J. Brown, Mach_D, Thusto , Keegan Amrine, Dan Hanvey, Simon Donkers, Kodzo , James Bridges, Liam , Andrea De Mezzo, Wendover Productions, Kendra Johnson.
Рекомендации по теме
Комментарии
Автор

Look mom, Simon is a real youtuber, he got the NordVPN sponsorship!

ShaoVideoProduction
Автор

Just for people who want to learn more about the state of current climate models: there is a podcast (Manifold) episode called 'Status and Future of Climate Modelling' with Tim Palmer.

_yonas
Автор

lol congrats on the nord VPN sponsorship

thes
Автор

One thing that’s easier to predict than precipitation: every machine learning researcher watching this video reeling from the sick linear regression burn

DrAndrewSteele
Автор

6:35 what the network does is still a very big question mark. training the model is analogous to linear regression, but what those weights do is a much more complicated picture.

Treebark
Автор

Given whats happening in Auckland NZ now and the past couple of days this is highly relevant and timely

carolyncopeland
Автор

I hope we'll not lose the science and the ingenuity that went behind the models, as dependent on initial conditions as they are.
Just as generating a torrent of A.I. art can stop people from going into Art, learning techniques, lighting, composition, perspective, etc., I wish we will keep improving the principles that could let us carry on if global supply chains are not able to manifacture the insanely complicated tech needed to sustain our current system (if for example, fossile fuels came to be costlier and costlier to extract, refine, process, transport, etc.).
Let's not surrender everything to A.I., though it's a great tool to use while we can.

DeathToMockingBirds
Автор

This comment is for feeding the algorithm monster. 🍪
Seems it likes snacking on comments, replies and likes to both. 👍
Why not spread some happiness to day and share a treat or two and watch the channel grow? 💖 🌩⛈

ShirleeKnott
Автор

This is such a good video. You explained complicated ideas in very digestible terms, and the interviews were awesome! Keep it up!

MRfuzzjr
Автор

This is very similar to what I am researching: Species distribution models. Many of the terms are the same, but instead of weather forecast, we do species forecasts.

miguelguerreiro
Автор

as someone who lives in ireland this is somewhat concerning, but luckily it wasn't too bad where I lived

elismart
Автор

not a fan of not explicitly stating who you are sponsored by at the start of the video

caittastic
Автор

It was cool to learn about a use for GAN that isn't just bypassing licensing and copyright laws. An area close to where I live got hit by desasterous rain and floods two years ago and while there where warnings, nobody knew how bad it would get. It would be great to get more accurate forecasts.

strawberrycheesecake
Автор

It's funny when you got to the sponsor spot and the way you announced it, I was guessing it was either Raid Shadow Legends or Nord VPN

douglasboyle
Автор

"It's really just linear regession" 😄
Yessir it is...but don't tell the funder

ciaranmcinerney
Автор

As a cyclist to work i hate how bad predicting rain is.
Like i can dress for the cold...
But rain is just annoying as heck.
Dont wanna sit in wet clothes all day

benjaminfraeyman
Автор

Dr Andrew and Dr Lucy are showing us an example of uppers and downers :D

GOATMENTATOR
Автор

How likely is it, that this video gets uploaded the day before I start my PhD in meteorology, where a large part of my work will be with post Processing 😅

REXilef
Автор

...i wont find out; i use a chrome extension called SponsorBlock...it blocks all those in show sponsors that adblock misses

jonathandevries
Автор

Shhhh!!! Don't tell them it's just linear regression!!!

ShubhamBhushanCC