Neural General Circulation Models for Weather and Climate

General circulation models (GCMs) are the foundation of weather and climate prediction. GCMs are physics-based simulators which combine a numerical solver for large-scale dynamics with tuned representations for small-scale processes such as cloud formation. Recently, machine learning (ML) models trained on reanalysis data achieved comparable or better skill than GCMs for deterministic weather forecasting. However, these models have not demonstrated improved ensemble forecasts, or shown sufficient stability for long-term weather and climate simulations. Here we present the first GCM that combines a differentiable solver for atmospheric dynamics with ML components, and show that it can generate forecasts of deterministic weather, ensemble weather and climate on par with the best ML and physics-based methods. NeuralGCM is competitive with ML models for 1-10 day forecasts, and with the European Centre for Medium-Range Weather Forecasts ensemble prediction for 1-15 day forecasts. With prescribed sea surface temperature, NeuralGCM can accurately track climate metrics such as global mean temperature for multiple decades, and climate forecasts with 140 km resolution exhibit emergent phenomena such as realistic frequency and trajectories of tropical cyclones. For both weather and climate, our approach offers orders of magnitude computational savings over conventional GCMs. Our results show that end-to-end deep learning is compatible with tasks performed by conventional GCMs, and can enhance the large-scale physical simulations that are essential for understanding and predicting the Earth system.

Paper: https://arxiv.org/pdf/2311.07222v3.pdf

Code: https://github.com/google-research/neuralgcm

Code: https://github.com/google-research/dinosaur

https://news.1rj.ru/str/DataScienceT ⭐

LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Portrait Animation aims to synthesize a lifelike video from a single source image, using it as an appearance reference, with motion (i.e., facial expressions and head pose) derived from a driving video, audio, text, or generation. Instead of following mainstream diffusion-based methods, we explore and extend the potential of the implicit-keypoint-based framework, which effectively balances computational efficiency and controllability. Building upon this, we develop a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficiency for practical usage. To enhance the generation quality and generalization ability, we scale up the training data to about 69 million high-quality frames, adopt a mixed image-video training strategy, upgrade the network architecture, and design better motion transformation and optimization objectives. Additionally, we discover that compact implicit keypoints can effectively represent a kind of blendshapes and meticulously propose a stitching and two retargeting modules, which utilize a small MLP with negligible computational overhead, to enhance the controllability.

page: https://liveportrait.github.io/

paper: https://arxiv.org/abs/2407.03168

code: https://github.com/KwaiVGI/LivePortrait

jupyter: https://github.com/camenduru/LivePortrait-jupyter

https://news.1rj.ru/str/DataScienceT ⭐️

Guess what? There's a chance to snag 10 million $Whale tokens! 🐳

And the best part? You can get them for FREE right now! 🎁

Here’s how:

1️⃣ Share your referral link from the "Earn" section at @Whale.
2️⃣ Every USD you earn equals a $Whale token.
3️⃣ Earn cash bonuses for every friend you invite!

Get your tokens before they’re all gone! 🥰

⚡️⚡️ SAM v2 is out! ❤️‍🔥❤️‍🔥

✅ #Meta announced SAM 2, the novel unified model for real-time promptable segmentation in images and videos. 6x faster, it's the new SOTA by a large margin. Source Code, Dataset, Models & Demo released under permissive licenses 💙

🔗 Review: https://t.ly/oovJZ

✅ Paper: https://t.ly/sCxMY

✅ Demo: https://sam2.metademolab.com

🔥 Project: ai.meta.com/blog/segment-anything-2/

⭐️ Models: github.com/facebookresearch/segment-anything-2

https://news.1rj.ru/str/DataScienceT 🗣

🖥 StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset.

🖥 Github: https://github.com/huochf/StackFLOW

📕 Paper: https://arxiv.org/abs/2407.20545v1

🚀 Dataset: https://paperswithcode.com/dataset/behave

https://news.1rj.ru/str/DataScienceT ⭐️

This channels is for Programmers, Coders, Software Engineers.

0️⃣ Python
1️⃣ Data Science
2️⃣ Machine Learning
3️⃣ Data Visualization
4️⃣ Artificial Intelligence
5️⃣ Data Analysis
6️⃣ Statistics
7️⃣ Deep Learning
8️⃣ programming Languages

✅ https://news.1rj.ru/str/addlist/8_rRW2scgfRhOTc0

✅ https://news.1rj.ru/str/Python53

⚡️ EMO-Disentanger

🖥 Github: https://github.com/yuer867/emo-disentanger

📕 Paper: https://arxiv.org/abs/2407.20955v1

🚀 Dataset: https://paperswithcode.com/dataset/emopia

https://news.1rj.ru/str/DataScienceT ⭐️

✅ Don't worry about data for your projects anymore!
🔻 Get to know MagPie-Ultra, the first quality synthetic dataset!

👨🏻‍💻 Have you ever thought about what makes artificial intelligence projects and machine learning models work better and smarter? The answer is simple: quality data!

✅ Now with MagPie-Ultra, the first synthetic dataset created by Llama 3.1 405B-Instruct advanced artificial intelligence model, you have a ready, high-quality and diverse dataset for training and improving artificial intelligence models , which can make your projects more accurate and smarter and reach Help for better results.👇

┌ 💸 MagPie-Ultra
├ 🖥 Pipeline
└ 💰 Dataset

🌐 https://news.1rj.ru/str/DataScienceT ⭐️

✅ Good evening: We have launched an urgent donation campaign in order to continue our channels with the momentum you are accustomed to. Contribute if you think our work deserves thanks.

🥇 BTC:
bc1qgjmr3ffh48jw5vw2tqad9useumutt5tql0pa6w

💲 USDT TRC20:
TMzAr8AFcZ1n5RXZa3BHPXHBRqugx9Skr7

🐬 TON:
UQAVMaOmfh8vsaXTykpBX45A3tsYv4Guo09eMw1Tl_uSYFcq

🏦 PAYPAL:
https://www.paypal.me/HusseinSheikho

No learning rates needed: Introducing SALSA - Stable Armijo Line Search Adaptation

💻 Github: https://github.com/themody/no-learning-rates-needed-introducing-salsa-stable-armijo-line-search-adaptation

📕 Paper: https://arxiv.org/abs/2407.20650v1

✈️ Dataset: https://paperswithcode.com/dataset/cifar-10

🌐 https://news.1rj.ru/str/DataScienceT ⭐️