Tessera
Folgen

@jmlepioufle.bsky.social

AI - Environment

2 Posts20 Follower115 Folgt
Nicolas Gonthier@nicaogr.bsky.social · last yr.

📢 FLAIR-HUB dataset A new large-scale, multimodal dataset for land cover and crop type mapping 🤗 Dataset: huggingface.co/datasets/IGN... 📄 Preprint: arxiv.org/abs/2506.07080 🤗 Pretrained models: huggingface.co/collections/... 💻 Code: github.com/IGNF/FLAIR-HUB 🌐 Project : arxiv.org/abs/2506.07080

FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping

The growing availability of high-quality Earth Observation (EO) data enables accurate global land cover and crop type monitoring. However, the volume and heterogeneity of these datasets pose major pro...

arxiv.org

Microsoft Research@msftresearch.bsky.social · last yr.

A new paper published in Nature explains how Microsoft’s Aurora AI foundation model goes beyond weather forecasting to more accurately predict a range of environmental events, from hurricanes and typhoons to air quality and ocean waves. aka.ms/AAvgi2k

Microsoft’s Aurora AI foundation model goes beyond weather forecasting

Aurora, an AI foundation revolutionizes weather and environmental forecasting with accuracy, speed and efficiency.

aka.ms

Ian Brown@ianabrown.bsky.social · 2y ago

New paper alert! 🚨📢 Weather impacts on #drone #photogrammetry: - seasonal and weather effects on accuracy - canopy height model and DEMs evaluated - reference #lidar dataset with #dGPS control points with @linegreis.bsky.social #UAV #forest #remotesensing dx.doi.org/10.1111/avsc...

Seasonal optimisation of drone‐based photogrammetry in a heterogeneous boreal landscape

In this study we show how weather and flight parameters affect photogrammetric surveys from drones. Using a commercial (off-the-shelf) drone we surveyed a mixed boreal forest site in summer, autumn a...

dx.doi.org

KinarNicholas.bsky.social@kinarnicholas.bsky.social · last yr.

Hydrology Paper of the Day @rodolfonobrega.bsky.social on extending the MOD16 evapotranspiration algorithm for MODIS: an improvement of spatiotemporal resolutions via the ESTIMET algorithm; day and night ET over all sky conditions; a comparison with EC data over Brazil; and spatial comparisons.

Rodolfo Nobrega@rodolfonobrega.bsky.social · last yr.

In times of AI we show how some robust tweaks can greatly improve well established ET models. It was a pleasure to have Cinthia in Bristol and discuss every step of this research! www.sciencedirect.com/science/arti...

Gilles Louppe@glouppe.bsky.social · last yr.

While Appa is still a prototype, it demonstrates the potential of latent score-based data assimilation for global atmospheric modeling. Huge congrats to @gandry.bsky.social for leading this work and to everyone on our amazing team for this effort! Paper: arxiv.org/abs/2504.18720

Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation

Deep learning has transformed weather forecasting by improving both its accuracy and computational efficiency. However, before any forecast can begin, weather centers must identify the current atmosph...

arxiv.org

Scott Hosking@scotthosking.bsky.social · 2y ago

🌤️ Our #AI weather forecasting model has been published today in Nature 🤖 🥇the first AI weather model to learn directly from raw environmental observations 🌎 compared to existing AI models it is cheaper to train, uses less carbon and easier to deploy locally www.turing.ac.uk/news/fully-a...

Fully AI driven weather prediction system could start revolution in forecasting

A new AI weather prediction system, Aardvark Weather, can deliver accurate forecasts tens of times faster and using thousands of times less computing power t

turing.ac.uk

alphaXiv@alphaxiv.org · 2y ago

🚀This week was huge for AI—whether through sparse attention, mastering long-context reasoning, or even creating million-dollar software engineering gigs, it's all about smarter, more efficient models shaping a dynamic future.🚨

Bild
Stephan Hoyer@handle.invalid · 2y ago

Can incorporating AI improve precipitation in global weather and climate models? Yes! In the latest NeuralGCM paper, we show that training on satellite-based precipitation results in significant improvements over traditional atmospheric models: arxiv.org/abs/2412.11973

Neural general circulation models optimized to predict satellite-based precipitation observations

Climate models struggle to accurately simulate precipitation, particularly extremes and the diurnal cycle. Here, we present a hybrid model that is trained directly on satellite-based precipitation obs...

arxiv.org

Tom Andersson 🌍@tom-andersson.bsky.social · 2y ago

So excited to share our Google DeepMind team's new Nature paper on GenCast, an ML-based probabilistic weather forecasting model: www.nature.com/articles/s41... It represents a substantial step forward in how we predict weather and assess the risk of extreme events. 🌪️🧵

Probabilistic weather forecasting with machine learning - Nature

GenCast, a probabilistic weather model using artificial intelligence for weather forecasting, has greater skill and speed than the top operational medium-range weather forecast in the world and provid...

nature.com