ERA5
PulseAugur coverage of ERA5 — every cluster mentioning ERA5 across labs, papers, and developer communities, ranked by signal.
10 day(s) with sentiment data
-
Frozen neural weather models adapted for climate simulation with Rescene
Researchers have developed Rescene, a novel method to adapt frozen neural weather models for climate simulation. By adding a deterministic wrapper and a spectrally shaped stochastic perturbation, Rescene enables a previ…
-
AI weather models show competitive skill in extreme conditions, study finds
A new study published on arXiv investigates the performance of AI weather models, specifically examining whether they underperform in extreme weather conditions. The research evaluated eleven different physical and AI f…
-
New framework links climate memory to European summer warming risk
A new research paper proposes an empirical framework to better understand and predict European summer warming. The framework decomposes regional warming indicators into inherited memory from slow-state climate patterns …
-
New generative model forecasts tropical cyclones with enhanced speed and accuracy
Researchers have developed a novel deep generative model for tropical cyclone forecasting that can jointly predict satellite imagery and atmospheric fields. This single-pass model, called Latent Rectified Flow, is signi…
-
VeinCast framework enhances weather forecasting with physics-guided graphs
Researchers have developed VeinCast, a novel framework for global medium-range weather forecasting that integrates physics-guided dynamic field graphs with graph-conditioned fusion. This approach combines predefined atm…
-
New latent flow-matching method enhances atmospheric data assimilation
Researchers have developed a novel approach to atmospheric data assimilation using latent video flow-matching. This method trains a prior model on ERA5 reanalysis data and then uses posterior sampling to integrate real-…
-
Study links European warming rates to temperature persistence and Atlantic Ocean influence
A new study analyzing European warming trends from 1950-2024 reveals that regions with higher temperature persistence, particularly those near the Atlantic, are warming at a slower rate compared to continental areas wit…
-
New Conditional Informer model improves ship trajectory prediction
Researchers have developed a new model called the Conditional Informer for predicting ship trajectories over long distances. This model utilizes a novel Conditional Attention mechanism, allowing vessel states to query e…
-
Deep generative models evaluated for reproducing complex spatial data structures
A new research paper evaluates the ability of four deep generative models (DGMs) to reproduce non-stationary Gaussian Random Fields. The study found that while all models could recover the mean surface, their performanc…
-
New toolkit SetGo enhances AI dataset metadata for discovery and reuse
Researchers have developed SetGo, an open-source Python toolkit designed to assess and improve the metadata readiness of scientific datasets for AI applications. SetGo evaluates datasets across six dimensions: completen…
-
New AI method enhances atmospheric data downscaling with physics constraints
Researchers have developed a new Physics-Informed Super-Resolution (PISR) method to improve the accuracy and physical consistency of downscaled atmospheric data. This approach constrains machine learning models with hyd…
-
Machine learning model predicts high-altitude clear air turbulence
Researchers have developed a machine learning approach to predict high-altitude clear air turbulence (CAT) in U.S. airspace. Utilizing pilot reports, ERA5 reanalysis data, and aircraft aerodynamic parameters, the study …
-
LLM-PDESR framework uses LLMs to improve PDE discovery from noisy data
Researchers have developed LLM-PDESR, a new framework designed to improve the discovery of partial differential equations (PDEs) from noisy data. This method combines the symbolic hypothesis generation capabilities of L…
-
Deep learning models analyzed for agricultural weather forecasting
A new research paper explores the effectiveness of deep learning models for meteorological forecasting in agriculture. The study compares recurrent architectures like GRU and LSTM with hybrid models such as 1D-CNN-GRU a…
-
GlacierCastAI uses satellite imagery and climate data to predict glacier retreat
Researchers have developed GlacierCastAI, a novel deep learning model designed to predict glacier retreat using a combination of multi-modal satellite imagery and climate data. The model integrates data from the Landsat…
-
New Sparse-Reslim method boosts weather forecast accuracy and efficiency
Researchers have developed a new method called Sparse-Reslim to improve the efficiency of Vision Transformer (ViT)-based weather forecasting models. This parameter-free module selectively processes only 25% of spatial t…
-
New method probes geospatial SSL representations using environmental signals
Researchers have developed a new method to evaluate self-supervised learning (SSL) representations in geospatial satellite imagery. Instead of relying solely on downstream tasks, this approach probes the representations…
-
New method probes geospatial SSL representations with environmental signals
Researchers have developed a new method to evaluate self-supervised learning (SSL) representations in geospatial data by probing them with environmental signals. This approach uses co-located ERA5 reanalysis variables, …
-
AI downscales climate projections to 25km resolution
Researchers have developed a deep learning framework to downscale climate projections from a lightweight emulator to higher resolutions. This new method utilizes diffusion-based generative models to enhance the ~300 km …
-
New Transformer Framework Enhances Medium-Range Precipitation Forecasting
Researchers have developed CSU-PCAST, a novel deep learning framework utilizing a dual-branch Transformer architecture for medium-range ensemble precipitation forecasting. Trained on ERA5 and NASA IMERG data, the model …