ERA5
PulseAugur coverage of ERA5 — every cluster mentioning ERA5 across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
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 …
-
Federated Learning Optimizes IoT Rainfall Prediction with Adaptive Compression
Researchers have developed a novel Federated Split Learning (FSL) framework designed to optimize communication efficiency for IoT devices engaged in rainfall prediction. This framework uniquely integrates activation com…
-
Otter Weather AI model offers efficient, skillful medium-range forecasting
Researchers have developed Otter Weather, a new AI model for medium-range weather forecasting that aims to be more efficient and accessible than current state-of-the-art methods. The model significantly improves the ski…
-
New CanadaFireSat dataset enables high-resolution wildfire forecasting
Researchers have developed a new benchmark dataset called CanadaFireSat to improve high-resolution wildfire forecasting. This dataset utilizes multi-modal data, including high-resolution satellite imagery from Sentinel-…
-
Graph Neural Networks Reconstruct Historical Water Storage Data
Researchers have developed a novel approach using spatio-temporal graph neural networks (MTGNN) to reconstruct historical terrestrial water storage (TWS) data. This deep learning model learns from meteorological forcing…
-
SIMBA framework enhances weather prediction with bidirectional radiance modeling · 2 sources tracked
Researchers have developed SIMBA, a novel bidirectional framework for modeling hyperspectral infrared radiances from the FY-4A GIIRS instrument. This framework uniquely integrates atmospheric profile retrieval and radia…
-
Deep Neural Networks Show Mixed Results in Scientific Data Compression
A new research paper explores the use of deep neural networks for compressing large scientific datasets, specifically within the climate domain. The study integrated models like VAEformer, GraphCast, and Aurora into a c…
-
Quantum-Informed ML Shows Practical Advantage in Chaos Prediction
Researchers have developed a new theoretical framework for achieving practical quantum advantage in quantum-informed machine learning, specifically for predicting chaotic systems. This approach utilizes higher-order qua…
-
New RGFiLM Method Improves Anomaly Detection in Rare Contexts
Researchers have developed a new method called Rarity-Gated Feature-wise Linear Modulation (RGFiLM) to improve anomaly detection in contexts with imbalanced data distributions. This technique uses a rarity score to cont…
-
AI models ArchesWeather and ArchesWeatherGen show climate simulation stability
Researchers have evaluated ArchesWeather and ArchesWeatherGen, two machine learning models originally designed for weather forecasting, for their capabilities in long-term climate simulations. When adapted to act as for…
-
AI model generates realistic global precipitation fields
Researchers have developed a novel machine learning approach using a conditional diffusion model with a UNet architecture to generate realistic global precipitation fields. This method aims to improve the representation…
-
New benchmark RealBench improves AI weather forecast evaluation
Researchers have introduced RealBench, a new benchmark designed to more accurately evaluate AI weather forecasting models under real-world operational conditions. Unlike previous benchmarks that relied on reanalysis dat…
-
New solver bridges AI with physics for field reconstruction
Researchers have developed a novel physics-informed generative solver designed to reconstruct complex physical fields from limited data. This method integrates data-driven learning with fundamental conservation laws, en…
-
Multi-Scale Wavelet Transformers Enhance Dynamical System Operator Learning
Researchers have developed Multi-Scale Wavelet Transformers (MSWTs) to improve the accuracy of data-driven models for dynamical systems, particularly in areas like weather forecasting. These models, known as neural oper…
-
AI models learn tropical cyclone dynamics and aid weather data discovery
Researchers have developed a new 10-term cubic stochastic differential equation model to simulate tropical cyclone intensification, trained on historical intensity data and environmental features. This model successfull…
-
Earth System Foundation Model integrates diverse data for climate forecasting
Researchers have developed the Earth System Foundation Model (ESFM), an open-source framework designed to integrate and forecast using diverse Earth system data. ESFM builds upon the Aurora model's architecture and inco…
-
AI weather models show promise for extreme event prediction with uncertainty quantification
A new study published on arXiv investigates the effectiveness of AI-based weather models in predicting extreme events by quantifying their uncertainty. Researchers found that while models like FuXi, GraphCast, and SFNO …
-
New signature kernel scoring rule enhances weather forecasting accuracy
Researchers have introduced a new metric called the signature kernel scoring rule for probabilistic weather forecasting. This rule reframes weather variables as continuous paths, using iterated integrals to capture temp…
-
AI model enhances climate data resolution for renewable energy forecasting
Researchers have developed a super-resolution recurrent diffusion model (SRDM) to enhance the temporal resolution of climate data for more accurate renewable energy generation predictions. This model addresses the limit…