Jesper Dramsch
YOU?
Author Swipe
View article: AIFS 1.1.0: An update to ECMWF's machine-learned weather forecast model AIFS
AIFS 1.1.0: An update to ECMWF's machine-learned weather forecast model AIFS Open
We present an update to ECMWF's machine-learned weather forecasting model AIFS Single with several key improvements. The model now incorporates physical consistency constraints through bounding layers, an updated training schedule, and an …
View article: Towards full AI model lifecycle management on EuroHPC systems, experiences with AIFS for DestinE
Towards full AI model lifecycle management on EuroHPC systems, experiences with AIFS for DestinE Open
View article: AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score
AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score Open
Over the last three decades, ensemble forecasts have become an integral part of forecasting the weather. They provide users with more complete information than single forecasts as they permit to estimate the probability of weather events b…
View article: Robustness of AI-based weather forecasts in a changing climate
Robustness of AI-based weather forecasts in a changing climate Open
Data-driven machine learning models for weather forecasting have made transformational progress in the last 1-2 years, with state-of-the-art ones now outperforming the best physics-based models for a wide range of skill scores. Given the s…
View article: Regional data-driven weather modeling with a global stretched-grid
Regional data-driven weather modeling with a global stretched-grid Open
A data-driven model (DDM) suitable for regional weather forecasting applications is presented. The model extends the Artificial Intelligence Forecasting System by introducing a stretched-grid architecture that dedicates higher resolution o…
View article: AIFS -- ECMWF's data-driven forecasting system
AIFS -- ECMWF's data-driven forecasting system Open
Machine learning-based weather forecasting models have quickly emerged as a promising methodology for accurate medium-range global weather forecasting. Here, we introduce the Artificial Intelligence Forecasting System (AIFS), a data driven…
View article: AIFS – ECMWF’s Data-Driven Probabilistic Forecasting 
AIFS – ECMWF’s Data-Driven Probabilistic Forecasting  Open
In just two years, the idea of an operational data-driven system for medium-range weather forecasting has been transformed from dream to very real possibility. This has occurred through a series of publications from innovators, which have …
View article: The Rise of Data-Driven Weather Forecasting: A First Statistical Assessment of Machine Learning–Based Weather Forecasts in an Operational-Like Context
The Rise of Data-Driven Weather Forecasting: A First Statistical Assessment of Machine Learning–Based Weather Forecasts in an Operational-Like Context Open
Data-driven modeling based on machine learning (ML) is showing enormous potential for weather forecasting. Rapid progress has been made with impressive results for some applications. The uptake of ML methods could be a game changer for the…
View article: The rise of data-driven weather forecasting
The rise of data-driven weather forecasting Open
Data-driven modeling based on machine learning (ML) is showing enormous potential for weather forecasting. Rapid progress has been made with impressive results for some applications. The uptake of ML methods could be a game-changer for the…
View article: Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers
Improving medium-range ensemble weather forecasts with hierarchical ensemble transformers Open
Statistical post-processing of global ensemble weather forecasts is revisited by leveraging recent developments in machine learning. Verification of past forecasts is exploited to learn systematic deficiencies of numerical weather predicti…
View article: Outcomes of the WMO Prize Challenge to Improve Subseasonal to Seasonal Predictions Using Artificial Intelligence
Outcomes of the WMO Prize Challenge to Improve Subseasonal to Seasonal Predictions Using Artificial Intelligence Open
There is a high demand and expectation for subseasonal to seasonal (S2S) prediction, which provides forecasts beyond 2 weeks, but less than 3 months ahead. To assess the potential benefit of artificial intelligence (AI) methods for S2S pre…
View article: Complex-valued neural networks for machine learning on non-stationary physical data
Complex-valued neural networks for machine learning on non-stationary physical data Open
View article: Machine Learning in Geoscience Applications of Deep Neural Networks in 4D Seismic Data Analysis
Machine Learning in Geoscience Applications of Deep Neural Networks in 4D Seismic Data Analysis Open
Machine Learning provides a tool for the modelling and analysis of geoscientific data. I have placed recent developments in deep learning into the greater context of machine learning by reviewing the approaches and challenges of the use of…
View article: Trace Interpolation with Partial CRS-Stacks
Trace Interpolation with Partial CRS-Stacks Open
This bachelor thesis is about seismic trace interpolation, data regularization and extrapolation using partial CRS stacks. I edit the underlying synthetic data record to create sparse data and prepare for extrapolation. The gaps appear ran…
View article: Seismic Subsalt Imaging with Prestack Data Enhancement Methods
Seismic Subsalt Imaging with Prestack Data Enhancement Methods Open
The Levantine basin is a world class site to study the onsets of salt tectonics. A commercial data set will be processed in a conventional processing flow, as well as, several prestack data enhancement methods. These methods include partia…
View article: Deep Unsupervised 4D Seismic 3D Time-Shift Estimation with Convolutional Neural Networks
Deep Unsupervised 4D Seismic 3D Time-Shift Estimation with Convolutional Neural Networks Open
We present a novel 3D warping technique for the estimation of 4D seismic time-shift. This unsupervised method provides a diffeomorphic 3D time shift field that includes uncertainties, therefore it does not need prior time-shift data to be …
View article: An integrated workflow for fracture characterization in chalk reservoirs, applied to the Kraka Field
An integrated workflow for fracture characterization in chalk reservoirs, applied to the Kraka Field Open
View article: Deep Learning Application for 4D Pressure Saturation Inversion Compared to Bayesian Inversion on North Sea Data
Deep Learning Application for 4D Pressure Saturation Inversion Compared to Bayesian Inversion on North Sea Data Open
In this work we present a deep neural network inversion on map-based 4D seismic data for pressure and saturation. We present a novel neural network architecture that trains on synthetic data and provides insights into observed field seismi…
View article: Including Physics in Deep Learning – An Example from 4D Seismic Pressure Saturation Inversion
Including Physics in Deep Learning – An Example from 4D Seismic Pressure Saturation Inversion Open
Geoscience data often have to rely on strong priors in the face of\nuncertainty. Additionally, we often try to detect or model anomalous sparse\ndata that can appear as an outlier in machine learning models. These are\nclassic examples of …
View article: Information Theory Considerations In Patch-Based Training Of Deep Neural Networks On Seismic Time-Series
Information Theory Considerations In Patch-Based Training Of Deep Neural Networks On Seismic Time-Series Open
Recent advances in machine learning relies on convolutional deep neural networks. These are often trained on cropped image patches. Pertaining to non-stationary seismic signals this may introduce low frequency noise and non-generalizabilit…
View article: Gaussian Mixture Models For Robust Unsupervised Scanning-Electron Microscopy Image Segmentation Of North Sea Chalk
Gaussian Mixture Models For Robust Unsupervised Scanning-Electron Microscopy Image Segmentation Of North Sea Chalk Open
Scanning-Electron images from North Sea Chalk are studied for important rock properties. To relieve this manual labor, we investigated several standard image processing methods that underperformed on complicated chalk. Due to the lack of m…
View article: Rapid Seismic Domain Transfer: Seismic Velocity Inversion and Modeling Using Deep Generative Neural Networks
Rapid Seismic Domain Transfer: Seismic Velocity Inversion and Modeling Using Deep Generative Neural Networks Open
Traditional physics-based approaches to infer sub-surface properties such as full-waveform inversion or reflectivity inversion are time-consuming and computationally expensive. We present a deep-learning technique that eliminates the need …
View article: Fracture Characterization and Modelling in the Kraka Field
Fracture Characterization and Modelling in the Kraka Field Open