Search Results for author: Sebastian Lerch

Found 15 papers, 10 papers with code

Probabilistic measures afford fair comparisons of AIWP and NWP model output

1 code implementation4 Jun 2025 Tilmann Gneiting, Tobias Biegert, Kristof Kraus, Eva-Maria Walz, Alexander I. Jordan, Sebastian Lerch

Then we find PC as the mean continuous ranked probability score (CRPS) of the postprocessed probabilistic forecasts.

Learning low-dimensional representations of ensemble forecast fields using autoencoder-based methods

1 code implementation6 Feb 2025 Jieyu Chen, Kevin Höhlein, Sebastian Lerch

The first approach derives a distribution-based representation of an input ensemble by applying standard dimensionality reduction techniques in a member-by-member fashion and merging the member representations into a joint parametric distribution model.

Dimensionality Reduction

Graph Neural Networks and Spatial Information Learning for Post-Processing Ensemble Weather Forecasts

no code implementations8 Jul 2024 Moritz Feik, Sebastian Lerch, Jan Stühmer

Ensemble forecasts from numerical weather prediction models show systematic errors that require correction via post-processing.

Graph Neural Network

Improving Model Chain Approaches for Probabilistic Solar Energy Forecasting through Post-processing and Machine Learning

1 code implementation6 Jun 2024 Nina Horat, Sina Klerings, Sebastian Lerch

In a case study based on a benchmark dataset for the Jacumba solar plant in the U. S., we develop statistical and machine learning methods for post-processing ensemble predictions of global horizontal irradiance and solar power generation.

Uncertainty quantification for data-driven weather models

1 code implementation20 Mar 2024 Christopher Bülte, Nina Horat, Julian Quinting, Sebastian Lerch

In a case study on medium-range forecasts of selected weather variables over Europe, the probabilistic forecasts obtained by using the Pangu-Weather model in concert with uncertainty quantification methods show promising results and provide improvements over ensemble forecasts from the physics-based ensemble weather model of the European Centre for Medium-Range Weather Forecasts for lead times of up to 5 days.

Decision Making Uncertainty Quantification +1

Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks

no code implementations8 Sep 2023 Kevin Höhlein, Benedikt Schulz, Rüdiger Westermann, Sebastian Lerch

Statistical postprocessing is used to translate ensembles of raw numerical weather forecasts into reliable probabilistic forecast distributions.

Generative machine learning methods for multivariate ensemble post-processing

1 code implementation26 Sep 2022 Jieyu Chen, Tim Janke, Florian Steinke, Sebastian Lerch

Ensemble weather forecasts based on multiple runs of numerical weather prediction models typically show systematic errors and require post-processing to obtain reliable forecasts.

scoring rule

Convolutional autoencoders for spatially-informed ensemble post-processing

1 code implementation8 Apr 2022 Sebastian Lerch, Kai L. Polsterer

Ensemble weather predictions typically show systematic errors that have to be corrected via post-processing.

Aggregating distribution forecasts from deep ensembles

2 code implementations5 Apr 2022 Benedikt Schulz, Lutz Köhler, Sebastian Lerch

Using theoretical arguments and a comprehensive analysis on twelve benchmark data sets, we systematically compare probability- and quantile-based aggregation methods for three neural network-based approaches with different forecast distribution types as output.

Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparison

2 code implementations17 Jun 2021 Benedikt Schulz, Sebastian Lerch

Postprocessing ensemble weather predictions to correct systematic errors has become a standard practice in research and operations.

BIG-bench Machine Learning quantile regression

From Photometric Redshifts to Improved Weather Forecasts: machine learning and proper scoring rules as a basis for interdisciplinary work

no code implementations5 Mar 2021 Kai Lars Polsterer, Antonio D'Isanto, Sebastian Lerch

We present what we achieved when using proper scoring rules to train deep neural networks as well as to evaluate the model estimates and how this work led from well calibrated redshift estimates to improvements in probabilistic weather forecasting.

Weather Forecasting Instrumentation and Methods for Astrophysics

Machine learning for total cloud cover prediction

no code implementations16 Jan 2020 Ágnes Baran, Sebastian Lerch, Mehrez El Ayari, Sándor Baran

We further assess whether improvements in forecast skill can be obtained by incorporating ensemble forecasts of precipitation as additional predictor.

Astronomy BIG-bench Machine Learning +2

Neural networks for post-processing ensemble weather forecasts

1 code implementation23 May 2018 Stephan Rasp, Sebastian Lerch

Ensemble weather predictions require statistical post-processing of systematic errors to obtain reliable and accurate probabilistic forecasts.

Evaluating probabilistic forecasts with the R package scoringRules

1 code implementation14 Sep 2017 Alexander Jordan, Fabian Krüger, Sebastian Lerch

Probabilistic forecasts in the form of probability distributions over future events have become popular in several fields including meteorology, hydrology, economics, and demography.

Computation Applications

Probabilistic Forecasting and Comparative Model Assessment Based on Markov Chain Monte Carlo Output

no code implementations24 Aug 2016 Fabian Krüger, Sebastian Lerch, Thordis L. Thorarinsdottir, Tilmann Gneiting

Based on proper scoring rules, we develop a notion of consistency that allows to assess the adequacy of methods for estimating the stationary distribution underlying the simulation output.

Methodology

Cannot find the paper you are looking for? You can Submit a new open access paper.