-
Dr Richard Müller (DWD)
Artificial intelligence is nowadays a central key for the improvement of methods in many modern applications and research areas, e.g. autonomous driving, image / face recognition as well as system simulation and optimization. The usage of AI as well as its success stories are increasing quite rapidly. However, AI is still a little delicate little plant when it comes to weather research and...
Go to contribution page -
Dr Christian Sigg (MeteoSwiss)
MeteoSwiss is engaged in a multi-year effort to renew its automated quality control (AQC) system for surface data.
Go to contribution page
Our AQC used to be a classical expert system built from hand-designed rules. The ruleset follows WMO recommendations and includes tests for physical and climatological limits and tests for the consistency between measurements. Although a lot of domain expertise went into the... -
Hella Riede (DWD)
The nowcasting community at DWD aims to optimally combine all available observational data for a better understanding of convection and severe weather, with a focus on remote sensing data. Traditionally, forecasters use radar and satellite imagery and overlays. Data fusion and plausibility checks thus solely happen in the human brain, based on experience. The human brain is expert in pattern...
Go to contribution page -
Dr Andrea Pagani (KNMI), Mr Jan Willem Noteboom (KNMI)
Fog is a meteorological phenomenon that reduces visibility and poses safety threats to road, maritime and aeronautical traffic. Visibility observations are commonly obtained manually or by sensors that are expensive and usually limited to critical locations such as airports. Fog is difficult to accurately forecast since several factors play a role in its formation and dissipation. Furthermore,...
Go to contribution page -
Arthur Moraux (RMIB,VUB)
This paper proposes a multimodal and multi-task deep-learning model for instantaneous precipitation rate estimation. Using both thermal infrared satellite radiometer and automatic rain gauge measurements as input, our encoder–decoder convolutional neural network performs a multiscale analysis of these two modalities to estimate simultaneously the rainfall probability and the precipitation rate...
Go to contribution page -
Ms Petrina Papazek (ZAMG)
Seamless forecasting from nowcasting to days-ahead for the energy sector allows for targeted trading, maintenance, and providing active power grid safety measures such as re-scheduling of solar and wind power production farms. As direct NWP model output often is too coarse for targeted forecasts, post-processing is needed. In the past decades, machine learning tools are being used more...
Go to contribution page -
Mr Kevin Höhlein (Computer Graphics & Visualization Group, Technische Universität München, Garching, Germany)
High-resolution simulation models (of order kms or less) can deliver highly accurate low-level winds and their climatologies. The problem is that one cannot afford to run simulations at very high resolution over extended spatial domains for long periods because the computational power needed is prohibitive.
Instead, we propose using neural networks to downscale low-resolution wind-field...
Go to contribution page -
11. First Machine Learning Experiments Using Neural Networks for Postprocessing of NWP Output at DWDDr Bernhard Reichert (Deutscher Wetterdienst)
For about two decades, operational postprocessing of NWP output for short-range and medium-range forecasts at Deutscher Wetterdienst (DWD) has been mainly based on linear/logistic regression Model Output Statistics (MOS) approaches. However, Artificial Intelligence (AI) has nowadays become a central key for many modern applications and research areas, and it also gains more and more importance...
Go to contribution page -
Steven Dewitte
AI is transforming many aspects of society at an incredible speed. Also for the application to weather and climate studies is shows great promise.
Go to contribution page -
Markus Koskela (CSC - IT Center for Science Ltd)
The Improved Observation Usage in NWP (iOBS) project aims to contribute to improved weather forecast quality from existing and emerging observation systems by combining world-leading NWP with future generation e-infrastructure. The project targets to produce effective assimilation of diverse observations in regional high-resolution NWP models. The observations include, among other sources,...
Go to contribution page -
Dr Dirk Lauwaet (VITO)
In the framework of the H2020 Climate-fit.city project, VITO has developed an interactive heat stress mapping tool, based on neural network models. The tool builds on results from the high-resolution urban climate model UrbClim, which was used to map several heat stress indicators (Urban Heat Island intensity, number of Heat Wave Days, …) for a number of European cities. Afterwards, neural...
Go to contribution page -
Sebastian Lerch (Karlsruhe Institute of Technology)
Ensemble weather predictions require statistical postprocessing of systematic errors to obtain reliable and accurate probabilistic forecasts. Traditionally, this is accomplished with distributional regression models in which the parameters of a predictive distribution are estimated from a training period. We propose a flexible alternative based on neural networks that can incorporate nonlinear...
Go to contribution page -
Matteo Buzzi
Current state of the art numerical weather prediction models as COSMO-1 running at very high horizontal resolution (~1km) and using sophisticated assimilation techniques still show substantial biases in wind forecasts, above all in very complex topography such as the Alps.
Go to contribution page
The INCA-CH system, running at MeteoSwiss, tries to correct the COSMO-1 bias on a 1km grid using the available surface... -
Dr Jorge Sousa (Flemish Institute for Technological Research (VITO))
In this talk, we will demonstrate the performance of a neural network approach in predicting the daily average concentration of NO2, PM10 and PM2.5 in different countries. The neural network is trained with archived observations where meteorological parameters and chemical transport predictions serve as inputs. The archived and forecasted chemical transport predictions are obtained through the...
Go to contribution page -
Dr Bing Gong (Jülich Supercomputing Centre, Forschungszentrum Jülich, Germany )
This study explores the adaptation of state-of-the-art deep learning architectures for video frame prediction in the context of weather and climate applications. As a case study, we attempt to predict surface temperature fields over Europe for up to 24 hours based on meteorological analyses. Initial results have been achieved with a PredNet and a GAN architecture. To facilitate the massive...
Go to contribution page -
Lionel Moret (MeteoSwiss)
Weather forecasts have been steadily improving in quality over the last decades. At the same time, users demand more and more localized weather information for any locations and the large amount of weather forecast data and the pressure on resources demand the automation of the forecasting process. The ongoing improvements in forecast quality are due to advances in numerical weather prediction...
Go to contribution page -
Ms Emma Boucheron (WeatherForce)
Rain forecasting in Africa is essential in areas such as agriculture or flood and drought prevention. However, as rain gauges network are expensive to set up and maintain, unfortunately, a very limited number of them are operational in most African countries. The consequence of the lack of in-situ data negatively impact rain forecasting spatial and temporal accuracy. In this work, we present...
Go to contribution page -
Mrs kelly Grassi (Ifremer, UlLCO LISIC, WeatherForce)
Over the last decade, extreme events (i.e., storms, floods, droughts) are more and more frequent and/or intensive. 85% of the world's population is affected by these events. 70% of the world economy is dependent on meteorology according to the United Nations. 75% of the most vulnerable countries has no or little reliable, accurate and effective weather information. Indeed, some National...
Go to contribution page -
Dr Henry Odbert (Met Office)
The weather has wide-ranging impact on many aspects of transport, in terms of both efficiency and safety. As transport systems become more automated and more connected, there is a growing necessity for weather impacts to be assessed and managed by vehicles and the infrastructure they use. For example, a vehicle’s Automated Driving System (ADS) must be able to accurately determine whether or...
Go to contribution page -
Mr Simon Veldkamp (KNMI; Utrecht University), Dr Maurice Schmeits (KNMI)
Weather forecasts as provided by numerical weather prediction (NWP) models such as Harmonie-Arome, which is used by KNMI, are often (too) deterministic. Because of uncertainty in the forecast, it is preferable to have a full probability distribution instead.
Go to contribution page
Current statistical post-processing methods for providing a probabilistic forecast are not capable of using full spatial patterns from... -
Mr Charlie Kirkwood (University of Exeter)
Weather forecasting continues to become ever more data intensive. Numerical Weather Prediction (NWP) models are becoming more complex, with higher resolution, and there are increasing numbers of different models in operation around the world. For the weather forecaster and the end user, the amount and complexity of information available seems to make life more complicated. Which model should...
Go to contribution page -
Dr Michael Hoff (German Weather Service)
At DWD exists a weather interpretation of model output from the global ICON, ICON-EU and COSMO-D2, which will be replaced by ICON-LAM in the near future. By applying a whole bunch of WMO compliant thresholds with complex relationships to all relevant model variables, e.g. temperature, pressure in different height levels, rain rate, wind gusts, cloud cover, etc., the goal of the weather...
Go to contribution page -
Leif Denby
The representation of shallow trade-wind convective clouds in climate models
Go to contribution page
dominates the uncertainty in climate sensitivity estimates. In
particular the
radiative impact of cloud spatial organisation is poorly understood.
This work
presents the first unsupervised neural network model which
autonomously discovers cloud organisation regimes in satellite images.
Trained
on 10,000... -
Ms Meike Hellweg (Associated PhD Student of Audi and the Karlsruhe Institute of Technology (KIT))
Using artificial intelligence to correct weather related vehicle data
Hellweg, M.(1) ; Stiller, C.(1)
(1) Institute for Measurement and Control Systems, Karlsruhe Institute of Technology (KIT)The project “Fleet-Weather-Map” aims to use vehicles as mobile weather stations. With the vehicular data the improvement of spatial and temporal resolution of weather forecasts and...
Go to contribution page -
Dr Omar Jamil (Met Office)
The representation of subgrid processes is a source of uncertainty and a limitation of global models. Cloud Resolving Models (CRM) can model some of these processes more accurately. However, in terms of computational costs, running convection permitting CRMs on a global scale is prohibitively expensive. Here we present some early results of our work where deep neural networks are used to learn...
Go to contribution page -
Dr Daniele Nerini (MeteoSwiss)
In this study, we exploit a 10-year archive of composite radar images over the Swiss Alpine region to improve precipitation nowcasting methods based on persistence. The underpinning hypothesis is that growth and decay is more predictable in mountainous regions due to the presence of systematic orographic effects. To this end, the variables related to geographical location, mesoscale motion,...
Go to contribution page
Choose timezone
Your profile timezone: