arXiv subjects

Georg J. Mayr

Publications and source records attributed to Georg J. Mayr.

9 recordsLinked to original sources

arXiv2024

Long-term foehn reconstruction combining unsupervised and supervised learning

Foehn winds, characterized by abrupt temperature increases and wind speed changes, significantly impact regions on the leeward side of mountain ranges, e.g., by spreading wildfires. Understanding how foehn occurrences change under climate change is crucial. Unfortunately, foehn cannot be measured directly but has to be inferred from meteorological measurements employing suitable classification schemes. Hence, this approach is typically limited to specific periods for which the necessary data are available. We present a novel approach for reconstructing historical foehn occurrences using a combination of unsupervised and supervised probabilistic statistical learning methods. We utilize in-situ measurements (available for recent decades) to train an unsupervised learner (finite mixture model) for automatic foehn classification. These labeled data are then linked to reanalysis data (covering longer periods) using a supervised learner (lasso or boosting). This allows to reconstruct past foehn probabilities based solely on reanalysis data. Applying this method to ERA5 reanalysis data for six stations across Switzerland and Austria achieves accurate hourly reconstructions of north and south foehn occurrence, respectively, dating back to 1940. This paves the way for investigating how seasonal foehn patterns have evolved over the past 83 years, providing valuable insights into climate change impacts on these critical wind events.

stat.AP↗

arXiv2024

Identifying Lightning Processes in ERA5 Soundings with Deep Learning

Atmospheric environments favorable for lightning and convection are commonly represented by proxies or parameterizations based on expert knowledge such as CAPE, wind shears, charge separation, or combinations thereof. Recent developments in the field of machine learning, high resolution reanalyses, and accurate lightning observations open possibilities for identifying tailored proxies without prior expert knowledge. To identify vertical profiles favorable for lightning, a deep neural network links ERA5 vertical profiles of cloud physics, mass field variables and wind to lightning location data from the Austrian Lightning Detection and Information System (ALDIS), which has been transformed to a binary target variable labelling the ERA5 cells as cells with lightning activity and cells without lightning activity. The ERA5 parameters are taken on model levels beyond the tropopause forming an input layer of approx. 670 features. The data of 2010-2018 serve as training/validation. On independent test data, 2019, the deep network outperforms a reference with features based on meteorological expertise. SHAP values highlight the atmospheric processes learned by the network which identifies cloud ice and snow content in the upper and mid-troposphere as very relevant features. As these patterns correspond to the separation of charge in thunderstorm cloud, the deep learning model can serve as physically meaningful description of lightning. Depending on the region, the neural network also exploits the vertical wind or mass profiles to correctly classify cells with lightning activity.

physics.ao-ph↗

arXiv2024

Spatio-seasonal risk assessment of upward lightning at tall objects using meteorological reanalysis data

This study investigates lightning at tall objects and evaluates the risk of upward lightning (UL) over the eastern Alps and its surrounding areas. While uncommon, UL poses a threat, especially to wind turbines, as the long-duration current of UL can cause significant damage. Current risk assessment methods overlook the impact of meteorological conditions, potentially underestimating UL risks. Therefore, this study employs random forests, a machine learning technique, to analyze the relationship between UL measured at Gaisberg Tower (Austria) and $35$ larger-scale meteorological variables. Of these, the larger-scale upward velocity, wind speed and direction at 10 meters and cloud physics variables contribute most information. The random forests predict the risk of UL across the study area at a 1 km$^2$ resolution. Strong near-surface winds combined with upward deflection by elevated terrain increase UL risk. The diurnal cycle of the UL risk as well as high-risk areas shift seasonally. They are concentrated north/northeast of the Alps in winter due to prevailing northerly winds, and expanding southward, impacting northern Italy in the transitional and summer months. The model performs best in winter, with the highest predicted UL risk coinciding with observed peaks in measured lightning at tall objects. The highest concentration is north of the Alps, where most wind turbines are located, leading to an increase in overall lightning activity. Comprehensive meteorological information is essential for UL risk assessment, as lightning densities are a poor indicator of lightning at tall objects.

physics.soc-ph↗

arXiv2023

Upward lightning at wind turbines: Risk assessment from larger-scale meteorology

Upward lightning (UL) has become an increasingly important threat to wind turbines as ever more of them are being installed for renewably producing electricity. The taller the wind turbine the higher the risk that the type of lightning striking the man-made structure is UL. UL can be much more destructive than downward lightning due to its long lasting initial continuous current leading to a large charge transfer within the lightning discharge process. Current standards for the risk assessment of lightning at wind turbines mainly take the summer lightning activity into account, which is inferred from LLS. Ground truth lightning current measurements reveal that less than 50% of UL might be detected by lightning location systems (LLS). This leads to a large underestimation of the proportion of LLS-non-detectable UL at wind turbines, which is the dominant lightning type in the cold season. This study aims to assess the risk of LLS-detectable and LLS-non-detectable UL at wind turbines using direct UL measurements at the Gaisberg Tower (Austria) and Säntis Tower (Switzerland). Direct UL observations are linked to meteorological reanalysis data and joined by random forests, a powerful machine learning technique. The meteorological drivers for the non-/occurrence of LLS-detectable and LLS-non-detectable UL, respectively, are found from the random forest models trained at the towers and have large predictive skill on independent data. In a second step the results from the tower-trained models are extended to a larger study domain (Central and Northern Germany). The tower-trained models for LLS-detectable lightning is independently verified at wind turbine locations in that domain and found to reliably diagnose that type of UL. Risk maps based on case study events show that high diagnosed probabilities in the study domain coincide with actual UL events.

stat.ML↗

arXiv2022

Upward Lightning at the Gaisberg Tower: Initiation Mechanism and Flash Type and the Atmospheric Influence

Upward lightning is much rarer than downward lightning and requires tall ($100+$~m) structures to initiate. It may be either triggered by other lightning discharges or completely self-initiated. While conventional lightning location systems reliably detect downward lightning, they miss a specific flash type of upward lightning that consists only of a continuous current. Globally, only few specially instrumented towers can detect this flash type. The proliferation of wind turbines in combination with large damage from upward lightning necessitates an improved understanding under which conditions the self-initiated and the undetected subtype of upward lightning occur. To find larger-scale meteorological conditions favorable for self-initiated and undetectable upward lightning, this study uses a random forest machine learning model. It combines direct measurements at the specially instrumented tower at Gaisberg mountain in Austria with explanatory variables from larger-scale atmospheric reanalysis data (ERA5). Atmospheric variables reliably explain whether upward lightning is self-initiated by the tower or triggered by other lightning discharges. The most important variable is the height of the $-10~^\circ$C isotherm above the tall structure: the closer it is the higher is the probability of self-initiated upward lightning. Two-meter temperature and the amount of CAPE are also important. For the occurrence of upward lightning undetectable by lightning location systems, this study finds a strong relationship to the absence of lightning in the vicinity.

physics.ao-ph↗

arXiv2022

Daily-Resolved Lightning Climatology of the Eastern Alpine Region at the Kilometer Scale

Lightning flashes are rare albeit hazardous events. Despite this scarcity, generalized additive models (GAMs) succeed in producing a climatology of lightning occurrence for the eastern Alps and surrounding lowlands at an unprecedented resolution of 1\,km$^2$ for each day of April through September with data from the ALDIS lightning location system. The GAM adds the effects of seasonality, jaggedness of the terrain, and seasonally varying effects of elevation and region, thus combining information from analysis cells sharing similar characteristics. The probability of a cloud-to-ground discharge over 1\,km$^2$ on a given day is typically less than 1\,\% with a rapid increase in spring, followed by a plateau and a gentler tapering-off in fall. Probabilities early are lower at high elevations but increase once their snow cover is gone. Regional patterns of lightning also vary with season with an overall southward shift later in the year but more complex details. Grid cells with jagged topography have a higher probability of lightning.

physics.ao-ph↗

arXiv2021

Cholesky-based multivariate Gaussian regression

Distributional regression is extended to Gaussian response vectors of dimension greater than two by parameterizing the covariance matrix $Σ$ of the response distribution using the entries of its Cholesky decomposition. The more common variance-correlation parameterization limits such regressions to bivariate responses -- higher dimensions require complicated constraints among the correlations to ensure positive definite $Σ$ and a well-defined probability density function. In contrast, Cholesky-based parameterizations ensure positive definiteness for all distributional dimensions no matter what values the parameters take, enabling estimation and regularization as for other distributional regression models. In cases where components of the response vector are assumed to be conditionally independent beyond a certain lag $r$, model complexity can be further reduced by setting Cholesky parameters beyond this lag to zero a priori. Cholesky-based multivariate Gaussian regression is first illustrated and assessed on artificial data and subsequently applied to a real-world 10-dimensional weather forecasting problem. There the regression is used to obtain reliable joint probabilities of temperature across ten future times, leveraging temporal correlations over the prediction period to obtain more precise and meteorologically consistent probabilistic forecasts.

stat.ME↗

arXiv2020

Circular Regression Trees and Forests with an Application to Probabilistic Wind Direction Forecasting

While circular data occur in a wide range of scientific fields, the methodology for distributional modeling and probabilistic forecasting of circular response variables is rather limited. Most of the existing methods are built on the framework of generalized linear and additive models, which are often challenging to optimize and to interpret. Therefore, we suggest circular regression trees and random forests as an intuitive alternative approach that is relatively easy to fit. Building on previous ideas for trees modeling circular means, we suggest a distributional approach for both trees and forests yielding probabilistic forecasts based on the von Mises distribution. The resulting tree-based models simplify the estimation process by using the available covariates for partitioning the data into sufficiently homogeneous subgroups so that a simple von Mises distribution without further covariates can be fitted to the circular response in each subgroup. These circular regression trees are straightforward to interpret, can capture nonlinear effects and interactions, and automatically select the relevant covariates that are associated with either location and/or scale changes in the von Mises distribution. Combining an ensemble of circular regression trees to a circular regression forest yields a local adaptive likelihood estimator for the von Mises distribution that can regularize and smooth the covariate effects. The new methods are evaluated in a case study on probabilistic wind direction forecasting at two Austrian airports, considering other common approaches as a benchmark.

stat.ME↗

arXiv2019

Bivariate Gaussian models for wind vectors in a distributional regression framework

A new probabilistic post-processing method for wind vectors is presented in a distributional regression framework employing the bivariate Gaussian distribution. In contrast to previous studies all parameters of the distribution are simultaneously modeled, namely the means and variances for both wind components and also the correlation coefficient between them employing flexible regression splines. To capture a possible mismatch between the predicted and observed wind direction, ensemble forecasts of both wind components are included using flexible two-dimensional smooth functions. This encompasses a smooth rotation of the wind direction conditional on the season and the forecasted ensemble wind direction. The performance of the new method is tested for stations located in plains, mountain foreland, and within an alpine valley employing ECMWF ensemble forecasts as explanatory variables for all distribution parameters. The rotation-allowing model shows distinct improvements in terms of predictive skill for all sites compared to a baseline model that post-processes each wind component separately. Moreover, different correlation specifications are tested and small improvements compared to the model setup with no estimated correlation could be found for stations located in alpine valleys.

stat.AP↗