Refine
Year of publication
Document Type
- Article (25)
- Postprint (8)
- Other (2)
- Habilitation Thesis (1)
Language
- English (36) (remove)
Is part of the Bibliography
- yes (36)
Keywords
- Algorithm (2)
- Band (2)
- Kwajalein (2)
- Methodology (2)
- Reflectivity (2)
- Uncertainties (2)
- Weather (2)
- models (2)
- skill (2)
- weather (2)
- 3D CAVE (1)
- Extreme discharge data (1)
- Extreme event (1)
- Flash flood analysis (1)
- Flood forecasting (1)
- Forensic disaster analysis (1)
- Hydrological modelling (1)
- Nordic catchments (1)
- Radar rainfall data (1)
- Remote sensing (1)
- Soil moisture (1)
- Soil moisture measurement comparison (1)
- Weather radar (1)
- attenuation (1)
- differential split-sample test (1)
- flood generating processes (1)
- flood risk (1)
- flood seasonality (1)
- heavy rainfall (1)
- higher education (1)
- hydrological modelling (1)
- immersive 3D geovisualization (1)
- learning success (1)
- quantitative precipitation estimation (1)
- student survey (1)
Institute
- Institut für Geowissenschaften (36) (remove)
The phi(ev) is calculated from high-resolution discharge and precipitation data for several rain events with a cumulative precipitation P-cum ranging from less than 5mm to more than 80 mm. Because of the high uncertainty of phi(ev) associated with the hydrograph separation method, phi(ev) is calculated with several methods, including graphical methods, digital filters and a tracer-based method. The results indicate that the hydrological response depends on (theta) over bar (ini): during dry conditions phi(ev) is consistently below 0.1, even for events with high and intense precipitation. Above a threshold of (theta) over bar (ini) = 34 vol % phi(ev) can reach values up to 0.99 but there is a high scatter. Some variability can be explained with a weak correlation of phi(ev) with P-cum and rain intensity, but a considerable part of the variability remains unexplained. It is concluded that threshold-based methods can be helpful to prevent overestimation of the hydrological response during dry catchment conditions. The impact of soil moisture on the hydrological response during wet catchment conditions, however, is still insufficiently understood and cannot be generalized based on the present results.
High precipitation quantiles tend to rise with temperature, following the so-called Clausius-Clapeyron (CC) scaling. It is often reported that the CC-scaling relation breaks down and even reverts for very high temperatures. In our study, we investigate this reversal using observational climate data from 142 stations across Germany. One of the suggested meteorological explanations for the breakdown is limited moisture supply. Here we argue that, instead, it could simply originate from undersampling. As rainfall frequency generally decreases with higher temperatures, rainfall intensities as dictated by CC scaling are less likely to be recorded than for moderate temperatures. Empirical quantiles are conventionally estimated from order statistics via various forms of plotting position formulas. They have in common that their largest representable return period is given by the sample size. In small samples, high quantiles are underestimated accordingly. The small-sample effect is weaker, or disappears completely, when using parametric quantile estimates from a generalized Pareto distribution (GPD) fitted with L moments. For those, we obtain quantiles of rainfall intensities that continue to rise with temperature.
An Overview of Using Weather Radar for Climatological Studies: Successes, Challenges, and Potential
(2019)
Weather radars have been widely used to detect and quantify precipitation and nowcast severe weather for more than 50 years. Operational weather radars generate huge three-dimensional datasets that can accumulate to terabytes per day. So it is essential to review what can be done with existing vast amounts of data, and how we should manage the present datasets for the future climatologists. All weather radars provide the reflectivity factor, and this is the main parameter to be archived. Saving reflectivity as volumetric data in the original spherical coordinates allows for studies of the three-dimensional structure of precipitation, which can be applied to understand a number of processes, for example, analyzing hail or thunderstorm modes. Doppler velocity and polarimetric moments also have numerous applications for climate studies, for example, quality improvement of reflectivity and rain rate retrievals, and for interrogating microphysical and dynamical processes. However, observational data alone are not useful if they are not accompanied by sufficient metadata. Since the lifetime of a radar ranges between 10 and 20 years, instruments are typically replaced or upgraded during climatologically relevant time periods. As a result, present metadata often do not apply to past data. This paper outlines the work of the Radar Task Team set by the Atmospheric Observation Panel for Climate (AOPC) and summarizes results from a recent survey on the existence and availability of long time series. We also provide recommendations for archiving current and future data and examples of climatological studies in which radar data have already been used.
Many institutions struggle to tap into the potential of their large archives of radar reflectivity: these data are often affected by miscalibration, yet the bias is typically unknown and temporally volatile. Still, relative calibration techniques can be used to correct the measurements a posteriori. For that purpose, the usage of spaceborne reflectivity observations from the Tropical Rainfall Measuring Mission (TRMM) and Global Precipitation Measurement (GPM) platforms has become increasingly popular: the calibration bias of a ground radar (GR) is estimated from its average reflectivity difference to the spaceborne radar (SR). Recently, Crisologo et al. (2018) introduced a formal procedure to enhance the reliability of such estimates: each match between SR and GR observations is assigned a quality index, and the calibration bias is inferred as a quality-weighted average of the differences between SR and GR. The relevance of quality was exemplified for the Subic S-band radar in the Philippines, which is greatly affected by partial beam blockage.
The present study extends the concept of quality-weighted averaging by accounting for path-integrated attenuation (PIA) in addition to beam blockage. This extension becomes vital for radars that operate at the C or X band. Correspondingly, the study setup includes a C-band radar that substantially overlaps with the S-band radar. Based on the extended quality-weighting approach, we retrieve, for each of the two ground radars, a time series of calibration bias estimates from suitable SR overpasses. As a result of applying these estimates to correct the ground radar observations, the consistency between the ground radars in the region of overlap increased substantially. Furthermore, we investigated if the bias estimates can be interpolated in time, so that ground radar observations can be corrected even in the absence of prompt SR overpasses. We found that a moving average approach was most suitable for that purpose, although limited by the absence of explicit records of radar maintenance operations.
RainNet v1.0
(2020)
In this study, we present RainNet, a deep convolutional neural network for radar-based precipitation nowcasting. Its design was inspired by the U-Net and SegNet families of deep learning models, which were originally designed for binary segmentation tasks. RainNet was trained to predict continuous precipitation intensities at a lead time of 5min, using several years of quality-controlled weather radar composites provided by the German Weather Service (DWD). That data set covers Germany with a spatial domain of 900km × 900km and has a resolution of 1km in space and 5min in time. Independent verification experiments were carried out on 11 summer precipitation events from 2016 to 2017. In order to achieve a lead time of 1h, a recursive approach was implemented by using RainNet predictions at 5min lead times as model inputs for longer lead times. In the verification experiments, trivial Eulerian persistence and a conventional model based on optical flow served as benchmarks. The latter is available in the rainymotion library and had previously been shown to outperform DWD's operational nowcasting model for the same set of verification events.
RainNet significantly outperforms the benchmark models at all lead times up to 60min for the routine verification metrics mean absolute error (MAE) and the critical success index (CSI) at intensity thresholds of 0.125, 1, and 5mm h⁻¹. However, rainymotion turned out to be superior in predicting the exceedance of higher intensity thresholds (here 10 and 15mm h⁻¹). The limited ability of RainNet to predict heavy rainfall intensities is an undesirable property which we attribute to a high level of spatial smoothing introduced by the model. At a lead time of 5min, an analysis of power spectral density confirmed a significant loss of spectral power at length scales of 16km and below. Obviously, RainNet had learned an optimal level of smoothing to produce a nowcast at 5min lead time. In that sense, the loss of spectral power at small scales is informative, too, as it reflects the limits of predictability as a function of spatial scale. Beyond the lead time of 5min, however, the increasing level of smoothing is a mere artifact – an analogue to numerical diffusion – that is not a property of RainNet itself but of its recursive application. In the context of early warning, the smoothing is particularly unfavorable since pronounced features of intense precipitation tend to get lost over longer lead times. Hence, we propose several options to address this issue in prospective research, including an adjustment of the loss function for model training, model training for longer lead times, and the prediction of threshold exceedance in terms of a binary segmentation task. Furthermore, we suggest additional input data that could help to better identify situations with imminent precipitation dynamics. The model code, pretrained weights, and training data are provided in open repositories as an input for such future studies.
The flash-flood in Braunsbach in the north-eastern part of Baden-Wuerttemberg/Germany was a particularly strong and concise event which took place during the floods in southern Germany at the end of May/early June 2016. This article presents a detailed analysis of the hydro-meteorological forcing and the hydrological consequences of this event. A specific approach, the "forensic hydrological analysis" was followed in order to include and combine retrospectively a variety of data from different disciplines. Such an approach investigates the origins, mechanisms and course of such natural events if possible in a "near real time" mode, in order to follow the most recent traces of the event. The results show that it was a very rare rainfall event with extreme intensities which, in combination with catchment properties, led to extreme runoff plus severe geomorphological hazards, i.e. great debris flows, which together resulted in immense damage in this small rural town Braunsbach. It was definitely a record-breaking event and greatly exceeded existing design guidelines for extreme flood discharge for this region, i.e. by a factor of about 10. Being such a rare or even unique event, it is not reliably feasible to put it into a crisp probabilistic context. However, one can conclude that a return period clearly above 100 years can be assigned for all event components: rainfall, peak discharge and sediment transport. Due to the complex and interacting processes, no single flood cause or reason for the very high damage can be identified, since only the interplay and the cascading characteristics of those led to such an event. The roles of different human activities on the origin and/or intensification of such an extreme event are finally discussed. (C) 2018 Elsevier B.V. All rights reserved.
This paper investigates the transferability of calibrated HBV model parameters under stable and contrasting conditions in terms of flood seasonality and flood generating processes (FGP) in five Norwegian catchments with mixed snowmelt/rainfall regimes. We apply a series of generalized (differential) split-sample tests using a 6-year moving window over (i) the entire runoff observation periods, and (ii) two subsets of runoff observations distinguished by the seasonal occurrence of annual maximum floods during either spring or autumn. The results indicate a general model performance loss due to the transfer of calibrated parameters to independent validation periods of -5 to -17%, on average. However, there is no indication that contrasting flood seasonality exacerbates performance losses, which contradicts the assumption that optimized parameter sets for snowmelt-dominated floods (during spring) perform particularly poorly on validation periods with rainfall-dominated floods (during autumn) and vice versa.
RainNet v1.0
(2020)
In this study, we present RainNet, a deep convolutional neural network for radar-based precipitation nowcasting. Its design was inspired by the U-Net and SegNet families of deep learning models, which were originally designed for binary segmentation tasks. RainNet was trained to predict continuous precipitation intensities at a lead time of 5min, using several years of quality-controlled weather radar composites provided by the German Weather Service (DWD). That data set covers Germany with a spatial domain of 900km × 900km and has a resolution of 1km in space and 5min in time. Independent verification experiments were carried out on 11 summer precipitation events from 2016 to 2017. In order to achieve a lead time of 1h, a recursive approach was implemented by using RainNet predictions at 5min lead times as model inputs for longer lead times. In the verification experiments, trivial Eulerian persistence and a conventional model based on optical flow served as benchmarks. The latter is available in the rainymotion library and had previously been shown to outperform DWD's operational nowcasting model for the same set of verification events.
RainNet significantly outperforms the benchmark models at all lead times up to 60min for the routine verification metrics mean absolute error (MAE) and the critical success index (CSI) at intensity thresholds of 0.125, 1, and 5mm h⁻¹. However, rainymotion turned out to be superior in predicting the exceedance of higher intensity thresholds (here 10 and 15mm h⁻¹). The limited ability of RainNet to predict heavy rainfall intensities is an undesirable property which we attribute to a high level of spatial smoothing introduced by the model. At a lead time of 5min, an analysis of power spectral density confirmed a significant loss of spectral power at length scales of 16km and below. Obviously, RainNet had learned an optimal level of smoothing to produce a nowcast at 5min lead time. In that sense, the loss of spectral power at small scales is informative, too, as it reflects the limits of predictability as a function of spatial scale. Beyond the lead time of 5min, however, the increasing level of smoothing is a mere artifact – an analogue to numerical diffusion – that is not a property of RainNet itself but of its recursive application. In the context of early warning, the smoothing is particularly unfavorable since pronounced features of intense precipitation tend to get lost over longer lead times. Hence, we propose several options to address this issue in prospective research, including an adjustment of the loss function for model training, model training for longer lead times, and the prediction of threshold exceedance in terms of a binary segmentation task. Furthermore, we suggest additional input data that could help to better identify situations with imminent precipitation dynamics. The model code, pretrained weights, and training data are provided in open repositories as an input for such future studies.
Many institutions struggle to tap into the potential of their large archives of radar reflectivity: these data are often affected by miscalibration, yet the bias is typically unknown and temporally volatile. Still, relative calibration techniques can be used to correct the measurements a posteriori. For that purpose, the usage of spaceborne reflectivity observations from the Tropical Rainfall Measuring Mission (TRMM) and Global Precipitation Measurement (GPM) platforms has become increasingly popular: the calibration bias of a ground radar (GR) is estimated from its average reflectivity difference to the spaceborne radar (SR). Recently, Crisologo et al. (2018) introduced a formal procedure to enhance the reliability of such estimates: each match between SR and GR observations is assigned a quality index, and the calibration bias is inferred as a quality-weighted average of the differences between SR and GR. The relevance of quality was exemplified for the Subic S-band radar in the Philippines, which is greatly affected by partial beam blockage. The present study extends the concept of quality-weighted averaging by accounting for path-integrated attenuation (PIA) in addition to beam blockage. This extension becomes vital for radars that operate at the C or X band. Correspondingly, the study setup includes a C-band radar that substantially overlaps with the S-band radar. Based on the extended quality-weighting approach, we retrieve, for each of the two ground radars, a time series of calibration bias estimates from suitable SR overpasses. As a result of applying these estimates to correct the ground radar observations, the consistency between the ground radars in the region of overlap increased substantially. Furthermore, we investigated if the bias estimates can be interpolated in time, so that ground radar observations can be corrected even in the absence of prompt SR overpasses. We found that a moving average approach was most suitable for that purpose, although limited by the absence of explicit records of radar maintenance operations.