Refine
Year of publication
- 2023 (4) (remove)
Language
- English (4)
Is part of the Bibliography
- yes (4)
Institute
Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany
(2023)
Data-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is thus not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains than RF models.
Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany
(2023)
Data-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is thus not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains than RF models.
Cosmic-ray neutron sensing (CRNS) allows for the estimation of root-zone soil water content (SWC) at the scale of several hectares. In this paper, we present the data recorded by a dense CRNS network operated from 2019 to 2022 at an agricultural research site in Marquardt, Germany - the first multi-year CRNS cluster. Consisting, at its core, of eight permanently installed CRNS sensors, the cluster was supplemented by a wealth of complementary measurements: data from seven additional temporary CRNS sensors, partly co-located with the permanent ones; 27 SWC profiles (mostly permanent); two groundwater observation wells; meteorological records; and Global Navigation Satellite System reflectometry (GNSS-R). Complementary to these continuous measurements, numerous campaign-based activities provided data by mobile CRNS roving, hyperspectral im-agery via UASs, intensive manual sampling of soil properties (SWC, bulk density, organic matter, texture, soil hydraulic properties), and observations of biomass and snow (cover, depth, and density). The unique temporal coverage of 3 years entails a broad spectrum of hydro-meteorological conditions, including exceptional drought periods and extreme rainfall but also episodes of snow coverage, as well as a dedicated irrigation experiment. Apart from serving to advance CRNS-related retrieval methods, this data set is expected to be useful for vari-ous disciplines, for example, soil and groundwater hydrology, agriculture, or remote sensing. Hence, we show exemplary features of the data set in order to highlight the potential for such subsequent studies. The data are available at doi.org/10.23728/b2share.551095325d74431881185fba1eb09c95 (Heistermann et al., 2022b).
Our subject is a new catalogue of radar-based heavy rainfall events (CatRaRE) over Germany and how it relates to the concurrent atmospheric circulation. We classify daily ERA5 fields of convective indices according to CatRaRE, using an array of 13 statistical methods, consisting of 4 conventional (“shallow”) and 9 more recent deep machine learning (DL) algorithms; the classifiers are then applied to corresponding fields of
simulated present and future atmospheres from the Coordinated Regional Climate Downscaling Experiment (CORDEX) project. The inherent uncertainty of the DL results from the stochastic nature of their optimization is addressed by employing an ensemble approach using 20 runs for each network. The shallow random forest method performs best with an equitable threat score (ETS) around 0.52, followed by the DL networks ALL-CNN and ResNet with an ETS near 0.48. Their success can be understood as a result of conceptual simplicity and parametric parsimony, which obviously best fits the relatively simple classification task. It is found that, on summer days, CatRaRE convective atmospheres over Germany occur with a probability of about 0.5. This probability is projected to increase, regardless of method, both in ERA5-reanalyzed and CORDEX-simulated atmospheres: for the historical period we find a centennial increase of about 0.2 and for the future period one of slightly below 0.1.