... years intensive faunal studies were done in many boreholes used for monitoring subterranean water quality in Germany ( Hahn and Matzke, 2005 ; Hahn and Fuchs, 2009 ; Griebler et al., 2010 ). Samples of invertebrate fauna and water for chemical analyses were collected from 26 wells in particular...

...:1804.02767. Ronneberger O. Fischer P. , and Brox T. 2015 . U‐net: Convolutional networks for biomedical image segmentation , International Conf. on Medical Image Computing and Computer‐Assisted Intervention , Munich, Germany , 5–9 October 2015 . Ross Z. E. Meier M...

... for some fields of data processing ( Ronneberger et al., 2015 ; Simonyan and Zisserman, 2015 ; Zhang et al., 2017 ). Because convolutional neural networks (CNNs) perform well in learning prior information from a large amount of data, this makes networks preferable to classical algorithms and has recently...

... . Ronneberger O. Fischer P. , and Brox T. 2015 . U‐net: Convolutional networks for biomedical image segmentation , Medical Image Computing and Computer‐Assisted Intervention–MICCAI 2015: 18th International Conference , Munich, Germany , 5–9 October , Proceedings, Part III 18, Springer , 234...

.... As in simplified networks from U-Net ( Ronneberger et al., 2015 ), the number of convolutional filters and features in FaultSeg3D is reduced to save computer memory and training time. In this example, 200 and 20 pairs of synthetic seismic cubes and fault images are used to train and validate the proposed networks...

... architecture of Ronneberger et al. (2015) is a good example of an encoder-decoder setup that can predict sample-wise attributes (such as the first break probability) over an entire line gather at once. This particular architecture seems to have been the most popular design choice for first break picking...

... into a modern usable resource , Seismol. Res. Lett. 91 , no.  3 , 1531 – 1541 . Ronneberger O. Fischer P. , and Brox T. 2015 . U‐net: Convolutional networks for biomedical image segmentation , Int. Conf. on Medical Image Computing and Computer‐Assisted Intervention , Munich, Germany...

... is similar to the structure of U‐net ( Ronneberger et al. , 2015 ) with the encoder. The three pooling layers of the encoder and the three up‐sampling layers of the decoder ensure the consistency of input and output dimensions. The fully connected layers are used to constitute a classifier to classify...

... of images, DL can provide models that exploit the hierarchical structure within the images, such as local combinations of edges and patterns to achieve a desired output. Within the broad panorama of DL, a noteworthy architecture suitable for semantic segmentation tasks is the U-Net ( Ronneberger et al...

... the U‐GPD network architecture (Fig.  3 ; Lapins et al. , 2021 ) that redesigned the existing seismological generalized phase detection (GPD) model ( Ross et al. , 2018 ) with a U‐Net architecture ( Ronneberger et al. , 2015 ). The original GPD model architecture consists of convolutional layers...

... , doi: 10.1126/sciadv.aao6596 . Ronneberger O. Fischer P. , and Brox T. 2015 . U‐Net: Convolutional networks for biomedical image segmentation , BIOSS Centre for Biological Signalling Studies , Department of Computer Science , University of Freiburg , Germany , 1 – 8 pp...

...). 'Spirograptus' conspectus Přibyl 1944 occurs in the sedgwickii and linnaei biozones of Germany. It was tentatively referred to Torquigraptus by Loydell (1993 ), but its thecae may be symmetrically hooked. Its rhabdosome forms a helical spiral with up to three whorls, and in this respect resembles T...

.... Res. Lett. 93 , 1673 – 1682 . Ronneberger O. Fischer P. , and Brox T. 2015 . U‐net: Convolutional networks for biomedical image segmentation , International Conf. on Medical Image Computing and Computer‐Assisted Intervention , Munich, Germany , 5–9 October 2015 , Vol.  9351...

... the Finite-fault Rupture Detector (FinDer) in New Zealand. Böse, M., Behr, Y., Massin, F., Andrews, J. 54. An Earthquake Early Warning System for the Lower Rhine Embayment, Germany. Najdahmadi, B., Pilz, M., Razafindrakoto, H., Oth, A., Cotton, F. 55. Low-latency Digitization, Communication and Alerting...