Valentin Kasburg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Valentin Kasburg has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Nina Kukowski
Friedrich-Schiller-University
7 shared publications Alexander Breuer
Institute of Informatics, Friedrich Schiller University Jena, Germany
2 shared publications- Jozef Müller
Friedrich Schiller Univ Jena, Burgweg 11, D-07749 Jena, Germany
2 shared publications - Marcel van Laaten
Institute of Geosciences Friedrich Schiller University Jena Jena Germany
2 shared publications Markus Zehner
Institute of Geography Friedrich Schiller University Jena Jena Germany
2 shared publicationsNina Kukowski
Institute of Geosciences Friedrich Schiller University Jena Jena Germany
2 shared publications
Latest Publications
- Open Access
- 14 March 2026
- Published by Copernicus GmbH
Physics-Guided Neural Network Parameter Estimation of Groundwater–Strain Coupling at Moxa Geodynamic Observatory
High-resolution laser strainmeter measurements in an underground gallery at Moxa Geodynamic Observatory (Thuringia, central Germany) provide detailed records of crustal deformation. Beyond Earth tides, deformation induced by pore-pressure fluctuations produces the largest signals. These observations reveal that the relationship between groundwater transport and crustal strain is temporally fluctuating, highlighting the need for a quantitative approach to systematically characterize potential coupling.Here, we present a physics-guided, data-driven approach for estimating effective groundwater–strain coupling from multivariate time series of groundwater levels and nanometer-scale strain measurements, based on linear Biot poro-elasticity. The approach incorporates physically guided Biot neurons into an autoregressive neural network architecture; these neurons model horizontal poro-elastic responses of fractured rock driven by groundwater variations. It dynamically adjusts to temporal changes in groundwater levels and the resulting pore-pressure-induced strain. Using orientation-specific laser strainmeter measurements and spatially distributed groundwater levels from boreholes, we estimate Biot coupling in two horizontal directions (North–South and East–West) and derive effective coupling parameters from over a decade of observatory records.Our results provide insights into the dynamic hydro-mechanical behaviour of the shallow crust and highlight the potential of physics-guided neural architectures to support the interpretation of high-resolution deformation and stress–strain responses in geomechanical studies.
- 14 March 2026
- Published by Copernicus GmbH
Open AccessPhysics-Guided Neural Network Parameter Estimation of Groundwater–Strain Coupling at Moxa Geodynamic Observatory
High-resolution laser strainmeter measurements in an underground gallery at Moxa Geodynamic Observatory (Thuringia, central Germany) provide detailed records of crustal deformation. Beyond Earth tides, deformation induced by pore-pressure fluctuations produces the largest signals. These observations reveal that the relationship between groundwater transport and crustal strain is temporally fluctuating, highlighting the need for a quantitative approach to systematically characterize potential coupling.Here, we present a physics-guided, data-driven approach for estimating effective groundwater–strain coupling from multivariate time series of groundwater levels and nanometer-scale strain measurements, based on linear Biot poro-elasticity. The approach incorporates physically guided Biot neurons into an autoregressive neural network architecture; these neurons model horizontal poro-elastic responses of fractured rock driven by groundwater variations. It dynamically adjusts to temporal changes in groundwater levels and the resulting pore-pressure-induced strain. Using orientation-specific laser strainmeter measurements and spatially distributed groundwater levels from boreholes, we estimate Biot coupling in two horizontal directions (North–South and East–West) and derive effective coupling parameters from over a decade of observatory records.Our results provide insights into the dynamic hydro-mechanical behaviour of the shallow crust and highlight the potential of physics-guided neural architectures to support the interpretation of high-resolution deformation and stress–strain responses in geomechanical studies.
- Open Access
- 26 September 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 2 (4)
Explainable Seismic Event Discrimination: Improved Explainability With Vision Transformers
The discrimination of seismic events traditionally relies on manual expert analysis or cross‐correlation techniques for pattern recognition. Although flexible algorithms from deep learning, such as convolutional neural networks, have demonstrated high discrimination accuracy for different seismic event origins based on spectral characteristics, their use in automated discrimination remains limited. Two main challenges hinder further deployment: first, these models are typically not transferable across regions with differing event characteristics; second, deep learning models often lack interpretability due to their black‐box nature. In this study, we investigate vision transformers as a novel architecture for seismic event discrimination and compare their accuracy and explainability to a convolutional neural network baseline. Vision transformers leverage attention mechanisms offering a distinct approach to visualizing the decision‐making process of deep learning models. We evaluate both model types on seismic data from two regions in Germany: the Vogtland‐West Bohemian region where earthquakes along the Leipzig‐Regensburg fault zone are discriminated from quarry blasts (QBs), and the Ruhr Area, where mining‐induced events are discriminated from QBs. Our results show that vision transformers achieve high discrimination accuracy on test data from both regions (97%–98%) performing on par with the baseline. For explainability, we apply Attention Rollout and the gradient‐based LeGrad method for vision transformers and SmoothGrad for the baseline. Combined with occlusion techniques, these methods demonstrate that vision transformers analyze spectrograms more comprehensively. Our findings highlight the potential of vision transformers as both a high‐performing and interpretable alternative to convolutional neural networks for automated seismic event discrimination.
- 26 September 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 2 (4)
Open AccessExplainable Seismic Event Discrimination: Improved Explainability With Vision Transformers
The discrimination of seismic events traditionally relies on manual expert analysis or cross‐correlation techniques for pattern recognition. Although flexible algorithms from deep learning, such as convolutional neural networks, have demonstrated high discrimination accuracy for different seismic event origins based on spectral characteristics, their use in automated discrimination remains limited. Two main challenges hinder further deployment: first, these models are typically not transferable across regions with differing event characteristics; second, deep learning models often lack interpretability due to their black‐box nature. In this study, we investigate vision transformers as a novel architecture for seismic event discrimination and compare their accuracy and explainability to a convolutional neural network baseline. Vision transformers leverage attention mechanisms offering a distinct approach to visualizing the decision‐making process of deep learning models. We evaluate both model types on seismic data from two regions in Germany: the Vogtland‐West Bohemian region where earthquakes along the Leipzig‐Regensburg fault zone are discriminated from quarry blasts (QBs), and the Ruhr Area, where mining‐induced events are discriminated from QBs. Our results show that vision transformers achieve high discrimination accuracy on test data from both regions (97%–98%) performing on par with the baseline. For explainability, we apply Attention Rollout and the gradient‐based LeGrad method for vision transformers and SmoothGrad for the baseline. Combined with occlusion techniques, these methods demonstrate that vision transformers analyze spectrograms more comprehensively. Our findings highlight the potential of vision transformers as both a high‐performing and interpretable alternative to convolutional neural networks for automated seismic event discrimination.
- Open Access
- 18 March 2025
- Published by Copernicus GmbH
Thermal Conductivity Measurements of in Resin-Embedded Cuttings Using the Optical Scanning Method
The transport of heat from the Earth’s interior to its surface is the maindriving force for many geological processes, like e.g. lithosphere dynamics andmantle convection. To understand these processes, it is essential to capturethe spatially and temporally dependent temperature field of the Earth’s crust.The structure of this temperature field is largely determined by the thermalproperties of the rocks. One of the key thermophysical properties is thermalconductivity, which plays a critical role in various scientific and economic fields,such as the study of sedimentary basins and geothermal potentials.To characterize the thermal properties of various lithologies, measurementson core samples are of ultimate interest. However, as coring is highly expen-sive, drill cores are not often taken during drilling campaigns. Nonetheless, drillcuttings would be available from nearly all drill holes. The drill cuttings canbe ground and compressed to form measuring tablets for thermal conductivitytests, which changes the rock structure and thus also the thermal properties. Analternative could be to embed drill cuttings in materials of known thermal prop-erties like resin to prepare samples ready to be used with the widely availableThermal Conductivity Scanner (TCS).In this study, we present an innovative method for determining the thermalconductivity of drill cuttings using TCS by preparing various samples drill cut-tings embedded in epoxy resin. We investigate how grain size of the encasedcuttings affects the estimation of thermal conductivity with the TCS. To testthis novel approach, we use artificially produced drill cuttings, mini-cores em-bedded in epoxy resin, and undisturbed reference samples. Our investigationssuggest that grain size and thermal edge effects resulting from embedding thesamples in resin can be corrected with sufficient precision to enable accurateconclusions about the thermal conductivity of the undisturbed rock.
- 18 March 2025
- Published by Copernicus GmbH
Open AccessThermal Conductivity Measurements of in Resin-Embedded Cuttings Using the Optical Scanning Method
The transport of heat from the Earth’s interior to its surface is the maindriving force for many geological processes, like e.g. lithosphere dynamics andmantle convection. To understand these processes, it is essential to capturethe spatially and temporally dependent temperature field of the Earth’s crust.The structure of this temperature field is largely determined by the thermalproperties of the rocks. One of the key thermophysical properties is thermalconductivity, which plays a critical role in various scientific and economic fields,such as the study of sedimentary basins and geothermal potentials.To characterize the thermal properties of various lithologies, measurementson core samples are of ultimate interest. However, as coring is highly expen-sive, drill cores are not often taken during drilling campaigns. Nonetheless, drillcuttings would be available from nearly all drill holes. The drill cuttings canbe ground and compressed to form measuring tablets for thermal conductivitytests, which changes the rock structure and thus also the thermal properties. Analternative could be to embed drill cuttings in materials of known thermal prop-erties like resin to prepare samples ready to be used with the widely availableThermal Conductivity Scanner (TCS).In this study, we present an innovative method for determining the thermalconductivity of drill cuttings using TCS by preparing various samples drill cut-tings embedded in epoxy resin. We investigate how grain size of the encasedcuttings affects the estimation of thermal conductivity with the TCS. To testthis novel approach, we use artificially produced drill cuttings, mini-cores em-bedded in epoxy resin, and undisturbed reference samples. Our investigationssuggest that grain size and thermal edge effects resulting from embedding thesamples in resin can be corrected with sufficient precision to enable accurateconclusions about the thermal conductivity of the undisturbed rock.
- Open Access
- 18 March 2025
- Published by Copernicus GmbH
Automating Seismic Event Discrimination: A Comparative Study of Convolutional Neural Networks and Vision Transformers
To date, the discrimination of seismic events recorded in seismic networks is often performed manually by experts, classifying events into categories such as earthquakes, quarry blasts, or mining events. While recent studies have shown that deep learning algorithms, particularly Convolutional Neural Networks (CNNs), can efficiently and accurately distinguish between different types of seismic events, their application for automated seismic event discrimination remains limited. This limitation arises from several factors, including the absence of globally applicable models that maintain high precision for local seismic networks, the scarcity of data required for fine-tuning Deep Learning (DL) models, and the lack of interpretability in the decision-making processes of these black-box models.In this contribution, we explore the use of Vision Transformers (ViTs) as a novel approach for automating seismic event discrimination. To assess their potential for accuracy and explainability, we applied CNNs and ViTs to classify seismic events such as earthquakes, quarry blasts, and mining events. For this purpose, we pretrained the models on openly available seismic event data from Utah and Northern California and then fine-tuned and tested them on data from the Seismic Network of the Ruhr-University Bochum (RuhrNet) and the Thuringian Seismic Network (TSN).Our findings reveal that ViTs can analyze the entire spectrogram of a seismic event in a coherent manner, offering superior generalizability in pattern recognition compared to CNNs. In addition to achieving high discrimination accuracy, the attention weights of ViTs provide insights into the models’ decision-making process, offering a transparent and interpretable explanation of the underlying mechanisms driving its classifications.
- 18 March 2025
- Published by Copernicus GmbH
Open AccessAutomating Seismic Event Discrimination: A Comparative Study of Convolutional Neural Networks and Vision Transformers
To date, the discrimination of seismic events recorded in seismic networks is often performed manually by experts, classifying events into categories such as earthquakes, quarry blasts, or mining events. While recent studies have shown that deep learning algorithms, particularly Convolutional Neural Networks (CNNs), can efficiently and accurately distinguish between different types of seismic events, their application for automated seismic event discrimination remains limited. This limitation arises from several factors, including the absence of globally applicable models that maintain high precision for local seismic networks, the scarcity of data required for fine-tuning Deep Learning (DL) models, and the lack of interpretability in the decision-making processes of these black-box models.In this contribution, we explore the use of Vision Transformers (ViTs) as a novel approach for automating seismic event discrimination. To assess their potential for accuracy and explainability, we applied CNNs and ViTs to classify seismic events such as earthquakes, quarry blasts, and mining events. For this purpose, we pretrained the models on openly available seismic event data from Utah and Northern California and then fine-tuned and tested them on data from the Seismic Network of the Ruhr-University Bochum (RuhrNet) and the Thuringian Seismic Network (TSN).Our findings reveal that ViTs can analyze the entire spectrogram of a seismic event in a coherent manner, offering superior generalizability in pattern recognition compared to CNNs. In addition to achieving high discrimination accuracy, the attention weights of ViTs provide insights into the models’ decision-making process, offering a transparent and interpretable explanation of the underlying mechanisms driving its classifications.
- Open Access
- 25 October 2024
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 11 (10)
Deep‐Learning Based Causal Inference: A Feasibility Study Based on Three Years of Tectonic‐Climate Data From Moxa Geodynamic Observatory
Highly sensitive laser strainmeters at Moxa Geodynamic Observatory (MGO) measure motions of the upper Earth's crust. Since the mountain overburden of the laser strainmeters installed in the gallery of the observatory is relatively low, the recorded time series are strongly influenced by local meteorological phenomena. To estimate the nonlinear effect of the meteorological variables on strain measurements in a non‐stationary environment, advanced methods capable of learning the nonlinearity and discovering causal relationships in the non‐stationary multivariate tectonic‐climate time series are needed. Methods for causal inference generally perform well in identifying linear causal relationships but often struggle to retrieve complex nonlinear causal structures prevalent in real‐world systems. This work presents a novel model invariance‐based causal discovery (CDMI) method that utilizes deep networks to model nonlinearity in a multivariate time series system. We propose to use the theoretically well‐established Knockoffs framework to generate in‐distribution, uncorrelated copies of the original data as interventional variables and test the model invariance for causal discovery. To deal with the non‐stationary behavior of the tectonic‐climate time series recorded at the MGO, we propose a regime identification approach that we apply before causal analysis to generate segments of time series that possess locally consistent statistical properties. First, we evaluate our method on synthetically generated time series by comparing it to other causal analysis methods. We then investigate the hypothesized effect of meteorological variables on strain measurements. Our approach outperforms other causality methods and provides meaningful insights into tectonic‐climate causal interactions.
- 25 October 2024
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 11 (10)
Open AccessDeep‐Learning Based Causal Inference: A Feasibility Study Based on Three Years of Tectonic‐Climate Data From Moxa Geodynamic Observatory
Highly sensitive laser strainmeters at Moxa Geodynamic Observatory (MGO) measure motions of the upper Earth's crust. Since the mountain overburden of the laser strainmeters installed in the gallery of the observatory is relatively low, the recorded time series are strongly influenced by local meteorological phenomena. To estimate the nonlinear effect of the meteorological variables on strain measurements in a non‐stationary environment, advanced methods capable of learning the nonlinearity and discovering causal relationships in the non‐stationary multivariate tectonic‐climate time series are needed. Methods for causal inference generally perform well in identifying linear causal relationships but often struggle to retrieve complex nonlinear causal structures prevalent in real‐world systems. This work presents a novel model invariance‐based causal discovery (CDMI) method that utilizes deep networks to model nonlinearity in a multivariate time series system. We propose to use the theoretically well‐established Knockoffs framework to generate in‐distribution, uncorrelated copies of the original data as interventional variables and test the model invariance for causal discovery. To deal with the non‐stationary behavior of the tectonic‐climate time series recorded at the MGO, we propose a regime identification approach that we apply before causal analysis to generate segments of time series that possess locally consistent statistical properties. First, we evaluate our method on synthetically generated time series by comparing it to other causal analysis methods. We then investigate the hypothesized effect of meteorological variables on strain measurements. Our approach outperforms other causality methods and provides meaningful insights into tectonic‐climate causal interactions.
- 27 December 2023
- Published by Seismological Society of America (SSA) in Bulletin of the Seismological Society of America
- Vol. 114 (2) , 842-856
Cross-Regional Seismic Event Discrimination via Convolutional Neural Networks: Exploring Fine-Tuning and Ensemble Averaging
The gradual densification of seismic networks has facilitated the acquisition of large amounts of data. However, alongside natural tectonic earthquakes, seismic networks also record anthropogenic events such as quarry blasts or other induced events. Identifying and distinguishing these events from natural earthquakes requires experienced interpreters to ensure that seismological studies of natural phenomena are not compromised by anthropogenic events. Advanced artificial intelligence methods have already been deployed to tackle this problem. One of the applications includes Convolutional Neural Networks (CNN) to discriminate different kinds of events, such as natural earthquakes and quarry blasts. In this study, we investigate the effects of ensemble averaging and fine-tuning on seismic event discrimination accuracy to estimate the potential of these methods. We compare discrimination accuracy of two different CNN model architectures across three datasets. This was done with the best models from an ensemble of each model architecture, as well as with ensemble averaging and fine-tuning methods. Soft voting was used for the CNN ensemble predictions. For the transfer learning approach, the models were pretrained with data from two of the datasets (nontarget regions) and fine-tuned with data from the third one (target region). The results show that ensemble averaging and fine-tuning of CNN models leads to better generalization of the model predictions. For the region with the lowest numbers of one event type, the combination of ensemble averaging and fine-tuning led to an increase in discrimination accuracy of up to 4% at station level and up to 10% at event level. We also tested the impact of the amount of training data on the fine-tuning method, showing, that to create a global model, the selection of comprehensive training data is needed.
- 27 December 2023
- Published by Seismological Society of America (SSA) in Bulletin of the Seismological Society of America
- Vol. 114 (2) , 842-856
Cross-Regional Seismic Event Discrimination via Convolutional Neural Networks: Exploring Fine-Tuning and Ensemble Averaging
The gradual densification of seismic networks has facilitated the acquisition of large amounts of data. However, alongside natural tectonic earthquakes, seismic networks also record anthropogenic events such as quarry blasts or other induced events. Identifying and distinguishing these events from natural earthquakes requires experienced interpreters to ensure that seismological studies of natural phenomena are not compromised by anthropogenic events. Advanced artificial intelligence methods have already been deployed to tackle this problem. One of the applications includes Convolutional Neural Networks (CNN) to discriminate different kinds of events, such as natural earthquakes and quarry blasts. In this study, we investigate the effects of ensemble averaging and fine-tuning on seismic event discrimination accuracy to estimate the potential of these methods. We compare discrimination accuracy of two different CNN model architectures across three datasets. This was done with the best models from an ensemble of each model architecture, as well as with ensemble averaging and fine-tuning methods. Soft voting was used for the CNN ensemble predictions. For the transfer learning approach, the models were pretrained with data from two of the datasets (nontarget regions) and fine-tuned with data from the third one (target region). The results show that ensemble averaging and fine-tuning of CNN models leads to better generalization of the model predictions. For the region with the lowest numbers of one event type, the combination of ensemble averaging and fine-tuning led to an increase in discrimination accuracy of up to 4% at station level and up to 10% at event level. We also tested the impact of the amount of training data on the fine-tuning method, showing, that to create a global model, the selection of comprehensive training data is needed.
- Open Access
- 15 May 2023
- Published by Copernicus GmbH
Influence of Environmental Parameters on Highly Sensitive Instruments at Moxa Geodynamic Observatory
Strainmeters measure the change in length between two known fixed points and are used primarily to identify and estimate tectonic strain. In addition to tectonic strain, these instruments also record changes in strain caused by other phenomena such as Earth tides and fluctuations of meteorological signals like changes in groundwater levels caused by precipitation, which may be much larger than tectonic strain and thus mask its signals. To avoid meteorological influences as far as possible, horizontal strainmeters often are maintained in galleries such that tectonically induced strain signals are not affected by other sources of noise.At Moxa Geodynamic Observatory, located in central Germany, two laser strainmeters with a base length of 26 m each are maintained in galleries oriented north-south and east-west. Their resolution is in the nano-scale and sampling rate is 0.1 Hz. Mountain overburden in the gallery is comparatively low at approx. 30 m and in addition, the hydrogeological situation of the subsurface surrounding the observatory, is very heterogeneous. Therefore, amplitudes of meteorological phenomena are still quite high. In order to correct meteorological influences in the recorded strain time-series, they first need to be better understood. For doing so, long time-series - a decade at least – are needed. As the laser strainmeters continuously record since summer 2011, these are now available.We present the results of weighting various meteorological parameters on the strainmeter recordings by training Long Short Term Memory Networks and perturbing input parameters for the test data. In this way, the contribution of each parameter to the meteorologically induced strain signals can be estimated. This knowledge is subsequently used to eliminate meteorological influences from the time-series recordings of strain.
- 15 May 2023
- Published by Copernicus GmbH
Open AccessInfluence of Environmental Parameters on Highly Sensitive Instruments at Moxa Geodynamic Observatory
Strainmeters measure the change in length between two known fixed points and are used primarily to identify and estimate tectonic strain. In addition to tectonic strain, these instruments also record changes in strain caused by other phenomena such as Earth tides and fluctuations of meteorological signals like changes in groundwater levels caused by precipitation, which may be much larger than tectonic strain and thus mask its signals. To avoid meteorological influences as far as possible, horizontal strainmeters often are maintained in galleries such that tectonically induced strain signals are not affected by other sources of noise.At Moxa Geodynamic Observatory, located in central Germany, two laser strainmeters with a base length of 26 m each are maintained in galleries oriented north-south and east-west. Their resolution is in the nano-scale and sampling rate is 0.1 Hz. Mountain overburden in the gallery is comparatively low at approx. 30 m and in addition, the hydrogeological situation of the subsurface surrounding the observatory, is very heterogeneous. Therefore, amplitudes of meteorological phenomena are still quite high. In order to correct meteorological influences in the recorded strain time-series, they first need to be better understood. For doing so, long time-series - a decade at least – are needed. As the laser strainmeters continuously record since summer 2011, these are now available.We present the results of weighting various meteorological parameters on the strainmeter recordings by training Long Short Term Memory Networks and perturbing input parameters for the test data. In this way, the contribution of each parameter to the meteorologically induced strain signals can be estimated. This knowledge is subsequently used to eliminate meteorological influences from the time-series recordings of strain.
- Open Access
- 27 March 2022
- Published by Copernicus GmbH
Earthquake detection in time-series of laser strainmeter measurements as a first step towards automatic signal classification.
Geophysical observatories around the world collect data on various natural phenomena within the Earth and on its surface. Many of these measurements are made automatically, sometimes at high sampling rates, so that enormous amounts of data accumulate over the years. Continuous analysis is important to classify current phenomena and decide which data are important and which can be downsampled later.At Moxa Geodynamic Observatory, located in central Germany, several laser strainmeters have been installed in subsurface galleries in order to measure strain of the Earth's crust. These instruments run in north-south, east-west, and northwest-southeast directions. Nano-strain rates are determined with a sampling rate of 0.1 Hz almost continuously over distances of 26 and 38 m, respectively, since summer 2011.Signals of tectonically induced crustal deformation are superimposed by other signals of greater amplitude, e.g., tides, changes in atmospheric pressure, hydrologic events such as heavy rainfall, and earthquakes. Classification of these events is important to better associate jumps in the temporal vicinity and to distinguish anomalies from instrument failures. To avoid time-consuming pattern recognition by hand, algorithms are required to do most of the work automatically. Due to recent advances in the field of artificial intelligence, it is possible to implement time series algorithms that are capable of unifying and automating many steps of data analysis. Although artificial intelligence applications are increasingly used to support data analysis, their use for time series of geophysical origin so far is not widespread outside of seismology.In this contribution, an approach to automatically detect earthquakes in the strain data using 1D Convolutional Neural Networks is presented, including the generation of artificial training data with time series data augmentation. Also the training process and generation of new training data, based on classification by hand and false predictions of the trained model is described. The 1D Convolutional Neural Networks are able to identify almost all earthquakes in the strain data and have F1 values > 0.99, showing that their application has the potential to significantly reduce the time required in signal classification of observatory time series data.
- 27 March 2022
- Published by Copernicus GmbH
Open AccessEarthquake detection in time-series of laser strainmeter measurements as a first step towards automatic signal classification.
Geophysical observatories around the world collect data on various natural phenomena within the Earth and on its surface. Many of these measurements are made automatically, sometimes at high sampling rates, so that enormous amounts of data accumulate over the years. Continuous analysis is important to classify current phenomena and decide which data are important and which can be downsampled later.At Moxa Geodynamic Observatory, located in central Germany, several laser strainmeters have been installed in subsurface galleries in order to measure strain of the Earth's crust. These instruments run in north-south, east-west, and northwest-southeast directions. Nano-strain rates are determined with a sampling rate of 0.1 Hz almost continuously over distances of 26 and 38 m, respectively, since summer 2011.Signals of tectonically induced crustal deformation are superimposed by other signals of greater amplitude, e.g., tides, changes in atmospheric pressure, hydrologic events such as heavy rainfall, and earthquakes. Classification of these events is important to better associate jumps in the temporal vicinity and to distinguish anomalies from instrument failures. To avoid time-consuming pattern recognition by hand, algorithms are required to do most of the work automatically. Due to recent advances in the field of artificial intelligence, it is possible to implement time series algorithms that are capable of unifying and automating many steps of data analysis. Although artificial intelligence applications are increasingly used to support data analysis, their use for time series of geophysical origin so far is not widespread outside of seismology.In this contribution, an approach to automatically detect earthquakes in the strain data using 1D Convolutional Neural Networks is presented, including the generation of artificial training data with time series data augmentation. Also the training process and generation of new training data, based on classification by hand and false predictions of the trained model is described. The 1D Convolutional Neural Networks are able to identify almost all earthquakes in the strain data and have F1 values > 0.99, showing that their application has the potential to significantly reduce the time required in signal classification of observatory time series data.
- Open Access
- 4 March 2021
- Published by Copernicus GmbH
Identification of a fault zone beneath Moxa observatory (Central Germany): evidence from combining logging, rock physical measurements, and geophysical profiling
Geophysical observatories aim to decipher natural processes taking place in very different parts of the Earth’s interior by recording long time series of various signals related to these processes. As such signals, e.g. fluctuations of deformation or temperature, may be very small, complementary information e.g. from climate stations and very good knowledge of geological structures in the vicinity of an observatory is indispensable. Moxa Geodynamic Observatory, belonging to Jena university is located in a remote area in the Palaeozoic Thuringian Slate Mountains, which however, is characterized by complex subsurface structures with regard to fluid transport and hydrology, including a suspected fault beneath the observatory.Information about the subsurface beneath the observatory and its geological structures is available from various near-surface geophysical surveys including numerous geo-electrical profiles. These were used to undertake 3D resistivity tomography.Here we use rock physical measurements, including thermal conductivity, permeability and seismic velocities, on core material from the research drill hole next to the observatory building to characterise the silty greywackes. This data set is complemented by the evaluation of logging data and inspection of long-term temperature data obtained from records of an optical fibre deployed in the borehole to characterize the drilled rocks and identify sections which may favour ground water transport. We also identified fissures from the acoustic televiewer and thus found several depth intervals which could represent a fault zone. Finally we used this information and the results of the resistivity tomography to propose a structural model for the subsurface including the position and type of the suspected fault zone.
- 4 March 2021
- Published by Copernicus GmbH
Open AccessIdentification of a fault zone beneath Moxa observatory (Central Germany): evidence from combining logging, rock physical measurements, and geophysical profiling
Geophysical observatories aim to decipher natural processes taking place in very different parts of the Earth’s interior by recording long time series of various signals related to these processes. As such signals, e.g. fluctuations of deformation or temperature, may be very small, complementary information e.g. from climate stations and very good knowledge of geological structures in the vicinity of an observatory is indispensable. Moxa Geodynamic Observatory, belonging to Jena university is located in a remote area in the Palaeozoic Thuringian Slate Mountains, which however, is characterized by complex subsurface structures with regard to fluid transport and hydrology, including a suspected fault beneath the observatory.Information about the subsurface beneath the observatory and its geological structures is available from various near-surface geophysical surveys including numerous geo-electrical profiles. These were used to undertake 3D resistivity tomography.Here we use rock physical measurements, including thermal conductivity, permeability and seismic velocities, on core material from the research drill hole next to the observatory building to characterise the silty greywackes. This data set is complemented by the evaluation of logging data and inspection of long-term temperature data obtained from records of an optical fibre deployed in the borehole to characterize the drilled rocks and identify sections which may favour ground water transport. We also identified fissures from the acoustic televiewer and thus found several depth intervals which could represent a fault zone. Finally we used this information and the results of the resistivity tomography to propose a structural model for the subsurface including the position and type of the suspected fault zone.