RESUMEN
In observatory seismology, the effective automatic processing of seismograms is a time-consuming task. A contemporary approach for seismogram processing is based on the Deep Neural Network formalism, which has been successfully applied in many fields. Here, we present a 4D network, based on U-net architecture, that simultaneously processes seismograms from an entire network. We also interpret Acoustic Emission data based on a laboratory loading experiment. The obtained data was a very good testing set, similar to real seismograms. Our Neural network is designed to detect multiple events. Input data are created by augmentation from previously interpreted single events. The advantage of the approach is that the positions of (multiple) events are exactly known, thus, the efficiency of detection can be evaluated. Even if the method reaches an average efficiency of only around 30% for the onset of individual tracks, average efficiency for the detection of double events was approximately 97% for a maximum target, with a prediction difference of 20 samples. Such is the main benefit of simultaneous network signal processing.
RESUMEN
Evaluating physical properties and mechanical parameters of rock slopes and their spatial variability is challenging, particularly at locations inaccessible for fieldwork. This obstacle can be bypassed by acquiring spatially-distributed field data indirectly. InfraRed Thermography (IRT) has emerged as a promising technology to statistically infer rock properties and inform slope stability models. Here, we explore the use of Cooling Rate Indices (CRIs) to quantify the thermal response of a granodiorite rock wall within the recently established Pozáry Test Site in Czechia. We observe distinct cooling patterns across different segments of the wall, compatible with the different degrees of weathering evaluated in the laboratory and suggested by IRT observations of cored samples. Our findings support previous examinations of the efficacy of this method and unveil correlations between cooling phases in the field and in the laboratory. We discuss the scale-dependency of the Informative Time Window (ITW) of the CRIs, noting that it may serve as a reference for conducting systematic IRT field surveys. We contend that our approach not only represents a viable and scientifically robust strategy for characterising rock slopes but also holds the potential for identifying unstable areas.