Seismograms contain multiple sources of seismic waves, from distinct transient signals such as earthquakes to continuous ambient seismic vibrations such as microseism. Ambient vibrations contaminate the earthquake signals, while the earthquake signals pollute the ambient noise’s statistical properties necessary for ambient-noise seismology analysis. Separating ambient noise from earthquake signals would thus benefit multiple seismological analyses. This work develops a multitask encoder–decoder network named WaveDecompNet to separate transient signals from ambient signals directly in the time domain for 3-component seismograms. We choose the active-volcanic Big Island in Hawai’i as a natural laboratory given its richness in transients (tectonic and volcanic earthquakes) and diffuse ambient noise (strong microseism). The approach takes a noisy 3-component seismogram as input and independently predicts the 3-component earthquake and noise waveforms. The model is trained on earthquake and noise waveforms from the STandford EArthquake Dataset (STEAD) and on the local noise of seismic station IU.POHA. We estimate the network’s performance by using the explained variance metric on both earthquake and noise waveforms. We explore different neural network designs for WaveDecompNet and find that the model with long-short-term memory (LSTM) performs best over other structures. Overall, we find that WaveDecompNet provides satisfactory performance down to a signal-to-noise ratio (SNR) of 0.1. The potential of the method is (1) to improve broad-band SNR of transient (earthquake) waveforms and (2) to improve local ambient noise to monitor the Earth’s structure using ambient noise signals. To test this, we apply a short-time average to a long-time average filter and improve the number of detected events. We also measure single-station cross-correlation functions of the recovered ambient noise and establish their improved coherence through time and over different frequency bands. We conclude that WaveDecompNet is a promising tool for a broad range of seismological research.
- NSF-PAR ID:
- 10189142
- Date Published:
- Journal Name:
- Journal of Neurophysiology
- Volume:
- 123
- Issue:
- 4
- ISSN:
- 0022-3077
- Page Range / eLocation ID:
- 1472 to 1485
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
SUMMARY -
It is widely assumed that distributed neuronal networks are fundamental to the functioning of the brain. Consistent spike timing between neurons is thought to be one of the key principles for the formation of these networks. This can involve synchronous spiking or spiking with time delays, forming spike sequences when the order of spiking is consistent. Finding networks defined by their sequence of time-shifted spikes, denoted here as spike timing networks, is a tremendous challenge. As neurons can participate in multiple spike sequences at multiple between-spike time delays, the possible complexity of networks is prohibitively large. We present a novel approach that is capable of (1) extracting spike timing networks regardless of their sequence complexity, and (2) that describes their spiking sequences with high temporal precision. We achieve this by decomposing frequency-transformed neuronal spiking into separate networks, characterizing each network’s spike sequence by a time delay per neuron, forming a spike sequence timeline. These networks provide a detailed template for an investigation of the experimental relevance of their spike sequences. Using simulated spike timing networks, we show network extraction is robust to spiking noise, spike timing jitter, and partial occurrences of the involved spike sequences. Using rat multi-neuron recordings, we demonstrate the approach is capable of revealing real spike timing networks with sub-millisecond temporal precision. By uncovering spike timing networks, the prevalence, structure, and function of complex spike sequences can be investigated in greater detail, allowing us to gain a better understanding of their role in neuronal functioning.more » « less
-
more » « less
Abstract Objective. High-density electromyography (HD-EMG) decomposition algorithms are used to identify individual motor unit (MU) spike trains, which collectively constitute the neural code of movements, to predict motor intent. This approach has advanced from offline to online decomposition, from isometric to dynamic contractions, leading to a wide range of neural-machine interface applications. However, current online methods need offline retraining when applied to the same muscle on a different day or to a different person, which limits their applications in a real-time neural-machine interface. We proposed a deep convolutional neural network (CNN) framework for neural drive estimation, which takes in frames of HD-EMG signals as input, extracts general spatiotemporal properties of MU action potentials, and outputs the number of spikes in each frame. The deep CNN can generalize its application without retraining to HD-EMG data recorded in separate sessions, muscles, or participants.Approach. We recorded HD-EMG signals from the vastus medialis and vastus lateralis muscles from five participants while they performed isometric contractions during two sessions separated by ∼20 months. We identified MU spike trains from HD-EMG signals using a convolutive blind source separation (BSS) method, and then used the cumulative spike train (CST) of these MUs and the HD-EMG signals to train and validate the deep CNN.Main results. On average, the correlation coefficients between CST from the BSS and that from deep CNN wereSignificance. We can conclude that the deep CNN is generalizable across the aforementioned conditions without retraining. We could potentially generate a robust deep CNN to estimate neural drive to muscles for neural-machine interfaces. -
more » « less
Abstract Objective . Patients with photovoltaic subretinal implant PRIMA demonstrated letter acuity ∼0.1 logMAR worse than sampling limit for 100μ m pixels (1.3 logMAR) and performed slower than healthy subjects tested with equivalently pixelated images. To explore the underlying differences between natural and prosthetic vision, we compare the fidelity of retinal response to visual and subretinal electrical stimulation through single-cell modeling and ensemble decoding.Approach . Responses of retinal ganglion cells (RGCs) to optical or electrical white noise stimulation in healthy and degenerate rat retinas were recorded via multi-electrode array. Each RGC was fit with linear–nonlinear and convolutional neural network models. To characterize RGC noise, we compared statistics of spike-triggered averages (STAs) in RGCs responding to electrical or visual stimulation of healthy and degenerate retinas. At the population level, we constructed a linear decoder to determine the accuracy of the ensemble of RGCs onN -way discrimination tasks.Main results . Although computational models can match natural visual responses well (correlation ∼0.6), they fit significantly worse to spike timings elicited by electrical stimulation of the healthy retina (correlation ∼0.15). In the degenerate retina, response to electrical stimulation is equally bad. The signal-to-noise ratio of electrical STAs in degenerate retinas matched that of the natural responses when 78 ± 6.5% of the spikes were replaced with random timing. However, the noise in RGC responses contributed minimally to errors in ensemble decoding. The determining factor in accuracy of decoding was the number of responding cells. To compensate for fewer responding cells under electrical stimulation than in natural vision, more presentations of the same stimulus are required to deliver sufficient information for image decoding.Significance . Slower-than-natural pattern identification by patients with the PRIMA implant may be explained by the lower number of electrically activated cells than in natural vision, which is compensated by a larger number of the stimulus presentations. -
more » « less
Abstract We evaluate several neural-network architectures, both convolutional and recurrent, for gravitational-wave time-series feature extraction by performing point parameter estimation on noisy waveforms from binary-black-hole mergers. We build datasets of 100 000 elements for each of four different waveform models (or approximants) in order to test how approximant choice affects feature extraction. Our choices include
SEOBNRv4P andIMRPhenomPv3 , which contain only the dominant quadrupole emission mode, alongsideIMRPhenomPv3HM andNRHybSur3dq8 , which also account for high-order modes. Each dataset element is injected into detector noise corresponding to the third observing run of the LIGO-Virgo-KAGRA (LVK) collaboration. We identify the temporal convolutional network architecture as the overall best performer in terms of training and validation losses and absence of overfitting to data. Comparison of results between datasets shows that the choice of waveform approximant for the creation of a dataset conditions the feature extraction ability of a trained network. Hence, care should be taken when building a dataset for the training of neural networks, as certain approximants may result in better network convergence of evaluation metrics. However, this performance does not necessarily translate to data which is more faithful to numerical relativity simulations. We also apply this network on actual signals from LVK runs, finding that its feature-extracting performance can be effective on real data.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1152/jn.00641.2019
