Improvements on particle swarm optimization algorithm for velocity calibration in microseismic monitoring

Yang, Yue; Wen, Jian; Chen, Xiaofei

doi:10.1007/s11589-015-0127-y

Cited by 13 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previously, numerous methods have been used for model calibration, including the linearized Occam's inversion (Pei et al ., 2008), modified Newton–Raphson method (Du and Warpinski, 2013), simulated annealing (Bardainne and Gaucher, 2010), pattern‐search (Akram and Eaton, 2017), PSO (Urbancic et al ., 2006; Yang et al ., 2015; Akram, 2020) and the neighbourhood algorithm (Tan et al., 2018). When the objective function involves many variables, the likelihood for the existence of local minima becomes high.…”

Section: Theorymentioning

confidence: 99%

Comparison of hypocentre locations from the reprocessing of a downhole microseismic dataset

Akram

Yang

Peter

2022

Geophysical Prospecting

View full text Add to dashboard Cite

Focusing on a single vertical‐well microseismic monitoring dataset, the aim here is to objectively look at the hypocentre location determination workflow and compare results from another independent processing effort of the same dataset. To that end, we use the Akaike information criterion–based picker followed by the cross‐correlation‐based refinement for P‐ and S‐wave arrival times. We apply a particle swarm optimization algorithm to calibrate a one‐dimensional velocity model using a single ball‐drop event. Due to the absence of any a priori information, we obtain three different local solutions for the velocity model using the particle swarm optimization algorithm with different upper and lower bounds on the search space. We also use the particle swarm optimization algorithm to determine hypocentre locations for microseismic events. In addition, we perform a waveform‐similarity‐based analysis to identify clusters of closely located microseismic events. Our results show that the hypocentre locations from all three local solutions exhibit similar fracture orientations and dimensions, as compared to the results from another independent processing effort. However, random differences with mean and standard deviation values in x, y, z as (53.9, −23.2, −6.2 m) and (35.5, 42.6, 17.6 m) exist between the two processing versions. These differences can be explained by the combined effect of errors in arrival times, back‐azimuths and velocity models, and the use of different algorithms in the two processing efforts. We also find that the comparison of event clusters other than full event distributions is an effective way of identifying any systematic differences between the two processing results.

show abstract

Section: Theorymentioning

confidence: 99%

Comparison of hypocentre locations from the reprocessing of a downhole microseismic dataset

Akram

Yang

Peter

2022

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…Since then, the widespread use of PSO has been found in solving real-life problems [2,3]. The convergence of the algorithms to a local minim is still a challenge that has been reported in [4]. Several methods and variants of the original PSO were proposed in the past several years to overcome this problem and improve its performance.…”

Section: Introductionmentioning

confidence: 99%

PSOα: A Fragmented Swarm Optimisation for Improved Load Frequency Control of a Hybrid Power System Using FOPID

et al. 2023

View full text Add to dashboard Cite

Particle swarm optimisation (PSO) is one of the widely adopted meta-heuristic methods for solving real-life problems. Its practical utility can be further enhanced by improving its performance. In order to acheive this, academics have presented several variants of the original PSO over the past few years, including the quantum PSO (QPSO), bare-bones PSO (BB-PSO), hybrid PSO, fuzzy PSO, etc. In this paper, the performance of PSO is improved by proposing a fragmented swarm optimisation approach known as the PSOα. The PSOα is tested and compared with PSOs over 14 different benchmarking cost functions to validate its efficacy. The analysis is also carried out to see the impact of α on its performance. It is observed that the average value of the cost function over 50 simulations obtained using the fragmented swarm approach is lower than that obtained using the standard PSO in 12 out of 14 benchmark functions. Similarly, the fragmented approach outperforms the standard PSO in 13 out of 14 benchmark functions when compared with the best fitness value achieved out of 50 simulations. Finally, the proposed approach is applied to solve the well-known real-life optimisation problem of load frequency control (LFC) in power systems. A test system comprising both renewable and traditional power sources is considered to evaluate the efficacy of the proposed technique. A fractional order proportional-integral-differential (FOPID) controller is used, whose parameters are optimised using the proposed PSO for achieving the LFC. The proposed fragmentation approach can be applied with other optimisation techniques to improve their performance.

show abstract

“…The velocity model calibration is an iterative process in which layer velocities and/or thicknesses are perturbed to minimize the difference between the modelled and observed traveltimes from known source locations to all receiver locations used in the data acquisition. Previously, numerous studies have used various methods for model calibration including Occam's inversion (Pei et al ., 2009), simulated annealing (Bardainne & Gaucher, 2010), pattern search (Akram & Eaton, 2017), the neighbourhood algorithm (Tan et al ., 2018), conjugate‐gradient method (Huang et al ., 2019) and particle swarm optimization (Yang et al ., 2015; Akram, 2020). Artificial neural networks (ANNs) have also been used as a supervised learning approach for velocity model inversion (e.g., Moya & Irikura, 2010).…”

Section: Introductionmentioning

confidence: 99%

A physics‐guided neural network‐based approach to velocity model calibration for microseismic data

Zhang

Akram

Innanen

2022

Geophysical Prospecting

View full text Add to dashboard Cite

The physics‐guided neural network framework combines the effectiveness of data‐driven and physics‐based models, and it is, therefore, becoming increasingly popular in geophysical applications. We present a physics‐guided neural network–based approach to calibrate velocity models for microseismic data. In our implementation, the physics‐guided neural network comprises of a user‐selected number of fully connected layers, a scaling and shifting layer and a forward modelling operator layer. We input the observed P‐ and S‐wave arrival times to the neural network. In the forward pass, the network's output layer produces normalized P‐ and S‐wave velocities for the subsurface model. The scaling and shifting layer converts the normalized output to realistic velocity values. The forward modelling operator (i.e. a ray‐shooting algorithm) layer computes traveltimes using the velocities from the preceding scaling and shifting layer and the known source–receiver locations. We then evaluate a loss function that compares the predicted traveltimes with the input observed arrival times, and update network's weights and bias parameters. We also use a weight‐based saliency measure to evaluate whether the selected network architecture (i.e. number of hidden layers and neurons) is optimal for the model calibration problem. Finally, using synthetic data examples, we demonstrate that our unsupervised physics‐guided neural network–based approach can provide robust velocity model and uncertainty estimates.

show abstract

Improvements on particle swarm optimization algorithm for velocity calibration in microseismic monitoring

Cited by 13 publications

References 25 publications

Comparison of hypocentre locations from the reprocessing of a downhole microseismic dataset

Comparison of hypocentre locations from the reprocessing of a downhole microseismic dataset

PSOα: A Fragmented Swarm Optimisation for Improved Load Frequency Control of a Hybrid Power System Using FOPID

A physics‐guided neural network‐based approach to velocity model calibration for microseismic data

Contact Info

Product

Resources

About