CWChunlu Wang

Chunlu Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chunlu Wang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:

  • Zubin Chen

    College of Instrumentation and Electrical Engineering, the National Key Laboratory of Deep Exploration and Imaging, and the Key Laboratory of Geophysical Exploration Equipment, Ministry of Education of China, Jilin University, Changchun, China

    6 shared publications
  • Renjie He

    College of Instrumentation and Electrical Engineering, the National Key Laboratory of Deep Exploration and Imaging, and the Key Laboratory of Geophysical Exploration Equipment, Ministry of Education of China, Jilin University, Changchun, China

    3 shared publications
  • Xiaohua Zhou

    College of Instrumentation and Electrical Engineering, the National Key Laboratory of Deep Exploration and Imaging, and the Key Laboratory of Geophysical Exploration Equipment, Ministry of Education of China, Jilin University, Changchun, China

    3 shared publications
  • Jiwu Li

    College of Instrumentation and Electrical Engineering, Jilin University , Changchun 130026

    2 shared publications
  • Qinxu Zhang

    College of Instrumentation and Electrical Engineering, the National Key Laboratory of Deep Exploration and Imaging, and the Key Laboratory of Geophysical Exploration Equipment, Ministry of Education of China, Jilin University, Changchun, China

    2 shared publications
  • Renjie He

    College of Instrumentation and Electrical Engineering and the Key Laboratory of Geo-Exploration Instrumentation, Ministry of Education, Jilin University, Changchun, China

    2 shared publications

Latest Publications

  • Robust Microseismic Denoising via Multivariate Singular Spectrum Analysis Coupled With Frequency-Domain-Aware U-Net

    by Renjie He, Qinxu Zhang, Chunlu Wang, Zhiwen Li, Zubin Chen, Yuxuan Zhang, Sebastian Bader

    Understanding subsurface processes is a central task in geophysical sciences, with direct implications for energy resource development, seismic hazard assessment, and environmental monitoring. Among the available techniques, microseismic monitoring provides critical information on fracture propagation and reservoir stimulation in unconventional oil and gas operations. However, surface-based measurements are often severely degraded by environmental and anthropogenic noise, which compromises the accuracy of event detection, localization, and subsequent interpretation. Conventional denoising methods based on sparse transforms or time–frequency analysis rely on rigid assumptions, while existing U-Net based approaches tend to introduce boundary artifacts and loss of fine signal details. This study proposes MFU-Net, a hybrid denoising framework that integrates multivariate singular spectrum analysis (MSSA) with a frequency-domain-aware U-Net. MSSA reconstructs dominant signal components to suppress random noise and provides physics-informed priors as two-channel inputs. The network further incorporates multi-scale temporal convolution (MSTC) and frequency-domain processing (FDP) modules, enabling joint time–frequency feature learning for robust suppression of low-frequency coupled noise. Experiments on synthetic datasets show that MFU-Net consistently outperforms MSSA and conventional U-Net across a wide input signal-to-noise ratio(SNR) range (–20 dB to 20 dB). At –20 dB, MFU-Net achieves an output SNR improvement to 10.271 dB, while preserving waveform fidelity. Field validation on hydraulic fracturing data from the Sichuan Basin confirms the robust performance of MFU-Net in orangesurface-based microseismic denoising under low-SNR conditions. These results indicate that MFU-Net provides a reliable solution for the studied monitoring scenario, effectively improving data quality and supporting subsequent microseismic analysis and interpretation.

  • Low-SNR Microseismic Source Localization via Multiscale Convolutional Network With Coordinate Attention

    by Renjie He, Qinxu Zhang, Chunlu Wang, Zubin Chen, Yuxuan Zhang, Sebastian Bader

    Microseismic (MS) source localization is essential for mitigating rockburst hazards and optimizing the reconstruction of energy reservoir. However, conventional convolutional neural networks (CNNs) remain highly sensitive to noise, and LSTM-FCNN models fail to effectively capture the spatial–temporal correlations among geophone arrays, resulting in degraded performance under low signal-to-noise ratio (SNR) conditions, typically below 0 dB. To overcome these limitations, This paper presents a multi-scale convolutional localization model with coordinate attention (MSCAR-Net). The model exploits the heterogeneous responses of noise and the correlated features of effective signals through multiscale convolutions, while a feature fusion strategy balances noise suppression and signal enhancement. In addition, the coordinate attention (CA) mechanism establishes spatial-temporal correlations between geophone positions and signal sequences, significantly improving localization robustness under low-SNR conditions. Experimental results demonstrate that MSCAR-Net achieves a stable localization error of approximately 7.9 m at SNR ≥ −5 dB, representing an 87% improvement over the baseline CNN and a 44% enhancement compared with the LSTM-FCNN. Field validation using known perforation locations in the S-H2 hydraulic fracturing project confirms an average error of 8.2 m, while real-time localization of 65 events further validates the method’s applicability as a measurement solution for low-SNR MS monitoring systems.


  • A Novel Method for Detecting Geological Anomalies in Tunnel Space Using Multiparameter Elastic Full Waveform Inversion

    by Chunyang Pei, Zhixian Zhu, Chunlu Wang, Jiwu Li, Xiaohua Zhou, Linhang Zhang, Zubin Chen

    During tunnel excavation, precise detection of low-velocity anomalies ahead of the tunnel face is crucial for ensuring the smooth construction of the tunnel project. However, current tunnel seismic prediction (TSP) system can only provide reflection interface imaging, which lacks the required accuracy and reliability in seismic data interpretation. In response to these limitations, this study presents a tunnel geological anomaly detection approach by utilizing the developed GEI-TSP system in combination with the multiparameter elastic full waveform inversion (EFWI) technique. This approach enables the retrieval of multiparameter distributions, including P-wave velocity, S-wave velocity, and density, for the geological anomalies ahead of the tunnel face, thereby enhancing the detection reliability. First, we design the tunnel forward model to generate the hybrid seismic data encompassing both body waves and Rayleigh surface waves. Second, we derive gradients and pseudo-Hessian operators using a wave mode decomposition strategy to mitigate crosstalk effects among various model parameters and improve inversion accuracy. With an activity level measurement, we conduct a novel model updating strategy to balance contributions from different wavefield combinations and avoid crosstalk between velocities and density. Experiments with several theoretical tunnel models demonstrate the feasibility of the proposed detection method and highlight its substantial potential for imaging anomalies. Meanwhile, the inversion performance of the proposed detection method is evaluated under different noise levels and observation layouts. Finally, a comprehensive assessment of the computational and storage performance of this method is carried out.


  • Automatic arrival picking for microseismic signals based on variational mode decomposition and Akaike information criterion

    by Chunlu Wang, Yanqing Fan, Renjie He, Jiwu Li, Fa Zhao, Xiaohua Zhou, Zubin Chen

    Microseismic (MS) monitoring, which captures signals generated during rock mass fractures, can monitor changes in underground reservoir characteristics. It is of significant importance for the guidance and evaluation of hydraulic fracturing and prediction of geological disasters. However, the signals recorded by seismic detectors often contain various types of noise, especially in surface monitoring with more complex environments. Extracting effective MS signals and accurately picking up their arrivals serves as the foundation for subsequent positioning and other inversion processes. Given the unknown frequency distribution of effective MS signals, it is difficult to achieve signal-to-noise separation through simple filtering methods. In this paper, we propose a novel automatic arrival picking method based on variational mode decomposition (VMD) and Akaike information criterion (AIC). First, VMD is utilized to decompose the original signal into several intrinsic mode functions (IMFs). Then, the Pearson correlation coefficient (CC) and peak-to-average power ratio (PAPR) are combined to determine the effective components. Finally, we reconstruct the signal and employ the AIC method to pick up the arrival of MS events. Applying this method to synthetic tests based on Ricker wavelet, the results demonstrate that it can accurately distinguish effective signals from noise components, exhibiting superior robustness to noise compared to other arrival picking methods. Furthermore, the processing results of field MS signals during the fracturing process of a shale gas well in Sichuan Province also validate the advantages and application potential of the proposed method.


  • Localization for Surface Microseismic Monitoring Based on Local Equivalent Path and Virtual Field Optimization Method

    by Chunlu Wang, Renjie He, Chunyang Pei, Feng Sun, Xiaohua Zhou, Zubin Chen

    In the field of oil and gas exploration, microseismic monitoring has long been utilized in hydraulic fracturing to assess reservoir enhancement treatments and mitigate the risk of induced seismic activity. The fundamental task of microseismic monitoring is to locate microseismic events resulting from rock fracturing during the fracturing process, serving as the foundation for other advanced processing procedures. Surface monitoring has gained popularity over downhole monitoring due to its cost-effectiveness and flexibility, despite potentially lower data quality. Therefore, the development of high-precision and robust surface monitoring localization algorithms is of great importance. In this study, we propose a novel method for localizing microseismic events based on local equivalent path (LEP) and virtual field optimization method (VFOM), which reduces the reliance on velocity models and precise time picking. Our method begins by establishing a hypothetical observation surface (HOS) and simplifying the propagation paths above it to equivalently transfer the surface geophones. Then, by combining VFOM with an iterative algorithm to determine the intersection of hyperbolas from the geophone pairs, we achieve accurate localization of microseismic events. Extensive testing using synthetic and field data confirms the high accuracy and stability of the proposed method, even in the presence of errors in velocity models and arrival time picking. Furthermore, our approach exhibits high computational efficiency, making it suitable for real-time localization requirements.


  • Localization for surface microseismic monitoring based on arrival time correction and VFOM

    by Chunlu Wang, Zeyan Xu, Renjie He, Linhang Zhang, Jiang Wang, Xiaohua Zhou, Zubin Chen

    Unconventional resources have emerged as the primary source to meet the escalating demand for energy consumption, with hydraulic fracturing standing out as an effective means of boosting production. The utilization of microseismic monitoring is crucial for acquiring real-time or semi-real-time extension information of the fracture network to guide the fracturing process. The precise positioning of microseismic events is a fundamental aspect of microseismic monitoring. Traditional methods relying on (relative) arrival time significantly impact positioning accuracy due to picking errors. While waveform-based methods offer high accuracy, they require precise velocity models and are time-consuming. To overcome challenges associated with arrival time pickup and velocity accuracy, we introduce a virtual field optimization method (VFOM) based on arrival time correction. Initially, an equivalent velocity model is established, and the arrival time difference resulting from the model transformation of the master event is calculated to correct the observed arrival time of the target event. Subsequently, we match detector pairs, establish hyperboloids based on the corrected arrival time difference, and employ the intersection point of all hyperboloids as the positioning result. After that, we use the location results of the master event to enhance the accuracy of the target event. Finally, we apply the proposed method to both synthetic test and field datasets, demonstrating a significant improvement in the positioning accuracy and stability provided by the novel method. The robustness against arrival time error renders it a suitable choice for surface monitoring applications where signal quality is compromised. Furthermore, the simplified velocity model significantly diminishes the computational requirements in the positioning process, enhancing its efficiency, and consequently holds vast potential for application in real-time monitoring.