Jun Zhu

Jun Zhu

Auto-generated profile, based on publicly available information

Jun Zhu

University of Science and Technology of China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 January 2024 in Communications Earth & Environment
Verified
Journal Article
Open access
PDF file
XSXu Si
Xu Si
XWXinming Wu
Xinming Wu
ZLZefeng Li
Zefeng Li
SWShenghou Wang
Shenghou Wang
JZJun Zhu
Jun Zhu
Earthquake monitoring is vital for understanding the physics of earthquakes and assessing seismic hazards. A standard monitoring workflow includes the interrelated and interdependent tasks of phase picking, association, and location. Although deep learning methods have been successfully applied to earthquake monitoring, they mostly address the tasks separately and ignore the geographic relationships among stations. Here, we propose a graph neural network that operates directly on multi-station seismic data and achieves simultaneous phase picking, association, and location. Particularly, the inter-station and inter-task physical relationships are informed in the network architecture to promote accuracy, interpretability, and physical consistency among cross-station and cross-task predictions. When applied to data from the Ridgecrest region and Japan, this method showed superior performance over previous deep learning-based phase-picking and localization methods. Overall, our study provides a prototype self-consistent all-in-one system of simultaneous seismic phase picking, association, and location, which has the potential for next-generation automated earthquake monitoring.

15 January 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XSXu Si
Xu Si
XWXinming Wu
Xinming Wu
HSHanlin Sheng
Hanlin Sheng
JZJun Zhu
Jun Zhu
ZLZefeng Li
Zefeng Li
In seismology, while training a specific deep learning model for each task is common, it often faces challenges such as the scarcity of labeled data and limited regional generalization. Addressing these issues, we introduce SeisCLIP: a foundation model for seismology, leveraging contrastive learning during pretraining on multimodal data of seismic waveform spectra and the corresponding local and global event information. SeisCLIP consists of a transformer-based spectrum encoder and an multilayer perceptron (MLP)-based information encoder that are jointly pre-trained on massive data. During pretraining, contrastive learning aims to enhance representations by training two encoders to bring the corresponding waveform spectra and event information closer in the feature space, while distancing uncorrelated pairs. Remarkably, the pre-trained spectrum encoder offers versatile features, enabling its application across diverse tasks and regions. Thus, it requires only modest datasets for fine-tuning to specific downstream tasks. Our evaluations demonstrate SeisCLIP’s superior performance over baseline methods in tasks like event classification, localization, and focal mechanism analysis, even when using distinct datasets from various regions. In essence, SeisCLIP emerges as a promising foundational model for seismology, potentially revolutionizing foundation-model-based research in the domain.

28 November 2023 in Geophysical Journal International
Verified
Journal Article
Open access
PDF file
JZJun Zhu
Jun Zhu
LFLihua Fang
Lihua Fang
FMFajun Miao
Fajun Miao
LFLiping Fan
Liping Fan
JZJi Zhang
Ji Zhang
ZLZefeng Li
Zefeng Li
Discrimination between tectonic earthquakes (EQs) and quarry blasts is important for accurate EQ cataloguing and seismic hazard analysis. However, reliable classification of these two types of seismic events is challenging with no prior knowledge of source parameters. Here, we applied deep learning to perform this classification task in southern California and eastern Kentucky. Since the two regions differ significantly in available labelled data, class imbalance and waveform characteristics, we adopted different strategies for them. We directly trained a convolutional neural network (CNN) for southern California due to its data abundancy. To alleviate the class imbalance, the blast data were augmented by repeated sampling. The model for California yields F1-scores of >83.5 per cent when estimated by individual stations and >98.1 per cent by network average (i.e. averaging the CNN’s outputs on all available stations for each event). As eastern Kentucky has a much smaller data size, we apply transfer learning to the pre-trained California model to fit the Kentucky data. The transfer-learned model yields F1-scores of >86.9 per cent when estimated by individual stations and >96.7 per cent by network average. The transfer-learned model outperforms the model re-trained from scratch for the Kentucky data. Gradient-weighted class activation mapping shows the S onset and the S long-period coda are important to identify EQs and blasts, respectively. By visual inspections of the seismograms, the source locations, the origin time and the P-wave polarities, we verified that most of the events falsely predicted by our models are actually mislabelled by seismic analysts. Our models thus show great potential in helping seismic analysts find those mislabelled events which remain hidden in the historical catalogue. Our results demonstrate that deep learning can achieve high accuracy in seismic event discrimination and that transfer learning is effective and efficient to generalize deep learning models across different regions.

31 August 2025 in Geophysical Research Letters
Verified
Journal Article
Open access
SMShang Ma
Shang Ma
ZLZefeng Li
Zefeng Li
DSDaoyuan Sun
Daoyuan Sun
YSYulong Su
Yulong Su
JLJiewen Li
Jiewen Li
JZJun Zhu
Jun Zhu
Seismic waves preceding the core phase PKIKP, known as PKP precursors, have been used to map small scatterers near the core‐mantle boundary (CMB). However, their low signal‐to‐noise ratio has required manual identification, hindering systematic and comprehensive analysis. Here, we develop GraphCursor, a model based on Graph Neural Networks (GNNs), to detect PKP precursors across multiple stations. Trained on manually picked precursors, GraphCursor identifies 37,512 precursor waveforms from 5,499 global earthquakes (2000–2024). We locate scatterers by stacking multistation probability functions and estimate their strengths relative to global averages. Our exhaustive search produces unprecedentedly abundant scatterers, including new discoveries of those beneath Antarctica. The distribution of most global scatterers largely correlates with ultra‐low velocity zones (ULVZs). GraphCursor's potential extends to identifying other deep seismic phases and aids in promoting the discovery of new deep Earth structures.

28 April 2026 in Earth and Planetary Science Letters
Verified
Journal Article
Open access
XWXin Wang
Xin Wang
DLDuo Li
Duo Li
JZJun Zhu
Jun Zhu
XXXiaohua Xu
Xiaohua Xu
ZLZefeng Li
Zefeng Li
RFRongxin Fang
Rongxin Fang

9 March 2022 in arXiv
Verified
Preprint
Open access
PDF file
LWLiyuan Wang
Liyuan Wang
XZXingxing Zhang
Xingxing Zhang
KYKuo Yang
Kuo Yang
LYLonghui Yu
Longhui Yu
CLChongxuan Li
Chongxuan Li
JZJun Zhu
Jun Zhu
Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves the state-of-the-art (SOTA) performance. However, existing work is mainly built on a small memory buffer containing a few original data, which cannot fully characterize the old data distribution. In this work, we propose memory replay with data compression (MRDC) to reduce the storage cost of old training samples and thus increase their amount that can be stored in the memory buffer. Observing that the trade-off between the quality and quantity of compressed data is highly nontrivial for the efficacy of memory replay, we propose a novel method based on determinantal point processes (DPPs) to efficiently determine an appropriate compression quality for currently-arrived training samples. In this way, using a naive data compression algorithm with a properly selected quality can largely boost recent strong baselines by saving more compressed data in a limited storage space. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.