Fanlei Meng

Dr. Fanlei Meng

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
2 April 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
FMFanlei Meng
Fanlei Meng
QFQinYin Fan
QinYin Fan
YLYue Li
Yue Li
With their powerful feature extraction ability, convolutional neural network (CNN) models achieve excellent signal reconstruction and recovery performances compared with those of traditional methods. The CNN-based approaches mainly use supervised learning approaches; thus, they require large numbers of ground-truth labeled samples. However, in the seismic denoising field, collecting large numbers of labeled samples is impossible; thus, the main challenge to using deep learning methods is a lack of labeled data. Moreover, the data that are available contain noise. To resolve these shortcomings, this letter proposes a novel self-supervised learning framework to reconstruct and perform blind denoising of seismic data images; this approach requires no labeled training data. We utilize a masking procedure to modify an observation input to a CNN to create a $\mathcal {J}$ -invariant function and incorporate a specific CNN architecture known as U 2 Net, which implements a two-level nested autoencoder that extracts complex feature information from different scales. We modify the network to make it more suitable for seismic signal reconstruction. Finally, we use the self-supervised loss between the original observation and the net output to update the weights of U 2 Net through backpropagation. Tests on both synthetic and field data demonstrate the superior performance of our algorithm on low signal-to-noise ratio data.

30 July 2024 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
FMFanlei Meng
Fanlei Meng
HSHaixin Sun
Haixin Sun
JLJie Li
Jie Li
TXTingfa Xu
Tingfa Xu

28 July 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
HSHaixin Sun
Haixin Sun
JXJingwen Xu
Jingwen Xu
FMFanlei Meng
Fanlei Meng
QCQiuguang Cao
Qiuguang Cao
MCMengdi Cheng
Mengdi Cheng
In recent years, deep learning approaches that integrate convolutional neural networks (CNNs) with Transformer architectures have greatly enhanced the accuracy of hyperspectral image (HSI) classification. However, the combination of these two methods has not fully explored the deep correlations between spectral and spatial features nor effectively utilized the discriminative information from the central pixels. To address these issues, we propose a novel spectral-spatial dual-branch selection fusion enhanced Transformer (DSFEFormer) network. Specifically, a spectral-spatial dual-branch structure is designed to extract comprehensive and rich spectral and spatial features, thereby enhancing the feature representation capability of the image. Subsequently, a spectral spatial selection attention (SSSA) is introduced to guide the deep fusion of spectral and spatial features, adaptively focusing on the most discriminative regions while effectively suppressing redundant information. Additionally, to fully leverage the deep fusion features, we design a Center Manhattan Transformer Encoder (CMTE) composed of two key modules, Pooling Manhattan Attention (PMA) and convolutional gated feed forward network (CGFFN) to model the relationships between central pixels and their neighboring pixels effectively, further enhancing the ability to perceive subtle feature differences. Comparative experiments and analyses are conducted on four publicly available datasets—Pavia University, Salinas, Xuzhou, and WHU-Hi-LongKou. The experimental results indicate that DSFEFormer achieves superior classification performance while maintaining low computational complexity, and also exhibits certain robustness and generalization potential.

15 July 2016 in Journal of Geophysics and Engineering
Verified
Journal Article
Open access
PDF file
FMFanlei Meng
Fanlei Meng
YLYue Li
Yue Li
YLYanping Liu
Yanping Liu
YTYanan Tian
Yanan Tian
Ning WuNing Wu
Ning Wu
The fractal conservation law (FCL) is a linear partial differential equation that is modified by an anti-diffusive term of lower order. The analysis indicated that this algorithm could eliminate high frequencies and preserve or amplify low/medium-frequencies. Thus, this method is quite suitable for the simultaneous noise suppression and enhancement or preservation of seismic signals. However, the conventional FCL filters seismic data only along the time direction, thereby ignoring the spatial coherence between neighbouring traces, which leads to the loss of directional information. Therefore, we consider the development of the conventional FCL into the time-space domain and propose a Radon–FCL approach. We applied a Radon transform to implement the FCL method in this article; performing FCL filtering in the Radon domain achieves a higher level of noise attenuation. Using this method, seismic reflection events can be recovered with the sacrifice of fewer frequency components while effectively attenuating more random noise than conventional FCL filtering. Experiments using both synthetic and common shot point data demonstrate the advantages of the Radon–FCL approach versus the conventional FCL method with regard to both random noise attenuation and seismic signal preservation.

13 March 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HCHongyue Cao
Hongyue Cao
FMFanlei Meng
Fanlei Meng
HSHaixin Sun
Haixin Sun
XCXinyu Cui
Xinyu Cui
DSDan Shao
Dan Shao
Hyperspectral unmixing (HU) is fundamental for conducting quantitative analyses in remote sensing, yet existing methods face a persistent tradeoff between model performance and physical interpretability. Although deep learning models achieve superior performance, even “gray-box” models that incorporate physical constraints still suffer from an intrinsically opaque decision-making process, which hinders their trustworthiness in critical applications. To address this challenge, this paper introduces a theory-guided unmixing framework aimed at enhancing mechanistic interpretability called the sparse and subspace-attentive transformer unmixing network (SSTU-Net). Unlike heuristic architectures, SSTU-Net is rigorously derived from the first principles of sparse rate reduction (SRR) theory. Its core modules—the multi-head subspace self-attention (MSSA) and the iterative shrinkage-thresholding algorithm (ISTA)—directly implement the essential mathematical steps of information compression and sparsification within the SRR theory, respectively. Extensive experiments on both synthetic and real hyperspectral datasets demonstrate that SSTU-Net achieves competitive performance compared to representative state-of-the-art methods—including advanced autoencoder-based networks (e.g., CyCU-Net and DAAN) and recent transformer-based unmixing architectures (e.g., DeepTrans and MAT-Net)—while strictly adhering to theoretically predicted evolutionary trajectories. More importantly, a series of specifically designed structural interpretability validation experiments mechanistically confirm the theoretically predicted behaviors, such as layer-wise information compression, feature sparsification, and subspace orthogonalization. These results reveal the internal working mechanisms of SSTU-Net, validating the feasibility and significant potential of our principled theory-guided framework for developing high-performance and trustworthy intelligent models in remote sensing.

19 July 2025 in Sensors
Verified
Journal Article
Open access
PDF file
HSHaixin Sun
Haixin Sun
QCQiuguang Cao
Qiuguang Cao
FMFanlei Meng
Fanlei Meng
JXJingwen Xu
Jingwen Xu
MCMengdi Cheng
Mengdi Cheng
In recent years, deep learning (DL) has been demonstrated remarkable capabilities in hyperspectral unmixing (HU) due to its powerful feature representation ability. Convolutional neural networks (CNNs) are effective in capturing local spatial information, but limited in modeling long-range dependencies. In contrast, transformer architectures extract global contextual features via multi-head self-attention (MHSA) mechanisms. However, most existing transformer-based HU methods focus only on spatial or spectral modeling at a single scale, lacking a unified mechanism to jointly explore spatial and channel-wise dependencies. This limitation is particularly critical for multiscale contextual representation in complex scenes. To address these issues, this article proposes a novel Spatial-Channel Multiscale Transformer Network (SCMT-Net) for HU. Specifically, a compact feature projection (CFP) module is first used to extract shallow discriminative features. Then, a spatial multiscale transformer (SMT) and a channel multiscale transformer (CMT) are sequentially applied to model contextual relations across spatial dimensions and long-range dependencies among spectral channels. In addition, a multiscale multi-head self-attention (MMSA) module is designed to extract rich multiscale global contextual and channel information, enabling a balance between accuracy and efficiency. An efficient feed-forward network (E-FFN) is further introduced to enhance inter-channel information flow and fusion. Experiments conducted on three real hyperspectral datasets (Samson, Jasper and Apex) and one synthetic dataset showed that SCMT-Net consistently outperformed existing approaches in both abundance estimation and endmember extraction, demonstrating superior accuracy and robustness.