Lianghai Wu

Mr. Lianghai Wu

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
11 January 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
YCYUYUN CHEN
YUYUN CHEN
Zhanchuan CaiZhanchuan Cai
Zhanchuan Cai
Jieyu YuanJieyu Yuan
Jieyu Yuan
LWLianghai Wu
Lianghai Wu
The presence of thick clouds in single optical images shows the contamination of interesting objects. Besides, the difficulty of thick cloud removal is mainly the restoration of the weak boundary information from cloud-contaminated areas. Recently, many deep-learning-based frameworks were applied for cloud removal by obtain the related semantic information from the weak boundary information. However, the large-size cloud-contaminated areas lead to the artificial textures in the resulting images. Thus, obtaining the optimal semantic information from finite boundary information is the key to solve this problem. In this work, we design a deep-learning framework for cloud removal, especially large-size clouds removal (i.e., more than 30% coverage of the whole image). First, we design a cloud location model (CLM) which adopted the fully convolutional network to locate the cloud. Second, desired by theory of the coarse-to-fine restoration, we build a dense-attention network (termed as DANet) for restoring cloud contaminated areas. In the DANet, we design a dense block into the coarse network for training the features of restoring directions of each pixel from the weak boundary information. Furthermore, a contextual attention module is built into refinement network for restoring contaminated areas relying on the semantic relationship between the background and foreground information. Compared with the state-of-the-art methods, the proposed DANet achieved greater removal performances and reconstruct more natural image textures.

19 November 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
JLJunjie Liu
Junjie Liu
JZJiaxian Zhu
Jiaxian Zhu
WBWeihua Bai
Weihua Bai
HZHuibing ZHANG
Huibing ZHANG
LWLianghai Wu
Lianghai Wu
Keqin LiKeqin Li
Keqin Li
Industrial IoT (IIoT) sensing nodes for bearing monitoring often operate in high-noise environments, where acoustic and mechanical interference masks weak fault signatures and undermines diagnostic reliability. To address this challenge, we propose a lightweight multi-modal fusion framework for robust fault diagnosis under extreme noise. Our method first applies multi-resolution decomposition with selective reconstruction and adaptive enhancement to preserve fault-related components while suppressing interference. The enhanced signals are transformed from 1D time series into two-dimensional representations to jointly capture temporal dynamics and spectral characteristics. We then design a tri-branch multi-head attention architecture that integrates a multiscale recurrence plot network, a Gramian angular field network, and a lightweight residual network. Learnable attention weights enable adaptive fusion of complementary cross-modal features with low computational overhead. Extensive experiments on the CWRU benchmark show superior robustness from 0 dB to -6 dB SNR, with a mean accuracy above 99.6% and consistent gains over eight state-of-the-art methods. Additional tasks on single-domain diagnosis, cross-condition fault type recognition, and fault degree discrimination (T1–T3) confirm strong generalization and multi-scale adaptability, with average improvements of 2–4% over the second-best baseline and stable variance under noise. The compact architecture and high noise immunity indicate practical suitability for IIoT sensing nodes and edge deployment in complex industrial scenarios.

5 April 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
LWLianghai Wu
Lianghai Wu
Zhanchuan CaiZhanchuan Cai
Zhanchuan Cai
YCYUYUN CHEN
YUYUN CHEN
Zhiguo MengZhiguo Meng
Zhiguo Meng
King crater is a Copernican crater located near the equator in the western highlands of the lunar farside. The study of the microwave brightness temperature (TB) in this region is of great significance for exploring the interior structure of the lunar farside. The Chang’e-2 (CE-2) microwave radiometer (MRM) is mainly used to obtain TB data on the lunar surface under four channels. This study uses the ordinary Kriging algorithm to interpolate the midday and midnight MRM data of this region and generates the TB maps and TB difference (dTB) maps for each channel in two moments. Combined with UVVIS data from Clementine satellite and Diviner data from LRO satellite, the characteristics of microwave thermal radiation are discussed. The results show that (FeO+TiO2) abundance (FTA) and rock abundance (RA) are important factors affecting thermal radiation anomalies in the King crater. It also provides evidence for the formation of the King-Bruno anomalous belt, which is believed to be significantly related to the formation of the King crater.

3 August 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LWLianghai Wu
Lianghai Wu
Zhanchuan CaiZhanchuan Cai
Zhanchuan Cai
XHXiu He
Xiu He
YCYUYUN CHEN
YUYUN CHEN
Zhiguo MengZhiguo Meng
Zhiguo Meng
Microwave radiometer (MRM) is one of the important payloads on the Chang’e-2 (CE-2) Lunar satellite. In the Chang’e satellite’s observation of the microwave radiation brightness temperature (TB) on the lunar surface, there are some “cold spots” of microwave thermal radiation at night containing the Jackson crater. In order to compare the diurnal radiation TB differences of “cold spots” on the lunar surface, two typical craters at similar latitudes on the northern hemisphere on the lunar farside were selected: Jackson, which represents the new craters with a large number of discrete rocks on their surfaces; and Morse, which no longer has a large number of rocks after long-term meteorite impact and lunar evolution. In this paper, the diurnal variation of CE-2 MRM data in the two craters is presented, and a comparative analysis is made with the (FeO + TiO2) abundance (FTA) obtained by Clementine UV-VIS data and the rock abundance (RA) data of LRO Diviner. We find that the variation of the "cold spots" of lunar surface thermal radiation is closely related to the RA distribution in the newly formed craters on the lunar surface, and also has a certain correlation with the FTA.