Zhiwei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhiwei Li has a total of 94 co-authors. Here are the top co-authors by number of shared publications:
- Huanfeng Shen
Wuhan University
10 shared publications Huanfeng Shen
6 shared publications- Qihao Weng
The Hong Kong Polytechnic University
5 shared publications - Qing Cheng
School of Computer Science, China University of Geosciences, Wuhan, China
4 shared publications - Liangpei Zhang
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China
3 shared publications - Qiangqiang Yuan
Wuhan University
3 shared publications
Latest Publications
- Open Access
- 3 October 2026
- Published by Springer Nature in Communications Sustainability
- Vol. 1 (1) , 156
Rooftop solar supports carbon-neutral transition in Hong Kong’s building sector
- 3 October 2026
- Published by Springer Nature in Communications Sustainability
- Vol. 1 (1) , 156
Open AccessRooftop solar supports carbon-neutral transition in Hong Kong’s building sector
- Open Access
- 6 May 2026
- Published by Taylor & Francis in Geo-spatial Information Science
- p. 1-20
A joint thin and thick cloud removal method for high-resolution optical satellite images
1. With the rapid advancement of satellite technology, high spatial resolution optical remote sensing images (HRIs) have been widely applied in various fields (Chen et al. 2022; Li et al. 2024; Xie...
- 6 May 2026
- Published by Taylor & Francis in Geo-spatial Information Science
- p. 1-20
Open AccessA joint thin and thick cloud removal method for high-resolution optical satellite images
1. With the rapid advancement of satellite technology, high spatial resolution optical remote sensing images (HRIs) have been widely applied in various fields (Chen et al. 2022; Li et al. 2024; Xie...
- Open Access
- 26 February 2026
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 63 (1)
Weakly supervised cloud detection combining spectral features and multi-scale deep network
1. High-resolution optical satellite imagery can be affected by varying degrees of clouds, resulting in different cases of surface information loss. Thick clouds result in a complete loss of inform...
- 26 February 2026
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 63 (1)
Open AccessWeakly supervised cloud detection combining spectral features and multi-scale deep network
1. High-resolution optical satellite imagery can be affected by varying degrees of clouds, resulting in different cases of surface information loss. Thick clouds result in a complete loss of inform...
- Open Access
- 23 September 2025
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 144
TerrainFloodSense: Improving seamless flood mapping with cloudy satellite imagery via water occurrence and terrain data fusion
- 23 September 2025
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 144
Open AccessTerrainFloodSense: Improving seamless flood mapping with cloudy satellite imagery via water occurrence and terrain data fusion
- Open Access
- 28 November 2024
- Published by Springer Nature in npj Urban Sustainability
- Vol. 4 (1) , 1-9
How will ai transform urban observing, sensing, imaging, and mapping?
- 28 November 2024
- Published by Springer Nature in npj Urban Sustainability
- Vol. 4 (1) , 1-9
Open AccessHow will ai transform urban observing, sensing, imaging, and mapping?
- Open Access
- 7 August 2024
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 216, 185-199
Beyond clouds: Seamless flood mapping using Harmonized Landsat and Sentinel-2 time series imagery and water occurrence data
- 7 August 2024
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 216, 185-199
Open AccessBeyond clouds: Seamless flood mapping using Harmonized Landsat and Sentinel-2 time series imagery and water occurrence data
- 11 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
A Unified Cloud Detection Method for Suomi-NPP VIIRS Day and Night PAN Imagery
Cloud detection is a necessary step before the application of remote sensing images. However, the radiation intensity similarity between artificial lights and clouds is higher in nighttime remote sensing images than in daytime remote sensing images, making it difficult to distinguish artificial lights from clouds. This article proposes a deep learning method called multifeature fusion for cloud detection network (MFFCD-Net) to detect clouds in daytime and nighttime remote sensing images. A dilated residual upsampling module was designed for upsampling feature maps while enlarging the receptive field. A multiscale feature-extraction fusion module (MFEF) was designed to enhance the ability to distinguish regular textures of artificial lights from random textures of clouds. Moreover, an adaptive feature-fusion module (AFF) was designed to select and fuse the feature in the encoding stage and decoding stage, thus improving the cloud detection accuracy. To the best of our knowledge, this is the first time that a method is designed for cloud detection in both daytime and nighttime remote sensing images. The experimental results on Suomi-NPP Visible Infrared Imaging Radiometer Suite (VIIRS) of the panchromatic (PAN) day/night band (DNB) images show that MFFCD-Net could obtain a better balance in commission and omission rates than baseline methods (92.3% versus 90.5% on the F1-score) in daytime remote sensing images. Although artificial lights introduce strong interference in nighttime remote sensing images, MFFCD-Net can better distinguish artificial lights from clouds than baseline methods (90.8% versus 88.4% on the F1-score). The results indicate that MFFCD-Net is promising for cloud detection both in daytime and nighttime remote sensing images. The source code and dataset are available at https://github.com/Neooolee/MFFCD-Net .
- 11 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-13
A Unified Cloud Detection Method for Suomi-NPP VIIRS Day and Night PAN Imagery
Cloud detection is a necessary step before the application of remote sensing images. However, the radiation intensity similarity between artificial lights and clouds is higher in nighttime remote sensing images than in daytime remote sensing images, making it difficult to distinguish artificial lights from clouds. This article proposes a deep learning method called multifeature fusion for cloud detection network (MFFCD-Net) to detect clouds in daytime and nighttime remote sensing images. A dilated residual upsampling module was designed for upsampling feature maps while enlarging the receptive field. A multiscale feature-extraction fusion module (MFEF) was designed to enhance the ability to distinguish regular textures of artificial lights from random textures of clouds. Moreover, an adaptive feature-fusion module (AFF) was designed to select and fuse the feature in the encoding stage and decoding stage, thus improving the cloud detection accuracy. To the best of our knowledge, this is the first time that a method is designed for cloud detection in both daytime and nighttime remote sensing images. The experimental results on Suomi-NPP Visible Infrared Imaging Radiometer Suite (VIIRS) of the panchromatic (PAN) day/night band (DNB) images show that MFFCD-Net could obtain a better balance in commission and omission rates than baseline methods (92.3% versus 90.5% on the F1-score) in daytime remote sensing images. Although artificial lights introduce strong interference in nighttime remote sensing images, MFFCD-Net can better distinguish artificial lights from clouds than baseline methods (90.8% versus 88.4% on the F1-score). The results indicate that MFFCD-Net is promising for cloud detection both in daytime and nighttime remote sensing images. The source code and dataset are available at https://github.com/Neooolee/MFFCD-Net .
- Open Access
- 22 April 2024
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 211, 372-391
First retrieval of daily 160 m aerosol optical depth over urban areas using Gaofen-1/6 synergistic observations: Algorithm development and validation
- 22 April 2024
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 211, 372-391
Open AccessFirst retrieval of daily 160 m aerosol optical depth over urban areas using Gaofen-1/6 synergistic observations: Algorithm development and validation
- 19 March 2024
- Published by Taylor & Francis
- p. 44-57
Urban Flooding Monitoring and Management in Geospatial Perspective
The increasing frequency of flooding caused by global climate change poses severe threats to densely populated urban areas. Urban flooding monitoring and management are critical for a better response to potential flood disasters. This chapter provides a brief review of the recent advances in geospatial data, techniques, and platforms applied for urban flooding monitoring and management. Moreover, this chapter explores applications of geospatial techniques for flood mitigation, preparation, response, and recovery before, during, and after flood disasters. The geospatial techniques discussed in this chapter include flood modeling and forecasting, flood mapping and risk assessment, flood impact assessment, recovery, and adaptation. Additionally, the benefits and limitations of various geospatial platforms for flood management are discussed. Furthermore, this chapter identifies current challenges and future prospects in the field, emphasizing the need to incorporate multi-sensor data and integrate geospatial techniques with advanced artificial intelligence to improve flood monitoring and management and promote flood resilience.
- 19 March 2024
- Published by Taylor & Francis
- p. 44-57
Urban Flooding Monitoring and Management in Geospatial Perspective
The increasing frequency of flooding caused by global climate change poses severe threats to densely populated urban areas. Urban flooding monitoring and management are critical for a better response to potential flood disasters. This chapter provides a brief review of the recent advances in geospatial data, techniques, and platforms applied for urban flooding monitoring and management. Moreover, this chapter explores applications of geospatial techniques for flood mitigation, preparation, response, and recovery before, during, and after flood disasters. The geospatial techniques discussed in this chapter include flood modeling and forecasting, flood mapping and risk assessment, flood impact assessment, recovery, and adaptation. Additionally, the benefits and limitations of various geospatial platforms for flood management are discussed. Furthermore, this chapter identifies current challenges and future prospects in the field, emphasizing the need to incorporate multi-sensor data and integrate geospatial techniques with advanced artificial intelligence to improve flood monitoring and management and promote flood resilience.
- 14 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-18
Transferring Deep Models for Cloud Detection in Multisensor Images via Weakly Supervised Learning
Recently, deep learning has been widely used for cloud detection in satellite images. However, due to radiometric and spatial resolution differences in images from different sensors and time-consuming process of manually labeling cloud detection datasets, it is difficult to effectively generalize deep learning models for cloud detection in multi-sensor images. This paper propose a weakly supervised learning method for transferring deep models for cloud detection in multi-sensor images (TransMCD), which leverages the generalization of deep models and the spectral features of clouds to construct pseudo-label dataset to improve the generalization of models. A deep model is first pre-trained using a well-annotated cloud detection dataset, which is used to obtain a rough cloud mask of unlabeled target image. The rough mask can be used to determine the spectral threshold adaptively for cloud segmentation of target image. Block-level pseudo-labels with high confidence in target image are selected using the rough mask and spectral mask. Unsupervised segmentation technique is utilized to construct a high-quality pixel-level pseudo-label dataset. Finally, the pseudo-label dataset is utilized as supervised information for transferring the pre-trained model to target image. The TransMCD method was validated by transferring model trained on 16-m Gaofen-1 wide field of view images to 8-m Gaofen-1, 4-m Gaofen-2 and 10-m Sentinel-2 images. The F1-score of the transferred models on target images achieves improvements of 1.23–9.63% over the pre-trained models, which is comparable to the fully-supervised models trained with well-annotated target images, suggesting the efficiency of the TransMCD method for cloud detection in multi-sensor images.
- 14 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-18
Transferring Deep Models for Cloud Detection in Multisensor Images via Weakly Supervised Learning
Recently, deep learning has been widely used for cloud detection in satellite images. However, due to radiometric and spatial resolution differences in images from different sensors and time-consuming process of manually labeling cloud detection datasets, it is difficult to effectively generalize deep learning models for cloud detection in multi-sensor images. This paper propose a weakly supervised learning method for transferring deep models for cloud detection in multi-sensor images (TransMCD), which leverages the generalization of deep models and the spectral features of clouds to construct pseudo-label dataset to improve the generalization of models. A deep model is first pre-trained using a well-annotated cloud detection dataset, which is used to obtain a rough cloud mask of unlabeled target image. The rough mask can be used to determine the spectral threshold adaptively for cloud segmentation of target image. Block-level pseudo-labels with high confidence in target image are selected using the rough mask and spectral mask. Unsupervised segmentation technique is utilized to construct a high-quality pixel-level pseudo-label dataset. Finally, the pseudo-label dataset is utilized as supervised information for transferring the pre-trained model to target image. The TransMCD method was validated by transferring model trained on 16-m Gaofen-1 wide field of view images to 8-m Gaofen-1, 4-m Gaofen-2 and 10-m Sentinel-2 images. The F1-score of the transferred models on target images achieves improvements of 1.23–9.63% over the pre-trained models, which is comparable to the fully-supervised models trained with well-annotated target images, suggesting the efficiency of the TransMCD method for cloud detection in multi-sensor images.