Liu, Shengjie Kris
This webpage is no longer updated. Please visit skrisliu.com for latest news.
I am a PhD student at University of Southern California.
Prior to joining USC, I was a research assistant in light pollution at The University of Hong Kong.
My research interests include remote sensing, machine learning, and environment & sustainability.
I develop advanced AI methods to process Earth Observation data (AI4EO) for sustainability research.
Email  / 
CV  / 
Github  / 
Google Scholar
|
Canarias 2021
|
|
Estimating PM2.5 and PM10 on Zhuhai-1 Hyperspectral Imagery
Shengjie Liu, Qian Shi
Proceedings of IEEE International Geoscience and Remote Sensing Symposium, 2022
preprint
Estimated PM2.5 and PM10 simultaneously on the newly-launched Zhuhai-1 hyperspectral imagery to distinguish off-road and near-road air pollution
|
|
A Multinational Study of Night Sky Brightness Patterns: Preliminary Results from the Globe at Night – Sky Brightness Monitoring Network (GaN-MN): the Study of Cloud
Amplification on NSB
So, C.W., Chang, N.Y.J., Liu, S., Canas, L., Walker, C.E., Cheung, S.L., and Pun, C.S.J.
7th International Conference on Artificial Light at Night (ALAN), 2021
abstract /
ask for video presentation
Analyzed the cloud amplification effect on NSB based on 30+ stations of the GaN-MN
|
|
The relationship between night sky brightness and remote sensing data: Preliminary result from Luojia-1 and the International Space Station
Shengjie Liu, Chu Wing SO, Janet Chang, Chun Shing Jason Pun
7th International Conference on Artificial Light at Night (ALAN), 2021
abstract /
ask for video presentation
Examined the relationship between night sky brightness (NSB) and two medium-resolution remote sensing data (Luojia-1 and ISS) in Hong Kong
|
|
Analyzing long-term artificial light at night using VIIRS monthly product with land use data: Preliminary result of Hong Kong
Shengjie Liu, Chu Wing SO, Chun Shing Jason Pun
Proceedings of IEEE International Geoscience and Remote Sensing Symposium, 2021
preprint /
bibtex
Analyzed the long-term artificial light at night (ALAN) using VIIRS monthly product in Hong Kong between 2012 and 2019
|
|
Multi-label local climate zone mapping as scene classification using very high resolution imagery: Preliminary result of Hong Kong
Shengjie Liu, Qian Shi
Proceedings of IEEE International Geoscience and Remote Sensing Symposium, 2021
preprint /
bibtex /
LCZ Map of Hong Kong
Generated multi-label local climate zone map in Hong Kong using very high-resolution imagery
|
|
Few-shot Hyperspectral Image Classification with Unknown Classes Using Multitask Deep
Learning
Shengjie Liu,
Qian Shi,
Liangpei Zhang
IEEE Transactions on Geoscience and Remote Sensing, 2020
project page /
code /
preprint
/
published version /
bibtex
Identify unknown classes in hyperspectral land cover mapping in the open world using multitask
deep learning. Empower the deep learning models with the ability to reject unseen categories of land
cover.
|
|
Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image
Classification
Shengjie Liu, Haowen Luo, Qian Shi
IEEE Geoscience and Remote Sensing Letters, 2020
bibtex
Enhanced multiview active learning based on the disagreement of local minima of convolutional
neural
networks in a snapshot ensemble fashion. Improved the stability of neural networks for PolSAR image
classification.
|
|
Local climate zone mapping as remote sensing scene classification using deep learning: A
case study of metropolitan China
Shengjie Liu,
Qian Shi
ISPRS Journal of Photogrammetry and Remote Sensing, 2020
project page /
paper /
preprint /
New LCZ Map /
bibtex
Using scene classification strategy with deep neural network to generate local climate zone maps in
fifteen cities in China.
|
|
Multitask Deep Learning With Spectral Knowledge for Hyperspectral Image Classification
Shengjie Liu, Qian Shi
IEEE Geoscience and Remote Sensing Letters, 2020
bibtex
Enhanced hyperspectral image classification with spectral knowledge from other images using
multitask deep learning. * The figure presented is from a working paper based on this method.
|
|
Integration of Convolutional Neural Networks and Object-Based Post-Classification
Refinement for Land Use and Land Cover Mapping with Optical and SAR Data
Shengjie Liu, Zhixin
Qi, Xia Li, Anthony Gar-On Yeh
Remote Sensing, 2019
paper /
bibtex /
data
Proposed a novel method to empower CNNs to produce object-based classification maps, named
“Object-Based Post-classification Refinement” (OBPR). Also analyzed the effect of fusing Sentinel
optical and PolSAR data in urban land cover mapping.
|
|
Wide Contextual Residual Network with Active Learning for Remote Sensing Image
Classification
Shengjie Liu, Haowen Luo, Ying Tu, Zhi He, Jun Li
Proceedings of IEEE International Geoscience and Remote Sensing Symposium, 2018
paper /
bibtex
Proposed a light-weight neural network named Wide Contextual Residual Network (WCRN), and combined
it with active learning to reduce the need of training samples for remote sensing image
classification.
|
|