269 citations · 372 across the 9 of their papers we have counts for
9 papers
Spectroscopic study of the light-polluted night sky in Hong Kong
Chu Wing So, Chun Shing Jason Pun, Shengjie Liu
Spectroscopic study of the night sky has been a common way to assess the impacts of artificial light at night at remote astronomical observatories. However, the spectroscopic prope…
Uncertainty-Aware Hourly Air Temperature Mapping at 2 km Resolution via Physics-Guided Deep Learning
Shengjie Kris Liu, Siqin Wang, Lu Zhang
Near-surface air temperature is a key physical property of the Earth's surface. Although weather stations offer continuous monitoring and satellites provide broad spatial coverage,…
Resolution Revolution: A Physics-Guided Deep Learning Framework for Spatiotemporal Temperature Reconstruction
Shengjie Liu, Lu Zhang, Siqin Wang
Central to Earth observation is the trade-off between spatial and temporal resolution. For temperature, this is especially critical because real-world applications require high spa…
Natural experiments from Earth Hour reveal urban night sky being drastically lit up by few decorative buildings
Chu Wing So, Chun Shing Jason Pun, Shengjie Liu +4
Light pollution, a typically underrecognized environmental issue, has gained attention in recent years. While controlling light pollution requires sustained efforts, Earth Hour off…
Daily Land Surface Temperature Reconstruction in Landsat Cross-Track Areas Using Deep Ensemble Learning With Uncertainty Quantification
Shengjie Liu, Siqin Wang, Lu Zhang
Many real-world applications rely on land surface temperature (LST) data at high spatiotemporal resolution. In complex urban areas, LST exhibits significant variations, fluctuating…
Deep Feature Gaussian Processes for Single-Scene Aerosol Optical Depth Reconstruction
Shengjie Liu, Lu Zhang
Remote sensing data provide a low-cost solution for large-scale monitoring of air pollution via the retrieval of aerosol optical depth (AOD), but is often limited by cloud contamin…
Few-Shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning
Shengjie Liu, Qian Shi, Liangpei Zhang
Current hyperspectral image classification assumes that a predefined classification system is closed and complete, and there are no unknown or novel classes in the unseen data. How…
Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification
Sheng-Jie Liu, Haowen Luo, Qian Shi
Although deep learning has achieved great success in image classification tasks, its performance is subject to the quantity and quality of training samples. For classification of p…
Multitask Deep Learning with Spectral Knowledge for Hyperspectral Image Classification
Shengjie Liu, Qian Shi
In this letter, we propose a multitask deep learning method for classification of multiple hyperspectral data in a single training. Deep learning models have achieved promising res…