Related Experiment Video
Updated: Jan 25, 2026

Measuring Light-Switching Behavior Using an Occupancy and Light Data Logger
Published on: January 16, 2020
An Extended VIIRS-like Artificial Nighttime Light Data Reconstruction (1986-2024)
Yihe Tian1, Kwan Man Cheng2, Zhengbo Zhang3
1Department of Earth System Science, Ministry of Education, Ecological Field Station for East Asian Migratory Birds, Tsinghua University, Beijing, 100084, China.
A new Extended VIIRS-like Artificial Nighttime Light (EVAL) dataset provides annual nighttime light data for China from 1986-2024. This advanced dataset overcomes limitations of previous products, offering improved accuracy for human activity analysis.
Area of Science:
- Remote Sensing
- Earth Observation
- Geospatial Analysis
Background:
- Night-time light (NTL) remote sensing quantifies human activities.
- Existing NPP-VIIRS data (post-2012) limits long-term studies.
- Current extended NTL products underestimate intensity and omit details.
Purpose of the Study:
- Introduce the Extended VIIRS-like Artificial Nighttime Light (EVAL) dataset.
- Provide annual NTL data for China (1986-2024).
- Overcome limitations of existing NTL datasets.
Main Methods:
- Developed a novel two-stage deep learning model.
- Model estimates initial NTL and refines details using impervious surface data.
- Generated annual NTL data for China from 1986 to 2024.
Main Results:
- EVAL dataset shows superior performance compared to state-of-the-art products.
- Demonstrates enhanced temporal consistency.
- Exhibits a stronger correlation with socioeconomic indicators.
Conclusions:
- The EVAL dataset offers a significant advancement for long-term NTL research in China.
- It provides more accurate and detailed insights into human activity.
- Facilitates improved socioeconomic and environmental studies.
More Related Videos
Related Concept Videos
Gravitational Potential Energy for Extended Objects
Natural and Artificial Concepts
Photoreceptors and Plant Responses to Light
How Data are Classified: Numerical Data
Quantitative data may be either discrete or continuous. All quantitative data that take on only specific numerical...
How Data are Classified: Categorical Data
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
Light Acquisition

