Extracting built-up land area of airports in China using Sentinel-2 imagery through deep learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In China, airports have a profound impact on people’s lives, and understanding their dimensions has great significance for research and development. However, few existing airport databases contain such details, which can be reflected indirectly by the built-up land in the airport. In this study, a deep learning-based method was used for extraction of built-up land of airports in China using Sentinel-2 imagery and for further estimating their area. Here, a benchmark generation method is introduced by fusing two reference maps and cropping images into patches. Following this, a series of experiments were conducted to evaluate the network architectures and select the positive impact bands in Sentinel-2 imagery. A well-trained model was used to extract the built-up land for China airports, and the relationship between China airports’ built-up land and the carrying capacity of air transportation was further analysed. Results show that ResUNet-a outperformed U-Net, ResUNet, and SegNet, and the B2, B4, B6, B11, and B12 bands of Sentinel-2 had a positive impact on built-up land extraction. A well-trained model with an overall accuracy of 0.9423 and an F1 score of 0.9041 and 434 China airports’ built-up land was extracted. The four most developed airports are located in Beijing, Shanghai, and Guangzhou, which matches China’s political and economic development. The area of built-up land influenced the passenger throughput and aircraft movements. The total area influenced the cargo throughput, and we found a certain correlation among the built-up land, carrying capacity, and nighttime light.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it