Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 68 tok/s
Gemini 2.5 Pro 56 tok/s Pro
GPT-5 Medium 34 tok/s Pro
GPT-5 High 31 tok/s Pro
GPT-4o 84 tok/s Pro
Kimi K2 184 tok/s Pro
GPT OSS 120B 441 tok/s Pro
Claude Sonnet 4.5 33 tok/s Pro
2000 character limit reached

Tracking the industrial growth of modern China with high-resolution panchromatic imagery: A sequential convolutional approach (2301.09620v3)

Published 23 Jan 2023 in cs.CV, cs.CY, and cs.LG

Abstract: Due to insufficient or difficult to obtain data on development in inaccessible regions, remote sensing data is an important tool for interested stakeholders to collect information on economic growth. To date, no studies have utilized deep learning to estimate industrial growth at the level of individual sites. In this study, we harness high-resolution panchromatic imagery to estimate development over time at 419 industrial sites in the People's Republic of China using a multi-tier computer vision framework. We present two methods for approximating development: (1) structural area coverage estimated through a Mask R-CNN segmentation algorithm, and (2) imputing development directly with visible & infrared radiance from the Visible Infrared Imaging Radiometer Suite (VIIRS). Labels generated from these methods are comparatively evaluated and tested. On a dataset of 2,078 50 cm resolution images spanning 19 years, the results indicate that two dimensions of industrial development can be estimated using high-resolution daytime imagery, including (a) the total square meters of industrial development (average error of 0.021 $\textrm{km}2$), and (b) the radiance of lights (average error of 9.8 $\mathrm{\frac{nW}{cm{2}sr}}$). Trend analysis of the techniques reveal estimates from a Mask R-CNN-labeled CNN-LSTM track ground truth measurements most closely. The Mask R-CNN estimates positive growth at every site from the oldest image to the most recent, with an average change of 4,084 $\textrm{m}2$.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Mapping missing population in rural india: A deep learning approach with satellite imagery. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, AIES ’19, page 353–359, New York, NY, USA, 2019. Association for Computing Machinery.
  2. Using publicly available satellite imagery and deep learning to understand economic well-being in africa. Nature Communications, 11, 05 2020.
  3. Combining satellite imagery and machine learning to predict poverty. Science, 353(6301):790–794, 2016.
  4. A convolutional neural network approach to predict non-permissive environments from moderate-resolution imagery. Transactions in GIS, 25(2):674–691, 2021.
  5. Deep learning fusion of satellite and social information to estimate human migratory flows. Transactions in GIS, 2022.
  6. Using satellite data and deep learning to estimate educational outcomes in data-sparse environments. Remote Sensing Letters, 13(1):87–97, 2022.
  7. Predicting road quality using high resolution satellite imagery: A transfer learning approach. PLOS ONE, 16(7):1–18, 07 2021.
  8. Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(7):2217–2226, 2019.
  9. Seth M. Goodman. Filling in the Gaps: Applications of Deep Learning, Satellite Imagery, and High Performance Computing for the Estimation and Distribution of Geospatial Data. PhD thesis, William & Mary, 2021. Copyright - Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works; Last updated - 2021-05-11.
  10. pyshore: A deep learning toolkit for shoreline structure mapping with high-resolution orthographic imagery and convolutional neural networks. Computers & Geosciences, 171:105296, 2023.
  11. Ethan Brewer. Deep learning from space: Methods & applications in high-resolution satellite imagery analysis. William & Mary Dissertations and Theses, 2022.
  12. Using satellite imagery to understand and promote sustainable development. Science, 371(6535):eabe8628, 2021.
  13. Land use change and economic growth in urban china: A structural equation analysis. Urban Studies, 51(13):2880–2898, 2014.
  14. Natural resource sector fdi, government policy, and economic growth: Quasi-experimental evidence from liberia. World Development, 107:151–162, 2018.
  15. Comparison of support vector machine and maximum likelihood classification technique using satellite imagery. International Journal of Remote Sensing and GIS, 1:116–123, 01 2012.
  16. An analysis of land use pattern in the industrial development city using high resolution satellite imagery. Journal of Geographical Sciences, 21:79–88, 02 2011.
  17. Economy estimation of mainland china at county-level based on landsat images and multi-task deep learning framework. Photogrammetric Engineering & Remote Sensing, 86(2):99–105, 2020.
  18. The multi-temporal urban development spacenet dataset. CoRR, abs/2102.04420, 2021.
  19. Vehicle detection in satellite images by hybrid deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 11(10):1797–1801, 2014.
  20. Susceptibility & defense of satellite image-trained convolutional networks to backdoor attacks. Information Sciences, 603:244–261, 2022.
  21. Recent progress in object detection in satellite imagery: A review. In Sagaya Aurelia, Somashekhar S. Hiremath, Karthikeyan Subramanian, and Saroj Kr. Biswas, editors, Sustainable Advanced Computing, pages 209–218, Singapore, 2022. Springer Singapore.
  22. U-net: Convolutional networks for biomedical image segmentation. CoRR, abs/1505.04597, 2015.
  23. Mask R-CNN. CoRR, abs/1703.06870, 2017.
  24. Deep learning approach for building detection in satellite multispectral imagery. In 2018 International Conference on Intelligent Systems (IS), pages 461–465, 2018.
  25. A deep learning approach to an enhanced building footprint and road detection in high-resolution satellite imagery. Remote Sensing, 13(16), 2021.
  26. Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, abs/1506.01497, 2015.
  27. Fully convolutional networks for semantic segmentation. CoRR, abs/1411.4038, 2014.
  28. Building extraction from satellite images using mask r-cnn with building boundary regularization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2018.
  29. Large-scale building extraction in very high-resolution aerial imagery using mask r-cnn. In 2019 Joint Urban Remote Sensing Event (JURSE), pages 1–4, 2019.
  30. Long short-term memory. Neural Comput., 9(8):1735–1780, nov 1997.
  31. A deep multitask learning framework coupling semantic segmentation and fully convolutional lstm networks for urban change detection. IEEE Transactions on Geoscience and Remote Sensing, 59(9):7651–7668, 2021.
  32. Multitemporal relearning with convolutional lstm models for land use classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14:3251–3265, 2021.
  33. GeoNames Team. Geonames. https://www.geonames.org/, 2022. Accessed: September 2021.
  34. Maxar Technologies Inc. Digitalglobe. http://evwhs.digitalglobe.com/myDigitalGlobe, 2022. Accessed: September-December 2021.
  35. geoboundaries: A global database of political administrative boundaries. PLOS ONE, 15(4):1–9, 04 2020.
  36. MathWorks. rgb2ntsc - convert rgb color values to ntsc color space. https://www.mathworks.com/help/images/ref/rgb2ntsc.html, 2022. Accessed: June 2022.
  37. Microsoft COCO: common objects in context. CoRR, abs/1405.0312, 2014.
  38. SpaceNet. Spacenet aoi 4 – shanghai. https://spacenet.ai/shanghai/, 2022. Accessed: May 2022.
  39. Mustafa Aktas. Building-detection-maskrcnn. https://github.com/Mstfakts/Building-Detection-MaskRCNN/blob/master/SpaceNet_train.py, 2021. Accessed: February 2022.
  40. Torchgeo: deep learning with geospatial data. CoRR, abs/2111.08872, 2021.
  41. Spatial analysis of global urban extent from dmsp-ols night lights. Remote Sensing of Environment, 96(3):277–291, 2005.
  42. An investigation on deep learning approaches to combining nighttime and daytime satellite imagery for poverty prediction. IEEE Geoscience and Remote Sensing Letters, 18(9):1545–1549, 2021.
  43. Earth Observation Group (EOG) at Colorado School of Mines. Visible and infrared imaging suite (viirs). https://eogdata.mines.edu/products/vnl/, 2022. Accessed: June 2022.
  44. Made in china 2025 and shanghai’s zhangjiang high-tech industrial park. https://www.tearline.mil/public_page/tech-park-shanghai/#article_authors, 2022. Accessed: July 2022.
  45. Object detection and instance segmentation in remote sensing imagery based on precise mask r-cnn. In IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, pages 1454–1457, 2019.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 1 post and received 0 likes.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up to View