{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T08:36:13Z","timestamp":1773390973208,"version":"3.50.1"},"reference-count":50,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T00:00:00Z","timestamp":1621814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["17XNLG09"],"award-info":[{"award-number":["17XNLG09"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The official method of collecting county-level GDP values in the Chinese Mainland relies mainly on administrative reporting data and suffers from high costs of time, money, and human labor. To date, a series of studies have been conducted to generate fine-grained maps of socioeconomic indicators from the easily accessed remote sensing data and achieved satisfactory results. This paper proposes a transfer learning framework that regards nightlight intensities as a proxy of economic activity degrees to estimate county-level GDP around the Chinese Mainland. In the framework, paired daytime satellite images and nightlight intensity levels were applied to train a VGG-16 architecture, and the output features at a specific layer, after dimensional reduction and statistics calculation, were fed into a simple regressor to estimate county-level GDP. We trained the model with data of 2017 and utilized it to predict county-level GDP of 2018, achieving an R-squared of 0.71. Furthermore, the results of gradient visualization confirmed the validity of the proposed framework qualitatively. To the best of our knowledge, this is the first time that county-level GDP values around the Chinese Mainland have been estimated from both daytime and nighttime remote sensing data relying on attention-augmented CNN. We believe that our work will shed light on both the evolution of fine-grained socioeconomic surveys and the application of remote sensing data in economic research.<\/jats:p>","DOI":"10.3390\/rs13112067","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T23:35:05Z","timestamp":1621899305000},"page":"2067","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Nightlight as a Proxy of Economic Indicators: Fine-Grained GDP Inference around Chinese Mainland via Attention-Augmented CNN from Daytime Satellite Imagery"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0839-5460","authenticated-orcid":false,"given":"Haoyu","family":"Liu","sequence":"first","affiliation":[{"name":"Center for Applied Statistics, School of Statistics, Renmin University of China, Beijing 100872, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2782-4248","authenticated-orcid":false,"given":"Xianwen","family":"He","sequence":"additional","affiliation":[{"name":"Center for Applied Statistics, School of Statistics, Renmin University of China, Beijing 100872, China"}]},{"given":"Yanbing","family":"Bai","sequence":"additional","affiliation":[{"name":"Center for Applied Statistics, School of Statistics, Renmin University of China, Beijing 100872, China"}]},{"given":"Xing","family":"Liu","sequence":"additional","affiliation":[{"name":"Graduate School of Information Sciences, Tohoku University, Sendai 980-8579, Japan"}]},{"given":"Yilin","family":"Wu","sequence":"additional","affiliation":[{"name":"Center for Applied Statistics, School of Statistics, Renmin University of China, Beijing 100872, China"}]},{"given":"Yanyun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Center for Applied Statistics, School of Statistics, Renmin University of China, Beijing 100872, China"}]},{"given":"Hanfang","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Applied Statistics, School of Statistics, Renmin University of China, Beijing 100872, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,24]]},"reference":[{"key":"ref_1","unstructured":"Bureau, C.N.S. (2020, October 14). Data Release and Update (10), Available online: http:\/\/www.stats.gov.cn\/tjzs\/cjwtjd\/201407\/t20140714_580886.html."},{"key":"ref_2","unstructured":"Bureau, C.N.S. (2020, October 14). National Economic Accounting (17), Available online: http:\/\/www.stats.gov.cn\/tjzs\/cjwtjd\/201308\/t20130829_74319.html."},{"key":"ref_3","first-page":"5","article-title":"The overall analysis of current Chinese GDP accounting system","volume":"V34","author":"Gao","year":"2014","journal-title":"Econ. Theory Econ. Manag."},{"key":"ref_4","first-page":"463","article-title":"Considerations on county-level GDP accounting","volume":"10","author":"Liao","year":"2014","journal-title":"Mod. Econ. Inf."},{"key":"ref_5","first-page":"6","article-title":"County-level GDP accounting work","volume":"09","author":"Zhang","year":"2015","journal-title":"Stat. Manag."},{"key":"ref_6","first-page":"428","article-title":"Lightweight and Robust Representation of Economic Scales from Satellite Imagery","volume":"34","author":"Han","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1579\/0044-7447-29.3.157","article-title":"Night-time Imagery as a Tool for Global Mapping of Socioeconomic Parameters and Greenhouse Gas Emissions","volume":"29","author":"Doll","year":"2000","journal-title":"Ambio A J. Hum. Environ."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.ecolecon.2005.03.007","article-title":"Mapping regional economic activity from night-time light satellite imagery","volume":"57","author":"Doll","year":"2006","journal-title":"Ecol. Econ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1080\/15481603.2015.1072400","article-title":"Analysis of urban growth and estimating population density using satellite images of nighttime lights and land-use and population data","volume":"52","author":"Bagan","year":"2015","journal-title":"GIScience Remote Sens."},{"key":"ref_10","first-page":"218","article-title":"Night Lights and Economic Activity in India: A study using DMSP-OLS night time images","volume":"32","author":"Laveesh","year":"2011","journal-title":"Proc. Asia-Pac. Adv. Netw."},{"key":"ref_11","first-page":"192","article-title":"Assessing Income Distribution at the District Level for India Using Nighttime Satellite Imagery","volume":"32","author":"Chaturvedi","year":"2011","journal-title":"Proc. Asia Pac. Adv. Netw."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1016\/j.asr.2012.01.025","article-title":"Poverty assessment using DMSP\/OLS night-time light satellite imagery at a provincial scale in China","volume":"49","author":"Wen","year":"2012","journal-title":"Adv. Space Res."},{"key":"ref_13","first-page":"89","article-title":"DMSP-OLS and NPP-VIIRS night lighting data measurement statistical index capability assessment\u2014Take the Beijing-Tianjin-Hebei area county GDP, population and energy consumption as an example","volume":"09","author":"Li","year":"2020","journal-title":"Mapp. Advis."},{"key":"ref_14","first-page":"62","article-title":"Why VIIRS data are superior to DMSP for mapping nighttime lights","volume":"35","author":"Elvidge","year":"2013","journal-title":"Proc. Asia Pac. Adv. Netw."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Engstrom, R., Hersh, J., and Newhouse, D. (2017). Poverty from Space: Using High-Resolution Satellite Imagery for Estimating Economic Well-Being, The World Bank. Available online: https:\/\/elibrary.worldbank.org\/doi\/abs\/10.1596\/1813-9450-8284.","DOI":"10.1596\/1813-9450-8284"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1080\/17538947.2016.1255789","article-title":"Estimating geographic concentrations of quaternary industries in Europe using Artificial Light-At-Night (ALAN) data","volume":"10","author":"Rybnikova","year":"2017","journal-title":"Int. J. Digit. Earth"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xie, M., Jean, N., Burke, M., Lobell, D., and Ermon, S. (2016, January 12\u201317). Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v30i1.9906"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1126\/science.aaf7894","article-title":"Combining satellite imagery and machine learning to predict poverty","volume":"353","author":"Jean","year":"2016","journal-title":"Science"},{"key":"ref_19","first-page":"955","article-title":"Night Lights in Economics: Sources and Uses","volume":"34","author":"Gibson","year":"2020","journal-title":"LICOS Discuss. Pap."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/S0924-2716(01)00040-5","article-title":"Night-time lights of the world: 1994\u20131995","volume":"56","author":"Elvidge","year":"2001","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_21","first-page":"71","article-title":"A study on the pattern of time and space economic development in Shandong Province based on night light data","volume":"09","author":"Ding","year":"2019","journal-title":"Mapp. Spat. Geogr. Inf."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.rse.2018.03.018","article-title":"Deblurring DMSP nighttime lights: A new method using Gaussian filters and frequencies of illumination","volume":"210","author":"Abrahams","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Gibson, J., Olivia, S., Boe-Gibson, G., and Li, C. (2021). Which night lights data should we use in economics, and where?. J. Dev. Econ., 149.","DOI":"10.1016\/j.jdeveco.2020.102602"},{"key":"ref_24","unstructured":"Ran, G., Heilmann, K., and Vaizman, Y. (2019). Can Medium-Resolution Satellite Imagery Measure Economic Activity at Small Geographies? Evidence from Landsat In Vietnam, The World Bank."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4937","DOI":"10.3390\/rs70404937","article-title":"A Test of the New VIIRS Lights Data Set: Population and Economic Output in Africa","volume":"7","author":"Chen","year":"2015","journal-title":"Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, X., and Nordhaus, W.D. (2019). VIIRS Nighttime Lights in the Estimation of Cross-Sectional and Time-Series GDP. Remote Sens., 11.","DOI":"10.3390\/rs11091057"},{"key":"ref_27","first-page":"1476","article-title":"Night lighting data predict social and economic activity at different scales","volume":"40","author":"Chen","year":"2020","journal-title":"Geography"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.3390\/rs6021705","article-title":"Evaluating the Ability of NPP-VIIRS Nighttime Light Data to Estimate the Gross Domestic Product and the Electric Power Consumption of China at Multiple Scales: A Comparison with DMSP-OLS Data","volume":"6","author":"Shi","year":"2014","journal-title":"Remote Sens."},{"key":"ref_29","first-page":"89","article-title":"Based on night light data, the level of county-level urbanization in Anhui Province is estimated","volume":"22","author":"Sun","year":"2020","journal-title":"J. Earth Inf. Sci."},{"key":"ref_30","first-page":"41","article-title":"The fine simulation of regional economic spatial pattern supported by night light remote sensing data is an example of Henan Province","volume":"04","author":"Li","year":"2020","journal-title":"Reg. Res. Dev."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Vogel, K.B., Goldblatt, R., Hanson, G.H., and Khandelwal, A.K. (2018). Detecting Urban Markets with Satellite Imagery: An Application to India, National Bureau of Economic Research. NBER Working Papers.","DOI":"10.3386\/w24796"},{"key":"ref_32","unstructured":"Abitbol, J.L., and Karsai, M. (2020). Socioeconomic Correlations of Urban Patterns Inferred from Aerial Images: Interpreting Activation Maps of Convolutional Neural Networks. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Robinson, C., Hohman, F., and Dilkina, B. (2017, January 7). A Deep Learning Approach for Population Estimation from Satellite Imagery. Proceedings of the 1st ACM SIGSPATIAL Workshop, Redondo Beach, CA, USA.","DOI":"10.1145\/3149858.3149863"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Doupe, P., Bruzelius, E., Faghmous, J., and Ruchman, S.G. (2016, January 18\u201320). Equitable Development through Deep Learning: The Case of Sub-National Population Density Estimation. Proceedings of the 7th Annual Symposium on Computing for Development (ACM DEV \u201916), Nairobi, Kenya.","DOI":"10.1145\/3001913.3001921"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hu, W., Patel, J.H., Robert, Z.A., Novosad, P., Asher, S., Tang, Z., Burke, M., Lobell, D., and Ermon, S. (2019, January 27\u201328). Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery. Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, Honolulu, HI, USA.","DOI":"10.1145\/3306618.3314263"},{"key":"ref_36","unstructured":"Babenko, B., Hersh, J., Newhouse, D., Ramakrishnan, A., and Swartz, T. (2017). Poverty Mapping Using Convolutional Neural Networks Trained on High and Medium Resolution Satellite Images, With an Application in Mexico. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Han, S., Ahn, D., Park, S., Yang, J., Lee, S., Kim, J., Yang, H., Park, S., and Cha, M. (2020, January 23\u201327). Learning to score economic development from satellite imagery. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Virtual Event, CA, USA.","DOI":"10.1145\/3394486.3403347"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"(2015). ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis., 115, 211\u2013252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref_39","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_40","unstructured":"Ni, Y., Li, X., Ye, Y., Li, Y., and Chu, D. (2020). An Investigation on Deep Learning Approaches to Combining Nighttime and Daytime Satellite Imagery for Poverty Prediction. IEEE Geosci. Remote Sens. Lett., 1\u20135."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Laurens, V., and Weinberger, K.Q. (2016). Densely Connected Convolutional Networks, IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Jian, S. (2016). Identity Mappings in Deep Residual Networks, Springer.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Head, A., Manguin, M., Tran, N., and Blumenstock, J.E. (2017, January 16\u201319). Can Human Development Be Measured with Satellite Imagery?. Proceedings of the Ninth International Conference on Information and Communication Technologies and Development (ICTD \u201917), Lahore, Pakistan.","DOI":"10.1145\/3136560.3136576"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2583","DOI":"10.1038\/s41467-020-16185-w","article-title":"Using publicly available satellite imagery and deep learning to understand economic well-being in Africa","volume":"11","author":"Yeh","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1109\/34.865189","article-title":"Assessing a mixture model for clustering with the integrated completed likelihood","volume":"22","author":"Biernacki","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_46","unstructured":"Pypi (2020, November 11). GeoPandas. Available online: https:\/\/pypi.org\/project\/geopandas\/."},{"key":"ref_47","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","volume":"2","author":"Abdi","year":"2010","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"ref_49","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv."},{"key":"ref_50","unstructured":"Arriaga, O., Valdenegro-Toro, M., and Pl\u00f6ger, P. (2017). Real-time convolutional neural networks for emotion and gender classification. arXiv."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/11\/2067\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:07:08Z","timestamp":1760162828000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/11\/2067"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,24]]},"references-count":50,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["rs13112067"],"URL":"https:\/\/doi.org\/10.3390\/rs13112067","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,24]]}}}