From earth observation to human observation: Geocomputation for social science

doi:10.1007/s11442-020-1725-8

Abstract

Abstract:

It is possible to obtain vast amounts of spatiotemporal data related to human activities to support the study of human behavior and social evolution. In this context, geography, with the human-nature relationship as its core, is undergoing a transition from strictly earth observations to the observation of human activities. Geocomputation for social science is one manifestation thereof. Geocomputation for social science is an interdisciplinary approach combining remote sensing techniques, social science, and big data computation. Driven by the availability of spatially and temporally expansive big data, geocomputation for social science uses spatiotemporal statistical analyses to detect and analyze the interactions between human behavior, the natural environment, and social activities; Remote sensing (RS) observations are used as primary data. Geocomputation for social science can be used to investigate major social issues and to assess the impact of major natural and societal events, and will surely be an area of focused development in geography in the near future. We briefly review the background of geocomputation in the social sciences, discuss its definition and disciplinary characteristics, and highlight the main research foci. Several key technologies and applications are also illustrated with relevant case studies of the Syrian Civil War, typhoon transits, and traffic patterns.

Key words: geocomputation for social science, nighttime light remote sensing, social network, traffic patterns

LI Deren, GUO Wei, CHANG Xiaomeng, LI Xi. From earth observation to human observation: Geocomputation for social science[J].Journal of Geographical Sciences, 2020, 30(2): 233-250.

Figures/Tables 8

Figure 1

Figure 2

Table 1

Research foci of geocomputation in social science"

Research topics	Data type	Main results and conclusions
Assessment of social and economic development	Nighttime light image	Investigation on the spatial patterns of economic recessions (Li et al., 2014)
		Identification and evolution analysis of urban agglomeration and urban system (Yu et al., 2014)
		Analyses of the impact of urbanization on ecological environment (He et al., 2015)
	Mobile phone metadata	Socioeconomic status and socioeconomic characteristic of people were inferred (Blumenstock et al., 2015)
	Remote sensing image	Population consumption and asset changes were predicted (Jean et al., 2016)
	Remote sensing image and online rental information	Poverty measurement of urban internal space (Yuan et al., 2018)
	Street view image	The demographics and socioeconomic characteristics were estimated and voting trends in presidential elections were predicted (Fei-Fei L, 2017 )
	Street view image	Quantifying the street-visible greenery and estimating the economic benefits that the neighbor visible greenery would have on residential developments (Zhang and Dong, 2018)
	High-speed railway and airline networks	The influence of high-speed railway and air networks on urban system was analyzed (Yang et al., 2018)
Causal analysis of major social events	Nighttime light image	The impact of war was assessed (Witmer et al., 2011)
		Monitoring humanitarian crises (Li et al., 2011)
		The correlation between night light change and disaster loss in earthquake-stricken areas was analyzed (Zhang et al., 2018)
		Assessing the impact of three types of natural disasters: earthquakes, floods, and storms (Zhao et al., 2018)
Crowd activity in large cities	Mobile phone data	The taxi demand characteristics and potential land use patterns between two places were revealed (Kang et al., 2013)
		Human mobility was speculated to improve traffic planning and urban planning management (Zhu et al., 2015)
		The disparities in park access were explored (Xiao et al., 2019)
	Nighttime light image	The house vacancy rate was estimated. (Chen et al., 2015)
	Nighttime light image and cancer registry data	There is a significant correlation between the intensity of light at night and the incidence of breast cancer. (Bauer et al., 2013)
	Nighttime light image and taxi trajectories data	The nighttime light and taxi trajectory data were integrated to estimate population at micro levels. (Yu et al., 2019)
Research topics	Data type	Main results and conclusions
Crowd activity in large cities	Taxi trajectories data	The demand-supply of healthcare services was analyzed (Chen et al., 2018)
	Sharing bikes’ trajectories	Illegal parking behaviors were detected to ease traffic congestion (He et al., 2018)
	Transit smart card data	To discuss the influence of housing burden pressure on housing spatial distribution pattern (Li et al., 2018)
	Social media data	The development trend and spatial distribution law of emergency events are mined to provide decision-making basis for disaster emergency response (Wang et al., 2016)
	Street view image	Image detection methods are used to determine the presence of pedestrian and extract pedestrian count data (Li et al., 2015)
	Street view image	Examining associations between exposure to green and blue spaces as well as geriatric depression (Helbich et al., 2019)
	Crime data	It reveals the spatial-temporal characteristics and influences of crimes, and predicts of space crimes (Liu et al., 2018)
Analysis of human activity in virtual space	Social media data	It extracts the public interest and attention to the event and predicts the reported disease level (Signorini et al., 2011)
		It reveals the users who made political comments onsocial networking sites were mostly urban males (Barbera and Rivero., 2014)
		The traveler’s family and workplace were estimated and the characteristics of human travel were depicted (Chang et al., 2017)

Table 1

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

References 46

[1]	Bao J, He T, Ruan S. et al., 2017. Planning bike lanes based on sharing-bikes’ trajectories. In: KDD ’17 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 1377-1386.
[2]	Barbera P, Rivero G , 2014. Understanding the political representativeness of Twitter users. Social Science Computer Review, 33(6):712-729.
[3]	Bauer S E, Wagner S E, Burch J et al., 2013. A case-referent study: Light at night and breast cancer risk in Georgia. International Journal of Health Geographics, 12:23. doi: 10.1186/1476-072X-12-23.
[4]	Blumenstock J, Cadamuro G, On R , 2015. Predicting poverty and wealth from mobile phone metadata. Science, 350(6264):1073-1076.
[5]	Chen Y M, Wang B B, Liu X P et al., 2018. Mapping the spatial disparities in urban health care services using taxi trajectories data. Transactions in GIS, 22(2):602-615.
[6]	Chen, Z Q, Yu B L, Hu Y J et al., 2015. Estimating house vacancy rate in metropolitan areas using NPP-VIIRS nighttime light composite data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(5):2188-2197.
[7]	China Central Television, 2017. More than 60 drug-related vehicles were seized and 15 people were forcibly detoxified in Wuhan, Hubei province. Retrieved August 26, 2017, from .
[8]	Diao M, Zhu Y, Ferreira Jr J et al., 2015. Inferring individual daily activities from mobile phone traces: A Boston example. Environment and Planning B-Planning & Design, 43(5):920-940.
[9]	Elvidge C D, Baugh K E, Kihn E A et al., 1997. Relation between satellite observed visible-near infrared emissions, population, economic activity and electric power consumption. International Journal of Remote Sensing, 18(6):1373-1379.
[10]	Fan J , 2011. Perspective on the development process of Human-Economic Geography and regional development studies: On the evolution of the field in the Institute of Geographic Sciences and Natural Resources Research of CAS. Progress in Geography, 30(4):387-396. (in Chinese)
[11]	Gao Q, Li Q, Yue Y et al., 2018. Exploring changes in the spatial distribution of the low-to-moderate income group using transit smart card data. Computers, Environment & Urban Systems, 72:68-77.
[12]	Gebru T, Krause J, Wang Y et al., 2017. Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States. Proceedings of the National Academy of Sciences of the United States of America, 114(50):13108-13113.
[13]	Golledge R G, Stimson R J , 1997. Spatial Behavior: A Geographic Perspective. New York: Guilford Press, 620 p.
[14]	He C Y, Liu Z F, Tian J et al., 2014. Urban expansion dynamics and natural habitat loss in China: A multiscale landscape perspective. Global Change Biology, 20(9):2886-2902.
[15]	He T F, Bao J, Li R Y. et al., 2018. Detecting vehicle illegal parking events using sharing bikes’ trajectories. In: KDD ‘18 Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 340-349.
[16]	Helbich M, Yao Y, Liu Y et al., 2019. Using deep learning to examine street view green and blue spaces and their associations with geriatric depression in Beijing, China. Environment International, 126:107-117.
[17]	Jean N, Burke M, Xie M et al., 2016. Combining satellite imagery and machine learning to predict poverty. Science, 353(6301):790-794.
[18]	Kang C, Sobolevsky S, Liu Y. et al., 2013. Exploring human movements in Singapore: A comparative analysis based on mobile phone and taxicab usages. In: The 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago, IL.
[19]	Lazer D, Pentland A, Adamic L et al., 2009. Computational social science. Science, 323(5915):721-723.
[20]	Li D , 1996. On the formation of geomatics and its cross-century development. World Sci-Tech R & D, 5:1-8.
[21]	Li D, Li X , 2015. An overview on data mining of nighttime light remote sensing. Acta Geodaeticaet Cartographica Sinica, 44(6):591-601. (in Chinese)
[22]	Li D, Ma J, Shao Z , 2015. The application of spatial temporal big data. Satellite Application, 9:7-11.
[23]	Li D, Zhao X, Li X , 2016. Remote sensing of human beings: A perspective from nighttime light. Geo-spatial Information Science, 19(1):69-79.
[24]	Li X, Li D , 2014. Can night-time light images play a role in evaluating the Syrian Crisis? International Journal of Remote Sensing, 35(18):6648-6661.
[25]	Li X, Liu S, Jendryke M et al., 2018. Night-time light dynamics during the Iraqi Civil War. Remote Sensing, 10(6):858. doi: .
[26]	Longley P A, Goodchild M F, Maguire D J et al., 2005. Geographic Information Systems: Principles, Techniques, Management and Applications. 2nd ed. New York: John Wiley & Sons, 401 p.
[27]	McDowell L , 1995. Understanding diversity: The problem of theory. In: Johnston R J, Taylor P J, Watts M J (eds.), Geographies of Global Change: Remapping the World in the Late Twentieth Century. Oxford: Blackwell, 280-294.
[28]	Schuler D , 1994. Social computing. Communications of the ACM, 37(1):28-29.
[29]	Signorini A, Segre A M, Polgreen P M , 2011. The use of Twitter to track levels of disease activity and public concern in the U.S. during the Influenza A H1N1 pandemic. PloS One, 6(5):e19467. doi: 10.1371/journal. pone.0019467.
[30]	Tu W, Cao J, Yue Y et al., 2017. Coupling mobile phone and social media data: A new approach to understanding urban functions and diurnal patterns. International Journal of Geographical Information Science, 31(12):2331-2358.
[31]	Wang Y D, Li H, Wang T et al., 2017. Modeling urban air quality trend surface using media data. Geomatics and Information Science of Wuhan University, 42(1):14-20. (in Chinese)
[32]	Williams R E , 1987. Selling a geographical information system to government policy makers. Papers from the 1987 Annual Conference of the Urban and Regional Information Systems Association. Des Plaines, IL: Urisa.
[33]	Witmer F W, Loughlin J O , 2011. Detecting the effects of wars in the Caucasus regions of Russia and Georgia using radiometrically normalized DMSP-OLS nighttime lights imagery. GIScience & Remote Sensing, 48(4):478-500.
[34]	Wuhan University (WU), 2015. Remote sensing research on the Syrian Conflict has attracted high attention from the global media. Retrieved on March 16, 2015, from .
[35]	Xiao L, Liu L, Song G et al., 2018. Journey-to-crime distances of residential burglars in China disentangled: Origin and destination effects. International Journal of Geo-Information, 7(8):325. doi: 10.3390/ijgi7080325
[36]	Xiao Y, Wang D, Fang , 2019. Exploring the disparities in park access through mobile phone data: Evidence from Shanghai, China. Landscape and Urban Planning, 181:80-91.
[37]	Yang H R, Dobruszkes F, Wang J E et al., 2018. Comparing China’s urban systems in high-speed railway and airline networks. Journal of Transport Geography, 68:233-244.
[38]	Yin L, Cheng Q M, Wang Z X et al., 2015. ‘Big data’ for pedestrian volume: Exploring the use of Google Street View images for pedestrian counts. Applied Geography, 63:337-345.
[39]	Yu B L, Lian T, Huang Y X et al., 2019. Integration of nighttime light remote sensing images and taxi GPS tracking data for population surface enhancement. International Journal of Geographical Information Science, 33(4):687-706.
[40]	Yu B L, Shu S, Liu H X et al., 2014. Object-based spatial cluster analysis of urban landscape pattern using nighttime light satellite images: A case study of China. International Journal of Geographical Information Science, 28(11):2328-2355.
[41]	Yu H, Shaw S-L , 2008. Exploring potential human activities in physical and virtual spaces: A spatio-temporal GIS approach. International Journal of Geographical Information Science, 22(4):409-430.
[42]	Yuan Y, Liu J, Chen Y M et al., 2018. Poverty measurement of urban internal space based on remote sensing images and online rental information: A case study of the city core of Guangzhou. Human Geography, 33(3):60-67. (in Chinese)
[43]	Zhang B J , 2018. Analysis of the inter-annual variation of nighttime lights in the most affected area of Wenchuan earthquake from 2003 to 2013. Journal of Catastrophology, 33(1):12-18. (in Chinese)
[44]	Zhang Y L, Dong R C , 2018. Impacts of street-visible greenery on housing prices: Evidence from a hedonic price model and a massive street view image dataset in Beijing. International Journal of Geo-Information, 7(3):104. doi: 10.3390/ijgi7030104.
[45]	Zhao X Z, Yu B L, Liu Y et al., 2018. NPP-VIIRS DNB daily data in natural disaster assessment: Evidence from selected case studies. Remote Sensing, 10(10):1526. doi: 10.3390/rs10101526.
[46]	Zheng Y, Capra L, Wolfson O. et al., 2014. Urban computing: Concepts, methodologies, and applications. ACM Transactions on Intelligent Systems and Technology, 5(3): 38. doi: .