Nowadays, the demand of utilization of urban land use maps by urban authorities, researchers, and citizens, steadily increased since the past decades. Utilization urban land use map reveals the human activity issues especially for human behavior in cities. Discovering patterns of human behavior is useful for urban authorities and citizens, especially in traffic forecasting, social science and urban planning. To discover patterns of land use in cities, sensing and analyzing the remote and social sensing data need to be conducted.

New York City in the United States of America (USA) is selected as the study area in this research including Manhattan District, Brooklyn District and Queens District. Two types of openly accessible data, namely remote sensing data and social sensing data are selected as the datasets. The social sensing data are bike and taxi data, whereas remoted sensed imagery is the Sentinel 2 sattelite image data. This research contains two aims, to sense and analyze the human behavior pattern, and to classify land use from the integration of remote sensing and social sensing data. The human behavior in the city can be discovered by extracting the bike and taxi data and understanding where and when people are in the city based on Geographic Information System (GIS). The two peak times at weekday happen at 8-9 am and 6-7 pm for both bike and taxi usage. Meanwhile, the peak times at weekend happen at 5-6 pm for bike usage, while for taxi usage happen at 6-7 pm. The bike and taxi density maps are generated to display where people are located in the city during the peak times, and it also can be reflected as residential area, office area and entertainment area.

A decision tree and random forest are used to perform the urban land use classification for 5 classes and 6 classes in the city. Accuracy assessment of the urban land use classification map is required to test the quality of supervised classification result of decision tree and random forest. Therefore, the overall accuracy of the 5 classes land use classified map reach 85.33% for decision tree and 86.96% for random forest, whereas the 6 classes land use classified map for decision tree and random forest reach 83.33% and 85.67%, respectively. The result of overall accuracy shows if demonstrate the integration of remote sensing data and social sensing data are capable for urban land use classification accurately and random forest has better overall accuracy than decision tree.

Chen, L., Yang,D., Jakubowicz, J., Pan,G., Zhang,D., Li, S., 2015. Sensing the Pulse of Urban Activity Centers Leveraging Bike Sharing Open Data. In: IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing.

Chu, D. A. Sheets, Y. Zhao, Y. Wu, J. Yang, M. Zheng, and G. Chen., 2014. Visualizing hidden themes of taxi movement with semantic transformation. In: Pacific Visualization Symposium (PacificVis), IEEE, pp.137–144.

CitiBike.2018. https://www.citibikenyc.com/ (1 June 2018).

Cohen, J. A Coefficient of agreement for nominal scales. Educ. Psychol. Meas 1960, 20, 37–46.

DeMaio., P. 2009. “Bike-Sharing: History, Impacts, Models of Provision, and Future,” Journal of Public Transportation, Vol. 12,no. 4, pp. 41–56.

Dohuki, S., Kamw, R., Zhao, Y., Ma, C., Wu, Y., Yang,J., Ye,X., Wang,F., Li,X., Chen,W., 2017. SemanticTraj: A New Approach to Interacting with Massive Taxi Trajectories. In: IEE Transactions on Visualization and Computer Graphics, Vol.23, no.1.

Ellis, E., Pontius, R., 2007. Land-Use and Land-Cover Change, Encycl. Earth.

Friedl, M, A., Brodley, C, E., 1997. Decision Tree Classification of Land Cover from Remotely Sensed Data. In: Remote Sensing Environment. Elsevier, Vol.61, issue 3, pp. 399-409.

Froehlich, J., Neumann, J., Oliver, N., 2009. Sensing and predicting the pulse of the city through shared bicycling. In: IJCAI’09 Proceedings of the 21th international jont conference on Artificial intelligent. Pages 1420-1426.

Herold, M.; Liu, X.; Clarke, K.C., 2003. Spatial metrics and image texture for mapping urban land use. Photogramm. Eng. Remote Sens. 69, 991–1001.

Hu, S.; Wang, L., 2013. Automated urban land-use classification with remote sensing. Int. J. Remote Sens, 34, 790–803.

Jensen, J.R.; Cowen, D.C., 2011. Remote sensing of urban/suburban infrastructure and socio-economic attributes. In The Map Reader; JohnWiley & Sons, Ltd.: Hoboken, NJ, USA; pp. 153–163.

Jones, K., 2008. Importance of Land Cover and Biophysical Data in Landscape-based Environmental Assessments. N. Am. Land Cover Summit Assoc. Am. Geogr., Wash., DC, USA pp. 215–249.

Kasetkasem, T., Arora, M.K., Varshney, P.K., 2005. Super-resolution land cover mapping using a Markov random field based approach. Remote Sens. Environ. 96 (3), 302–314.

Latour, B., 2007. Beware, your imagination leaves digital traces, Column for Times Higher Education Supplement, 6th of April 2007. http://www.brunolatour.fr/poparticles/poparticle/P-129-THES-GB.doc

Liaw, A., Wiener, M., 2002. Classification and Regression by randomForest. 2. R news, pp. 18–22.

Liu, Y.; Liu, X.; Gao, S.; Gong, L.; Kang, C.; Zhi, Y.; Chi, G.; Shi, L., 2015. Social sensing: A new approach to understanding our socioeconomic environments. Ann. Assoc. Am. Geogr. 105, 512–530.

NYC Planning, 2018. PLUTO and MapPLUTO of Departement of City Planning. https://www1.nyc.gov/site/planning/data-maps/open-data/dwn-pluto-mappluto.page. (1 June 2018).

Pal, M., and P.M. Mather, 2003. An assessment of the effectiveness of decision tree methods for land cover classification, Remote Sensing of Environment, 86(1):554–565.
Quinlan, J.R., 1986. Induction of Decision Trees. Mach Learn 1, 81-106. Doi:10.1023/A:1022643204877

Prajwala, T, R., 2015. A Comparative Study on Decision Tree and Random Forest Using R Tool. In: International Jurnal of Advanced Research in Computer and Communication Engineering. IJARCCE, Vol. 4, Issue 1.

Ramm, F., 2014. OpenStreetMap Data in Layered GIS Format.

Satellite Imaging Corporation, 2017. Sentinel-2A Satellite Sensor (10m). https://www.satimagingcorp.com/satellite-sensors/other-satellite sensors/sentinel-2a/ (1 June 2018).

Shultz, M., Voss, M., Auer M., Carter, S., Zipf, A., 2017. Open land cover from OpenStreetMap and remote sensing. In: Int J Appl Eath Obs Geoinformation. Elsevier, 63, 206-213.

Thenkabail, P.S., Schull, M., Turral, H., 2005. Ganges and Indus river basin land use/land cover (LULC) and irrigated area mapping using continuous streams of MODIS data. Remote Sens. Environ. 95 (3), 317–341.

Wei, W., Yunjia, W., Qing, W., Dajun, L., Zhijie, W. (2011). Application of Decision Tree in Land Use Classification. In: Jiang L.(eds) Proceedings of the 2011, International Conference on Informatics, Cybernetics, and Computer Engineering (ICCE2011) November 19-20,2011, Melbourne, Australia. Advances in Intelligent and Soft Computing, vol 111. Springer, Berlin, Heidelberg

Woznicky, A, S., Baynes, J., Panlasigui, S., Mehaffey, M., Neale, A., 2018. Development of a spatially complete floodplain map of the conterminous United States using random forest. In: Science of Total Environment. Elsevier, 647, 942-953.

Xu, Z., Chen, J., Xia, J., Du, P., Zheng, H., Gan, L. (2018). Multisource Earth Observation Data for Land-Cover Classification Using Random Forest. In: IEEE Geoscience and remote sensing letters, Vol.15, No.5.
Zhang, M., Chen,F., Tian, B., Liang, D., (2019). Multi-temporal SAR image classification of coastal plain wetlands using a new feature selection method and random forests, Remote Sensing Letters, 10:3, 312-321, DOI: 10.1080/2150704X.2018.1528397.