Using data derived from cellular phone locations to estimate visitation to natural areas: An application to water recreation in New England, USA

We introduce and validate the use of commercially available human mobility datasets based on cell phone locations to estimate visitation to natural areas. By combining this data with on-the-ground observations of visitation to water recreation areas in New England, we fit a model to estimate daily visitation for four months to more than 500 sites. The results show the potential for this new big data source of human mobility to overcome limitations in traditional methods of estimating visitation and to provide consistent information at policy-relevant scales. However, the data providers’ opaque and rapidly developing methods for processing locational information required a calibration and validation against data collected by traditional means to confidently reproduce the desired estimates of visitation. We found that with this calibration, the high-resolution information in both space and time provided by cell phone location-derived data creates opportunities for developing next-generation models of human interactions with the natural environment.

[1]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[2]  M. Mazzotta,et al.  Quantifying Recreational Use of an Estuary: A Case Study of Three Bays, Cape Cod, USA , 2019, Estuaries and Coasts.

[3]  K. Byrd,et al.  Interacting Coastal Based Ecosystem Services: Recreation and Water Quality in Puget Sound, WA , 2013, PloS one.

[4]  C. Silva.  Beach Carrying Capacity Assessment: How important is it? , 2002 .

[5]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[6]  H. Yamano,et al.  Mobile phone network data reveal nationwide economic value of coastal tourism under climate change , 2020 .

[7]  Petter Holme,et al.  Predictability of population displacement after the 2010 Haiti earthquake , 2012, Proceedings of the National Academy of Sciences.

[8]  A. Guerry,et al.  Using social media to quantify nature-based tourism and recreation , 2013, Scientific Reports.

[9]  Lindsey S. Smart,et al.  Quantifying the visual-sensory landscape qualities that contribute to cultural ecosystem services using social media and LiDAR , 2018, Ecosystem services.

[10]  Dong Kun Lee,et al.  Spatial tradeoff between biodiversity and nature-based tourism: Considering mobile phone-driven visitation pattern , 2020 .

[11]  C. Kolstad,et al.  Valuing Beach Recreation Lost in Environmental Accidents , 2000 .

[12]  Marta C. González,et al.  Analyzing Cell Phone Location Data for Urban Travel , 2015 .

[13]  Henrikki Tenkanen,et al.  Instagram, Flickr, or Twitter: Assessing the usability of social media data for visitor monitoring in protected areas , 2017, Scientific Reports.

[14]  R. Tourangeau,et al.  The Gulf Recreation Study: Assessing Lost Recreational Trips from the 2010 Gulf Oil Spill , 2017 .

[15]  Kate K. Mulvaney,et al.  Valuing Coastal Beaches and Closures Using Benefit Transfer: An Application to Barnstable, Massachusetts. , 2018, Journal of ocean and coastal economics.

[16]  Christopher G. Leggett.  Sampling Strategies for On-site Recreation Counts , 2017 .

[17]  Dietmar Bauer,et al.  Inferring land use from mobile phone activity , 2012, UrbComp '12.

[18]  Emilia H. Lia,et al.  Recreational use in dispersed public lands measured using social media data and on-site counts. , 2018, Journal of environmental management.

[19]  Christopher Monz,et al.  Using Mobile Device Data to Estimate Visitation in Parks and Protected Areas: An Example from the Nature Reserve of Orange County, California , 2019, Journal of Park and Recreation Administration.

[20]  David M. Blei,et al.  Estimating Heterogeneous Consumer Preferences for Restaurants and Travel Time Using Mobile Location Data , 2018, ArXiv.

[21]  J. Semenza,et al.  Beach attendance and bathing rates for Southern California beaches , 2007 .

[22]  S. Zarnoch,et al.  Forest Service National Visitor Use Monitoring Process: Research Method Documentation , 2002 .

[23]  Vanessa Frías-Martínez,et al.  Forecasting socioeconomic trends with cell phone records , 2013, ACM DEV '13.

[24]  Vincent D. Blondel,et al.  A survey of results on mobile phone datasets analysis , 2015, EPJ Data Science.

[25]  V. Smith,et al.  Recreation Demand Models , 2005 .

[26]  Best practices for collecting onsite data to assess recreational use impacts from an oil spill , 2017 .

[27]  S I Hay,et al.  Utilizing general human movement models to predict the spread of emerging infectious diseases in resource poor settings , 2019, Scientific Reports.

[28]  Laura Ferrari,et al.  Urban Sensing Using Mobile Phone Network Data: A Survey of Research , 2014, ACM Comput. Surv..

[29]  David Fisher,et al.  Geolocated social media as a rapid indicator of park visitation and equitable park access , 2018, Comput. Environ. Urban Syst..

[30]  T. Ricketts,et al.  Spatial and Temporal Dynamics and Value of Nature-Based Recreation, Estimated via Social Media , 2016, PloS one.

[31]  Andreas Ziegler,et al.  Mining data with random forests: current options for real‐world applications , 2014, WIREs Data Mining Knowl. Discov..

[32]  A. Nathanson,et al.  Analysis of lifeguard-recorded data at Hanauma Bay, Hawaii. , 2011, Wilderness & environmental medicine.

[33]  Zbigniew Smoreda,et al.  Assessing the Quality of Home Detection from Mobile Phone Data for Official Statistics , 2018, Journal of Official Statistics.

[34]  Craig A. Knoblock,et al.  A Survey of Digital Map Processing Techniques , 2014, ACM Comput. Surv..

[35]  Eran Toch,et al.  Analyzing large-scale human mobility data: a survey of machine learning methods and applications , 2019, Knowledge and Information Systems.

[36]  Zhijiong Huang,et al.  Using cell phone location to assess misclassification errors in air pollution exposure estimation. , 2018, Environmental pollution.

[37]  David L. Smith,et al.  Quantifying the Impact of Human Mobility on Malaria , 2012, Science.

[38]  José Antonio Lozano,et al.  Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Jayson R. Smith,et al.  Factors influencing human visitation of southern California rocky intertidal ecosystems , 2013 .

[40]  P. King,et al.  Who's counting: An analysis of beach attendance estimates and methodologies in southern California , 2012 .

[41]  Gürkan Solmaz,et al.  A Survey of Human Mobility Models , 2019, IEEE Access.

[42]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[43]  Andreas Ziegler,et al.  ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R , 2015, 1508.04409.

[44]  Stephen Polasky,et al.  Recreational demand for clean water: evidence from geotagged photographs by visitors to lakes , 2014 .

[45]  Carlo Ratti,et al.  Exploring Universal Patterns in Human Home-Work Commuting from Mobile Phone Data , 2013, PloS one.

[46]  Marta C. González,et al.  The path most traveled: Travel demand estimation using big data resources , 2015, Transportation Research Part C: Emerging Technologies.

[47]  Hengcai Zhang,et al.  Dynamic Estimation of Individual Exposure Levels to Air Pollution Using Trajectories Reconstructed from Mobile Phone Data , 2019, International journal of environmental research and public health.