Modeling and Forecasting Percent Changes in National Park Visitation Using Social Media

National parks are incredibly valuable places—for culture, for nature, and for local economies. To take good care of them, park managers need reliable information about how many people are visiting them. But counting visitors isn’t always easy. Many parks are huge, hard to access, and don’t have clear entry points, which makes accurate visitor counts difficult.

In this study, researchers explore a new way to estimate changes in park visitation without relying on traditional, on-site visitor counts. Using data from 20 U.S. national parks, they looked at how many national parks photos are shared on social media—specifically, images posted to Flickr.

Researchers built a model that uses these photo-sharing patterns over time to predict month-to-month changes in park visits. The model learns from past trends in both individual parks and across the national park system, without needing direct visitor counts from the parks themselves. Researchers also show how this approach could be combined with existing visitor data from the National Park Service to improve current estimates.

Results suggest that this social media–based approach performs as well as models that rely partly or even entirely on traditional visitor counts. This means park managers could use publicly available online data to better understand visitation trends—especially in places where counting visitors is difficult—helping them make more informed decisions about how to protect and manage these treasured landscapes.

Abstract

National parks have tremendous cultural, ecological, and economic value to societies. In order to manage and maintain these public spaces, decision-makers rely on detailed information about park use and park condition. Many parks, however, lack precise visitor counts because of challenges associated with monitoring large and inaccessible areas with porous boundaries. To facilitate better management, we propose a method to estimate percentage changes in park visitation without using any on-site visitor counts. Specifically, using 20 national parks in the United States, we develop a time series model for forecasting future monthly changes in visitation based on the volume of social media images shared by visitors to parks. Forecasts are generated from historic park-level and national-level photo-user-days (PUD) of images posted to Flickr, using singular spectrum analysis (SSA). We further propose an approach for augmenting existing on-site visitation data collected by the US National Park Service. Our model evaluations indicate that the proposed model that only uses social media data achieves competitive performance to the models which partially or fully utilizes on-site visitor counts.