COVID-19 pandemic changes the recreational use of Moscow parks in space and time: Outcomes from crowd-sourcing and machine learning

Abstract

The limited access to urban green spaces during the COVID-19 pandemic had a negative impact on the human-nature interaction in cities and human well-being. Number of visitors to green areas, initially declined due to imposed restrictions, was restored after they were lifted as established by several studies across the globe However, little is still known about changes in behavior and preferences of park visitors in the post-COVID time. In this study, we investigated spatial-temporal patterns of recreational activities in the three urban parks in Moscow (Russia) prior, during and after the COVID-19 lockdown (in 2019 and 2020). The selected parks represent two different types: a centrally located park with much infrastructure and open landscapes (Gorky Park) and parks located at the outskirts of the city center with a more forested landscape and little infrastructure (Timiryazevski and Sokolniki parks). Recreational activities were identified based on the analysis of social media photos using machine-learning algorithms. As expected, park closures during lockdown resulted in overall decrease in the number of taken photos. After the parks were re-opened, however, the number of photos did not grow immediately. The number of photos only restored after almost three months, and the visiting peak shifted to autumn. Differences between parks were related to the type of the park and its landscape structure. The lowest decrease in the number of photos was observed for the Timiryazevsky park - a semi-natural green area, while the centrally located Gorky Park was the most affected, likely due to the strictest control measures. In comparison to 2019, photos in 2020 were more evenly distributed across the area in all the three parks. Besides, 'natural' areas became the main attractors for the visitors - photos under 'nature observation' category became the most popular. Spatial distribution of the recreational activities in post-lockdown period was characterized by larger distances between photos, likely corresponding to the social distancing. COVID-19 pandemic highlighted the value of green areas for citizens, but also changed their recreational preferences and overall behavior in parks. The observed shift from high density of visitors around entertainments and attractions in 2019 to a more homogeneous and less dense distribution along the natural zones in 2020 reveals a new pattern in visitors behavior and preference, which shall be considered in spatial planning of the parks. Increasing availability of natural green areas and their integration in urban green infrastructures can become the most relevant policy to consider the crucial role of urban nature as a source of resilience in turbulent times.

Keywords: Cultural ecosystem services; Green infrastructure; Social media; Urban green spaces (UGS); Visitation.

Fig. 1

To the left – location of the studied parks within Moscow city boundaries (red outlined polygon). To the right – land cover structure of the parks – Timiryazevsky (A), Sokolniki (B) and Gorky Park (C).

Fig. 2

A conceptual scheme of data sources and processes.

Fig. 3

(A) Number of unique active VK users for all the three parks in 2019 (red colour) and 2020 (blue colour). (B) Number of photos posted by visitors by gender (red – female, blue – male).

Fig. 4

Number of photos taken in Timiryazevsky (A), Sokolniki (B) and Gorky Park (C) in 2019 (blue colour) and 2020 (orange colour).

Fig. 5

Spatial distribution of the number of photos in Timiryazevsky (A), Sokolniki (B) and Gorky Park (C) in 2019 and in Timiryazevsky (D), Sokolniki (E) and Gorky Park (F) in 2020.

Fig. 6

Dynamic in the average distance between the photos taken in 2019 (red colour) and 2020 (blue colour).

Fig. 7

Breakdown of number of photos taken in Timiryazevsky, Sokolniki and Gorky Parks in 2019 and 2020 by recreational activities depicted on them (“passive” = passive recreation; “nature” = nature observation; “water” = water recreation; “winter” = winter recreation; “children” = recreation with children; “sport” = active sports; “dog” = dog walking; “horse” = horse-riding; “food” = eating food; “music” = playing music and drawing).

Fig. 8

Spatial distribution of the photos depicting nature observation activity in Timiryazevsky (A, D), Sokolniki (B, E) and Gorky Park (C, F) in 2019 and 2020 respectively.