Lakeplace: Sensing interactions between lakes and human activities

TL;DR

This paper introduces a data-driven framework to analyze human interactions with lakes in urban areas using mobile data, revealing insights into social-demographics and activity patterns for sustainable urban water management.

Contribution

It presents a novel lakeplace sensing framework that combines geospatial big data and social-demographic profiling to study human-lake interactions at fine spatiotemporal scales.

Findings

Identified patterns of human activity around 2,036 lakes in TCMA.

Distinguished whether lake attractiveness is driven by the lake itself or surrounding demographics.

Provided insights for urban planning and water resource management.

Abstract

Urban freshwater ecosystems, composed of rivers, ponds, lakes, and other water bodies, have essential socioeconomic and ecological values for urban residents. However, research investigating how individuals interact with lakes remains limited, especially within cities and at fine spatiotemporal resolutions. To fill this gap, we propose a data-driven analytical framework that comprehensively senses human-lake interactions and profiles the social-demographic characteristics of intra-city lakes. The term "lakeplace" is proposed to depict a place containing lakes and human activities within it. For each lake, the geographic boundary of its lakeplace refers to the first-order administrative units, reflecting the neighboring scale of lake socioeconomics. Utilizing large-scale individual mobile positioning data, we performed lakeplace sensing on the 2,036 major lakes in the Twin Cities Metropolitan Area (TCMA), Minnesota, and the people interacting with them. The popularity of each lakeplace was measured by its temporal visitations and further categorized as on-lake and around-lake human activities. Popular lakeplaces were investigated to depict whether the attractiveness of a lake is mostly brought by the lake itself, or the social-demographic environment around it. The lakeplace sensing framework offers a practical approach to the spatiotemporal characteristics of human activities and understanding the social-demographic knowledge related to human-lake systems. Our work exemplifies the social sensing of human-environment interactions via geospatial big data, shedding light on human-oriented sustainable urban planning and urban water resource management.