Can your Smartwatch Measure Ambient Air Temperature?

Despite ongoing efforts to collect high-resolution datasets that capture the spatial distribution of urban heat, there remains a gap in human-centric monitoring that focuses on the immediate environment of individuals experiencing heat exposure. We aimed to develop a reliable prediction model for air temperature in dynamic outdoor settings using wrist-mounted wearable sensors. Data was collected for 22 days between 2020 and 2024 in Sydney, Australia. Each experiment involved 6 to 15 participants walking through different built environments. When air temperature and relative humidity measured by wrist-mounted sensors were compared to reference sensors, we found that wrist-mounted wearables cannot directly measure air temperature due to the influence of skin temperature. However, we can use their data to train a prediction model for air temperature. We explored three prediction methods: a steady-state heat transfer model of human skin, multi-linear regression, and random forest machine learning (ML). Results showed that the heat transfer model relied heavily on climatic parameters which could be measured by wrist-mounted sensors, limiting the applicability of this method. The linear regression model developed solely based on wrist-mounted data neglected the correlation between its inputs, such as wrist air temperature and wrist skin temperature. In comparison, the ML approach was capable of capturing non-linear, multi-dimensional relationships and demonstrated the best predictive performance. ML tested on out-of-sample data achieved a correlation coefficient (R²) of 0.97 (in contrast with 0.61 and 0.88 for heat transfer and linear regression) between predicted and observed air temperature, with a mean absolute error of <1℃(4.64℃ and 1.81℃). This performance is equivalent to the accuracy of many common air temperature sensors. This prediction model can be an effective method for providing high-resolution air temperature data in cities in moderate climates such as Sydney, while informing future work in other climate backgrounds.