Integrating Satellite and Ground Measurements for Predicting Locations of Extreme Urban Heat

Abstract

The emergence of urban heat as a climate-induced health stressor is receiving increasing attention among researchers, practitioners, and climate educators. However, the measurement of urban heat poses several challenges with current methods leveraging either ground based, in situ observations, or satellite-derived surface temperatures estimated from land use emissivity. While both techniques contain inherent advantages and biases to predicting temperatures, their integration may offer an opportunity to improve the spatial resolution and global application of urban heat measurements. Using a combination of ground-based measurements, machine learning techniques, and spatial analysis, we addressed three research questions: (1) How much do ambient temperatures vary across time and space in a metropolitan region? (2) To what extent can the integration of ground-based measurements and satellite imagery help to predict temperatures? (3) What landscape features consistently amplify and temper heat? We applied our analysis to the cities of Baltimore, Maryland, and Richmond, Virginia, and the District of Columbia using geocomputational machine learning processes on data collected on days when maximum air temperatures were above the 90th percentile of historic averages. Our results suggest that the urban microclimate was highly variable across all of the cities—with differences of up to 10 °C between coolest and warmest locations at the same time—and that these air temperatures were primarily dependent on underlying landscape features. Additionally, we found that integrating satellite data with ground-based measures provided highly accurate and precise descriptions of temperatures in all three study regions. These results suggest that accurately identifying areas of extreme urban heat hazards for any region is possible through integrating ground-based temperature and satellite data.

Integrating Satellite-Derived Data as Spatial Predictors in Multiple Regression Models to Enhance the Knowledge of Air Temperature Patterns

“…Moreover, temperature is one of the variables used in climate modelling. However, the latter is not a stationary phenomenon [26,52]. In this study, the prediction of air temperature gives results that are statistically very close to the air temperature measured at professional meteorological stations (R 2 average of 0.82 over the entire study area).…”

“…Moreover, a cross validation is still performed due to its ability to detect over fitting of multiple regression, although multiple regression provides internal validation and randomization [51,52]. In this way, the cross validation presents a more conservative estimate of predictive power.…”

“…The second limit relates to the necessity to have one model equation per day due to non-stationary weather conditions [52]. These limits can be at the same time a perspective of work, while continuing the study on several years to validate the contribution of the remote sensing variables in the air temperature model.…”

A New Approach for Understanding Urban Microclimate by Integrating Complementary Predictors at Different Scales in Regression and Machine Learning Models

“…Finally, after removing the correlated variables, multiple linear regressions are carried out on about 20 variables, between 21 for the August 30 th , 2016, and 27 for the August 1 st , 2017 (Table 6). In addition, a holdout cross-validation was performed because of its ability to detect multiple regression overfitting (80% learning data and 20% validation data) [97].…”

Urban-Rural Surface Temperature Deviation and Intra-Urban Variations Contained by an Urban Growth Boundary

“…The spatial variation in heat-related mortality is regressive, with disproportionate negative impact on the poor, elderly, and people of color [10][11][12][13][14][15]. It is now well-appreciated that land use planning can play a major role in amplifying urban heat, or can provide mitigation to help temper local experiences of heat [16][17][18][19][20][21]. The elevation of a city's temperature, by heat absorption and storage in the built environment and by heat production by dense and mechanized urban activity, is typically named an "urban heat island."…”