Mapping urban heat from citizen-collected data: a scalable Gaussian process approach to correcting for preferential sampling
Abstract
The urban heat island (UHI) effect amplifies heat stress in cities, increasing heat-related illness, mortality, sleep disruption, and energy demand. Because UHI intensity varies at neighborhood scales, intra-city temperature mapping is essential for assessing public health impacts, yet existing monitoring networks are sparse. Crowdsourced weather stations provide dense, hourly observations but suffer from noise and systematic biases, including preferential sampling driven by where residents install sensors. We introduce two scalable Gaussian process frameworks which adjust for preferential sampling and enable statewide, high-resolution temperature prediction. The first integrates sampling correction directly within a sparse variational Gaussian process (SVGPR+PS). The second uses a two-stage estimator involving a log-Gaussian Cox process (LGCP+GP) that estimates the sampling intensity field and incorporates it into temperature prediction. Both methods rely on inducing-point approximations and variational inference to scale beyond traditional Gaussian processes. Applied to approximately 10,000 citizen stations across North Carolina, the models generate hourly temperature fields within minutes. Validation against independent urban heat campaign data shows that the preferential sampling correction improves predictive performance, increasing average afternoon correlations across four cities from 0.26 to 0.43. This scalable framework enables neighborhood-level UHI assessment and supports studies of heat exposure disparities statewide.
Related
- Scalable Logistic Gaussian Process Density Regression with Kinetic Langevin Sampling
- Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes
- Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
- Scalable generative modeling of non-Gaussian spatio-temporal fields via autoregressive Gaussian processes
- Scalable Sparse Autoregressive Variational Inference for Non-Gaussian Spatial Fields
BibTeX
@misc{kim2026mapping,
title = {{Mapping urban heat from citizen-collected data: a scalable Gaussian process approach to correcting for preferential sampling}},
author = {Ellie K. Kim and Zachary D. Calhoun and Michael H. Bergin and David E. Carlson},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.03659},
eprint = {2611.03659},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.03659},
}
RIS
TY - UNPB
TI - Mapping urban heat from citizen-collected data: a scalable Gaussian process approach to correcting for preferential sampling
AU - Ellie K. Kim
AU - Zachary D. Calhoun
AU - Michael H. Bergin
AU - David E. Carlson
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.03659
UR - https://arxiv.org/abs/2611.03659
AB - The urban heat island (UHI) effect amplifies heat stress in cities, increasing heat-related illness, mortality, sleep disruption, and energy demand. Because UHI intensity varies at neighborhood scales, intra-city temperature mapping is essential for assessing public health impacts, yet existing monitoring networks are sparse. Crowdsourced weather stations provide dense, hourly observations but suffer from noise and systematic biases, including preferential sampling driven by where residents install sensors. We introduce two scalable Gaussian process frameworks which adjust for preferential sampling and enable statewide, high-resolution temperature prediction. The first integrates sampling correction directly within a sparse variational Gaussian process (SVGPR+PS). The second uses a two-stage estimator involving a log-Gaussian Cox process (LGCP+GP) that estimates the sampling intensity field and incorporates it into temperature prediction. Both methods rely on inducing-point approximations and variational inference to scale beyond traditional Gaussian processes. Applied to approximately 10,000 citizen stations across North Carolina, the models generate hourly temperature fields within minutes. Validation against independent urban heat campaign data shows that the preferential sampling correction improves predictive performance, increasing average afternoon correlations across four cities from 0.26 to 0.43. This scalable framework enables neighborhood-level UHI assessment and supports studies of heat exposure disparities statewide.
ER -