Climate change is expected to exacerbate the urban heat island (UHI) effect in cities worldwide, increasing the risk of heat-related morbidity and mortality. Solar reflective ‘cool pavement’ is one of several mitigation strategies that may counteract the negative effects of the UHI effect. An increase in pavement albedo results in less heat absorption, which results in reduced surface temperatures (Tsurface). Near surface air temperatures (Tair) could also be reduced if cool pavements are deployed at sufficiently large spatial scales, though this has never been confirmed by field measurements. This field study is the first to conduct controlled measurements of the impacts of neighborhood-scale cool pavement installations. We measured the impacts of cool pavement on albedo, Tsurface, and Tair. In addition, pavement albedo was monitored after installation to assess its degradation over time. The field site (∼0.64 km2) was located in Covina, California; ∼30 km east of Downtown Los Angeles. We found that an average pavement albedo increase of 0.18 (from 0.08 to 0.26) corresponded to maximum neighborhood averaged Tsurface and Tair reductions of 5 °C and 0.2 °C, respectively. Maximum Tsurface reductions were observed in the afternoon, while minimum reductions of 0.9 °C were observed in the morning. Tair reductions were detected at 12:00 local standard time (LST), and from 20:00 LST to 22:59 LST, suggesting that cool pavement decreases Tair during the daytime as well as in the evening. An average albedo reduction of 30% corresponded to a ∼1 °C reduction in the Tsurface cooling efficacy. Although we present here the first measured Tair reductions due to cool pavement, we emphasize that the tradeoffs between Tair reductions and reflected shortwave radiation increases are still unclear and warrant further investigation in order to holistically assess the efficacy of cool pavements, especially with regards to pedestrian thermal comfort.
Cloud microphysics—the collection of processes that govern the small‐scale formation, evolution, and interactions of liquid droplets and ice crystals in clouds and precipitation—remains a major source of uncertainty in weather and climate models. Although too small in scale to be explicitly resolved in any large‐eddy simulation, weather, or climate model, the representation of cloud microphysical processes has significant impact at the climate scale. Current microphysical schemes are limited by both parametric uncertainty, linked to uncertainty in physical parameter values, and structural uncertainty, arising from incomplete physical understanding of the processes at play or approximations made for computational efficiency. Recent advances in the application of machine learning (ML) to the physical sciences show significant potential for minimizing these limitations by leveraging high‐fidelity simulations and observations. Here we outline the challenges that must be addressed to apply ML toward cloud microphysics scheme development. This perspectives paper synthesizes recent progress in using data‐driven methods, including ML, to improve cloud microphysics parameterizations and highlights opportunities to address key uncertainties. We discuss the roles of aleatoric (irreducible, or statistical) and epistemic (reducible, or systematic) errors in contributing to microphysics parameterization uncertainty. ML can leverage observations to improve microphysical schemes via bottom‐up and top‐down constraints. Methods such as differentiable programming and ML‐enhanced sampling strategies and the creation of large scale benchmark data sets promise to bridge the gap between observations and models and to improve the consistency of cloud microphysical representation across temporal and spatial scales.
5 December 2025 in Journal of Geophysical Research: Machine Learning and Computation
The microphysical properties of ice crystals are important because they significantly alter the radiative properties and spatiotemporal distributions of clouds, which in turn strongly affect Earth's climate. However, it is challenging to measure key properties of ice crystals, such as mass or morphological features. Here, we present a proof‐of‐concept framework for predicting three‐dimensional (3D) microphysical properties of ice crystals from in situ two‐dimensional (2D) imagery. First, we computationally generated synthetic ice crystals using 3D modeling software along with geometric parameters estimated from the 2021 Ice Cryo‐Encapsulation Balloon (ICEBall) field campaign. Then, we used synthetic crystals to train machine learning (ML) models to predict effective density , effective surface area , and number of bullets from synthetic rosette imagery. On unseen synthetic images, our ML models accurately predicted ice crystal properties. ResNet‐18 performed best, achieving values of 0.99 and 0.98 for and , respectively, and MAE of 0.10 for in single view tasks. Stereo view ResNet‐18 further reduced RMSE by 40% for and and reduced MAE by 0.08 for . This work provides a novel ML‐driven framework for estimating ice microphysical properties from in situ imagery, which will allow for downstream constraints on microphysical parameterizations, such as the mass‐size relationship.
23 June 2026 in Journal of Geophysical Research: Atmospheres
Anthropogenic heat emissions from human energy consumption contribute to the urban heat island (UHI) effect, yet their spatiotemporal distributions and impacts remain uncertain. In this study, we develop a 100 m resolution, hourly anthropogenic heat flux (AHF) data set for Los Angeles County and use the Weather Research and Forecasting model to quantify the meteorological impacts of AHF and the heat mitigation potential of electrification and energy efficiency measures. Annual mean AHF across the county was 2.54 W m −2 , increasing to 9.65 W m −2 over urban areas, with substantial variability across both space and time. AHF increased urban mean 2 m air temperature by approximately ∼0.3°C and canopy air temperature by more than 1°C, with localized canopy warming exceeding 4°C in certain neighborhoods. Electrification and energy efficiency measures can substantially mitigate warming caused by AHF, with stronger cooling effects near highways. Under the most aggressive mitigation scenario, these measures offset more than 50% of the AHF‐induced warming in both mean 2 m air temperature and canopy air temperature across urban Los Angeles. This study confirms AHF as an important contributor to Los Angeles' UHI and demonstrates that energy‐use reductions can provide non‐trivial cooling benefits. More broadly, this study highlights the value of coupling high‐resolution AHF inventories and meteorological modeling to improve effective heat mitigation planning under future urbanization and climate change.
Anthropogenic heat emissions from human energy consumption contribute to the urban heat island (UHI) effect, yet their spatiotemporal distributions and impacts remain uncertain. In this study, we develop a 100 m resolution, hourly anthropogenic heat flux (AHF) dataset for Los Angeles County and use the Weather Research and Forecasting model to quantify the meteorological impacts of AHF and the heat mitigation potential of electrification and energy efficiency measures. Annual mean AHF across the county was 2.54 W m −2 , increasing to 9.65 W m −2 over urban areas, with substantial variability across both space and time. AHF increased urban mean 2 m air temperature by approximately ∼0.3 ◦C and canopy air temperature by more than 1 ◦C, with localized canopy warming exceeding 4 ◦C in certain neighborhoods. Electrification and energy efficiency measures can substantially mitigate warming caused by AHF, with stronger cooling effects near highways. Under the most aggressive mitigation scenario, these measures offset more than 50% of the AHF-induced warming in both mean 2 m air temperature and canopy air temperature across urban Los Angeles. This study confirms AHF as an important contributor to Los Angeles’ UHI and demonstrates that energy-use reductions can provide non-trivial cooling benefits. More broadly, this study highlights the value of coupling high-resolution AHF inventories and meteorological modeling to improve effective heat mitigation planning under future urbanization and climate change.