Parameterization of the Interaction between the Atmosphere and the Urban Surface: Current State and Prospects

Tarasova, M. A.; Varentsov, Mikhail; Stepanenko, Victor

doi:10.1134/s0001433823020068

Cited by 5 publications

(1 citation statement)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the deficit of in situ meteorological data in cities, hydrodynamic mesoscale models of the atmosphere are nowadays one of the main tools for obtaining spatially and temporally detailed data on the UHI. Such models coupled to urban canopy parameterizations [10,11] with a grid spacing of a few kilometers to hundreds of meters are able to reproduce the majority of urban-induced meteorological effects [12] and are routinely used in numerical weather prediction [13,14], regional heat stress assessments [15,16] and refinements of the climate change scenarios [17,18] for urban areas. However, such models demand computing resources and require complex software and hardware infrastructure (data storage, input and output data processing, etc.).…”

Section: Introductionmentioning

confidence: 99%

Machine Learning for Simulation of Urban Heat Island Dynamics Based on Large-Scale Meteorological Conditions

Varentsov,

Krinitskiy,

Stepanenko

2023

Climate

View full text Add to dashboard Cite

This study considers the problem of approximating the temporal dynamics of the urban-rural temperature difference (ΔT) in Moscow megacity using machine learning (ML) models and predictors characterizing large-scale weather conditions. We compare several ML models, including random forests, gradient boosting, support vectors, and multi-layer perceptrons. These models, trained on a 21-year (2001–2021) dataset, successfully capture the diurnal, synoptic-scale, and seasonal variations of the observed ΔT based on predictors derived from rural weather observations or ERA5 reanalysis. Evaluation scores are further improved when using both sources of predictors simultaneously and involving additional features characterizing their temporal dynamics (tendencies and moving averages). Boosting models and support vectors demonstrate the best quality, with RMSE of 0.7 K and R2 > 0.8 on average over 21 years. For three selected summer and winter months, the best ML models forced only by reanalysis outperform the comprehensive hydrodynamic mesoscale model COSMO, supplied by an urban canopy scheme with detailed city-descriptive parameters and forced by the same reanalysis. However, for a longer period (1977–2023), the ML models are not able to fully reproduce the observed trend of ΔT increase, confirming that this trend is largely (by 60–70%) driven by megacity growth. Feature importance assessment indicates the atmospheric boundary layer height as the most important control factor for the ΔT and highlights the relevance of temperature tendencies as additional predictors.

show abstract