Statistical estimation of next-day nighttime surface urban heat islands

Estimating future temporal patterns of Surface Urban Heat Islands (SUHIs) on multiple time scales is an ongoing research endeavor. Among these scales, estimation next-day SUHIs special significance to urban residents, yet we currently lack a simple but efficient approach for making such estimations. In the present study, propose statistical strategy estimating nighttime SUHIs, based incorporating various SUHI controls into support vector machine regression (SVR) model. The majority both surface (including factors related land cover and solar radiation) meteorological temperature fluctuations, relative humidity, accumulated precipitation, wind speed, aerosol optical depth, soil moisture) that have previously been found account daily variations were used as estimators, provide estimations overall intensity (SUHII) pixel-by-pixel Gaussian-based LSTs over 59 Chinese megacities. For SUHII, mean absolute error (MAE) 0.67 K average, percentage (MAPE) no more than 25% 90% cities. LSTs, associated MAE less 2.0 in most scenarios. addition, contribution from each selected estimator SUHII assessed comprehensively. all humidity greatest, followed by rural air temperature. Moreover, nearly 78% cities, estimators day-to-day make larger those intra-annual variations. We conclude our effective can potentially help residents better adapt heat stress.