Modeling urban evapotranspiration using remote sensing, flux footprints, and artificial intelligence

Stenka Vulova; Fred Meier; Alby Duarte Rocha; Justus Quanz; Hamideh Nouri; Birgit Kleinschmit

doi:10.1016/j.scitotenv.2021.147293

Modeling urban evapotranspiration using remote sensing, flux footprints, and artificial intelligence

Sci Total Environ. 2021 Sep 10:786:147293. doi: 10.1016/j.scitotenv.2021.147293. Epub 2021 Apr 28.

Authors

Stenka Vulova¹, Fred Meier², Alby Duarte Rocha³, Justus Quanz⁴, Hamideh Nouri⁵, Birgit Kleinschmit⁶

Affiliations

¹ Geoinformation in Environmental Planning Lab, Department of Landscape Architecture and Environmental Planning, Technische Universität Berlin, 10623 Berlin, Germany. Electronic address: stenka.vulova@tu-berlin.de.
² Chair of Climatology, Institute of Ecology, Technische Universität Berlin, 12165 Berlin, Germany. Electronic address: fred.meier@tu-berlin.de.
³ Geoinformation in Environmental Planning Lab, Department of Landscape Architecture and Environmental Planning, Technische Universität Berlin, 10623 Berlin, Germany. Electronic address: a.duarterocha@tu-berlin.de.
⁴ Chair of Climatology, Institute of Ecology, Technische Universität Berlin, 12165 Berlin, Germany; Department of Environmentally Sound Urban and Infrastructure Planning, HafenCity University Hamburg, 20457 Hamburg, Germany. Electronic address: justus.quanz@hcu-hamburg.de.
⁵ Division of Agronomy, University of Göttingen, 37075 Göttingen, Germany. Electronic address: hamideh.nouri@uni-goettingen.de.
⁶ Geoinformation in Environmental Planning Lab, Department of Landscape Architecture and Environmental Planning, Technische Universität Berlin, 10623 Berlin, Germany. Electronic address: birgit.kleinschmit@tu-berlin.de.

PMID: 33975115
DOI: 10.1016/j.scitotenv.2021.147293

Abstract

As climate change progresses, urban areas are increasingly affected by water scarcity and the urban heat island effect. Evapotranspiration (ET) is a crucial component of urban greening initiatives of cities worldwide aimed at mitigating these issues. However, ET estimation methods in urban areas have so far been limited. An expanding number of flux towers in urban environments provide the opportunity to directly measure ET by the eddy covariance method. In this study, we present a novel approach to model urban ET by combining flux footprint modeling, remote sensing and geographic information system (GIS) data, and deep learning and machine learning techniques. This approach facilitates spatio-temporal extrapolation of ET at a half-hourly resolution; we tested this approach with a two-year dataset from two flux towers in Berlin, Germany. The benefit of integrating remote sensing and GIS data into models was investigated by testing four predictor scenarios. Two algorithms (1D convolutional neural networks (CNNs) and random forest (RF)) were compared. The best-performing models were then used to model ET values for the year 2019. The inclusion of GIS data extracted using flux footprints enhanced the predictive accuracy of models, particularly when meteorological data was more limited. The best-performing scenario (meteorological and GIS data) showed an RMSE of 0.0239 mm/h and R² of 0.840 with RF and an RMSE of 0.0250 mm/h and a R² of 0.824 with 1D CNN for the more vegetated site. The 2019 ET sum was substantially higher at the site surrounded by more urban greenery (366 mm) than at the inner-city site (223 mm), demonstrating the substantial influence of vegetation on the urban water cycle. The proposed method is highly promising for modeling ET in a heterogeneous urban environment and can support climate change mitigation initiatives of urban areas worldwide.

Keywords: 1D convolutional neural networks (CNN); Deep learning; Eddy covariance; Harmonized Landsat and Sentinel-2; Latent heat flux; Urban water.