Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine Learning
Urban areas tend to be warmer than their rural surroundings, well-known as the “urban heat island” effect. Higher nocturnal air temperature (Tair) is associated with adverse effects on human health, higher mortality rates, and higher energy consumption. Prediction of the spatia...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9178414/ |
| _version_ | 1819137235907248128 |
|---|---|
| author | Stenka Vulova Fred Meier Daniel Fenner Hamideh Nouri Birgit Kleinschmit |
| author_facet | Stenka Vulova Fred Meier Daniel Fenner Hamideh Nouri Birgit Kleinschmit |
| author_sort | Stenka Vulova |
| collection | DOAJ |
| description | Urban areas tend to be warmer than their rural surroundings, well-known as the “urban heat island” effect. Higher nocturnal air temperature (Tair) is associated with adverse effects on human health, higher mortality rates, and higher energy consumption. Prediction of the spatial distribution of Tair is a step toward the “Smart City” concept, providing an early warning system for vulnerable populations. The study of the spatial distribution of urban Tair was thus far limited by the low spatial resolution of traditional data sources. Volunteered geographic information provides alternative data with higher spatial density, with citizen weather stations monitoring Tair continuously in hundreds or thousands of locations within a single city. In this article, the aim was to predict the spatial distribution of nocturnal Tair in Berlin, Germany, one day in advance at a 30-m resolution using open-source remote sensing and geodata from Landsat and Urban Atlas, crowdsourced Tair data, and machine learning (ML) methods. Results were tested with a “leave-one-date-out” training scheme (testingcrowd) and reference Tair data (testingref). Three ML algorithms were compared-Random Forest (RF), Stochastic Gradient Boosting, and Model Averaged Neural Network. The optimal model based on accuracy and computational speed is RF, with an average root mean square error (RMSE) for testingcrowd of 1.16 °C (R<sup>2</sup> = 0.512) and RMSE for testingref of 1.97 °C (R<sup>2</sup> = 0.581). Overall, the most important geographic information system (GIS) predictors were morphometric parameters and albedo. The proposed method relies on open-source datasets and can, therefore, be adapted to many cities worldwide. |
| first_indexed | 2024-12-22T10:47:39Z |
| format | Article |
| id | doaj.art-ea84ec018fb844019bc00e49404be286 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-22T10:47:39Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-ea84ec018fb844019bc00e49404be2862022-12-21T18:28:53ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01135074508710.1109/JSTARS.2020.30196969178414Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine LearningStenka Vulova0https://orcid.org/0000-0001-9083-1163Fred Meier1Daniel Fenner2https://orcid.org/0000-0003-0967-8697Hamideh Nouri3https://orcid.org/0000-0002-7424-5030Birgit Kleinschmit4https://orcid.org/0000-0002-8494-0053Geoinformation in Environmental Planning Lab, Technische Universität Berlin, Berlin, GermanyInstitute of Ecology, Technische Universität Berlin, Berlin, GermanyInstitute of Ecology, Technische Universität Berlin, Berlin, GermanyDivision of Agronomy, University of Göttingen, Göttingen, GermanyGeoinformation in Environmental Planning Lab, Technische Universität Berlin, Berlin, GermanyUrban areas tend to be warmer than their rural surroundings, well-known as the “urban heat island” effect. Higher nocturnal air temperature (Tair) is associated with adverse effects on human health, higher mortality rates, and higher energy consumption. Prediction of the spatial distribution of Tair is a step toward the “Smart City” concept, providing an early warning system for vulnerable populations. The study of the spatial distribution of urban Tair was thus far limited by the low spatial resolution of traditional data sources. Volunteered geographic information provides alternative data with higher spatial density, with citizen weather stations monitoring Tair continuously in hundreds or thousands of locations within a single city. In this article, the aim was to predict the spatial distribution of nocturnal Tair in Berlin, Germany, one day in advance at a 30-m resolution using open-source remote sensing and geodata from Landsat and Urban Atlas, crowdsourced Tair data, and machine learning (ML) methods. Results were tested with a “leave-one-date-out” training scheme (testingcrowd) and reference Tair data (testingref). Three ML algorithms were compared-Random Forest (RF), Stochastic Gradient Boosting, and Model Averaged Neural Network. The optimal model based on accuracy and computational speed is RF, with an average root mean square error (RMSE) for testingcrowd of 1.16 °C (R<sup>2</sup> = 0.512) and RMSE for testingref of 1.97 °C (R<sup>2</sup> = 0.581). Overall, the most important geographic information system (GIS) predictors were morphometric parameters and albedo. The proposed method relies on open-source datasets and can, therefore, be adapted to many cities worldwide.https://ieeexplore.ieee.org/document/9178414/Air temperaturealbedocitizen weather stations (CWS)crowdsourcingLandsaturban climate |
| spellingShingle | Stenka Vulova Fred Meier Daniel Fenner Hamideh Nouri Birgit Kleinschmit Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine Learning IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Air temperature albedo citizen weather stations (CWS) crowdsourcing Landsat urban climate |
| title | Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine Learning |
| title_full | Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine Learning |
| title_fullStr | Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine Learning |
| title_full_unstemmed | Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine Learning |
| title_short | Summer Nights in Berlin, Germany: Modeling Air Temperature Spatially With Remote Sensing, Crowdsourced Weather Data, and Machine Learning |
| title_sort | summer nights in berlin germany modeling air temperature spatially with remote sensing crowdsourced weather data and machine learning |
| topic | Air temperature albedo citizen weather stations (CWS) crowdsourcing Landsat urban climate |
| url | https://ieeexplore.ieee.org/document/9178414/ |
| work_keys_str_mv | AT stenkavulova summernightsinberlingermanymodelingairtemperaturespatiallywithremotesensingcrowdsourcedweatherdataandmachinelearning AT fredmeier summernightsinberlingermanymodelingairtemperaturespatiallywithremotesensingcrowdsourcedweatherdataandmachinelearning AT danielfenner summernightsinberlingermanymodelingairtemperaturespatiallywithremotesensingcrowdsourcedweatherdataandmachinelearning AT hamidehnouri summernightsinberlingermanymodelingairtemperaturespatiallywithremotesensingcrowdsourcedweatherdataandmachinelearning AT birgitkleinschmit summernightsinberlingermanymodelingairtemperaturespatiallywithremotesensingcrowdsourcedweatherdataandmachinelearning |