Amirhossein Hassani, Gabriela Sousa Santos, Philipp Schneider, Núria Castell
{"title":"插值,基于卫星的机器学习,还是气象模拟?城市中尺度气温时空制图的对比分析","authors":"Amirhossein Hassani, Gabriela Sousa Santos, Philipp Schneider, Núria Castell","doi":"10.1007/s10666-023-09943-9","DOIUrl":null,"url":null,"abstract":"Abstract Fine-resolution spatio-temporal maps of near-surface urban air temperature ( T a ) provide crucial data inputs for sustainable urban decision-making, personal heat exposure, and climate-relevant epidemiological studies. The recent availability of IoT weather station data allows for high-resolution urban T a mapping using approaches such as interpolation techniques or machine learning (ML). This study is aimed at executing these approaches and traditional numerical modeling within a practical and operational framework and evaluate their practicality and efficiency in cases where data availability, computational constraints, or specialized expertise pose challenges. We employ Netatmo crowd-sourced weather station data and three geospatial mapping approaches: (1) Ordinary Kriging, (2) statistical ML model (using predictors primarily derived from Earth Observation Data), and (3) weather research and forecasting model (WRF) to predict/map daily T a at nearly 1-km spatial resolution in Warsaw (Poland) for June–September and compare the predictions against observations from 5 meteorological reference stations. The results reveal that ML can serve as a viable alternative approach to traditional kriging and numerical simulation, characterized by reduced complexity and higher computational speeds within the domain of urban meteorological studies (overall RMSE = 1.06 °C and R 2 = 0.94, compared to ground-based meteorological stations). The results have implications for identifying the urban regions vulnerable to overheating and evidence-based urban management in response to climate change. Due to the open-sourced nature of the applied predictors and input parsimony, the ML method can be easily replicated for other EU cities.","PeriodicalId":50515,"journal":{"name":"Environmental Modeling & Assessment","volume":"6 1","pages":"0"},"PeriodicalIF":2.7000,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Interpolation, Satellite-Based Machine Learning, or Meteorological Simulation? A Comparison Analysis for Spatio-temporal Mapping of Mesoscale Urban Air Temperature\",\"authors\":\"Amirhossein Hassani, Gabriela Sousa Santos, Philipp Schneider, Núria Castell\",\"doi\":\"10.1007/s10666-023-09943-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Fine-resolution spatio-temporal maps of near-surface urban air temperature ( T a ) provide crucial data inputs for sustainable urban decision-making, personal heat exposure, and climate-relevant epidemiological studies. The recent availability of IoT weather station data allows for high-resolution urban T a mapping using approaches such as interpolation techniques or machine learning (ML). This study is aimed at executing these approaches and traditional numerical modeling within a practical and operational framework and evaluate their practicality and efficiency in cases where data availability, computational constraints, or specialized expertise pose challenges. We employ Netatmo crowd-sourced weather station data and three geospatial mapping approaches: (1) Ordinary Kriging, (2) statistical ML model (using predictors primarily derived from Earth Observation Data), and (3) weather research and forecasting model (WRF) to predict/map daily T a at nearly 1-km spatial resolution in Warsaw (Poland) for June–September and compare the predictions against observations from 5 meteorological reference stations. The results reveal that ML can serve as a viable alternative approach to traditional kriging and numerical simulation, characterized by reduced complexity and higher computational speeds within the domain of urban meteorological studies (overall RMSE = 1.06 °C and R 2 = 0.94, compared to ground-based meteorological stations). The results have implications for identifying the urban regions vulnerable to overheating and evidence-based urban management in response to climate change. Due to the open-sourced nature of the applied predictors and input parsimony, the ML method can be easily replicated for other EU cities.\",\"PeriodicalId\":50515,\"journal\":{\"name\":\"Environmental Modeling & Assessment\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2023-11-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Environmental Modeling & Assessment\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s10666-023-09943-9\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Modeling & Assessment","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s10666-023-09943-9","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Interpolation, Satellite-Based Machine Learning, or Meteorological Simulation? A Comparison Analysis for Spatio-temporal Mapping of Mesoscale Urban Air Temperature
Abstract Fine-resolution spatio-temporal maps of near-surface urban air temperature ( T a ) provide crucial data inputs for sustainable urban decision-making, personal heat exposure, and climate-relevant epidemiological studies. The recent availability of IoT weather station data allows for high-resolution urban T a mapping using approaches such as interpolation techniques or machine learning (ML). This study is aimed at executing these approaches and traditional numerical modeling within a practical and operational framework and evaluate their practicality and efficiency in cases where data availability, computational constraints, or specialized expertise pose challenges. We employ Netatmo crowd-sourced weather station data and three geospatial mapping approaches: (1) Ordinary Kriging, (2) statistical ML model (using predictors primarily derived from Earth Observation Data), and (3) weather research and forecasting model (WRF) to predict/map daily T a at nearly 1-km spatial resolution in Warsaw (Poland) for June–September and compare the predictions against observations from 5 meteorological reference stations. The results reveal that ML can serve as a viable alternative approach to traditional kriging and numerical simulation, characterized by reduced complexity and higher computational speeds within the domain of urban meteorological studies (overall RMSE = 1.06 °C and R 2 = 0.94, compared to ground-based meteorological stations). The results have implications for identifying the urban regions vulnerable to overheating and evidence-based urban management in response to climate change. Due to the open-sourced nature of the applied predictors and input parsimony, the ML method can be easily replicated for other EU cities.
期刊介绍:
Environmental Modeling & Assessment strives to achieve this by publishing high quality, peer-reviewed papers that may be regarded as either instances of best practice, or as studies that advance the evolution and applicability of the theories and techniques of modeling and assessment. Consequently, Environmental Modeling & Assessment will publish high quality papers on all aspects of environmental problems that contain a significant quantitative modeling or analytic component, interpreted broadly. In particular, we are interested both in detailed scientific models of specific environmental problems and in large scale models of the global environment.
We invite models of environmental problems and phenomena that utilise, in an original way, the techniques of ordinary and partial differential equations, simulation, statistics and applied probability, control theory, operations research, mathematical economics, and game theory.
Emphasis will be placed on the novelty of the model, the environmental relevance of the problem, and the generic applicability of the techniques used. Generally, papers should be written in a manner that is accessible to a wide interdisciplinary audience.