Traffic flows form a complex system, especially in the context of urban sprawl. Direct estimation of traffic flows requires significant efforts and knowing in advance where to focus the study and where to place tools ...Traffic flows form a complex system, especially in the context of urban sprawl. Direct estimation of traffic flows requires significant efforts and knowing in advance where to focus the study and where to place tools to directly measure traffic flows, and consequently traffic congestion could lead to significant savings in time and money. In the case of Rome municipality, we have monitored a situation in which a very high rate of urban fragmentation has occurred in the last 30 years, making the direct estimation of traffic difficult. The work described here can help to solve the problem of estimating traffic flows and in particular the congestion phenomenon through a very cheap approach by using remote sensing and geographical information system technology. This method is based on the identification of attractor points that draw traffic flows such as malls, schools, offices, shops, etc. that is to say, points in a territory that attract a certain number of people with vehicles (estimated with a scale) in specific periods of the day. The identification of those points and the calculation of the urban density through the satellite image processing have allowed the creation of a congestion map for the study area. Then the road network and the buildings have been classified according to the congestion values. The results highlight the most critical and congested areas that affect the traffic flows and impact the quality of life.展开更多
Current vegetation indices and biophysical parameters derived from optical satellite data for forest monitoring are widely used in various applications but can be limited by atmospheric effects like clouds.Synthetic a...Current vegetation indices and biophysical parameters derived from optical satellite data for forest monitoring are widely used in various applications but can be limited by atmospheric effects like clouds.Synthetic aperture radar(SAR)data can offer insightful and systematic forest monitoring with complete time series due to signal penetration through clouds and day and night image acquisitions.This study explores the use of SAR data,combined with ancillary data and machine learning(ML),to estimate forest parameters typically derived from optical satellites.It investigates whether SAR signals provide sufficient information for the accurate estimation of these parameters,focusing on two spectral vegetation indices(Normalized Difference Vegetation Index-NDVI and Enhanced Vegetation Index-EVI)and two biophysical parameters(Leaf Area Index-LAI and Fraction of Absorbed Photosynthetically Active Radiation-FAPAR)in healthy and disturbed temperate forests in Czechia and Central Europe in 2021.Vegetation metrics derived from Sentinel-2 multispectral data were used to evaluate the results.A paired multi-modal time-series dataset was created using Google Earth Engine(GEE),including temporally and spatially aligned Sentinel-1,Sentinel-2,DEM-based features and meteorological variables,along with a forest type class.The inclusion of DEM-based auxiliary features and additional meteorological information improved the results.In the comparison of ML models,the traditional ML algorithms,Random Forest Regressor and Extreme Gradient Boosting(XGB)slightly outperformed the Automatic Machine Learning(AutoML)approach,auto-sklearn,for all forest parameters,achieving high accuracies(R2 between 70%and 86%)and low errors(0.055-0.29 of mean absolute error).XGB was the most computationally efficient.Moreover,SAR-based estimations over Central Europe achieved comparable results to those obtained in testing within Czechia,demonstrating their transferability for large-scale modeling.A key advantage of the SAR-based vegetation metrics is the ability to detect abrupt forest changes with sub-weekly temporal accuracy,providing up to 240 measurements per year at a 20 m resolution.展开更多
文摘Traffic flows form a complex system, especially in the context of urban sprawl. Direct estimation of traffic flows requires significant efforts and knowing in advance where to focus the study and where to place tools to directly measure traffic flows, and consequently traffic congestion could lead to significant savings in time and money. In the case of Rome municipality, we have monitored a situation in which a very high rate of urban fragmentation has occurred in the last 30 years, making the direct estimation of traffic difficult. The work described here can help to solve the problem of estimating traffic flows and in particular the congestion phenomenon through a very cheap approach by using remote sensing and geographical information system technology. This method is based on the identification of attractor points that draw traffic flows such as malls, schools, offices, shops, etc. that is to say, points in a territory that attract a certain number of people with vehicles (estimated with a scale) in specific periods of the day. The identification of those points and the calculation of the urban density through the satellite image processing have allowed the creation of a congestion map for the study area. Then the road network and the buildings have been classified according to the congestion values. The results highlight the most critical and congested areas that affect the traffic flows and impact the quality of life.
基金supported by the Charles University Grant Agency-GrantováAgentura Univerzity Karlovy(GAUK)Grant No.[412722]the European Union’s Caroline Herschel Framework Partnership Agreement on Copernicus User Uptake under grant agreement No.[FPA 275/G/GRO/COPE/17/10042]+2 种基金project FPCUP(Framework Partnership Agreement on Copernicus User Uptake)The authors would like to thank the Spatial Data Analyst project(NPO_UK_MSMT-16602/2022)funded by the European Union-NextGenerationEU,for providing computational resources needed for AutoMLDaniel Paluba would like to thank the Erasmus+programme for the financial support during his research stay at theΦ-lab,European Space Agency(ESA)in Frascati,Italy.
文摘Current vegetation indices and biophysical parameters derived from optical satellite data for forest monitoring are widely used in various applications but can be limited by atmospheric effects like clouds.Synthetic aperture radar(SAR)data can offer insightful and systematic forest monitoring with complete time series due to signal penetration through clouds and day and night image acquisitions.This study explores the use of SAR data,combined with ancillary data and machine learning(ML),to estimate forest parameters typically derived from optical satellites.It investigates whether SAR signals provide sufficient information for the accurate estimation of these parameters,focusing on two spectral vegetation indices(Normalized Difference Vegetation Index-NDVI and Enhanced Vegetation Index-EVI)and two biophysical parameters(Leaf Area Index-LAI and Fraction of Absorbed Photosynthetically Active Radiation-FAPAR)in healthy and disturbed temperate forests in Czechia and Central Europe in 2021.Vegetation metrics derived from Sentinel-2 multispectral data were used to evaluate the results.A paired multi-modal time-series dataset was created using Google Earth Engine(GEE),including temporally and spatially aligned Sentinel-1,Sentinel-2,DEM-based features and meteorological variables,along with a forest type class.The inclusion of DEM-based auxiliary features and additional meteorological information improved the results.In the comparison of ML models,the traditional ML algorithms,Random Forest Regressor and Extreme Gradient Boosting(XGB)slightly outperformed the Automatic Machine Learning(AutoML)approach,auto-sklearn,for all forest parameters,achieving high accuracies(R2 between 70%and 86%)and low errors(0.055-0.29 of mean absolute error).XGB was the most computationally efficient.Moreover,SAR-based estimations over Central Europe achieved comparable results to those obtained in testing within Czechia,demonstrating their transferability for large-scale modeling.A key advantage of the SAR-based vegetation metrics is the ability to detect abrupt forest changes with sub-weekly temporal accuracy,providing up to 240 measurements per year at a 20 m resolution.
