GIS Ostrava 2022 Earth Observation for Smart City and Smart Region最新文献

{"title":"A Machine Learning Detection of Outliers in InSAR Displacement Time Series","authors":"Lukáš Kubica, J. Papčo, R. Czikhardt, M. Bakon, Jan Barlak, M. Rovňák","doi":"10.31490/9788024846026-11","DOIUrl":"https://doi.org/10.31490/9788024846026-11","url":null,"abstract":"Multi-temporal SAR interferometry (InSAR) estimates the displacement time series of coherent radar scatterers. Current InSAR processing approaches often assume the same deformation model for all scatterers within the area of interest. However, this assumption is often wrong, and time series need to be approached individually. Individual, point-wise approach for large InSAR datasets is limited by high computational demands. The additional problem is imposed by the presence of outliers and phase unwrapping errors, which directly affect the estimation quality. This work describes the algorithm for (i) estimating and selecting the best displacement model for individual point time series and (ii) detecting outlying measurements in the time series. The InSAR measurement quality of individual scatterers varies, which affects the estimation methods. Therefore, our approach uses a priori variances obtained by the variance components estimation within geodetic InSAR processing. We present two different approaches for outlier detection and correction in InSAR displacement time series. The first approach uses the conventional statistical methods for individual point-wise outlier detection, such as median absolute deviation (MAD) confidence intervals around the displacement model. The second approach uses machine learning principles to cluster points based on their displacement behaviour as well as the temporal occurrence of outliers. Using clusters instead of individual points allows for more efficient analysis of average time series per cluster and consequent cluster-wise outlier detection, correction, and time-series filtering. The two approaches have been applied on the Sentinel-1 InSAR time series of a case study from monitoring landslides in Slovakia. The area of interest is affected by characteristic non-linear progression of the movement. Our post-processing procedure parameterized the displacement time series despite the presence of a non-linear motion, thus enabling reliable outlier detection and unwrapping error correction. The validation of the proposed approaches was performed on an existing network of corner reflectors located within the area of interest.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129836117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simulating Solar Radiation Under Canopy Using Point Clouds and an Hemispherical Photography Simulator","authors":"F. Pirotti, M. Piragnolo, R. Cavalli","doi":"10.31490/9788024846026-5","DOIUrl":"https://doi.org/10.31490/9788024846026-5","url":null,"abstract":"Solar radiation illuminating the canopy and reaching lower strata of vegetation is an important ecological factor that can enhance biodiversity and contribute to species composition in habitats. It is also part of the many factors that make a natural environment a positive contribution to the health and wellbeing of people interacting with it. Aerial survey methods using drones can now provide digital twins with a very high level of detail. In this work, we developed a software, lasPhotoCamSIM, for simulating hemispherical imagery using dense point clouds as input data. The simulated hemispherical images are used to map the diffuse solar radiation reaching the average height of the human eye from the ground. For the sample design, a regular grid with nodes at 0.5 m ground sampling distance and 1.5 m height from the terrain was used. The study area is a historical garden, Villa Revedin Bolasco. It was surveyed via a drone flight with three sensors, two LiDAR sensors (Riegl VUX-120 and Riegl miniVUX-3UAV) and a camera. The camera provided overlapping imagery that was used to create a third point cloud using photogrammetry. The three point clouds were used as input data to lasPhotoCamSIM together with coordinates of the nodes of the grid, resulting in ~330,000 virtual hemispherical images. Gap fraction and estimated solar diffuse radiation was calculated from each hemispheric image, and it was then converted back to a regular raster map.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130849581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Głuszyńskie Lake Water Quality Assesment Using Sentinel-2 Data","authors":"W. Ciężkowski, M. Frąk, I. Kardel, P. Popielarski, J. Chormański","doi":"10.31490/9788024846026-16","DOIUrl":"https://doi.org/10.31490/9788024846026-16","url":null,"abstract":"Traditional inland water monitoring is time and labor consuming, as well as expensive. Additionally, on its basis, only point values are obtained. Sometimes only single value represents the whole lake water quality. In the literature many remote sensing measurement based formulas for water quality parameters can be find. Ocean and marine waters are better recognized in this area. However, also for inland water some formulas can by find in literature. In this study selected formulas for 4 water quality parameters (biological oxygen demand, dissolved organic carbon, chlorophyll concentration and electrical conductivity) were applied for two-year (only vegetation season) series of Sentienl-2 images registered over the Głuszyńskie Lake, Poland. Results were validated based on measurements conducted in 2021-10-08 (one day before Sentienl-2 acquisition). Two from four validated parameters strongly correlated (R 2 =0.61 for DOC and R 2 =0.84 for EC) with field data. However, coefficients of this relationship shows that formulas from literature can show spatial distribution of these parameters and hotspots, but for correct quantitative estimation further analysis should be done to adapt formulas for local conditions.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132271047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of Vehicle Detection Using Very High-Resolution Satellite Images","authors":"Peter Golej, J. Horák","doi":"10.31490/9788024846026-17","DOIUrl":"https://doi.org/10.31490/9788024846026-17","url":null,"abstract":"Traffic can be monitored using data obtained from mobile or permanent sensors such as induction loops, bridge sensors or cameras. This is an opportunity to obtain traffic data on main roads, but data from large parts of the road network is not available. Today´s optical sensors on satellites provide images covering large areas with resolution better than 1 meter and with frequency better 1 week, which can provide us with various information. Such information is important for urban and transport planning, intelligent transport systems, emergency control etc. Panchromatic imagery from WorldView3 was processed. The pilot area for WorldView3 is located in Prague, close to the Old Town Square. Panchromatic images were processed in two software. First software was ENVI and second was CATALYST Pro. Object detection was performed, then training data were created and finally classification methods were used. ENVI offers three classification methods (SVM, PCA, KNN) and CATALYST Pro offers two classification methods (SVM, RT). The detection of vehicles was relatively successful, especially in open public places without shade or vegetation. The detection of dark vehicles had the best results. The detection of vehicles in shadow had the worst results.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128671407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Long Term Monitoring of Land Use – Land Cover Change and its Effect on Surface Temperature by Use of LANDSAT Images and Google Earth Engine Platform","authors":"E. Şengün, U. Alganci, S. Aksoy","doi":"10.31490/9788024846026-8","DOIUrl":"https://doi.org/10.31490/9788024846026-8","url":null,"abstract":"The harmful impacts of fast urbanization and population growth on nature are becoming more pronounced every day. Human demands are growing in tandem with population growth, and the most common solutions advocated to address these needs are agricultural development and urbanization. The increase in urban areas causes a decrease in forest and green areas that contribute to the occurrence of urban heat islands and an increase in surface temperature. This study, choosing the city of Istanbul, the largest metropolis of Europe, as the study area, investigates the land cover - land use (LCLU) changes and their effects on the surface temperature covering the years 2001, 2011, and 2020. To produce an urban heat island, LST data from Level 2 Collection 2 data of Landsat satellite images were used. The urban thermal field variance index (UTFVI) was calculated form the LST data, which can be considered as an indicator of urban heat islands (UHI). When the heat islands in urban regions were compared to those in rural areas, it was discovered that the heat islands in urban areas were much observable with higher surface temperature. When the UTFVI index maps of different years were compared, it is determined that UHI is increased about 21 percent between 2001 – and 2011 and by 5 percent between 2011 and 2020. These findings are also comparable with the increased amount of urban areas through these dates.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116664438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combination of OpenLandUse Database and Sentinel Data for Agriculture Purposes","authors":"P. Hájek, M. Kepka, Heřman Švenajs, D. Kozhukh, K. Charvát, F. Zadražil","doi":"10.31490/9788024846026-2","DOIUrl":"https://doi.org/10.31490/9788024846026-2","url":null,"abstract":"Creating an Earth’s twin in sufficient detail and complex relations is a challenge for the future arising from strategies like DestinE or Green Deal. Enormous amount of geospatial data available these days leads to a necessity of a suitable data structure to provide understandable information to a general user. An OpenLandUse (OLU) database can serve as such a structure for integrating datasets of different themes, different spatial resolution, and different temporal validity. This paper shows an example of incorporating Earth observation data into the Open Land Use data model, to provide enhanced information about field blocks of a farm in Vyškov region in CZE with information about crop types planted in fields. The data for enhancing the OLU database were based on Sentinel-1 and Sentinel-2 images from 2020, analysed into the form of supervised classification of crop types and various indexes, especially Enhanced Vegetation Index (EVI) and Radar Vegetation Index for Sentinel-1 SAR data (RVI4S1).","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"279 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133271548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revisiting Czech System for InSAR Monitoring Using Sentinel-1 Data","authors":"M. Lazecký","doi":"10.31490/9788024846026-14","DOIUrl":"https://doi.org/10.31490/9788024846026-14","url":null,"abstract":"This contribution will revisit a complex system established to prepare analysis ready data from Copernicus Sentinel-1 satellite system, primarily to allow independent interferometric (InSAR) measurements of terrain deformation over Czechia, in both local and nation-wide scale. With the high revisit rate of 6 days, medium ground resolution of several meters and sensitivity to millimetric motion in the satellite line of sight (LOS), the quality of InSAR results from Sentinel-1 are applicable practically. This contribution will present results over selected areas of interest in Czechia, where a subsidence or other deformation was detected.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125968548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping Canopy-Level Crop Traits Using Top-of-Atmosphere Sentinel-2 Data in Google Earth Engine","authors":"J. Estévez, K. Berger, Matías Salinero-Delgado, L. Pipia, J. Vicent, J. P. Rivera-Caicedo, Matthias Wocher, P. Reyes-Muñoz, G. Tagliabue, M. Boschetti, J. Verrelst","doi":"10.31490/9788024846026-15","DOIUrl":"https://doi.org/10.31490/9788024846026-15","url":null,"abstract":"To take advantage of the vast amount of remote sensing data, cloud computing platforms such as Google Earth Engine (GEE) open new possibilities to develop crop trait retrieval models applicable to any corner of the world. In the present study, we implemented hybrid models directly in GEE for processing Sentinel-2 (S2) top-of-atmosphere (TOA) reflectance data into crop traits. To achieve this, a training dataset was generated using the leaf-canopy RTM PROSAIL in combination with the atmospheric model 6SV. Gaussian processes regression (GPR) retrieval models were then established for 4 canopy-level crop traits namely: leaf area index, canopy chlorophyll content, canopy water content and canopy dry matter content. Successful reduction of the training dataset by 78% was achieved using the active learning technique Euclidean distance-based diversity (EBD). The EBD-GPR model showed moderate to good performance against in situ data over an independent study site (Grosseto, Italy). Obtained maps compared against ESA Sentinels' Application Platform (SNAP) vegetation estimates showed high consistency of both retrievals. Finally, local and national scale maps were successfully generated in GEE, with additionally providing uncertainties. In summary, the proposed retrieval workflow demonstrates the possibility of routine processing S2 TOA data into crop trait maps at any place on Earth as required for operational agricultural applications.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116026865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Detection of New Building Construction from Sentinel-1 Multi-temporal Imagery","authors":"I. Hlaváčová, M. Kačmařík, M. Lazecký, J. Struhár, P. Rapant","doi":"10.31490/9788024846026-4","DOIUrl":"https://doi.org/10.31490/9788024846026-4","url":null,"abstract":"An automatic processing chain for detecting a new building construction solely from multitemporal satellite synthetic aperture radar data was developed and introduced in the paper. Although it was developed while utilising Sentinel-1 imagery, it can be adapted to other satellite radar systems. The solution was developed to be used mainly in protected critical infrastructure zones to identify prohibited constructions. In order to eliminate detection of changes happening on natural surfaces due to common agricultural works or seasonal changes in vegetation, the algorithm mainly uses a combination of a backscatter change statistical evaluation and coherence change evaluation. The solution was first tested in a selected area, including urban and natural environments. Although mean success in detecting a new building construction from a single track was only 36%, processing data from more tracks significantly increased the probability of a new building detection, especially of the larger ones.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121594251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identification of the Factors Conditioning the Susceptibility of Natural and Man-Made Hazards in an Urban Context","authors":"A. Vavassori, Angelly De Jesús Pugliese Viloria, M. Brovelli","doi":"10.31490/9788024846026-10","DOIUrl":"https://doi.org/10.31490/9788024846026-10","url":null,"abstract":"The problem of multi-hazard mapping in urban areas is relevant for preventing and mitigating the impact of natural and human-induced disasters and it is a very complex one because different expertises have to be put together. Single-hazard maps may be produced by taking advantage of Machine and Deep Learning techniques, once the factors conditioning the susceptibility of the hazard are defined and relevant data inventory is collected. From a proper combination of single-hazard maps, a multi-hazard map may be derived. The objective of this study is the identification of the conditioning factors for the most relevant natural and human-induced hazards in an urban context through an exhaustive literature review. All factors found in the literature were methodically listed in tables and order of importance was assigned to each factor depending on the number of citations of each paper and on the number of publications in which such a factor was taken into account. The resulting list will be then validated with domain experts. The obtained results can be used for the production of single and multi-hazard susceptibility maps in urban areas.","PeriodicalId":419801,"journal":{"name":"GIS Ostrava 2022 Earth Observation for Smart City and Smart Region","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128599610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}