Centre dedocumentation
scientifique

Estimating spatio-temporal air temperature in London (UK) using machine learning and earth observation satellite data / Rochelle Schneider dos Santos in International journal of applied Earth observation and geoinformation, vol 88 (June 2020)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 88 (June 2020) . - 10 p. Titre : Estimating spatio-temporal air temperature in London (UK) using machine learning and earth observation satellite data Type de document : Article/Communication Auteurs : Rochelle Schneider dos Santos, Auteur Année de publication : 2020 Article en page(s) : 10 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] algorithme du gradient [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] chaleur [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] ilot thermique urbain [Termes descripteurs IGN] image MODIS [Termes descripteurs IGN] Londres [Termes descripteurs IGN] modèle de régression [Termes descripteurs IGN] mortalité [Termes descripteurs IGN] Normalized Difference Vegetation Index [Termes descripteurs IGN] politique publique [Termes descripteurs IGN] Python (langage de programmation) [Termes descripteurs IGN] régression linéaire [Termes descripteurs IGN] santé [Termes descripteurs IGN] station météorologique [Termes descripteurs IGN] température au sol [Termes descripteurs IGN] température de l'air [Termes descripteurs IGN] zone urbaine Résumé : (auteur) Urbanisation generates greater population densities and an increase in anthropogenic heat generation. These factors elevate the urban–rural air temperature (Ta) difference, thus generating the Urban Heat Island (UHI) phenomenon. Ta is used in the fields of public health and epidemiology to quantify deaths attributable to heat in cities around the world: the presence of UHI can exacerbate exposure to high temperatures during summer periods, thereby increasing the risk of heat-related mortality. Measuring and monitoring the spatial patterns of Ta in urban contexts is challenging due to the lack of a good network of weather stations. This study aims to produce a parsimonious model to retrieve maximum Ta (Tmax) at high spatio-temporal resolution using Earth Observation (EO) satellite data. The novelty of this work is twofold: (i) it will produce daily estimations of Tmax for London at 1 km2 during the summertime between 2006 and 2017 using advanced statistical techniques and satellite-derived predictors, and (ii) it will investigate for the first time the predictive power of the gradient boosting algorithm to estimate Tmax for an urban area. In this work, 6 regression models were calibrated with 6 satellite products, 3 geospatial features, and 29 meteorological stations. Stepwise linear regression was applied to create 9 groups of predictors, which were trained and tested on each regression method. This study demonstrates the potential of machine learning algorithms to predict Tmax: the gradient boosting model with a group of five predictors (land surface temperature, Julian day, normalised difference vegetation index, digital elevation model, solar zenith angle) was the regression model with the best performance (R² = 0.68, MAE = 1.60 °C, and RMSE = 2.03 °C). This methodological approach is capable of being replicated in other UK cities, benefiting national heat-related mortality assessments since the data (provided by NASA and the UK Met Office) and programming languages (Python) sources are free and open. This study provides a framework to produce a high spatio-temporal resolution of Tmax, assisting public health researchers to improve the estimation of mortality attributable to high temperatures. In addition, the research contributes to practice and policy-making by enhancing the understanding of the locations where mortality rates may increase due to heat. Therefore, it enables a more informed decision-making process towards the prioritisation of actions to mitigate heat-related mortality amongst the vulnerable population. Numéro de notice : A2020-448 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.jag.2020.102066 date de publication en ligne : 10/02/2020 En ligne : https://doi.org/10.1016/j.jag.2020.102066 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95524 [article]

Street-Frontage-Net: urban image classification using deep convolutional neural networks / Stephen Law in International journal of geographical information science IJGIS, vol 34 n° 4 (April 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 4 (April 2020) . - pp 681- 707 Titre : Street-Frontage-Net: urban image classification using deep convolutional neural networks Type de document : Article/Communication Auteurs : Stephen Law, Auteur ; Chanuki Illushka Seresinhe, Auteur ; Yao Shen, Auteur Année de publication : 2020 Article en page(s) : pp 681- 707 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] espace public [Termes descripteurs IGN] évaluation foncière [Termes descripteurs IGN] extraction de données [Termes descripteurs IGN] façade [Termes descripteurs IGN] habitat urbain [Termes descripteurs IGN] image Streetview [Termes descripteurs IGN] immobilier (secteur) [Termes descripteurs IGN] information géographique [Termes descripteurs IGN] Londres [Termes descripteurs IGN] matrice de confusion [Termes descripteurs IGN] Paris (75) [Termes descripteurs IGN] paysage urbain [Termes descripteurs IGN] urbanisme [Termes descripteurs IGN] vision par ordinateur Résumé : (auteur) Quantifying aspects of urban design on a massive scale is crucial to help develop a deeper understanding of urban designs elements that contribute to the success of a public space. In this study, we further develop the Street-Frontage-Net (SFN), a convolutional neural network (CNN) that can successfully evaluate the quality of street frontage as either being active (frontage containing windows and doors) or blank (frontage containing walls, fences and garages). Small-scale studies have indicated that the more active the frontage, the livelier and safer a street feels. However, collecting the city-level data necessary to evaluate street frontage quality is costly. The SFN model uses a deep CNN to classify the frontage of a street. This study expands on the previous research via five experiments. We find robust results in classifying frontage quality for an out-of-sample test set that achieves an accuracy of up to 92.0%. We also find active frontages in a neighbourhood has a significant link with increased house prices. Lastly, we find that active frontage is associated with more scenicness compared to blank frontage. While further research is needed, the results indicate the great potential for using deep learning methods in geographic information extraction and urban design. Numéro de notice : A2020-110 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1555832 date de publication en ligne : 26/12/2018 En ligne : https://doi.org/10.1080/13658816.2018.1555832 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94712 [article]

Exploring the synergy between Landsat and ASAR towards improving thematic mapping accuracy of optical EO data / Alexander Cass in Applied geomatics, vol 11 n° 3 (September 2019)  

Public [article]  inApplied geomatics > vol 11 n° 3 (September 2019) . - pp 277 - 288 Titre : Exploring the synergy between Landsat and ASAR towards improving thematic mapping accuracy of optical EO data Type de document : Article/Communication Auteurs : Alexander Cass, Auteur ; George P. Petropoulos, Auteur ; Konstantinos P. Ferentinos, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 277 - 288 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes descripteurs IGN] carte d'occupation du sol [Termes descripteurs IGN] cartographie thématique [Termes descripteurs IGN] classification orientée objet [Termes descripteurs IGN] image Envisat-ASAR [Termes descripteurs IGN] image Landsat-TM [Termes descripteurs IGN] image optique [Termes descripteurs IGN] image radar [Termes descripteurs IGN] Pays de Galles [Termes descripteurs IGN] surface cultivée Résumé : (Auteur) Earth Observation (EO) provides a unique means of obtaining information on land use/cover and of its changes, which is of key importance in many scientific and practical applications. EO data is already widely used, for example, in environmental practices or decision-making related to food availability and security. As such, it is imperative to examine the suitability of different EO datasets, including their synergies, in respect to their ability to create products and tools for such practices and to guide effectively such decisions. This work aims at exploring the added value of the synergistic use of optical and radar data (from the Landsat TM and Advanced Synthetic Aperture Radar (ASAR) sensors respectively). Such information can help towards improving the accuracy of land cover classifications from EO datasets. As a case study, the region of Wales in the UK has been used. Two classifications—one based on optical data alone and another one developed from the synergy of optical and RADAR datasets acquired nearly, concurrently were developed for the studied region. Evaluation of the derived land/use cover maps was performed on the basis of the confusion matrix using validation points derived from a Phase 1 habitat map of Wales. The results showed 15% increase in overall accuracy (84% from 69%) and kappa coefficient (0.81 from 0.65) using the synergistic approach over the scenario where only optical data were used in the classification. In addition, McNemar’s test was used to assess the statistical significance of the obtained results. Results of this test provided further confirmed that the use of optical data synergistically with the radar data provides more accurate land use/cover maps in comparison with the use of optical data alone. Numéro de notice : A2019-461 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s12518-019-00258-7 date de publication en ligne : 13/04/2019 En ligne : https://doi.org/10.1007/s12518-019-00258-7 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93601 [article]

Improving public data for building segmentation from Convolutional Neural Networks (CNNs) for fused airborne lidar and image data using active contours / David Griffiths in ISPRS Journal of photogrammetry and remote sensing, vol 154 (August 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 154 (August 2019) . - pp 70 - 83 Titre : Improving public data for building segmentation from Convolutional Neural Networks (CNNs) for fused airborne lidar and image data using active contours Type de document : Article/Communication Auteurs : David Griffiths, Auteur ; Jan Boehm, Auteur Année de publication : 2019 Article en page(s) : pp 70 - 83 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] bati [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection de contours [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] données publiques [Termes descripteurs IGN] fusion de données [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] Royaume-Uni [Termes descripteurs IGN] scène urbaine [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] zone rurale Résumé : (Auteur) Robust and reliable automatic building detection and segmentation from aerial images/point clouds has been a prominent field of research in remote sensing, computer vision and point cloud processing for a number of decades. One of the largest issues associated with deep learning methods is the high quantity of data required for training. To help address this we present a method to improve public GIS building footprint labels by using Morphological Geodesic Active Contours (MorphGACs). We demonstrate by improving the quality of building footprint labels for detection and semantic segmentation, more robust and reliable models can be obtained. We evaluate these methods over a large UK-based dataset of 24556 images containing 169835 building instances. This is achieved by training several Mask/Faster R-CNN and RetinaNet deep convolutional neural networks. Networks are supplied with both RGB and fused RGB-lidar data. We offer quantitative analysis on the benefits of the inclusion of depth data for building segmentation. By employing both methods we achieve a detection accuracy of 0.92 (mAP@0.5) and segmentation f1 scores of 0.94 over a 4911 test images ranging from urban to rural scenes. Numéro de notice : A2019-265 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.05.013 date de publication en ligne : 06/06/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.05.013 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93079 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019081	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019083	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019082	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Geographic space as a living structure for predicting human activities using big data / Bin Jiang in International journal of geographical information science IJGIS, Vol 33 n° 3-4 (March - April 2019)  

Public [article]  inInternational journal of geographical information science IJGIS > Vol 33 n° 3-4 (March - April 2019) . - pp 764 - 779 Titre : Geographic space as a living structure for predicting human activities using big data Type de document : Article/Communication Auteurs : Bin Jiang, Auteur ; Zheng Ren, Auteur Année de publication : 2019 Article en page(s) : pp 764 - 779 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] données issues des réseaux sociaux [Termes descripteurs IGN] données massives [Termes descripteurs IGN] information topologique [Termes descripteurs IGN] métadonnées [Termes descripteurs IGN] mise à l'échelle [Termes descripteurs IGN] OpenStreetMap [Termes descripteurs IGN] polygone de Thiessen [Termes descripteurs IGN] représentation des détails topographiques [Termes descripteurs IGN] Royaume-Uni Résumé : (Auteur) Inspired by Christopher Alexander’s conception of the world – space is not lifeless or neutral, but a living structure involving far more small things than large ones – a topological representation has been previously developed to characterize the living structure or the wholeness of geographic space. This paper further develops the topological representation and living structure for predicting human activities in geographic space. Based on millions of street nodes of the United Kingdom extracted from OpenStreetMap, we established living structures at different levels of scale in a nested manner. We found that tweet locations at different levels of scale, such as country and city, can be well predicted by the underlying living structure. The high predictability demonstrates that the living structure and the topological representation are efficient and effective for better understanding geographic forms. Based on this major finding, we argue that the topological representation is a truly multiscale representation, and point out that existing geographic representations are essentially single scale, so they bear many scale problems such as modifiable areal unit problem, the conundrum of length and the ecological fallacy. We further discuss on why the living structure is an efficient and effective instrument for structuring geospatial big data, and why Alexander’s organic worldview constitutes the third view of space. Numéro de notice : A2019-215 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2018.1427754 date de publication en ligne : 31/01/2018 En ligne : https://doi.org/10.1080/13658816.2018.1427754 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92687 [article]

Réservation

Réserver ce document

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2019032	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
079-2019031	SL	Revue	Centre de documentation	Revues en salle	Disponible

Aerial data acquisition for a digital railway / James Dunthorne in GIM international, vol 32 n° 4 (July - August 2018)  

Permalink

Exploring the sensitivity of coastal inundation modelling to DEM vertical error / Harry West in International journal of geographical information science IJGIS, vol 32 n° 5-6 (May - June 2018)  

Permalink

Improving the analysis of biogeochemical patterns associated with internal waves in the strait of Gibraltar using remote sensing images / Gabriel Navarro in Estuarine, Coastal and Shelf Science, vol 204 (May 2018)  

Permalink

A review of the effects of forest management intensity on ecosystem services for northern European temperate forests with a focus on the UK / Louise Sing in Forestry, an international journal of forest research, vol 91 n° 2 (April 2018)  

Permalink

Graph-based matching of points-of-interest from collaborative geo-datasets / Tessio Novack in ISPRS International journal of geo-information, vol 7 n° 3 (March 2018)  

Permalink

Extraction of pluvial flood relevant volunteered geographic information (VGI) by deep learning from user generated texts and photos / Yu Feng in ISPRS International journal of geo-information, vol 7 n° 2 (February 2018)  

Permalink

Pensez à l'échelle du monde pour maîtriser le temps en France et en Grande-Bretagne, 1870-1914 / Isabelle Avila in Cartes & Géomatique, n° 234 (décembre 2017) 

Permalink

Depicting urban boundaries from a mobility network of spatial interactions : a case study of Great Britain with geo-located Twitter data / Junjun Yin in International journal of geographical information science IJGIS, vol 31 n° 7-8 (July - August 2017)  

Permalink

A GIS approach to exploring monetary value on enclosure era property-related maps / Christopher Macdonald Hewitt in Cartographic journal (the), Vol 54 n° 2 (May 2017)  

Permalink

A method for matching crowd-sourced and authoritative geospatial data / Heshan Du in Transactions in GIS, vol 21 n° 2 (April 2017)  

Permalink