Centre dedocumentation
scientifique

GIS and machine learning for analysing influencing factors of bushfires using 40-year spatio-temporal bushfire data / Wanqin He in ISPRS International journal of geo-information, vol 11 n° 6 (June 2022)  

Public [article]  inISPRS International journal of geo-information > vol 11 n° 6 (June 2022) . - n° 336 Titre : GIS and machine learning for analysing influencing factors of bushfires using 40-year spatio-temporal bushfire data Type de document : Article/Communication Auteurs : Wanqin He, Auteur ; Sara Shirowzhan, Auteur ; Christopher Pettit, Auteur Année de publication : 2022 Article en page(s) : n° 336 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] analyse diachronique [Termes IGN] apprentissage automatique [Termes IGN] brousse [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] coefficient de corrélation [Termes IGN] données météorologiques [Termes IGN] données spatiotemporelles [Termes IGN] humidité du sol [Termes IGN] incendie [Termes IGN] indice de végétation [Termes IGN] Nouvelle-Galles du Sud [Termes IGN] prévention des risques [Termes IGN] régression linéaire [Termes IGN] Spark [Termes IGN] système d'information géographique [Termes IGN] température de l'air Résumé : (auteur) The causes of bushfires are extremely complex, and their scale of burning and probability of occurrence are influenced by the interaction of a variety of factors such as meteorological factors, topography, human activity and vegetation type. An in-depth understanding of the combined mechanisms of factors affecting the occurrence and spread of bushfires is needed to support the development of effective fire prevention plans and fire suppression measures and aid planning for geographic, ecological maintenance and urban emergency management. This study aimed to explore how bushfires, meteorological variability and other natural factors have interacted over the past 40 years in NSW Australia and how these influencing factors synergistically drive bushfires. The CSIRO’s Spark toolkit has been used to simulate bushfire burning spread over 24 h. The study uses NSW wildfire data from 1981–2020, combined with meteorological factors (temperature, precipitation, wind speed), vegetation data (NDVI data, vegetation type) and topography (slope, soil moisture) data to analyse the relationship between bushfires and influencing factors quantitatively. Machine learning-random forest regression was then used to determine the differences in the influence of bushfire factors on the incidence and burn scale of bushfires. Finally, the data on each influence factor was imported into Spark, and the results of the random forest model were used to set different influence weights in Spark to visualise the spread of bushfires burning over 24 h in four hotspot regions of bushfire in NSW. Wind speed, air temperature and soil moisture were found to have the most significant influence on the spread of bushfires, with the combined contribution of these three factors exceeding 60%, determining the spread of bushfires and the scale of burning. Precipitation and vegetation showed a greater influence on the annual frequency of bushfires. In addition, burn simulations show that wind direction influences the main direction of fire spread, whereas the shape of the flame front is mainly due to the influence of land classification. Besides, the simulation results from Spark could predict the temporal and spatial spread of fire, which is a potential decision aid for fireproofing agencies. The results of this study can inform how fire agencies can better understand fire occurrence mechanisms and use bushfire prediction and simulation techniques to support both their operational (short-term) and strategic (long-term) fire management responses and policies. Numéro de notice : A2022-481 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi11060336 Date de publication en ligne : 05/06/2022 En ligne : https://doi.org/10.3390/ijgi11060336 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100894 [article]

A voxel-based method for the three-dimensional modelling of heathland from lidar point clouds: first results / N. Homainejad in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-3-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-3-2022 (2022 edition) . - pp 697 - 704 Titre : A voxel-based method for the three-dimensional modelling of heathland from lidar point clouds: first results Type de document : Article/Communication Auteurs : N. Homainejad, Auteur ; Sisi Zlatanova, Auteur ; Norbert Pfeifer, Auteur Année de publication : 2022 Article en page(s) : pp 697 - 704 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] canopée [Termes IGN] classification par nuées dynamiques [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] incendie de forêt [Termes IGN] lande [Termes IGN] modélisation 3D [Termes IGN] Nouvelle-Galles du Sud [Termes IGN] segmentation en régions [Termes IGN] semis de points [Termes IGN] voxel Résumé : (auteur) Bushfires are an intrinsic part of the New South Wales’ (NSW) environment in Australia, especially in the Blue Mountains region (11400km2), that is dominated by fire prone vegetation that includes heathland. Many of the Australian native plants in this region are fire-prone and combustible, and many species even require fire to regenerate. The classification of the lateral and vertical distribution of living vegetation is necessary to manage the complexity of bushfires. Currently, interpretation of aerial and satellite images is the prevalent method for the classification of vegetation in NSW. The result does not represent important vegetation structural attributes, such as vegetation height, subcanopy height, and destiny. This paper presents an automated method for the three-dimensional modelling of heathland and important heathland parameters, such as heath shrub height and continuity, and sparse tree and mallee height and density in support of bushfire behaviour modelling. For this study airborne lidar point clouds with a density of 120 points per square meter are used. For the processing and modelling the study is divided into a point cloud processing phase and a voxel-based modelling phase. The point cloud processing phase consists of the normalisation of the height and extraction of the above ground vegetation, while the voxel phase consists of seeded region growing for segmentation, and K-means clustering for the classification of the vegetation into three different canopy layers: a) heath shrubs, b) sparse trees and mallee, c) tall trees. Numéro de notice : A2022-436 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-3-2022-697-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-3-2022-697-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100783 [article]

Deep learning for wildfire progression monitoring using SAR and optical satellite image time series / Puzhao Zhang (2021)  

Public Titre : Deep learning for wildfire progression monitoring using SAR and optical satellite image time series Type de document : Thèse/HDR Auteurs : Puzhao Zhang, Auteur Editeur : Stockholm : Royal Institute of Technology Année de publication : 2021 Importance : 100 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-91-7873-935-6 Note générale : bibliographie Doctoral Thesis in Geoinformatics Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] Alberta (Canada) [Termes IGN] apprentissage profond [Termes IGN] bande C [Termes IGN] Californie (Etats-Unis) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] Colombie-Britannique (Canada) [Termes IGN] détection de changement [Termes IGN] gestion des risques [Termes IGN] image radar moirée [Termes IGN] image Sentinel-SAR [Termes IGN] incendie de forêt [Termes IGN] série temporelle [Termes IGN] surveillance forestière [Termes IGN] Sydney (Nouvelle-Galles du Sud) [Termes IGN] zone sinistrée Résumé : (auteur) Wildfires have coexisted with human societies for more than 350 million years, always playing an important role in affecting the Earth's surface and climate. Across the globe, wildfires are becoming larger, more frequent, and longer-duration, and tend to be more destructive both in lives lost and economic costs, because of climate change and human activities. To reduce the damages from such destructive wildfires, it is critical to track wildfire progressions in near real-time, or even real-time. Satellite remote sensing enables cost-effective, accurate, and timely monitoring on the wildfire progressions over vast geographic areas. The free availability of global coverage Landsat-8 and Sentinel-1/2 data opens the new era for global land surface monitoring, providing an opportunity to analyze wildfire impacts around the globe. The advances in both cloud computing and deep learning empower the automatic interpretation of spatio-temporal remote sensing big data on a large scale. The overall objective of this thesis is to investigate the potential of modern medium resolution earth observation data, especially Sentinel-1 C-Band synthetic aperture radar (SAR) data, in wildfire monitoring and develop operational and effective approaches for real-world applications. This thesis systematically analyzes the physical basis of earth observation data for wildfire applications, and critically reviews the available wildfire burned area mapping methods in terms of satellite data, such as SAR, optical, and SAR-Optical fusion. Taking into account its great power in learning useful representations, deep learning is adopted as the main tool to extract wildfire-induced changes from SAR and optical image time series. On a regional scale, this thesis has conducted the following four fundamental studies that may have the potential to further pave the way for achieving larger scale or even global wildfire monitoring applications. To avoid manual selection of temporal indices and to highlight wildfire-induced changes in burned areas, we proposed an implicit radar convolutional burn index (RCBI), with which we assessed the roles of Sentinel-1 C-Band SAR intensity and phase in SAR-based burned area mapping. The experimental results show that RCBI is more effective than the conventional log-ratio differencing approach in detecting burned areas. Though VV intensity itself may perform poorly, the accuracy can be significantly improved when phase information is integrated using Interferometric SAR (InSAR). On the other hand, VV intensity also shows the potential to improve VH intensity-based detection results with RCBI. By exploiting VH and VV intensity together, the proposed RCBI achieved an overall mapping accuracy of 94.68% and 94.17% on the 2017 Thomas Fire and the 2018 Carr Fire. For the scenario of near real-time application, we investigated and demonstrated the potential Sentinel-1 SAR time series for wildfire progression monitoring with Convolutional Neural Networks (CNN). In this study, the available pre-fire SAR time series were exploited to compute temporal average and standard deviation for characterizing SAR backscatter behaviors over time and highlighting the changes with kMap. Trained with binarized kMap time series in a progression-wise manner, CNN showed good capability in detecting wildfire burned areas and capturing temporal progressions as demonstrated on three large and impactful wildfires with various topographic conditions. Compared to the pseudo masks (binarized kMap), CNN-based framework brought an 0.18 improvement in F1 score on the 2018 Camp Fire, and 0.23 on the 2019 Chuckegg Creek Fire. The experimental results demonstrated that spaceborne SAR time series with deep learning can play a significant role for near real-time wildfire monitoring when the data becomes available at daily and hourly intervals. For continuous wildfire progression mapping, we proposed a novel framework of learning U-Net without forgetting in a near real-time manner. By imposing a temporal consistency restriction on the network response, Learning without Forgetting (LwF) allows the U-Net to learn new capabilities for better handling with newly incoming data, and simultaneously keep its existing capabilities learned before. Unlike the continuous joint training (CJT) with all available historical data, LwF makes U-Net learning not dependent on the historical training data any more. To improve the quality of SAR-based pseudo progression masks, we accumulated the burned areas detected by optical data acquired prior to SAR observations. The experimental results demonstrated that LwF has the potential to match CJT in terms of the agreement between SAR-based results and optical-based ground truth, achieving a F1 score of 0.8423 on the Sydney Fire (2019-2020) and 0.7807 on the Chuckegg Creek Fire (2019). We also found that the SAR cross-polarization ratio (VH/VV) can be very useful in highlighting burned areas when VH and VV have diverse temporal change behaviors. SAR-based change detection often suffers from the variability of the surrounding background noise, we proposed a Total Variation (TV)-regularized U-Net model to relieve the influence of SAR-based noisy masks. Considering the small size of labeled wildfire data, transfer learning was adopted to fine-tune U-Net from pre-trained weights based on the past wildfire data. We quantified the effects of TV regularization on increasing the connectivity of SAR-based areas, and found that TV-regularized U-Net can significantly increase the burned area mapping accuracy, bringing an improvement of 0.0338 in F1 score and 0.0386 in IoU score on the validation set. With TV regularization, U-Net trained with noisy SAR masks achieved the highest F1 (0.6904) and IoU (0.5295), while U-Net trained with optical reference mask achieved the highest F1 (0.7529) and IoU (0.6054) score without TV regularization. When applied on wildfire progression mapping, TV-regularized U-Net also worked significantly better than vanilla U-Net with the supervision of noisy SAR-based masks, visually comparable to optical mask-based results. On the regional scale, we demonstrated the effectiveness of deep learning on SAR-based and SAR-optical fusion based wildfire progression mapping. To scale up deep learning models and make them globally applicable, large-scale globally distributed data is needed. Considering the scarcity of labelled data in the field of remote sensing, weakly/self-supervised learning will be our main research directions to go in the near future. Note de contenu : 1- Introduction 2- Literature review 3- Study areas and data 4- Metodology 5- Results and discussion Numéro de notice : 28309 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Thèse étrangère Note de thèse : PhD Thesis : Geomatics : RTK Stockholm : 2021 DOI : sans En ligne : http://kth.diva-portal.org/smash/record.jsf?pid=diva2%3A1557429 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98130

Positional uncertainty of network RTK observations in a modern datum / T. Bernstein in Journal of geodetic science, vol 11 n° 1 (January 2021)  

Public [article]  inJournal of geodetic science > vol 11 n° 1 (January 2021) . - pp 38 - 47 Titre : Positional uncertainty of network RTK observations in a modern datum Type de document : Article/Communication Auteurs : T. Bernstein, Auteur ; Volker Janssen, Auteur Année de publication : 2021 Article en page(s) : pp 38 - 47 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Systèmes de référence et réseaux [Termes IGN] compensation de coordonnées [Termes IGN] Geocentric Datum of Australia 2020 [Termes IGN] incertitude de position [Termes IGN] Nouvelle-Galles du Sud [Termes IGN] positionnement cinématique en temps réel [Termes IGN] station virtuelle de référence Résumé : (auteur) The Geocentric Datum of Australia 2020 (GDA2020) is Australia’s new and much improved national datum. It is based on a single, nationwide leastsquares network adjustment that rigorously propagates uncertainty. This paper explores three options to include Network Real-Time Kinematic (NRTK) observations and their Positional Uncertainty (PU) in the survey control network of New South Wales (NSW) via the GDA2020 state adjustment. In the first option, PU is empirically estimated based on a dataset of more than 1,500 observations to obtain values that can be uniformly applied to all NRTK observations. In the second option, PU is calculated for each NRTK observation, based on the coordinate quality indicators provided by the Global Navigation Satellite System (GNSS) equipment. Both options continue to treatNRTK observations as point-based position solutions, resulting in poor correlation with surrounding surveycontrol marks. The third option overcomes this issue by utilising the automatically computed GNSS baselines between NRTK observations and their Virtual Reference Station (VRS) to create a connected network that can be adjusted like a static GNSS network. Using a typical urban NRTK survey in Sydney as an example, it is shown that this method offers a rigorous computation of PU, while maintaining the quick and easy nature of NRTK positioning. Numéro de notice : A2021-980 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1515/jogs-2020-0116 Date de publication en ligne : 10/08/2021 En ligne : https://doi.org/10.1515/jogs-2020-0116 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100977 [article]

Social media as passive geo-participation in transportation planning – how effective are topic modeling & sentiment analysis in comparison with citizen surveys? / Oliver Lock in Geo-spatial Information Science, vol 23 n° 4 (December 2020)  

Public [article]  inGeo-spatial Information Science > vol 23 n° 4 (December 2020) . - pp 275 - 292 Titre : Social media as passive geo-participation in transportation planning – how effective are topic modeling & sentiment analysis in comparison with citizen surveys? Type de document : Article/Communication Auteurs : Oliver Lock, Auteur ; Christopher Pettit, Auteur Année de publication : 2020 Article en page(s) : pp 275 - 292 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] artefact [Termes IGN] contenu généré par les utilisateurs [Termes IGN] données localisées des bénévoles [Termes IGN] données massives [Termes IGN] planification urbaine [Termes IGN] réseau social [Termes IGN] sentiment [Termes IGN] Sydney (Nouvelle-Galles du Sud) [Termes IGN] traitement du langage naturel [Termes IGN] transport public [Termes IGN] ville intelligente Résumé : (auteur) We live in an era of rapid urbanization as many cities are experiencing an unprecedented rate of population growth and congestion. Public transport is playing an increasingly important role in urban mobility with a need to move people and goods efficiently around the city. With such pressures on existing public transportation systems, this paper investigates the opportunities to use social media to more effectively engage with citizens and customers using such services. This research forms a case study of the use of passively collected forms of big data in cities – focusing on Sydney, Australia. Firstly, it examines social media data (Tweets) related to public transport performance. Secondly, it joins this to longitudinal big data – delay information continuously broadcast by the network over a year, thus forming hundreds of millions of data artifacts. Topics, tones, and sentiment are modeled using machine learning and Natural Language Processing (NLP) techniques. These resulting data, and models, are compared to opinions derived from a citizen survey among users. The validity of such data and models versus the intentions of users, in the context of systems that monitor and improve transport performance, are discussed. As such, key recommendations for developing Smart Cities were formed in an applied research context based on these data and techniques. Numéro de notice : A2020-787 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10095020.2020.1815596 Date de publication en ligne : 21/09/2020 En ligne : https://doi.org/10.1080/10095020.2020.1815596 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96545 [article]

Evaluating techniques for mapping island vegetation from unmanned aerial vehicle (UAV) images: Pixel classification, visual interpretation and machine learning approaches / S.M. Hamylton in International journal of applied Earth observation and geoinformation, vol 89 (July 2020)  

Permalink

Assessing environmental impacts of urban growth using remote sensing / John C. Trinder in Geo-spatial Information Science, vol 23 n° 1 (March 2020)  

Permalink

Remote sensing scene classification by unsupervised representation learning / Xiaoqiang Lu in IEEE Transactions on geoscience and remote sensing, vol 55 n° 9 (September 2017)  

Permalink

Surveying graffiti, an emerging culture / Anonyme in Position, n° 81 (February - March 2016)

Permalink

Updated best practice for EDM calibrations in New South Wales / Volker Janssen in Position, n° 78 (August - September 2015)

Permalink

How good is AUSGeoid09 in the Blue Mountains ? / Joseph Allerton in Position, n° 77 (June - July 2015)

Permalink

Markov land cover change modeling using pairs of time-series satellite images / Priyakant Sinha in Photogrammetric Engineering & Remote Sensing, PERS, vol 79 n° 11 (November 2013)  

Permalink

GPS and GIS assisted radar interferometry / Linlin Ge in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 10 (October 2004)  

Permalink

Integrating imaging spectroscopy (445-2543nm) and geographic information systems for post-disaster management: a case of hailstorm damage in Sydney / S. Bhaskaran in International Journal of Remote Sensing IJRS, vol 25 n° 13 (July 2004)  

Permalink

Densification surveys in New South Wales coping with distortions / D.A. Kinlyside (1992)

Permalink