kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Deep Learning for Wildfire Progression Monitoring Using SAR and Optical Satellite Image Time Series
KTH, School of Architecture and the Built Environment (ABE), Urban Planning and Environment, Geoinformatics.ORCID iD: 0000-0001-9907-0989
2021 (English)Doctoral thesis, comprehensive summary (Other academic)Alternative title
Djupinlärning för övervakning av skogsbränders utveckling med hjälp av tidsserier av SAR- och optiska satellittidsserier (Swedish)
Abstract [en]

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.

Abstract [sv]

Skogsbränder har funnits tillsammans med mänskliga samhällen i mer än350 miljoner år och har alltid spelat en viktig roll när det gäller att påverkajordens yta och klimat. Över hela världen blir skogsbränderna allt större, vanligareoch mer långvariga, och tenderar att bli mer destruktiva både när detgäller förlorade liv och ekonomiska kostnader, på grund av klimatförändringaroch mänsklig verksamhet. För att minska skadorna från sådana destruktivaskogsbränder är det viktigt att spåra utvecklingen av skogsbränder i nära realtid,eller till och med i realtid. Satellitbaserad fjärranalys gör det möjligtatt kostnadseffektivt, exakt och i rätt tid övervaka hur skogsbränder utvecklasöver stora geografiska områden. Den fria tillgången till data från Landsat-8och Sentinel-1/-2 som täcker hela världen öppnar en ny era för global övervakningav markytan och ger möjlighet att analysera effekterna av skogsbränderrunt om i världen. Framstegen inom både molntjänster och djupinlärning gördet möjligt att automatiskt tolkningen av rumslig och tidsmässig stora datafrån fjärranalys i stor skala.

Det övergripande målet med denna avhandling är att undersöka potentialenhos moderna jordobservationsdata med medelhög upplösning, särskiltSentinel-1 C-bands syntetisk aperturradar (SAR), för övervakning av skogsbränderoch att utveckla operativa och effektiva metoder för tillämpningar iverkligheten. I denna avhandling analyseras systematiskt den fysiska grundenför jordobservationsdata för tillämpningar vid skogsbränder, och de tillgängligametoderna för kartläggning av brända områden vid skogsbrändergranskas kritiskt med avseende på satellitdata, t.ex. SAR, optisk och SARoptiskfusion. Med hänsyn till dess stora förmåga att lära sig användbararepresentationer används djup inlärning som huvudverktyg för att extraheraförändringar orsakade av skogsbränder från tidsserier av SAR- och optiskabilder. På regional nivå har följande fyra grundläggande studier genomförts idenna avhandling, som kan ha potential att ytterligare bana väg för att uppnåmer omfattande eller till och med globala tillämpningar för övervakningav skogsbränder.

För att undvika manuellt urval av tidsmässiga index och för att belysaförändringar i brända områden som orsakats av skogsbränder, föreslog vi ettimplicit radarkonvolutionellt brännindex (RCBI), med vilket vi utvärderaderollerna för Sentinel-1 C-Band SAR-intensitet och fas i SAR-baserad kartläggningav brända områden. De experimentella resultaten visar att RCBI äreffektivare än den konventionella metoden med logförhållandedifferentieringnär det gäller att upptäcka brända områden. Även om VV-intensiteten i sigkan ge dåliga resultat kan noggrannheten förbättras avsevärt när fasinformationintegreras med hjälp av interferometrisk SAR (InSAR). Å andra sidanvisar VV-intensitet också potential att förbättra VH-intensitetsbaseradedetektionsresultat med RCBI. Genom att utnyttja VH- och VV-intensitettillsammans uppnådde den föreslagna RCBI en övergripande kartläggningsnoggrannhetpå 94,68

När det gäller scenariot för tillämpning i nära realtid undersökte och demonstrerade vi den potentiella Sentinel-1 SAR-tidsserien för övervakning av skogsbränders utveckling med hjälp av Convolutional Neural Networks(CNN). I den här studien utnyttjades de tillgängliga SAR-tidsserierna fråntiden före branden för att beräkna tidsmässigt medelvärde och standardavvikelseför att karaktärisera SAR-bakspridningsbeteenden över tiden och belysaförändringarna med kMap. CNN, som tränades med binäriserade kMaptidsserierpå ett progressivt sätt, visade god förmåga att upptäcka brändaområden i samband med skogsbränder och att fånga upp tidsmässiga förändringar,vilket visades på tre stora och påverkanfulla skogsbränder med olikatopografiska förhållanden. Jämfört med pseudomaskerna (binäriserad kMap)gav CNN-baserade ramverk en förbättring av F1-poängen med 0,18 för CampFire 2018 och 0,23 för Chuckegg Creek Fire 2019. De experimentella resultatenvisade att rymdburna SAR-tidsserier med djupinlärning kan spela en viktigroll för övervakning av vilda bränder i nära realtid när data blir tillgängligamed dagliga och timvisa intervaller.

För kontinuerlig kartläggning av skogsbränders utveckling föreslog vi ettnytt ramverk för inlärning av U-Net utan att glömma i nära realtid. Genomatt införa en begränsning av den tidsmässiga konsistensen för nätverksresponsengör inlärning utan glömska (LwF) det möjligt för U-Net att lära sig nyafunktioner för att bättre hantera ny inkommande data och samtidigt behållasina befintliga funktioner som man lärt sig tidigare. Till skillnad från kontinuerliggemensam träning (CJT) med alla tillgängliga historiska data gör LwFatt inlärningen av U-Net inte längre är beroende av historiska träningsdata.För att förbättra kvaliteten på SAR-baserade pseudoprogressionsmaskerackumulerade vi de brända områden som upptäcktes med optiska data somförvärvades före SAR-observationerna. De experimentella resultaten visadeatt LwF har potential att matcha CJT när det gäller överensstämmelsen mellanSAR-baserade resultat och optisk-baserad grundsanning, och uppnådde enF1-poäng på 0,8423 för Sydneybranden (2019-2020) och 0,7807 för ChuckeggCreek-branden (2019). Vi fann också att SAR:s korspolarisationsförhållande(VH/VV) kan vara mycket användbart för att lyfta fram brända områden närVH och VV har olika tidsmässiga förändringsbeteenden.

SAR-baserad förändringsdetektering lider ofta av variabiliteten hos detomgivande bakgrundsbruset, vi föreslog en Total Variation (TV)-reglerad UNet-modell för att lindra inflytandet av SAR-baserade bullriga masker. Medtanke på den lilla storleken på märkta uppgifter om skogsbränder användesöverföringsinlärning för att finjustera U-Net från förtränade vikter baseradepå tidigare uppgifter om skogsbränder. Vi kvantifierade effekternaav TV-regularisering för att öka konnektiviteten hos SAR-baserade områdenoch fann att TV-regulariserade U-Net kan öka noggrannheten i kartläggningenav brända områden avsevärt, vilket ger en förbättring på 0,0338i F1-poäng och 0,0386 i IoU-poäng på valideringsuppsättningen. Med TVregulariseringuppnådde U-Net som tränats med brusiga SAR-masker denhögsta F1- (0,6904) och IoU- (0,5295), medan U-Net som tränats med optiskreferensmask uppnådde den högsta F1- (0,7529) och IoU- (0,6054) poängenutan TV-regularisering. Vid tillämpning på kartläggning av skogsbrandsutvecklingfungerade TV-regulariserad U-Net också betydligt bättre än vanillaU-Net med övervakning av bullriga SAR-baserade masker, visuellt jämförbara med optiska maskbaserade resultat.

På regional nivå visade vi effektiviteten av djupinlärning på SAR-baseradoch SAR-optisk fusionsbaserad kartläggning av skogsbrandsutveckling. Föratt skala upp modeller för djupinlärning och göra dem globalt tillämpbarabehövs storskaliga globalt distribuerade data. Med tanke på bristen på märktadata inom fjärranalysområdet kommer svagt/självövervakad inlärning attvara vår huvudsakliga forskningsinriktning inom den närmaste framtiden.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2021. , p. 83
Series
TRITA-ABE-DLT ; 2129
Keywords [en]
Remote Sensing, Deep Learning, Wildfire, Burned Area Mapping, Synthetic Aperture Radar, Change Detection, Segmentation, Optical and Radar Image Analysis, Sentinel-1, Sentinel-2
Keywords [sv]
fjärranalys, djup inlärning, skogsbrand, kartläggning av brända områden, Synthetic Aperture Radar, upptäckt av förändringar, segmentering, analys av optiska och radarbilder, Sentinel-1, Sentinel-2
National Category
Earth and Related Environmental Sciences
Research subject
Geodesy and Geoinformatics, Geoinformatics
Identifiers
URN: urn:nbn:se:kth:diva-295725ISBN: 978-91-7873-935-6 (print)OAI: oai:DiVA.org:kth-295725DiVA, id: diva2:1557429
Public defence
2021-06-15, Videolänk:https://kth-se.zoom.us/j/65483992232, Du som saknar dator /datorvana kontakta yifang@kth.se / Use the e-mail address if you need technical assistance, Stockholm, 14:30 (English)
Opponent
Supervisors
Note

QC 210526

Available from: 2021-05-26 Created: 2021-05-25 Last updated: 2025-02-07Bibliographically approved
List of papers
1. An implicit radar convolutional burn index for burnt area mapping with Sentinel-1 C-band SAR data
Open this publication in new window or tab >>An implicit radar convolutional burn index for burnt area mapping with Sentinel-1 C-band SAR data
2019 (English)In: ISPRS journal of photogrammetry and remote sensing (Print), ISSN 0924-2716, E-ISSN 1872-8235, Vol. 158, p. 50-62Article in journal, Editorial material (Refereed) Published
Abstract [en]

Compared with optical sensors, the all-weather and day-and-night imaging ability of Synthetic Aperture Radar (SAR) makes it competitive for burnt area mapping. This study investigates the potential of Sentinel-1 C-band SAR sensors in burnt area mapping with an implicit Radar Convolutional Burn Index (RCBI). Based on multi temporal Sentinel-1 SAR data, a convolutional networks-based classification framework is proposed to learn the RCBI for highlighting the burnt areas. We explore the mapping accuracy level that can be achieved using SAR intensity and phase information for both VV and VH polarizations. Moreover, we investigate the decorrelation of Interferometric SAR (InSAR) coherence to wildfire events using different temporal baselines. The experimental results on two recent fire events, Thomas Fire (Dec., 2017) and Carr Fire (July, 2018) in California, demonstrate that the learnt RCBI has a better potential than the classical log-ratio operator in highlighting burnt areas. By exploiting both VV and VH information, the developed RCBI achieved an overall mapping accuracy of 94.68% and 94.17% on the Thomas Fire and Carr Fire, respectively.

Place, publisher, year, edition, pages
Elsevier, 2019
Keywords
Sentinel-1 SAR, Burnt area mapping, InSAR coherence, Change detection, Fully Convolutional Networks (FCN), Radar Convolutional Burn Index (RCBI)
National Category
Earth and Related Environmental Sciences
Identifiers
urn:nbn:se:kth:diva-266186 (URN)10.1016/j.isprsjprs.2019.09.013 (DOI)000501404100005 ()2-s2.0-85072860997 (Scopus ID)
Note

QC 20210526

Available from: 2020-01-08 Created: 2020-01-08 Last updated: 2025-02-07Bibliographically approved
2. Near Real-Time Wildfire Progression Monitoring with Sentinel-1 SAR Time Series and Deep Learning
Open this publication in new window or tab >>Near Real-Time Wildfire Progression Monitoring with Sentinel-1 SAR Time Series and Deep Learning
Show others...
2020 (English)In: Scientific Reports, E-ISSN 2045-2322, Vol. 10, no 1, article id 1322Article in journal (Refereed) Published
Abstract [en]

In recent years, the world witnessed many devastating wildfires that resulted in destructive human and environmental impacts across the globe. Emergency response and rapid response for mitigation calls for effective approaches for near real-time wildfire monitoring. Capable of penetrating clouds and smoke, and imaging day and night, Synthetic Aperture Radar (SAR) can play a critical role in wildfire monitoring. In this communication, we investigated and demonstrated the potential of Sentinel-1 SAR time series with a deep learning framework for near real-time wildfire progression monitoring. The deep learning framework, based on a Convolutional Neural Network (CNN), is developed to detect burnt areas automatically using every new SAR image acquired during the wildfires and by exploiting all available pre-fire SAR time series to characterize the temporal backscatter variations. The results show that Sentinel-1 SAR backscatter can detect wildfires and capture their temporal progression as demonstrated for three large and impactful wildfires: the 2017 Elephant Hill Fire in British Columbia, Canada, the 2018 Camp Fire in California, USA, and the 2019 Chuckegg Creek Fire in northern Alberta, Canada. Compared to the traditional log-ratio operator, CNN-based deep learning framework can better distinguish burnt areas with higher accuracy. These findings demonstrate 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 with the launches of RADARSAT Constellation Missions in 2019, and SAR CubeSat constellations.

Place, publisher, year, edition, pages
Springer Nature, 2020
National Category
Earth and Related Environmental Sciences
Identifiers
urn:nbn:se:kth:diva-267764 (URN)10.1038/s41598-019-56967-x (DOI)000546561800001 ()31992723 (PubMedID)2-s2.0-85078492193 (Scopus ID)
Note

QC 20200220

Available from: 2020-02-20 Created: 2020-02-20 Last updated: 2025-02-07Bibliographically approved
3. Learning U-Net without Forgetting for Near Real-Time Wildfire Monitoring by the Fusion of SAR and Optical Time Series
Open this publication in new window or tab >>Learning U-Net without Forgetting for Near Real-Time Wildfire Monitoring by the Fusion of SAR and Optical Time Series
2021 (English)In: Remote Sensing of Environment, ISSN 0034-4257, E-ISSN 1879-0704, Vol. 261, no 112467Article in journal, Editorial material (Other academic) Published
Abstract [en]

Wildfires are increasing in intensity and frequency across the globe due to climate change and rising global temperature. Development of novel approach to Monitor wildfire progressions in near real-time is therefore of critical importance for emergency responses. The objective of this research is to investigate continuous learning with U-Net by exploiting both Sentinel-1 SAR and Sentinel-2 MSI time series for increasing the frequency and accuracy of wildfire progression mapping. In this study, optical-based burned areas prior to each SAR acquisition (when available) were accumulated into SAR-based pseudo progression masks to train a deep residual U-Net model. Unlike multi-temporal fusion of SAR and optical data, the temporal fusion of progression masks allows us to track as many wildfire progressions as possible. Specifically, two approaches were investigated to train the deep residual U-Net model for continuous learning: 1) Continuous joint training (CJT) with all historical data (including both SAR and optical data); 2) Learning without forgetting (LwF) based on newly incoming data alone (SAR or optical). For LwF, a mean squared loss was integrated to keep the capabilities learned before and prevent it from overfitting to newly incoming data only. By fusing optical-based burned areas, SAR-based progression pseudo masks improve significantly, which benefits both data sampling and model training, considering the challenges in SAR-based change extraction attributed to the variability in SAR backscatter of the surrounding environments. Pre-trained ResNet was frozen as the encoder of the U-Net model, and the decoder part was trained to further refine the derived burned area maps in a progression-wise manner. 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 observed that the SAR cross-polarization ratio (VH/VV) shows good capability in suppressing multiplicative noise and detecting burned areas when VH and VV have diverse temporal behaviors.

National Category
Earth and Related Environmental Sciences
Research subject
Geodesy and Geoinformatics, Geoinformatics
Identifiers
urn:nbn:se:kth:diva-295656 (URN)10.1016/j.rse.2021.112467 (DOI)000663450900004 ()2-s2.0-85105352138 (Scopus ID)
Note

QC 20210720

Available from: 2021-05-24 Created: 2021-05-24 Last updated: 2025-02-07Bibliographically approved
4. SAR-Based Wildfire Progression Mapping withTotal-Variation Regularized Transfer Learning
Open this publication in new window or tab >>SAR-Based Wildfire Progression Mapping withTotal-Variation Regularized Transfer Learning
(English)In: IEEE Transactions on Geoscience and Remote Sensing, ISSN 0196-2892, E-ISSN 1558-0644Article in journal, Editorial material (Other academic) Submitted
Abstract [en]

Previous studies have demonstrated that SAR iscapable of detecting burned areas and thus useful for monitoringon-going wildfires. However, it is quite challenging to distinguishburned areas from the surrounding environmental backgroundnoise from SAR data, especially for generating pseudo progres-sion masks in near real-time. Therefore, in this paper we adoptedtransfer learning to train models from historical wildfire dataand then transferred it to unseen wildfire events for predicting wildfire progression maps. To suppress noise and increase the connectivity of SAR-based burned areas, we proposed a total-variation (TV) regularized transfer learning approach to learn effective models from noisy SAR pseudo masks. Based on the temporal average and standard deviation of pre-fire SAR timeseries, post-fire kMap is computed by subtracting post-fire SAR backscatter from the temporal average and dividing the temporal standard deviation. SAR-based kMap provides a relative change indicator that has the capability to take vegetation types and theirvarious temporal behaviors into account. In our experiments, two kinds of reference masks are investigated for training the U-Netmodel, i.e., binarized kMap (SARREF) and binarized optical differenced normalized burn ratio (OptREF). The experimental results demonstrate that TV-regularized U-Net can significantly increase the connectivity of burned areas when trained with noisy SARREF, leading to an improvement of 0.0338 in F1 and0.0386 in IoU. OptREF-supervised U-Net achieves the highest F1(0.7529) and IoU (0.6054) score without TV regularization, whileSARRAF-supervised U-Net achieves the highest F1 (0.6904) andIoU (0.5295) with TV regularization.

National Category
Earth and Related Environmental Sciences
Identifiers
urn:nbn:se:kth:diva-295658 (URN)
Note

QC 20210607

Available from: 2021-05-25 Created: 2021-05-25 Last updated: 2025-02-07Bibliographically approved

Open Access in DiVA

fulltext(49598 kB)2506 downloads
File information
File name FULLTEXT06.pdfFile size 49598 kBChecksum SHA-512
02a27826067433b1667f18fa9de4b4cdc1beb68119aada075c1feddd0e0161acd66227faaa747c4dc955c4afbd46889e8b076ea6e042251c4947da981384fb6c
Type fulltextMimetype application/pdf

Authority records

Zhang, Puzhao

Search in DiVA

By author/editor
Zhang, Puzhao
By organisation
Geoinformatics
Earth and Related Environmental Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 2516 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 2119 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf