Rapid mapping of landslides by Deep-Learning of combined optical and SAR data

2021 ◽  
Author(s):  
Lorenzo Nava ◽  
Filippo Catani ◽  
Oriol Monserrat
Keyword(s):  
Deep Learning ◽  
Cloud Cover ◽  
Optical Data ◽  
Rapid Mapping ◽  
Optical Images ◽  
Short Time Span ◽  
Before And After ◽  
Comparable Accuracy ◽  
Sar Data ◽  
Short Time

<div> <p><span>In the world, various natural calamities, like earthquakes and massive rainfalls sometimes combined with windstorms, can trigger multiple landslide events that can occur in groups of hundreds to thousands in a region, over a short time span. Therefore, there is a growing need to be able to intervene quickly to accurately map the impacted areas. To this end, VHR optical images ensure best performances in terms of spatial accuracy but, for rapid mapping, they present limitations due to the possible presence of cloud cover as, often, the first cloudless image is available with an unacceptable time delay, see, e.g., the cases of strong earthquakes of Chile 2017, Nepal 2015 and Ecuador 2016. A possible solution may stand in the combined exploitation of optical and SAR data. In this study, deep-learning convolution neural networks (CNNs) techniques have been used to compare and combine the mapping and classification performances of optical images (from Sentinel-2) and SAR images (from Sentinel-1). The training and test zones used to independently evaluate the performance of CNNs on different datasets are located in the eastern Iburi subprefecture in Hokkaido, where, at 03.08 local time (JST) on September 6, 2018, a Mw 6.6 earthquake triggered about 7837 coseismic landslides. We analyzed the conditions before and after the earthquake exploiting SAR and optical data by means of a series of CNNs implemented in Python that point out the locations where the <em>Landslide</em> class is predicted as more likely. As expected, the CNN run on optical images proved itself excellent for the landslide detection task, achieving an overall accuracy of 98.48% while a CNN based on the combination of ground range detected (GRD) data (SAR) achieved an overall accuracy of 95.54%. Despite this, the integrated use of SAR data allows for a rapid mapping even during storms and under cloud cover and seems to provide a comparable accuracy than optical change detection. We believe that, in the near future, such classification accuracy might even increase with the availability of new, VHR SAR products, such as the 50 cm x 50 cm resolution imagery from the Capella-2 satellite.</span></p> </div>

scholarly journals Rapid tranquillisation: practice in Zambia, before and after training

2013 ◽  
Vol 10 (4) ◽  
pp. 95-97
Author(s):  
Mahesh Jayaram ◽  
Ranga Rattehalli ◽  
Lindsay Moran ◽  
John Mwanza ◽  
Paul Banda ◽  
...  
Keyword(s):  
Evidence Base ◽  
Sub Saharan Africa ◽  
Collaborative Partnerships ◽  
Inappropriate Use ◽  
Short Time Span ◽  
Safety Awareness ◽  
Before And After ◽  
Sub Saharan ◽  
Therapeutic Doses ◽  
Short Time

The evidence base for rapid tranquillisation is small in higher-income countries but is even smaller in sub-Saharan Africa. We initiated the first ever survey on the use of rapid tranquillisation in Zambia in 2009; a further survey was then done in 2010, after a programme of teaching and training. It demonstrated an overall improvement in clinical practice, safety, awareness and use of medications within therapeutic doses. It also led to a reduction in inappropriate use of medications. These improvements in practice occurred within a short time span and with minimal effort. Further international collaborative partnerships are required to build stronger mental health infrastructure in Zambia.

Changes in nutrient and calorie intake, adipose mass, triglycerides and TNF-α concentrations after non-caloric sweetener intake: pilot study

2019 ◽  
pp. 1-12
Author(s):  
Marcela Sánchez-Delgado ◽  
José Antonio Estrada ◽  
Vladimir Paredes-Cervantes ◽  
Martha Kaufer-Horwitz ◽  
Irazú Contreras
Keyword(s):  
Calorie Intake ◽  
Normal Body Mass Index ◽  
Steviol Glycosides ◽  
Immunological Parameters ◽  
Serum Triglycerides ◽  
Positive Effects ◽  
Short Time Span ◽  
Tnf Α ◽  
Before And After ◽  
Short Time

Abstract. Establishing the safety of non-caloric sweetener consumption in humans is a difficult task, since many contradictory results have been reported. The objective of this study was to compare the effect of frequent intake of sucrose, sucralose or steviol glycosides, on selected anthropometric, biochemical and immunological parameters in healthy, young adults. 38 individuals with normal body mass index were recruited and randomly divided into three experimental groups. After a washout week (where food with added sweeteners was restricted), each group was supplemented with sucrose (8 × 5 g packets/day), sucralose or steviol glycosides (4 × 1 g packets/day each) for 6 weeks. Selected variables were measured before and after treatment in each group and differences within and among groups were assessed. Our results showed that, compared to baseline, there was a modest but significant increase in weight (p = 0.0293) in the sucralose group, while the steviol glycosides group reduced their fat mass (p = 0.0390). No differences were observed in glycaemia; however, there was a significant increase in serum triglycerides (77.8–110.8 mg/dL) and cholesterol (162.0–172.3 mg/dL) in the sucrose group, whereas the steviol glycosides group presented lower triglycerides (104.7–92.8 mg/dL) and TNF-α concentrations (51.1–47.5 pg/mL). Comparison among groups showed differences in serum triglycerides (p = 0.0226), TNF-α (p = 0.0460) and IL-β (p = 0.0008). Our results suggest that, even in a short time span, frequent intake of steviol glycosides may have positive effects on metabolic parameters that may be relevant for human health.

scholarly journals Multi-Temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation

2018 ◽  
Vol 7 (10) ◽  
pp. 389 ◽  
Author(s):  
Wei He ◽  
Naoto Yokoya
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Super Resolution ◽  
Optical Image ◽  
Optical Data ◽  
Image Simulation ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Multi Temporal ◽  
Sar Data

In this paper, we present the optical image simulation from synthetic aperture radar (SAR) data using deep learning based methods. Two models, i.e., optical image simulation directly from the SAR data and from multi-temporal SAR-optical data, are proposed to testify the possibilities. The deep learning based methods that we chose to achieve the models are a convolutional neural network (CNN) with a residual architecture and a conditional generative adversarial network (cGAN). We validate our models using the Sentinel-1 and -2 datasets. The experiments demonstrate that the model with multi-temporal SAR-optical data can successfully simulate the optical image; meanwhile, the state-of-the-art model with simple SAR data as input failed. The optical image simulation results indicate the possibility of SAR-optical information blending for the subsequent applications such as large-scale cloud removal, and optical data temporal super-resolution. We also investigate the sensitivity of the proposed models against the training samples, and reveal possible future directions.

scholarly journals ON THE CHALLENGES IN STEREOGRAMMETRIC FUSION OF SAR AND OPTICAL IMAGERY FOR URBAN AREAS

2016 ◽  
Vol XLI-B7 ◽  
pp. 719-722 ◽  
Author(s):  
M. Schmitt ◽  
X. X. Zhu
Keyword(s):  
Urban Areas ◽  
Optical Data ◽  
3D Analysis ◽  
Rapid Mapping ◽  
Optical Images ◽  
Urban Topography ◽  
Optical Imagery ◽  
The One ◽  
First Time

This paper discusses the challenges arising if SAR and optical imagery shall be fused for stereogrammetric 3D analysis of urban areas. In this context, a concept for SAR and optical data fusion is presented, which is meant to enable the reconstruction of urban topography independent of the type of the available data. This fusion is modelled in a voxelized object space, from which 3D hypotheses are projected into the available datasets. Among those hypotheses then the one showing the greatest SAR-optical similarity is chosen to be the reconstructed 3D point. Within first experiments, it is shown that the determination of similarity between high-resolution SAR and optical images is the major challenge within the framework of the proposed concept. After this challenge has been solved, the proposed method is expected to allow 3D reconstruction of urban areas from SAR-optical stereogrammetry for the first time. It is expected to be beneficial, e.g., for rapid mapping tasks in disaster situations where optical images may be available from geodata archives, but instantaneous data can only be provided by daylight- and weather-independent SAR sensors.

scholarly journals THE SEN1-2 DATASET FOR DEEP LEARNING IN SAR-OPTICAL DATA FUSION

2018 ◽  
Vol IV-1 ◽  
pp. 141-146 ◽  
Author(s):  
M. Schmitt ◽  
L. H. Hughes ◽  
X. X. Zhu
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Data Fusion ◽  
Training Data ◽  
Sensor Data ◽  
Optical Data ◽  
Multiple Sensors ◽  
Optical Images ◽  
Multi Sensor Data Fusion ◽  
Learning Techniques

<p><strong>Abstract.</strong> While deep learning techniques have an increasing impact on many technical fields, gathering sufficient amounts of training data is a challenging problem in remote sensing. In particular, this holds for applications involving data from multiple sensors with heterogeneous characteristics. One example for that is the fusion of synthetic aperture radar (SAR) data and optical imagery. With this paper, we publish the <i>SEN1-2</i> dataset to foster deep learning research in SAR-optical data fusion. <i>SEN1-2</i> comprises 282;384 pairs of corresponding image patches, collected from across the globe and throughout all meteorological seasons. Besides a detailed description of the dataset, we show exemplary results for several possible applications, such as SAR image colorization, SAR-optical image matching, and creation of artificial optical images from SAR input data. Since <i>SEN1-2</i> is the first large open dataset of this kind, we believe it will support further developments in the field of deep learning for remote sensing as well as multi-sensor data fusion.</p>

scholarly journals Newly Built Construction Detection in SAR Images Using Deep Learning

2019 ◽  
Vol 11 (12) ◽  
pp. 1444 ◽  
Author(s):  
Raveerat Jaturapitpornchai ◽  
Masashi Matsuoka ◽  
Naruo Kanemoto ◽  
Shigeki Kuzuoka ◽  
Riho Ito ◽  
...  
Keyword(s):  
Deep Learning ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Weather Conditions ◽  
Google Earth ◽  
Sar Images ◽  
Convolutional Network ◽  
Optical Images ◽  
Sar Data ◽  
Deep Learning Network

Remote sensing data can be utilized to help developing countries monitor the use of land. However, the problem of constant cloud coverage prevents us from taking full advantage of satellite optical images. Therefore, we instead opt to use data from synthetic-aperture radar (SAR), which can capture images of the Earth’s surface regardless of the weather conditions. In this study, we use SAR data to identify newly built constructions. Most studies on change detection tend to detect all of the changes that have a similar temporal change characteristic occurring on two occasions, while we want to identify only the constructions and avoid detecting other changes such as the seasonal change of vegetation. To do so, we study various deep learning network techniques and have decided to propose the fully convolutional network with a skip connection. We train this network with pairs of SAR data acquired on two different occasions from Bangkok and the ground truth, which we manually create from optical images available from Google Earth for all of the SAR pairs. Experiments to assign the most suitable patch size, loss weighting, and epoch number to the network are discussed in this paper. The trained model can be used to generate a binary map that indicates the position of these newly built constructions precisely with the Bangkok dataset, as well as with the Hanoi and Xiamen datasets with acceptable results. The proposed model can even be used with SAR images of the same specific satellite from another orbit direction and still give promising results.

scholarly journals Rapid Detection of Windthrows Using Sentinel-1 C-Band SAR Data

2019 ◽  
Vol 11 (2) ◽  
pp. 115 ◽  
Author(s):  
Marius Rüetschi ◽  
David Small ◽  
Lars Waser
Keyword(s):  
Rapid Detection ◽  
Temperate Forests ◽  
Weather Conditions ◽  
Independent Study ◽  
Storm Event ◽  
Storm Events ◽  
Before And After ◽  
Sar Data ◽  
Short Time ◽  
Flexible Application

Storm events are capable of causing windthrow to large forest areas. A rapid detection of the spatial distribution of the windthrown areas is crucial for forest managers to help them direct their limited resources. Since synthetic aperture radar (SAR) data is acquired largely independent of daylight or weather conditions, SAR sensors can produce temporally consistent and reliable data with a high revisit rate. In the present study, a straightforward approach was developed that uses Sentinel-1 (S-1) C-band VV and VH polarisation data for a rapid windthrow detection in mixed temperate forests for two study areas in Switzerland and northern Germany. First, several S-1 acquisitions of approximately 10 before and 30 days after the storm event were radiometrically terrain corrected. Second, based on these S-1 acquisitions, a SAR composite image of before and after the storm was generated. Subsequently, after analysing the differences in backscatter between before and after the storm within windthrown and intact forest areas, a change detection method was developed to suggest potential locations of windthrown areas of a minimum extent of 0.5 ha—as is required by the forest management. The detection is based on two user-defined parameters. While the results from the independent study area in Germany indicated that the method is very promising for detecting areal windthrow with a producer’s accuracy of 0.88, its performance was less satisfactory at detecting scattered windthrown trees. Moreover, the rate of false positives was low, with a user’s accuracy of 0.85 for (combined) areal and scattered windthrown areas. These results underscore that C-band backscatter data have great potential to rapidly detect the locations of windthrow in mixed temperate forests within a short time (approx. two weeks) after a storm event. Furthermore, the two adjustable parameters allow a flexible application of the method tailored to the user’s needs.

scholarly journals Cohort Differences in Swedish Union Membership 1956–2019 and the Role of Individualization

2021 ◽  
Author(s):  
Erik Vestin ◽  
Patrik Vulkan
Keyword(s):  
Union Membership ◽  
Academic Research ◽  
Cohort Differences ◽  
Central Hypothesis ◽  
Short Time Span ◽  
General Decline ◽  
Before And After ◽  
Short Time ◽  
Separate Cohort

Discussions of the role of cohort differences have long been part of academic research on union membership, with a central hypothesis being that the general decline in unionization is caused by changes toward more individualistic values in the younger generations. However, the short time span of most studies makes it uncertain if they can separate cohort effects from age effects. Using survey data going back to 1956, we test the individualization hypothesis. Our main result is that later Swedish cohorts are indeed less prone to join unions. In particular, the differences between cohorts born before and after ca 1970 are striking. We also provide evidence that the erosion in union membership in Sweden is not related to changes toward more individualistic values in later cohorts, or even to more negative views of unions per se.

THE USE OF SYNTHETIC APERTURE RADAR (SAR) DATA IN THE ANALYSIS OF INUNDATED AREAS DURING THE SPRING FLOOD

2018 ◽  
Vol 12 (7-8) ◽  
pp. 54-60 ◽  
Author(s):  
V. A. ZELENTSOV ◽  
S. A. POTRYASAEV ◽  
I. YU. PIMANOV ◽  
M. R. PONOMARENKO
Keyword(s):  
Synthetic Aperture Radar ◽  
Real Time ◽  
Spatial Resolution ◽  
Cloud Cover ◽  
Flood Forecasting ◽  
Synthetic Aperture ◽  
Optical Data ◽  
Sar Data ◽  
Space Data ◽  
Aperture Radar

The paper discusses the opportunities of remote sensing data application as one of the main sources of information for monitoring river floods. Effective operation of flood forecasting systems requires reliable real-time data on inundation areas for timely calibration and verification of the used hydrodynamic models. The opportunity to obtain data from optical sensors might be limited because of dense cloud cover. Synthetic aperture radar (SAR) techniques are increasingly used today due to ability to operate independently of the surface illumination and the state of cloud cover receiving high spatial resolution data in near real-time mode. An important feature of SAR from space today is the increase in the number of freely distributed space data, in particular — images from Sentinel satellites developed by the European Space Agency. For instance, for the territory of Russia Sentinel-1 performs SAR imaging with 2–3 days coverage frequency. Within the framework of the project carried out by the authors, the research area is the city of Velikiy Ustuyg (Russia) located at the confluence of rivers Suhona and Ug. To identify flooded areas the RADARSAT-2 and Sentinel-1 images classification based on thresholding was carried out in open-source software. The visualization of the results was performed on the basis of information analytical system “Prostor”. The results of SAR data processing were compared with contours obtained on the basis of the calculation of the NDWI index from optical data from the Sentinel-2 and Resurs-P satellites. According to the spatial resolution of the data and the selected processing technology, it is possible to achieve high accuracy of flood mapping in open areas with low urbanization. The result confirms that SAR data can be successfully applied for operational flood forecasting.

Combined analysis of polarimetric SAR data and optical imagery for rapid landslide mapping in vegetated areas

2020 ◽  
Author(s):  
Simon Plank ◽  
Sandro Martinis
Keyword(s):  
High Resolution ◽  
Change Detection ◽  
Optical Data ◽  
Polarimetric Sar ◽  
Rapid Mapping ◽  
Landslide Event ◽  
Landslide Mapping ◽  
Optical Imagery ◽  
Sar Data ◽  
Sar Imagery

&lt;p&gt;Rapid mapping of the extent of the affected area as well as type and grade of damage after a landslide event is crucial to enable fast crisis response, i.e., to support rescue and humanitarian operations. Change detection between pre- and post-event very high resolution (VHR) optical imagery is the state-of-the-art in operational rapid mapping of landslides. However, the suitability of optical data relies on clear sky conditions, which is not often the case after landslides events, as heavy rain is one of the most frequent triggers of landslides. In contrast to this, the acquisition of synthetic aperture radar (SAR) imagery is independent of atmospheric conditions. SAR data-based landslide detection approaches reported in the literature use change detection techniques, requiring VHR SAR imagery acquired shortly before the landslide event, which is commonly not available. Modern VHR SAR missions, e.g., Radarsat-2, TerraSAR-X, or COSMO-SkyMed, do not systematically cover the entire world, due to limitations in onboard disk space and downlink transmission rates. Here, we present a fast and transferable procedure for mapping of landslides in vegetated areas, based on change detection between pre-event optical imagery and the polarimetric entropy derived from post-event VHR polarimetric SAR data. Pre-event information is derived from high resolution optical imagery of Landsat-8 or Sentinel-2, which are freely available and systematically acquired over the entire Earth&amp;#8217;s landmass. The landslide mapping is refined by slope information from a digital elevation model generated from bi-static TanDEM-X imagery. The methodology was successfully applied to two landslide events of different characteristics: A rotational slide near Charleston, West Virginia, USA and a mining waste earthflow near Bolshaya Talda, Russia.&lt;/p&gt;

Sign in / Sign up

Export Citation Format

Share Document