scholarly journals Towards Circumpolar Mapping of Arctic Settlements and Infrastructure Based on Sentinel-1 and Sentinel-2

2020 ◽  
Vol 12 (15) ◽  
pp. 2368 ◽  
Author(s):  
Annett Bartsch ◽  
Georg Pointner ◽  
Thomas Ingeman-Nielsen ◽  
Wenjun Lu
Keyword(s):  
Deep Learning ◽  
Satellite Data ◽  
Industrial Development ◽  
Spectral Characteristics ◽  
Added Value ◽  
The Arctic ◽  
Gradient Boosting ◽  
Spatial Coverage ◽  
The Impact ◽  
Sentinel 2

Infrastructure expands rapidly in the Arctic due to industrial development. At the same time, climate change impacts are pronounced in the Arctic. Ground temperatures are, for example, increasing as well as coastal erosion. A consistent account of the current human footprint is needed in order to evaluate the impact on the environments as well as risk for infrastructure. Identification of roads and settlements with satellite data is challenging due to the size of single features and low density of clusters. Spatial resolution and spectral characteristics of satellite data are the main issues regarding their separation. The Copernicus Sentinel-1 and -2 missions recently provided good spatial coverage and at the same time comparably high pixel spacing starting with 10 m for modes available across the entire Arctic. The purpose of this study was to assess the capabilities of both, Sentinel-1 C-band Synthetic Aperture Radar (SAR) and the Sentinel-2 multispectral information for Arctic focused mapping. Settings differ across the Arctic (historic settlements versus industrial, locations on bedrock versus tundra landscapes) and reference data are scarce and inconsistent. The type of features and data scarcity demand specific classification approaches. The machine learning approaches Gradient Boosting Machines (GBM) and deep learning (DL)-based semantic segmentation have been tested. Records for the Alaskan North Slope, Western Greenland, and Svalbard in addition to high-resolution satellite data have been used for validation and calibration. Deep learning is superior to GBM with respect to users accuracy. GBM therefore requires comprehensive postprocessing. SAR provides added value in case of GBM. VV is of benefit for road identification and HH for detection of buildings. Unfortunately, the Sentinel-1 acquisition strategy is varying across the Arctic. The majority is covered in VV+VH only. DL is of benefit for road and building detection but misses large proportions of other human-impacted areas, such as gravel pads which are typical for gas and oil fields. A combination of results from both GBM (Sentinel-1 and -2 combined) and DL (Sentinel-2; Sentinel-1 optional) is therefore suggested for circumpolar mapping.

scholarly journals Large-scale Mapping of Arctic Coastal Infrastructure using Copernicus Sentinel Data and Machine Learning and Deep Learning Methods

2020 ◽  
Author(s):  
Georg Pointner ◽  
Annett Bartsch ◽  
Thomas Ingeman-Nielsen
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Land Cover ◽  
Mitigation Strategies ◽  
The Arctic ◽  
Gradient Boosting ◽  
Land Cover Mapping ◽  
Learning Methods ◽  
Sar Data ◽  
Sentinel 2

<p>The climate change induced increased warming of the Arctic is leading to an accelerated thawing of permafrost, which can cause ground subsidence. In consequence, buildings and other infrastructure of local settlements are endangered from destabilization and collapsing in many Arctic regions. The increase of the exploitation of Arctic natural resources has led to the establishment of large industrial infrastructures that are at risk likewise. Most of the human activity in the Arctic is located near permafrost coasts. The thawing of coastal permafrost additionally leads to coastal erosion, which makes Arctic coastal settlements even more vulnerable.</p><p>The European Union (EU) Horizon2020 project “Nunataryuk” aims to assess the impacts of thawing land, coast and subsea permafrost on the climate and on local communities in the Arctic. One task of the project is to determine the impacts of permafrost thaw on coastal Arctic infrastructures and to provide appropriate adaptation and mitigation strategies. For that purpose, a circumpolar account of infrastructure is needed.</p><p>During recent years, the two polar-orbiting Sentinel-2 satellites of the Copernicus program of the EU have been acquiring multi-spectral imagery at high spatial and temporal resolution. Sentinel-2 data is a common choice for land cover mapping. Most land cover products only include one class for built-up areas, however. The fusion of optical and Synthetic Aperture Radar (SAR) data for land cover mapping has gained more and more attention over the last years. By combining Sentinel-2 and Sentinel-1 SAR data, the classification of multiple types of infrastructure can be anticipated. Another emerging trend is the application machine learning and deep learning methods for land cover mapping.</p><p>We present an automated workflow for downloading, processing and classifying Sentinel-2 and Sentinel-1 data in order to map coastal infrastructure with circum-Arctic extent, developed on a highly performant virtual machine (VM) provided by the Copernicus Research and User Support (RUS). We further assess the first classification results mapped with two different methods, one being a pixel-based classification using a Gradient Boosting Machine and the other being a windowed semantic segmentation approach using the deep-learning framework keras.</p>

Using deep learning to nowcast the spatial coverage of convection from Himawari-8 satellite data

2021 ◽  
Author(s):  
Ryan Lagerquist ◽  
Jebb Q. Stewart ◽  
Imme Ebert-Uphoff ◽  
Christina Kumler
Keyword(s):  
Deep Learning ◽  
Satellite Data ◽  
Geographic Location ◽  
Ground Truth ◽  
Atmospheric Science ◽  
Skill Score ◽  
Time Of Day ◽  
Lead Times ◽  
Weather Radars ◽  
Spatial Coverage

AbstractPredicting the timing and location of thunderstorms (“convection”) allows for preventive actions that can save both lives and property. We have applied U-nets, a deep-learning-based type of neural network, to forecast convection on a grid at lead times up to 120 minutes. The goal is to make skillful forecasts with only present and past satellite data as predictors. Specifically, predictors are multispectral brightness-temperature images from the Himawari-8 satellite, while targets (ground truth) are provided by weather radars in Taiwan. U-nets are becoming popular in atmospheric science due to their advantages for gridded prediction. Furthermore, we use three novel approaches to advance U-nets in atmospheric science. First, we compare three architectures – vanilla, temporal, and U-net++ – and find that vanilla U-nets are best for this task. Second, we train U-nets with the fractions skill score, which is spatially aware, as the loss function. Third, because we do not have adequate ground truth over the full Himawari-8 domain, we train the U-nets with small radar-centered patches, then apply trained U-nets to the full domain. Also, we find that the best predictions are given by U-nets trained with satellite data from multiple lag times, not only the present. We evaluate U-nets in detail – by time of day, month, and geographic location – and compare to persistence models. The U-nets outperform persistence at lead times ≥ 60 minutes, and at all lead times the U-nets provide a more realistic climatology than persistence. Our code is available publicly.

scholarly journals The detectability of sea-ice leads in satellite data as a function of atmospheric conditions and measurement scale

1993 ◽  
Vol 17 ◽  
pp. 227-232 ◽  
Author(s):  
J. Key ◽  
R. Stone ◽  
J. Maslanik ◽  
E. Ellefsen
Keyword(s):  
Sea Ice ◽  
Brightness Temperature ◽  
Satellite Data ◽  
The Arctic ◽  
Transfer Model ◽  
Atmospheric Effects ◽  
Ice Crystal ◽  
Model Calculations ◽  
Ice Leads ◽  
The Impact

The release of heat from sea-ice leads is an important component of the heat budget in the Arctic, but the impact of leads on regional scale climate is difficult to assess without information on their distribution in both space and time. Remote sensing of leads using satellite data, specifically AVHRR thermal and Landsat visible imagery, is examined with respect to one lead parameter: lead width. Atmospheric effects are illustrated through the concept of thermal contrast transmittance, where the brightness temperature contrast between leads of various ice thicknesses and the surrounding multi-year ice is simulated using a radiative transfer model. Calculations are made as a function of aerosol, ice crystal precipitation, and cirrus cloud optical depths. For example, at ice crystal optical depths of more than about 1.5 under mean January conditions in the central Arctic, the brightness temperature differences between 2 m and 5 cm thick ice are similar to the ice temperature variability so that there would be insufficient contrast to distinguish a lead from the surrounding ice. The geometrical aspects of the sensor are also simulated by degrading Landsat data so that the effect of sensor field-of-view on retrieved lead width statistics can be assessed. Large leads tend to “grow” with increased pixel size while small leads disappear. Changes in lead width and orientation distributions can readily be seen.

scholarly journals Hyperspectral analysis of lithologies in the Arctic in areas with abundant lichen cover

2018 ◽  
pp. 51-55
Author(s):  
Sara Salehi
Keyword(s):  
Remote Sensing ◽  
Chemical Composition ◽  
Mineral Exploration ◽  
Spectral Characteristics ◽  
Image Data ◽  
Geological Mapping ◽  
The Arctic ◽  
Electromagnetic Spectrum ◽  
Rock Types ◽  
The Impact

Lithological mapping using remote sensing depends, in part, on the identification of rock types by their spectral characteristics. Chemical and physical properties of minerals and rocks determine their diagnostic spectral features throughout the electromagnetic spectrum. Shifts in the position and changes in the shape and depth of these features can be explained by variations in chemical composition of minerals. Detection of such variations is vital for discriminating minerals with similar chemical composition. Compared with multispectral image data, airborne or spaceborne hyperspectral imagery offers higher spectral resolution, which makes it possible to estimate the mineral composition of the rocks under study without direct contact. Arctic environments provide challenging ground for geological mapping and mineral exploration. Inaccessibility commonly complicates ground surveys, and the presence of ice, vegetation and rock-encrusting lichens hinders remote sensing surveys. This study addresses the following objectives: 1. Modelling the impact of lichen on the spectra of the rock substrate; 2. Identification of a robust lichen index for the deconvolution of lichen and rock mixtures and 3. Multiscale hyperspectral analysis of lithologies in areas with abundant lichens.

scholarly journals Gender-specific perceptions of environmental problems by the indigenous peoples of the North of Russia

POPULATION ◽  
2020 ◽  
Vol 23 (2) ◽  
pp. 72-84
Author(s):  
Evgenia V. Potravnaya
Keyword(s):  
Indigenous Peoples ◽  
Industrial Development ◽  
Local Population ◽  
Environmental Problems ◽  
The Arctic ◽  
Full Account ◽  
Mining Companies ◽  
The North ◽  
The Impact ◽  
Gender Specific

The article deals with gender aspects of the perception of environmental problems by the population in the industrial development of the Arctic. There is substantiated the need to develop an ethno-social approach to the study of environmental problems in the framework of interaction between mining companies and the indigenous peoples of the North. It is proposed to conduct sociological surveys of the population when assessing the impact on the ethnological environment (ethnological expertise of the project). The experience of conducting such research to identify and assess gender-specific perceptions of environmental problems in the implementation of investment projects in the Arctic is shown. Based on the results of the empirical research in 2017–2019 on alluvial gold and diamond mining projects in the Northern regions of the Republic of Sakha (Yakutia), the main environmental problems that concern the local population are identified. These include: pollution of the environment in the territories of traditional nature use, decrease in the number of deer, reduction in the number of objects of traditional crafts, lack of a system for garbage removal and processing, climate change, and others. The article shows specifics of the environmental problems perception by the indigenous inhabitants of the North (Evenks, Dolgans, Yukagirs, Sakha) on a gender basis. It proposes a mechanism for taking into account the gender characteristics of the population’s behavior in the impact of economic activities on the environment in order to ensure gender equality by signing an agreement between mining companies and the local population on the socio-economic development of the territory. The concept of a gender approach to the account of ethnosocial and environmental aspects of territory development with the account the life cycle of the project is substantiated. Implementation of this approach will allow a more full account of the interests and needs of the indigenous population in the industrial development of the territory in the Arctic.

scholarly journals The detectability of sea-ice leads in satellite data as a function of atmospheric conditions and measurement scale

1993 ◽  
Vol 17 ◽  
pp. 227-232 ◽  
Author(s):  
J. Key ◽  
R. Stone ◽  
J. Maslanik ◽  
E. Ellefsen
Keyword(s):  
Sea Ice ◽  
Brightness Temperature ◽  
Satellite Data ◽  
The Arctic ◽  
Transfer Model ◽  
Atmospheric Effects ◽  
Ice Crystal ◽  
Model Calculations ◽  
Ice Leads ◽  
The Impact

The release of heat from sea-ice leads is an important component of the heat budget in the Arctic, but the impact of leads on regional scale climate is difficult to assess without information on their distribution in both space and time. Remote sensing of leads using satellite data, specifically AVHRR thermal and Landsat visible imagery, is examined with respect to one lead parameter: lead width. Atmospheric effects are illustrated through the concept of thermal contrast transmittance, where the brightness temperature contrast between leads of various ice thicknesses and the surrounding multi-year ice is simulated using a radiative transfer model. Calculations are made as a function of aerosol, ice crystal precipitation, and cirrus cloud optical depths. For example, at ice crystal optical depths of more than about 1.5 under mean January conditions in the central Arctic, the brightness temperature differences between 2 m and 5 cm thick ice are similar to the ice temperature variability so that there would be insufficient contrast to distinguish a lead from the surrounding ice. The geometrical aspects of the sensor are also simulated by degrading Landsat data so that the effect of sensor field-of-view on retrieved lead width statistics can be assessed. Large leads tend to “grow” with increased pixel size while small leads disappear. Changes in lead width and orientation distributions can readily be seen.

Case study of an Arctic atmospheric river with the ICON model

2021 ◽  
Author(s):  
Hélène Bresson ◽  
Annette Rinke ◽  
Vera Schemann ◽  
Mario Mech ◽  
Susanne Crewell ◽  
...  
Keyword(s):  
Temporal Structure ◽  
Horizontal Resolution ◽  
Added Value ◽  
Arctic Climate ◽  
The Arctic ◽  
Limited Area ◽  
Polar Regions ◽  
Relative Role ◽  
The Impact

<p>The Arctic climate changes faster than the ones of other regions, but the relative role of the individual feedback mechanisms contributing to Arctic amplification is still unclear. Atmospheric Rivers (ARs) are narrow and transient river-style moisture flows from the sub-polar regions. The integrated water vapour transport associated with ARs can explain up to 70% of the precipitation variance north of 70°N. However, there are still uncertainties regarding the specific role and the impact of ARs on the Arctic climate variability. For the first time, the high-resolution ICON modelling framework is used over the Arctic region. Pan Arctic simulations (from 13 km down to ca. 6 and 3 km) are performed to investigate processes related with anomalous moisture transport into the Arctic. Based on a case study over the Nordic Seas, the representation of the atmospheric circulation and the spatio-temporal structure of water vapor, temperature and precipitation within the limited-area mode (LAM) of the ICON model is assessed, and compared with reanalysis and in-situ datasets. Preliminary results show that the moisture intrusion is relatively well represented in the ICON-LAM simulations. The study also shows added value in increasing the model horizontal resolution on the AR representation.</p>

Investigating chemical composition of the troposphere over the Russian Arctic using the "Optik" Tu-134 aircraft laboratory

2020 ◽  
Author(s):  
Boris D. Belan ◽  
Pavel N. Antokhin ◽  
Mikhail Yu. Arshinov ◽  
Sergey B. Belan ◽  
Denis K. Davydov ◽  
...  
Keyword(s):  
Satellite Data ◽  
Land Surface ◽  
General Scheme ◽  
Water Area ◽  
Kara Sea ◽  
Atmospheric Composition ◽  
The Arctic ◽  
Aerosol Composition ◽  
The Impact

<p>The need to undertake a comprehensive investigation of the atmospheric composition over the Russian segment of the Arctic is caused by a serious lack and irregularity in obtaining observational data from this regio of the Earth. In addition, a comparison of the aircraft in-situ measurements with satellite data retrieved for the Kara Sea region in 2017 revealed large uncertainties in determining the vertical distribution of greenhouse gas concentrations using remote sensing methods. The development and improvement of the last ones needs at least their periodic verification by means of undertaking precise in-situ aircraft measurements.</p><p>The general scheme of the proposed experiment is as follows (map is attached): flight from Novosibirsk to Naryan-Mar via Sabetta. From Naryan-Mar, flight to a water area of the Bering Sea (up to 1000 km). Flight from Naryan-Mar to Sabetta. From here, flight to a water area of the Kara Sea (up to 1000 km). Then, flight to Tiksi. Flight from Tiksi to a water area of the Laptev Sea (up to 1000 km). Flight to Chokurdakh or Chersky. From there, flight to a water area of the East Siberian Sea (up to 1000 km). Flight to Cape Schmidt. Flight to a water area of the Chukchi Sea (up to 1000 km). Return route: Cape Shmidt–Chersky (or Chokurdah)–Yakutsk–Bratsk–Novosibirsk. It will take about 100 hours of flying time to implement the entire aircraft campaign. Campaign period is about 2-3 weeks. It is better to undertake the campaign during summer when the ocean is open. Flights over the land surface are assumed to be undertaken from 0.5 km to 11 km above ground level while above the sea from 0.2 km to 11 km. The flight profile is variable from the maximum possible height to the minimum allowed one. Vertical profiles of gas and aerosol composition will be obtained, including black carbon and organic components, as well as basic meteorological quantities.</p><p>Satellite data will be verified that do not yet provide acceptable accuracy. For the first time, unique information will be obtained over the least explored region of the Arctic, which is crucial for the whole planet in terms of climate formation and the impact of global warming.</p>

scholarly journals Short-Term Daily Prediction of Sea Ice Concentration Based on Deep Learning of Gradient Loss Function

2021 ◽  
Vol 8 ◽  
Author(s):  
Quanhong Liu ◽  
Ren Zhang ◽  
Yangjun Wang ◽  
Hengqian Yan ◽  
Mei Hong
Keyword(s):  
Deep Learning ◽  
Sea Ice ◽  
Loss Function ◽  
Model Performance ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Short Term ◽  
Sea Ice Concentration ◽  
Ice Concentration ◽  
The Impact

The navigability potential of the Northeast Passage has gradually emerged with the melting of Arctic sea ice. For the purpose of navigation safety in the Arctic area, a reliable daily sea ice concentration (SIC) prediction result is required. As the mature application of deep learning technique in short-term prediction of other fields (atmosphere, ocean, and hurricane, etc.), a new model was proposed for daily SIC prediction by selecting multiple factors, adopting gradient loss function (Grad-loss) and incorporating an improved predictive recurrent neural network (PredRNN++). Three control experiments are designed to test the impact of these three improvements for model performance with multiple indicators. Results show that the proposed model has best prediction skill in our experiments by taking physical process and local SIC variation into consideration, which can continuously predict daily SIC for up to 9 days.

scholarly journals Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning

2020 ◽  
Vol 11 ◽  
Author(s):  
Liangxu Xie ◽  
Lei Xu ◽  
Ren Kong ◽  
Shan Chang ◽  
Xiaojun Xu
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Molecular Descriptor ◽  
Predictive Performance ◽  
Gradient Boosting ◽  
Support Vector ◽  
Quantitative Structure ◽  
Structure Activity ◽  
Extreme Gradient Boosting ◽  
The Impact

The accurate predicting of physical properties and bioactivity of drug molecules in deep learning depends on how molecules are represented. Many types of molecular descriptors have been developed for quantitative structure-activity/property relationships quantitative structure-activity relationships (QSPR). However, each molecular descriptor is optimized for a specific application with encoding preference. Considering that standalone featurization methods may only cover parts of information of the chemical molecules, we proposed to build the conjoint fingerprint by combining two supplementary fingerprints. The impact of conjoint fingerprint and each standalone fingerprint on predicting performance was systematically evaluated in predicting the logarithm of the partition coefficient (logP) and binding affinity of protein-ligand by using machine learning/deep learning (ML/DL) methods, including random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), long short-term memory network (LSTM), and deep neural network (DNN). The results demonstrated that the conjoint fingerprint yielded improved predictive performance, even outperforming the consensus model using two standalone fingerprints among four out of five examined methods. Given that the conjoint fingerprint scheme shows easy extensibility and high applicability, we expect that the proposed conjoint scheme would create new opportunities for continuously improving predictive performance of deep learning by harnessing the complementarity of various types of fingerprints.

Sign in / Sign up

Export Citation Format

Share Document