Lake Ice Detection from Sentinel-1 SAR with Deep Learning

  title={Lake Ice Detection from Sentinel-1 SAR with Deep Learning},
  author={Manu Tom and Roberto Aguilar and Pascal Imhof and Silvan Leinss and Emmanuel Baltsavias and Konrad Schindler},
Lake ice, as part of the Essential Climate Variable (ECV) lakes, is an important indicator to monitor climate change and global warming. The spatio-temporal extent of lake ice cover, along with the timings of key phenological events such as freeze-up and break-up, provide important cues about the local and global climate. We present a lake ice monitoring system based on the automatic analysis of Sentinel-1 Synthetic Aperture Radar (SAR) data with a deep neural network. In previous studies that… Expand
Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams using Machine Learning
This work investigates machine learning-based image analysis as a tool to determine the spatio-temporal extent of ice on Swiss Alpine lakes as well as the ice-on and ice-off dates, from both multispectral optical satellite images (VIIRS and MODIS) and RGB webcam images. Expand
Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery
This paper focuses on observing the LIP events such as freeze-up, break-up and temporal freeze extent in the Oberengadin region of Switzerland, where there are several small and medium-sized mountain lakes, across two decades (2000-2020) from optical satellite images. Expand
Learning a Sensor-invariant Embedding of Satellite Data: A Case Study for Lake Ice Monitoring
This work proposes to learn a joint, sensor-invariant embedding (feature representation) within a deep neural network for monitoring of lake ice on Alpine lakes, and sets a new state-of-the-art for determining the important ice-on and ice-off dates for the target lakes. Expand
A Deep Learning Method for Mapping Glacial Lakes from the Combined Use of Synthetic-Aperture Radar and Optical Satellite Images
The proposed method was found highly capable of distinguishing rivers and lakes and able to effectively reduce the misidentification and extraction of rivers, and can provide a reference for research and application expansion in related fields. Expand
Monitoring the Ice Phenology of Qinghai Lake from 1980 to 2018 Using Multisource Remote Sensing Data and Google Earth Engine
Climate factors were closely related to LIP, especially the accumulated freezing degree-day (AFDD) from October to April of the following year, and freeze-up start time was more sensitive to changes in wind speed and precipitation. Expand
50 years of lake ice research from active microwave remote sensing: Progress and prospects
Abstract Lake ice is an important feature of the physical landscape at northern latitudes. Not only does the presence of lake ice help modulate weather and climate but it also plays an important roleExpand
Comparing the Applicability of Sentinel-1 and Sentinel-2 for Mapping the Evolution of Ice-marginal Lakes in Southeast Iceland
Monitoring ice-marginal lakes is important for glaciological and geomorphological studies, as well as hazard and risk assessment. Sentinel-1 synthetic aperture radar (SAR) and Sentinel2 optical dataExpand
Small-Satellite Synthetic Aperture Radar for Continuous Global Biospheric Monitoring: A Review
A systems engineering perspective is presented to track the transitioning of space-based SAR platforms from large satellites to small satellites and the possible roles of small satellites in global biospheric monitoring and the subsequent research areas are discussed. Expand
Formulas for calculating ice cover thickness on selected spring lakes on the upper Radunia (Kashubian Lakeland, northern Poland)
Abstract This publication is to confirm the existence of a correlation between lakes under hydrometric supervision and unmonitored lakes using formulas for calculating thickness of ice cover observedExpand


Abstract. Continuous monitoring of climate indicators is important for understanding the dynamics and trends of the climate system. Lake ice has been identified as one such indicator, and has beenExpand
Sea Ice Concentration Estimation during Freeze-Up from SAR Imagery Using a Convolutional Neural Network
A convolutional neural network is used to estimate sea ice concentration using synthetic aperture radar scenes acquired during freeze-up in the Gulf of St. Lawrence on the east coast of Canada and is found to be less sensitive to pixel level details than the MLP and produces ice concentration that is less noisy and in closer agreement with that from image analysis charts. Expand
Lake Ice Detection in Low-Resolution Optical Satellite Images
Abstract. Monitoring and analyzing the (decreasing) trends in lake freezing provides important information for climate research. Multi-temporal satellite images are a natural data source to surveyExpand
The role of lake size and local phenomena for monitoring ground-fast lake ice
The results indicate that the largest lakes are likely most prone to errors by the threshold classification, which might reflect differences in temperatures between the winters with severe impact on wildlife and freshwater fish resources in the region. Expand
Integrated monitoring of ice in selected Swiss lakes. Final project report
The aim of this project is to monitor some target lakes and detect the extent of ice and especially the ice-on/off dates, with focus on the integration of various input data and processing methods. Expand
Advancement in Bedfast Lake ICE Mapping From Sentinel-1 Sar Data
  • C. Duguay, Junqian Wang
  • Computer Science, Geology
  • IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium
  • 2019
The thresholding algorithm was found to perform slightly better on average than the IRGS algorithm, and to outperform K-means, and was selected for implementation of a processing chain to generate a novel bedfast/floating lake ice product. Expand
Satellite microwave assessment of Northern Hemisphere lake ice phenology from 2002 to 2015
Abstract. A new automated method enabling consistent satellite assessment of seasonal lake ice phenology at 5 km resolution was developed for all lake pixels (water coverage  ≥  90 %) in the NorthernExpand
Ice Freeze-up and Break-up Detection of Shallow Lakes in Northern Alaska with Spaceborne SAR
Analysis of the temporal evolution of C-band σ° from Advanced Synthetic Aperture Radar (ASAR) Wide Swath and RADARSAT-2 ScanSAR was employed to evaluate the potential of SAR to detect the timing of key lake-ice events, and identifies limitations and provides recommendations for future work using C- band SAR for monitoring the lake- ice phenology of shallow Arctic lakes. Expand
Monitoring lake ice during spring melt using RADARSAT-2 SAR
Multipolarized RADARSAT-2 SAR imagery is used to monitor lake ice during the spring melt period. The study area is Old Crow Flats, Yukon, in the Canadian Arctic. HH and HV backscatter from lake iceExpand
Determining depth and ice thickness of shallow sub-Arctic lakes using space-borne optical and SAR data
An approach to determine depth and ice thickness of shallow lakes and ponds using Landsat Thematic Mapper (TM) and European Remote Sensing (ERS)-1 Synthetic Aperture Radar (SAR) data is presented. AExpand