Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams Using Machine Learning

Tom, Manu; Prabha, Rajanie; Wu, Tianyu; Baltsavias, E.; Leal-Taixé, Laura; Schindler, Konrad

doi:10.3390/rs12213555

Cited by 9 publications

(22 citation statements)

References 38 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When comparing the results on Table VI from different satellite remote sensing methods ( [13], [11]) methods, the joint embedding model, on average, deviates least from the ground truth. However, the results of in-situ temperature analysis [9], are better.…”

Section: Ice-on/off Resultsmentioning

confidence: 99%

“…We have developed a deep learning framework that learns a sensor-invariant embedding in order to fuse MODIS, VIIRS and S1-SAR satellite data into a task-specific, homogenised TABLE VI: Ice-on/off dates (winter 2016-17) estimated with the 2-step model, with two different thresholds. For comparison we show the ground truth (in chronological order when more than one candidate exists), the earlier remote sensing results ( [11], [13]), and the results of in-situ (temperature, T) analysis [9]. Results that meet the GCOS requirement are printed bold.…”

Section: Discussionmentioning

confidence: 99%

“…We use Terra MODIS [49] and Suomi NPP VIIRS [50] data in our analysis. For both these data types, we follow the download and preprocessing procedures as described in Tom et al [13], which include absolute geolocation correction, backprojection of the generalised lake outlines onto the satellite images to extract clean pixels, cloud filtering, and bilinear interpolation for low-resolution bands (upsampling the 500m and 1km bands to 250m, only for MODIS). All cloud-free lake pixels in acquisitions with >30% non-cloudy pixels are extracted and processed.…”

Section: B Target Satellites 1) Optical Satellite Data (Modis and Viirs)mentioning

confidence: 99%

“…Several papers have discussed lake ice observation with the help of machine learning, using a single satellite sensor [10], [11], [12], but unfortunately none of those sensors has so far met the criteria of ±2 days. In earlier work [13] we have integrated MODIS and VIIRS data at the decision level, but still failed to meet the GCOS target in most cases. Terrestrial webcams deliver image sequences that would satisfy the GCOS criteria [14], [15], but unlike satellite-based methods, they are not suitable for systematic and large-scale monitoring, since most lakes do not have webcams observing them, and even if there is a camera its field of view rarely covers the entire lake surface.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring

Tom,

Jiang,

Baltsavias

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Fusing satellite imagery acquired with different sensors has been a long-standing challenge of Earth observation, particularly across different modalities such as optical and Synthetic Aperture Radar (SAR) images. Here, we explore the joint analysis of imagery from different sensors in the light of representation learning: we propose to learn a joint, sensor-invariant embedding (feature representation) within a deep neural network. Our application problem is the monitoring of lake ice on Alpine lakes. To reach the temporal resolution requirement of the Swiss Global Climate Observing System (GCOS) office, we combine three image sources: Sentinel-1 SAR (S1-SAR), Terra MODIS and Suomi-NPP VIIRS. The large gaps between the optical and SAR domains and between the sensor resolutions make this a challenging instance of the sensor fusion problem. Our approach can be classified as a feature-level fusion that is learnt in a datadriven manner. The proposed network architecture has separate encoding branches for each image sensor, which feed into a single latent embedding. I.e., a common feature representation shared by all inputs, such that subsequent processing steps deliver comparable output irrespective of which sort of input image was used. By fusing satellite data, we map lake ice at a temporal resolution of <1.5 days. The network produces spatially explicit lake ice maps with pixel-wise accuracies >91.3% (respectively, mIoU scores >60.7%) and generalises well across different lakes and winters. Moreover, it sets a new state-of-the-art for determining the important ice-on and ice-off dates for the target lakes, in many cases meeting the GCOS requirement.

show abstract

Section: Ice-on/off Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: B Target Satellites 1) Optical Satellite Data (Modis and Viirs)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring

Tom,

Jiang,

Baltsavias

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Their electrical characteristics are greatly affected by ambient temperature and are more sensitive. Temperature changes can cause changes in the conductivity of semiconductor devices [25,26]. This characteristic can be applied to defect location in integrated circuits.…”

Section: Analysis Of Detecting Integrated Circuitmentioning

confidence: 99%

The Use of Artificial Intelligence‐Based Optical Remote Sensing and Positioning Technology in Microelectronic Processing Technology

Yan

Mengchao

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The purpose is to make defect detection in microelectronic processing technology fast, accurate, reliable, and efficient. A new optical remote sensing-optical beam induced resistance change (ORS-OBIRCH) target recognition and location defect detection method is proposed based on an artificial intelligence algorithm, optical remote sensing (ORS), and optical beam induced resistance change (OBIRCH) location technology using deep convolutional neural network. This method integrates the characteristics of high resolution and rich details of the image obtained by ORS technology and combines the advantages of photosensitive temperature characteristics in OBIRCH positioning technology. It can be adopted to identify, capture, and locate the defects of microdevices in the process of microelectronic processing. Simulation results show that this method can quickly reduce the detection range and locate defects accurately and efficiently. The experimental results reveal that the ORS-OBIRCH target recognition defect location detection method can complete the dynamic synchronization of the IC detection system and obtain high-quality images by changing the laser beam irradiation cycle. Moreover, it can analyze and process the detection results to quickly, accurately, and efficiently locate the defect location. Unlike the traditional detection methods, the success rate of detection has been greatly improved, which is about 95.8%, an increase of nearly 40%; the detection time has been reduced by more than half, from 5.5 days to 1.9 days, and the improvement rate has reached more than 65%. In a word, this method has good practical application value in the field of microelectronic processing.

show abstract

Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery

Tom

Baltsavias

et al. 2022

PFG

Self Cite

View full text Add to dashboard Cite

Depleting lake ice is a climate change indicator, just like sea-level rise or glacial retreat. Monitoring Lake Ice Phenology (LIP) is useful because long-term freezing and thawing patterns serve as sentinels to understand regional and global climate change. We report a study for the Oberengadin region of Switzerland, where several small- and medium-sized mountain lakes are located. We observe the LIP events, such as freeze-up, break-up and ice cover duration, across two decades (2000–2020) from optical satellite images. We analyse the time series of MODIS imagery by estimating spatially resolved maps of lake ice for these Alpine lakes with supervised machine learning. To train the classifier we rely on reference data annotated manually based on webcam images. From the ice maps, we derive long-term LIP trends. Since the webcam data are only available for two winters, we cross-check our results against the operational MODIS and VIIRS snow products. We find a change in complete freeze duration of $$-\,0.76$$ - 0.76 and $$-\,0.89$$ - 0.89 days per annum for lakes Sils and Silvaplana, respectively. Furthermore, we observe plausible correlations of the LIP trends with climate data measured at nearby meteorological stations. We notice that mean winter air temperature has a negative correlation with the freeze duration and break-up events and a positive correlation with the freeze-up events. Additionally, we observe a strong negative correlation of sunshine during the winter months with the freeze duration and break-up events.

show abstract

Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams Using Machine Learning

Cited by 9 publications

References 38 publications

Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring

Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring

The Use of Artificial Intelligence‐Based Optical Remote Sensing and Positioning Technology in Microelectronic Processing Technology

Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery

Contact Info

Product

Resources

About