Lake Ice Monitoring With Webcams

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 been included in the list of Essential Climate Variables (ECVs). Currently there are two main ways to survey lake ice cover and its change over time, in-situ measurements and satellite remote sensing. The challenge with both of them is to ensure sufficient spatial and temporal resolution. Here, we investigate the possibility to monitor lake ice with video streams acquired by publicly available webcams. Main advantages of webcams are their high temporal frequency and dense spatial sampling. By contrast, they have low spectral resolution and limited image quality. Moreover, the uncontrolled radiometry and low, oblique viewpoints result in heavily varying appearance of water, ice and snow. We present a workflow for pixel-wise semantic segmentation of images into these classes, based on state-of-the-art encoder-decoder Convolutional Neural Networks (CNNs). The proposed segmentation pipeline is evaluated on two sequences featuring different ground sampling distances. The experiment suggests that (networks of) webcams have great potential for lake ice monitoring. The overall per-pixel accuracies for both tested data sets exceed 95 %. Furthermore, per-image discrimination between ice-on and ice-off conditions, derived by accumulating per-pixel results, is 100 % correct for our test data, making it possible to precisely recover freezing and thawing dates.

Ice cover thickness formulas for selected flow-through lakes of the upper Łeba River (Kashubian Lakeland, northern Poland) and an overview of GIS methods, models for determining the thickness of ice cover on the selected examples

“…MyLake (Gebre et al 2013) -a model of lake dynamics, 1-D thermodynamic -a model based on an air and water temperature stream as well as on ice and snow density (Ohata et al 2016). Xiao et al (2018) presented an interesting method of monitoring ice on lakes with the use of common internet cameras. However, climate models are usually inaccurate and video cameras show only the moment when ice cover forms and melts (Xiao et al 2018).…”

“…Xiao et al (2018) presented an interesting method of monitoring ice on lakes with the use of common internet cameras. However, climate models are usually inaccurate and video cameras show only the moment when ice cover forms and melts (Xiao et al 2018). This is why the authors used a model based on real data which can be automatically implemented to the model and provide analysis for larger areas.…”

The ice regime of Lake Ostrzyckie (Kashubian Lakeland, northern Poland)

“…Nowadays, climate change and global warming are two phenomena affecting the natural environment. That is why it is so important to constantly monitor climate parameters (Xiao and al. 2018).…”

“…The way in which climate change affects the environment is one of the major challenges for modern science. Continuous monitoring of climate factors is extremely important for a proper understanding of the dynamics and trends of the climate system (Xiao et al 2018). Gradually increasing air temperature is a good indicator of ongoing changes in climate, it also visibly affects ice phenomena observed on lakes located in the temperate climate zone, including water bodies in the Kashubian Lakeland.…”

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

“…One question that still remains unanswered is: What is the reason that results in Deep-U-Lab outperforming the Tiramisu lake ice network [32][33][34]? One possible explanation is that our model profits from the smarter dilated convolutions and multi-scale pyramid pooling at the feature extraction stage, effectively letting the network grasp a relatively broader context as opposed to the Tiramisu network.…”