We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
SNOWED: Automatically Constructed Dataset of Satellite Imagery for Water Edge Measurements
Summary
Researchers developed SNOWED, an automatically constructed dataset of satellite imagery with labeled water edges, enabling deep learning models to accurately detect and monitor shoreline changes for environmental monitoring applications.
Monitoring the shoreline over time is essential to quickly identify and mitigate environmental issues such as coastal erosion. Monitoring using satellite images has two great advantages, i.e., global coverage and frequent measurement updates; but adequate methods are needed to extract shoreline information from such images. To this purpose, there are valuable non-supervised methods, but more recent research has concentrated on deep learning because of its greater potential in terms of generality, flexibility, and measurement accuracy, which, in contrast, derive from the information contained in large datasets of labeled samples. The first problem to solve, therefore, lies in obtaining large datasets suitable for this specific measurement problem, and this is a difficult task, typically requiring human analysis of a large number of images. In this article, we propose a technique to automatically create a dataset of labeled satellite images suitable for training machine learning models for shoreline detection. The method is based on the integration of data from satellite photos and data from certified, publicly accessible shoreline data. It involves several automatic processing steps, aimed at building the best possible dataset, with images including both sea and land regions, and correct labeling also in the presence of complicated water edges (which can be open or closed curves). The use of independently certified measurements for labeling the satellite images avoids the great work required to manually annotate them by visual inspection, as is done in other works in the literature. This is especially true when convoluted shorelines are considered. In addition, possible errors due to the subjective interpretation of satellite images are also eliminated. The method is developed and used specifically to build a new dataset of Sentinel-2 images, denoted SNOWED; but is applicable to different satellite images with trivial modifications. The accuracy of labels in SNOWED is directly determined by the uncertainty of the shoreline data used, which leads to sub-pixel errors in most cases. Furthermore, the quality of the SNOWED dataset is assessed through the visual comparison of a random sample of images and their corresponding labels, and its functionality is shown by training a neural model for sea-land segmentation.
Sign in to start a discussion.
More Papers Like This
Water Quality Grade Identification for Lakes in Middle Reaches of Yangtze River Using Landsat-8 Data with Deep Neural Networks (DNN) Model
Researchers developed a deep neural network model applied to Landsat-8 satellite data to automatically identify water quality grades for lakes in the middle Yangtze River reaches, demonstrating that machine learning and remote sensing can provide cost-effective large-scale monitoring as an alternative to labor-intensive in situ measurements.
Deep Learning Based Approach to Classify Saline Particles in Sea Water
Researchers developed a deep learning classification approach to identify saline particles in seawater images, demonstrating high accuracy in distinguishing salt crystals from other particles, with potential application to automated water quality monitoring systems.
Enhanced spatiotemporal mapping of urban wetland microplastics: An interpretable CNN-GRU approach using satellite imagery and limited samples
Researchers built an interpretable CNN-GRU deep learning model combining satellite remote sensing with limited in-situ measurements to map microplastic distribution in urban wetlands with enhanced spatiotemporal resolution, enabling more comprehensive monitoring with less field sampling.
Large-scale detection of marine debris in coastal areas with Sentinel-2
Researchers built a deep learning model to detect floating marine debris in coastal areas using satellite imagery from the Sentinel-2 program. The system achieved strong detection accuracy across multiple test sites and can monitor large stretches of coastline regularly. The tool could help environmental agencies track and respond to marine plastic pollution at a scale that manual surveys cannot match.
Aquatic Trash Detection and Classification: a Machine Learning and Deep Learning Perspective
This review examines machine learning and deep learning approaches for detecting and classifying aquatic trash in waterways, evaluating how computer vision algorithms trained on underwater and surface imagery can automate pollution monitoring for faster, more scalable ocean cleanup.