Boundary Aware U-Net for Glacier Segmentation
- URL: http://arxiv.org/abs/2301.11454v1
- Date: Thu, 26 Jan 2023 22:58:23 GMT
- Title: Boundary Aware U-Net for Glacier Segmentation
- Authors: Bibek Aryal, Katie E. Miles, Sergio A. Vargas Zesati, Olac Fuentes
- Abstract summary: We propose a modified version of the U-Net for large-scale, spatially non-overlapping, clean glacial ice, and debris-covered glacial ice segmentation.
We introduce a novel self-learning boundary-aware loss to improve debris-covered glacial ice segmentation performance.
We conclude that red, shortwave infrared, and near-infrared bands have the highest contribution toward debris-covered glacial ice segmentation from Landsat 7 images.
- Score: 1.1715858161748574
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large-scale study of glaciers improves our understanding of global glacier
change and is imperative for monitoring the ecological environment, preventing
disasters, and studying the effects of global climate change. Glaciers in the
Hindu Kush Himalaya (HKH) are particularly interesting as the HKH is one of the
world's most sensitive regions for climate change. In this work, we: (1)
propose a modified version of the U-Net for large-scale, spatially
non-overlapping, clean glacial ice, and debris-covered glacial ice
segmentation; (2) introduce a novel self-learning boundary-aware loss to
improve debris-covered glacial ice segmentation performance; and (3) propose a
feature-wise saliency score to understand the contribution of each feature in
the multispectral Landsat 7 imagery for glacier mapping. Our results show that
the debris-covered glacial ice segmentation model trained using self-learning
boundary-aware loss outperformed the model trained using dice loss.
Furthermore, we conclude that red, shortwave infrared, and near-infrared bands
have the highest contribution toward debris-covered glacial ice segmentation
from Landsat 7 images.
Related papers
- Global-Local Detail Guided Transformer for Sea Ice Recognition in Optical Remote Sensing Images [4.540236408836131]
A Global-Local Detail Guided Transformer (GDGT) method is proposed for sea ice recognition in optical remote sensing images.
In GDGT, a global-local feature fusiont mechanism is designed to fuse global structural correlation features and local spatial detail features.
A detail-guided decoder is developed to retain more high-resolution detail information during feature reconstruction for improving the performance of sea ice recognition.
arXiv Detail & Related papers (2024-05-21T21:02:20Z) - OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning [50.365198230613956]
Existing expert-dominated numerical simulations fail to catch up with the dynamic variation caused by global warming and human activities.
We propose OxyGenerator, the first deep learning based model, to reconstruct the global ocean deoxygenation from 1920 to 2023.
arXiv Detail & Related papers (2024-05-12T09:32:40Z) - Towards Global Glacier Mapping with Deep Learning and Open Earth Observation Data [0.718723384367814]
Glacier-VisionTransformer-U-Net (GlaViTU) is a convolutional-transformer deep learning model.
Adding synthetic aperture radar data, namely, backscatter and interferometric coherence, increases the accuracy in all regions where available.
We release a benchmark dataset that covers 9% of glaciers worldwide.
arXiv Detail & Related papers (2024-01-25T20:41:17Z) - Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting [52.77986479871782]
Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts.
In this work, we investigate the performance of the U-Net model trained in two regimes for predicting sea ice for up to the next 10 days.
We show that this deep learning model can outperform simple baselines by a significant margin and improve its quality by using additional weather data and training on multiple regions.
arXiv Detail & Related papers (2022-10-17T09:14:35Z) - GlacierNet2: A Hybrid Multi-Model Learning Architecture for Alpine
Glacier Mapping [5.953569982292301]
Thematic and quantitative information regarding glacier geometry is fundamental for understanding climate forcing and the sensitivity of glaciers to climate change.
accurately mapping debris-cover glaciers (DCGs) is notoriously difficult based upon the use of spectral information and conventional machine-learning techniques.
The objective of this research is to improve upon an earlier proposed deep-learning-based approach, GlacierNet, which was developed to exploit a convolutional neural-network segmentation model to accurately outline regional DCG ablation zones.
arXiv Detail & Related papers (2022-04-06T14:39:34Z) - Simulating surface height and terminus position for marine outlet
glaciers using a level set method with data assimilation [0.0]
We implement a data assimilation framework for integrating ice surface and terminus position observations into a numerical ice-flow model.
The model is also applied to simulate Helheim Glacier, a major tidewater-terminating glacier of the Greenland Ice Sheet.
arXiv Detail & Related papers (2022-01-28T16:45:37Z) - SALT: Sea lice Adaptive Lattice Tracking -- An Unsupervised Approach to
Generate an Improved Ocean Model [72.3183990520267]
We propose SALT: Sea lice Adaptive Lattice Tracking approach for efficient estimation of sea lice dispersion and distribution.
Specifically, an adaptive spatial mesh is generated by merging nodes in the lattice graph of the Ocean Model based on local ocean properties.
The proposed SALT technique shows promise for enhancing proactive aquaculture management through predictive modelling of sea lice infestation pressure maps in a changing climate.
arXiv Detail & Related papers (2021-06-24T17:29:42Z) - Physically-Consistent Generative Adversarial Networks for Coastal Flood
Visualization [60.690929022840685]
We propose the first deep learning pipeline to ensure physical-consistency in synthetic visual satellite imagery.
By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism.
We publish a dataset of over 25k labelled image-pairs to study image-to-image translation in Earth observation.
arXiv Detail & Related papers (2021-04-10T15:00:15Z) - Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya [54.12023102155757]
Glacier mapping is key to ecological monitoring in the hkh region.
Climate change poses a risk to individuals whose livelihoods depend on the health of glacier ecosystems.
We present a machine learning based approach to support ecological monitoring, with a focus on glaciers.
arXiv Detail & Related papers (2020-12-09T12:48:06Z) - Physics-informed GANs for Coastal Flood Visualization [65.54626149826066]
We create a deep learning pipeline that generates visual satellite images of current and future coastal flooding.
By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism.
While this work focused on the visualization of coastal floods, we envision the creation of a global visualization of how climate change will shape our earth.
arXiv Detail & Related papers (2020-10-16T02:15:34Z) - Deep Tiered Image Segmentation For Detecting Internal Ice Layers in
Radar Imagery [8.09102093271587]
Ground-penetrating radar is able to collect observations of the internal structure of snow and ice.
Recent work has developed automatic techniques for finding the boundaries between the ice and the bedrock.
We propose a novel deep neural network for solving a general class of tiered segmentation problems.
arXiv Detail & Related papers (2020-10-08T01:13:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.