NANovaAxisGroup
Menu
Cryosphere & Glacier Monitoring$39

Glacier Retreat Monitoring

1.

Category

Cryosphere & Glacier Monitoring

Format

PDF Report

Delivery

Digital download after purchase

Price

$39

Summary

This report assesses glacier retreat across ten globally distributed sites from 2017 to 2024 using Sentinel-2 Level-2A imagery. It compares two complementary delineation approaches: NDSI thresholding with automated Otsu segmentation, and a U-Net model trained on manually outlined glacier boundaries. The analysis quantifies areal change, annual retreat rates, uncertainty, and agreement between methods across contrasting glacier settings. Results indicate measurable glacier area loss across the sample, with stronger retreat at some sites than others and strong segmentation performance from the deep-learning workflow. The study is designed as a repeatable framework for large-scale glacier monitoring under changing climatic conditions.

What the report covers

Introduction Mountain glaciers and ice caps constitute a relatively small fraction of the global ice volume, yet their re Glaciers are among the most conspicuous indicators of sponse to rising temperatures has outsized consequences climate change, yet globally consistent, multi-temporal for sea-level rise, regional hydrology, and hazard assessmonitoring at high spatial resolution remains challengment [Masson-Delmotte et al., 2021, Hock et al., 2019].
This study presents a comprehensive assessment Since the mid-twentieth century, glaciers in virtually evof glacier retreat at ten globally distributed sites spanery mountain range have undergone sustained mass loss, ning the period 2017–2024, leveraging Sentinel-2 Levela trend that has accelerated markedly since the 1990s 2A imagery accessed through the Microsoft Planetary [Zemp et al., 2019, Hugonnet et al., 2021].
Two complementary mapping approaches ernmental Panel on Climate Change (IPCC) Sixth Asare applied: (1) a Normalised Difference Snow Index sessment Report confirms that glaciers contributed ap- (NDSI) thresholding pipeline with automated Otsu segproximately 0.21 mm yr−1 to global mean sea-level rise mentation, and (2) a U-Net convolutional neural network over 2006–2018, with projections indicating further losses trained on manually delineated glacier outlines.

Why it matters

Glacier monitoring supports climate-risk analysis, hydrology planning, and long-horizon environmental reporting.

Intended sectors and users

GovernmentHydrologyClimate researchInfrastructure planning

Methodology framing

The report is framed around Sentinel-2, Landsat, SAR, U-Net, change detection, segmentation, using the methods described in the source abstract and paper title.

Preview figures

Preview figure to be attached

Applications and use cases

Retreat monitoring
Change detection
Climate reporting support

Related reports

Need adjacent or bespoke work?

The report library is also intended to help start more focused consulting discussions where the exact geography, asset base, or monitoring need is more specific than a standard report can cover.

Discuss a Project