Intelligent Solutions for Navigating Big Data from the Arctic and Antarctic

image

Ice loss in Greenland and Antarctica has accelerated in recent decades. Melting polar ice sheets and mountain glaciers have considerable influence on sea level rise (SLR) and ocean currents; potential floods in coastal regions could put millions of people around the world at risk. The Intergovernmental Panel on Climate Change (IPCC) estimates that sea level could increase by 26–98cm by the end of this century. This large range in predicted SLR can be partially attributed to an incomplete understanding of bed topography and basal conditions in fast-flowing regions of ice sheets in Greenland and Antarctica. Therefore, precise calculation of ice thickness is very important for sea level and flood monitoring. The shape of the landscape hidden beneath the thick ice sheets is a key factor in predicting ice flow and future contribution to SLR in response to a changing climate. Recent large-scale radar surveys of Greenland and Antarctica reveal internal ice layers on a continental scale. Our large-scale dataset enables accurate detection and tracing of these internal layers to illuminate many aspects of ice sheet dynamics, including their history and their response to climate and subglacial forcing.

Our goal is to provide an intelligent data understanding to automatically mine and analyze the heterogeneous dataset collected by CReSIS.

NSF BIGDATA: IA: COLLABORATIVE RESEARCH #1947584, #1838230, #1838236.


Maryam Rahnemoonfar
Principal Investigator

John Paden
Co-Principal Investigator

Masoud Yari
Research Staff

Jilu Li
Research Staff

Debvrat Varshhney
PhD Student

Ibikunle Oluwanisola
PhD Student

Mattew Lyan
Undergraduate Student
• Maryam Rahnemoonfar, "AI Solutions for Navigating Big Data from the Arctic and Antarctic", EarthCube meeting, 2021  [video]
• Debvrat Varshney, Maryam Rahnemoonfar, Masoud Yari, John Paden, "Deep Radiostratigraphy of the Greenland Ice sheet through Deep Learning on Airborne Snow Radar Images (2009-2017)", IS poster Day, May 2021  [poster]
• Anjali Pare, John Paden, Reece Mathews, Victor Berger, Maryam Rahnemoonfar, Masoud Yari and Geoffrey Fox, "Cluster interface for 2D layer tracking", October 2020 
• Maryam Rahnemoonfar, "Deep Learning in Remote sensing: Challenges and Opportunities", Edinburgh University, UK, October 2020 
• Maryam Rahnemoonfar, "Sustainability Challenges in Arctic", NSF EarthCube PI meeting, September 2020 
• Maryam Rahnemoonfar, "Navigating the Arctic through Deep Learning", Earth Day, Maryland, April 2020 
• Debvrat Varshney, Maryam Rahnemoonfar, Masoud Yari, John Paden, "Deep Ice Layer Tracking and Thickness Estimation using Fully Convolutional Networks", IEEE BigData, 2020  [video]
• Masoud Yari, Maryam Rahnemoonfar, John Paden, L. Koenig, L. Montgomery, I. Oluwanisola, "Multi-Scale and Temporal Transfer Learning for Automatic Tracking of Internal Ice Layers", IGARSS, 2020 
• Maryam Rahnemoonfar, Masoud Yari, John Paden, "Radar Sensor Simulation with Generative Adversarial Network", IGARSS, 2020  [video]
• Ibikunle Oluwanisola, John Paden, Maryam Rahnemoonfar, David Crandall, Masoud Yari, "Snow Radar Layer Tracking Using Iterative Neural Network Approach", IGARSS, 2020 
• Maryam Rahnemoonfar, "Ice internal-layer tracking with deep multi-scale neural network, International", Symposium on Five Decades of Radioglaciology, Stanford University, July 2019 
• Maryam Rahnemoonfar, "Challenges and Opportunities of Data-Driven Machine Learning for Multi-dimensional Signals with and beyond the Visible Spectrum", Princeton University, 2019 
• Maryam Rahnemoonfar, "Intelligent Solutions for Navigating the Big Data from the Arctic and Antarctic", Rochester Institute of Technology, 2019 
• Masoud Yari, Maryam Rahnemoonfar, John Paden, Ibikunle Oluwanisola, Lora Koening, Lynn Montgomery, "Smart Tracking of Internal Layers of Ice in Radar Data via Multi-Scale Learning", IEEE BigData, 2019 
• Hamid Kamangir, Maryam Rahnemoonfar, Dugan Dobbs, John Paden, Geoffrey Fox, "Deep Hybrid Wavelet Networks for Detecting Ice Layers in Radar Images", IGARSS, 2018 
Acknowledgement
Copyright © 2021 Bina Lab, UMBC