Award Abstract # 2022438
NNA Track 2: Collaborative Research: Planning for Infrastructure Resiliency and Adaptation amid Increasing Mass-Movement Risks across the Cryosphere

NSF Org: RISE
Integrative and Collaborative Education and Research (ICER)
Recipient: UNIVERSITY OF ALASKA FAIRBANKS
Initial Amendment Date: August 26, 2020
Latest Amendment Date: October 13, 2020
Award Number: 2022438
Award Instrument: Standard Grant
Program Manager: Jonathan G Wynn
jwynn@nsf.gov
 (703)292-4725
RISE
 Integrative and Collaborative Education and Research (ICER)
GEO
 Directorate for Geosciences
Start Date: January 1, 2021
End Date: December 31, 2024 (Estimated)
Total Intended Award Amount: $125,000.00
Total Awarded Amount to Date: $125,000.00
Funds Obligated to Date: FY 2020 = $125,000.00
History of Investigator:
  • Margaret Darrow (Principal Investigator)
    mmdarrow@alaska.edu
  • Louise Farquharson (Co-Principal Investigator)
Recipient Sponsored Research Office: University of Alaska Fairbanks Campus
2145 N TANANA LOOP
FAIRBANKS
AK  US  99775-0001
(907)474-7301
Sponsor Congressional District: 00
Primary Place of Performance: University of Alaska Fairbanks
1764 Tanana Loop
Fairbanks
AK  US  99775-5910
Primary Place of Performance
Congressional District:
00
Unique Entity Identifier (UEI): FDLEQSJ8FF63
Parent UEI:
NSF Program(s): NNA-Navigating the New Arctic
Primary Program Source: 01002021DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 9150
Program Element Code(s): 104Y00
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.050

ABSTRACT

Navigating the New Arctic (NNA) is one of NSF's 10 Big Ideas. NNA projects address convergence scientific challenges in the rapidly changing Arctic. The Arctic research is needed to inform the economy, security and resilience of the Nation, the larger region and the globe. NNA empowers new research partnerships from local to international scales, diversifies the next generation of Arctic researchers, enhances efforts in formal and informal education, and integrates the co-production of knowledge where appropriate. This award fulfills part of that aim by supporting planning activities with clear potential to develop novel, leading edge research ideas and approaches to address NNA goals. It integrates aspects of the natural and built environments to address important societal challenges at this intersection, and engages internationally and with local communities.

Changing climate conditions have increased the occurrence of mass-movement hazards in the cryosphere, such as landslides, debris flows, and slope failures resulting from thawing of ice-rich permafrost. Mass-movement hazards across the cryosphere pose a significant risk to people and infrastructure, such as highways and pipelines. This project brings together experts from diverse backgrounds, including engineers, geoscientists, computer scientists, and officials from a variety of academic institutions, public and government agencies, and industry, to discuss key challenges and formulate research priorities in 1) characterizing mass-movement hazards in the cryosphere, 2) mapping such hazards using machine learning, 3) forecasting such hazards using artificial intelligence, and 4) building climate-change-resilient infrastructure through flexible and adaptive approaches to reduce costs. The project outcomes enable planners and policy makers to identify critical infrastructure that is most threatened by mass-movement hazards in the Arctic, sub-Arctic, and mountainous regions, and high- and low-hazard areas when planning future infrastructure near urban and rural sites.

This award funds the development and planning activities of a convergent research team to address infrastructure resilience and adaptation to increasing mass-movement risks across the cryosphere as the climate warms. Planning activities center around two annual workshops that will identify gaps in our current understanding and existing methodologies to develop: 1) more automated hazard mapping tools through remote sensing and machine learning, including well-established tools like convolutional neural networks; 2) compilations of datasets and databases and interactions with potential users; 3) more reliable artificial intelligence models including time series machine learning for hazard forecasting; and 4) more flexible and adaptive approaches to reduce costs for infrastructure resiliency and adaptation.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

Changing climate conditions have increased the occurrence of mass-movement hazards in the cryosphere, such as landslides, debris flows, and retrogressive thaw slumps. These mass-movement hazards pose a significant risk to people and infrastructure, such as highways and pipelines. This project brought together experts from diverse backgrounds to discuss key challenges and formulate research priorities in 1) characterizing mass-movement hazards in the cryosphere, 2) mapping such hazards using machine learning (ML), 3) forecasting such hazards using artificial intelligence (AI), and 4) building climate-resilient infrastructure through flexible and adaptive approaches to reduce costs.

To address these challenges, the focus of the CryoSlideRisk project was two hybrid, international workshops (May 12-13, 2022 at Penn State; and September 7-8, 2023 at the University of Alaska Fairbanks (UAF)), where the participants discussed using ML/AI for mapping and forecasting mass-movement hazards across the cryosphere, field observations of permafrost-induced mass movement hazards and their mitigations, and identifying public and private agency concerns and challenges. The research team also hosted an informal networking event at the 2024 International Conference on Permafrost. The workshop participants had a broad range of expertise including remote sensing, mapping of cryosphere mass movements, permafrost, ML, computer vision, and cold regions engineering. They represented a mix of engineers, geologists, computer scientists, and officials from a variety of academic institutions, public government agencies, and industry. Participants ranged from undergraduate and graduate students, to early career professionals, to seasoned practitioners. The CryoSlideRisk project met its objectives by facilitating interagency networking and developing new proposals and products, which include: addressing critical knowledge gaps in understanding permafrost degradation and its impacts on Arctic landscapes; creating a hazard map of the Denali Park Road; using ML to identify and map active layer detachment slides and produce a susceptibility map of part of the Yukon Territory; and developing a procedure to use ML/AI to detect and segment rock glaciers automatically in remote areas.

Some key conclusions from the CryoSlideRisk workshops are: 1) We need to predict a sequence of processes, such as atmospheric warming, permafrost thaw, mass-movement risk, and vulnerability of infrastructure, where our ability to predict each process is dependent on the accuracy/reliability of our prediction of the previous process. ML can help with these predictions; however, we need to build an adequate understanding between permafrost researchers, practitioners, policy makers, and ML specialists.  Dialogs and workshops (like those supported by this grant) are helpful and needed. 2) Using ML to map mass-movement hazards has challenges associated with the lack of regional landslide databases, unique landslide spatial features, and poor transferability of ML models trained from one ecoregion or mass-movement type to another. 3) It is imperative to be able to map and forecast these hazards and their impact areas under different climate-forcing conditions so that future infrastructure systems can avoid potentially vulnerable areas during the planning stage. 4) Interagency and international collaboration is essential to address the lack of databases for permafrost-induced mass-movement hazards in the cryosphere. 5) It is imperative to form an international working group to address the aforementioned challenges. Within the working group, protocols for data sharing and benchmarking the performance of various models from local to regional and global scales at various resolutions should be established.  More information on the CryoSlideRisk workshops can be found at: https://ine.uaf.edu/projects/cryosliderisk/.

 


Last Modified: 02/18/2025
Modified by: Margaret M Darrow

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page