Award Abstract # 1763108
Preserving Diversity via Robust Optimization

NSF Org: CMMI
Division of Civil, Mechanical, and Manufacturing Innovation
Recipient: UNIVERSITY OF SOUTHERN CALIFORNIA
Initial Amendment Date: July 13, 2018
Latest Amendment Date: June 12, 2024
Award Number: 1763108
Award Instrument: Standard Grant
Program Manager: Reha Uzsoy
ruzsoy@nsf.gov
 (703)292-2681
CMMI
 Division of Civil, Mechanical, and Manufacturing Innovation
ENG
 Directorate for Engineering
Start Date: July 15, 2018
End Date: June 30, 2025 (Estimated)
Total Intended Award Amount: $535,335.00
Total Awarded Amount to Date: $543,335.00
Funds Obligated to Date: FY 2018 = $535,335.00
FY 2020 = $8,000.00
History of Investigator:
  • Phebe Vayanos (Principal Investigator)
    phebe.vayanos@usc.edu
  • Bistra Dilkina (Co-Principal Investigator)
Recipient Sponsored Research Office: University of Southern California
3720 S FLOWER ST FL 3
LOS ANGELES
CA  US  90033
(213)740-7762
Sponsor Congressional District: 34
Primary Place of Performance: University of Southern California
3720 S. Flower St.
Los Angeles
CA  US  90089-0001
Primary Place of Performance
Congressional District:
37
Unique Entity Identifier (UEI): G88KLJR3KYT5
Parent UEI:
NSF Program(s): OE Operations Engineering
Primary Program Source: 01001819DB NSF RESEARCH & RELATED ACTIVIT
01002021DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 9178, 116E, 9102, 073E, 078E, 8024, 9231, 9251
Program Element Code(s): 006Y00
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.041

ABSTRACT

This award will support national health and prosperity by developing large-scale quantitative models for the strategic design of conservation plans to preserve biodiversity. Biodiversity is essential to human survival on Earth. A key strategy for preserving biodiversity involves making strategic land use decisions over time to create a system of habitat reserves. Long-term planning for these reserves faces challenges due to scarcity of data on species prevalence and resilience, uncertainty about land development activities, and changes over time in the ability of land tracts to sustain diverse species. This project uses a data-driven, computationally efficient robust optimization approach that can assist land use planners in making decisions that affect wildlife and fishery management and that may impact the prosperity of surrounding communities. The project will leverage ongoing collaborations with the United States Geological Survey, as well as Panthera and the Wildlife Conservation Society. The PIs will involve female graduate and undergraduate students in the project through the Women in Science and Engineering program at the University of Southern California. In addition, they will integrate the outcomes of this research into graduate and undergraduate courses they teach.

The project take a rigorous, quantitative approach to conservation planning that utilizes land acquisition and development data to inform novel multi-stage robust optimization models. The framework provides a general modeling scheme for optimization problems under endogenous uncertainty. These models involve binary adaptive decision variables with an exponential number of contingencies whose chance of occurrence is also decision-dependent. Spatio-temporal uncertainty sets are constructed using land use projections obtained from governmental agencies and NGOs. The PIs will extend the K-adaptability approach to the multi-stage setting, and will investigate techniques to provide lower bounds on the optimality gap.

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.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Shipley, Benjamin R. and Bach, Renee and Do, Younje and Strathearn, Heather and McGuire, Jenny L. and Dilkina, Bistra "megaSDM: integrating dispersal and timestep analyses into species distribution models" Ecography , v.2022 , 2022 https://doi.org/10.1111/ecog.05450 Citation Details
Kshirsagar, Meghana and Robinson, Caleb and Yang, Siyu and Gholami, Shahrzad and Klyuzhin, Ivan and Mukherjee, Sumit and Nasir, Md and Ortiz, Anthony and Oviedo, Felipe and Tanner, Darren and Trivedi, Anusua and Xu, Yixi and Zhong, Ming and Dilkina, Bistr "Becoming Good at AI for Good" Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society (AIES 21), May 1921, 2021, , 2021 https://doi.org/10.1145/3461702.3462599 Citation Details
Devulapalli, Pramith and Dilkina, Bistra and Xue, Yexiang "Embedding Conjugate Gradient in Learning Random Walks for Landscape Connectivity Modeling in Conservation" Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20) , 2020 https://doi.org/10.24963/ijcai.2020/598 Citation Details
Ye, Yingxiao and Doehring, Christopher and Georghiou, Angelos and Robinson, H. and Vayanos, P. "Conserving Biodiversity via Adjustable Robust Optimization" Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022), Workshop on Autonomous Agents for Social Good , 2022 Citation Details
Vayanos, Phebe and Jin, Qing and Elissaios, George "ROC++: Robust Optimization in C++" INFORMS Journal on Computing , v.34 , 2022 https://doi.org/10.1287/ijoc.2022.1209 Citation Details

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

Print this page

Back to Top of page