@article{Nichol.2026.accepted.certifyingML,year={2026},title={{Challenges of Certifying Machine Learning Trustworthiness in High-Consequence Domains}},author={Nichol, J. Jake and Milewicz, Reed M. and Kinney, Adrienne C. and Grayson, Samuel A. and Smith, Mark A. and Butler, Karin M. and Acquesta, Erin C. S. and Darling, Michael C.},journal={Data Science in Science},note={Accepted},}
MDAI
A Multi-Objective Optimization Framework for Trustworthy Machine Learning
E. Boaz Adikaibe, Alexander I. Dessanti, J. Jake Nichol, Mark A. Smith, and Michael C. Darling
In Proceedings of Modeling Decisions for Artificial Intelligence (MDAI) 2026 , 2026
@inproceedings{Adikaibe.2026.accepted.multiobjective,year={2026},title={{A Multi-Objective Optimization Framework for Trustworthy Machine Learning}},author={Adikaibe, E. Boaz and Dessanti, Alexander I. and Nichol, J. Jake and Smith, Mark A. and Darling, Michael C.},booktitle={Proceedings of Modeling Decisions for Artificial Intelligence (MDAI) 2026},note={To appear},}
SmartGridComm
Causal AI-Powered Dynamic ML Model Orchestration for Robust Cybersecurity
Georgios Fragkos, J. Jake Nichol, Tian Yu Yen, Logan Blakely, Shamina Hossain-McKenzie, Adrian Chavez, and Sidney Wright
In Proceedings of the IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) 2026 , 2026
@inproceedings{Fragkos.2026.accepted.causalAI,year={2026},title={{Causal AI-Powered Dynamic ML Model Orchestration for Robust Cybersecurity}},author={Fragkos, Georgios and Nichol, J. Jake and Yen, Tian Yu and Blakely, Logan and Hossain-McKenzie, Shamina and Chavez, Adrian and Wright, Sidney},booktitle={Proceedings of the IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) 2026},note={To appear},}
Preprint
Tracing the Space-Time Causal Origins of Earth System Extremes
Jhayron S. Pérez-Carrasquilla, J. Jake Nichol, Vanessa Robledo, Diana Bull, Katherine Dagon, Michael N. Evans, and Maria J. Molina
Identifying the causes of Earth’s extremes is challenging because counterfactual experiments are not possible in the observed world, while numerical experiments are computationally expensive and subject to biases. Data-driven causal discovery offers a complementary path, but existing approaches can fail in undersampled, high-dimensional regimes, and may not recover multi-timestep, multivariate pathways leading to particular events. We introduce Tracer of Causal Evolutions in Space and Time (TraCE-ST), a probabilistic Lagrangian approach that produces event-conditioned causal trajectories in multivariate gridded data. In synthetic experiments and real-world extreme events, TraCE-ST recovers known causal drivers and estimates their relative contributions, while also highlighting less-studied drivers, including orography-driven vorticity for Tropical Storm Debby (2006) and anomalous ocean-surface fluxes for the 2021 Pacific Northwest heatwave. Here, we propose causal tracking as an efficient data-driven framework for synthesizing causal evidence and generating testable hypotheses, complementing association analyses and numerical modeling while accelerating the study of high-impact events.
@unpublished{PerezCarrasquilla.2026.submitted.tracing,year={2026},title={{Tracing the Space-Time Causal Origins of Earth System Extremes}},author={P{\'e}rez-Carrasquilla, Jhayron S. and Nichol, J. Jake and Robledo, Vanessa and Bull, Diana and Dagon, Katherine and Evans, Michael N. and Molina, Maria J.},note={Under review},}
RWS
Causal Graphs for Threat Detection in Cyber-Physical Power Grids
J. Jake Nichol, Logan Blakely, and Georgios Fragkos
Submitted to IEEE Resilience Week (RWS) 2026 , 2026
@unpublished{Nichol.2026.submitted.causalgraphs,year={2026},title={{Causal Graphs for Threat Detection in Cyber-Physical Power Grids}},author={Nichol, J. Jake and Blakely, Logan and Fragkos, Georgios},note={Under review},}
Preprint
M-CaStLe: Uncovering Local Causal Structures in Multivariate Space-Time Gridded Data
J. Jake Nichol, Michael Weylandt, G. Matthew Fricke, and Melanie E. Moses
Target: Transactions on Machine Learning Research (TMLR) , 2026
@unpublished{Nichol.inprep.mcastle,year={2026},title={{M-CaStLe: Uncovering Local Causal Structures in Multivariate Space-Time Gridded Data}},author={Nichol, J. Jake and Weylandt, Michael and Fricke, G. Matthew and Moses, Melanie E.},note={In preparation},}
PNAS
Designing Institutions for an Era of Contested Expertise
A. R. Croker, D. Guariso, E. Landgren, K. Posch, A. Wiechman, E. Zajdela, and J. Jake Nichol
Opinion. Target: Proceedings of the National Academy of Sciences (PNAS) , 2026
@unpublished{Croker.inprep.institutions,year={2026},title={{Designing Institutions for an Era of Contested Expertise}},author={Croker, A. R. and Guariso, D. and Landgren, E. and Posch, K. and Wiechman, A. and Zajdela, E. and Nichol, J. Jake},note={In preparation},}
In Prep
If All Explanations Are Wrong, but Some Are Useful, How Do We Determine Which Are Credible?
@unpublished{Goode.inprep.explanations,year={2026},title={{If All Explanations Are Wrong, but Some Are Useful, How Do We Determine Which Are Credible?}},author={Goode, Katherine and Nichol, J. Jake},note={In preparation},}
2025
JGR:MLC
Space-Time Causal Discovery in Earth System Science: A Local Stencil Learning Approach
J. Jake Nichol, Michael Weylandt, G. Matthew Fricke, Melanie E. Moses, Diana Bull, and Laura P. Swiler
Journal of Geophysical Research: Machine Learning and Computation, 2025
Causal discovery tools enable scientists to infer meaningful relationships from observational data, spurring advances in fields as diverse as biology, economics, and climate science. Despite these successes, the application of causal discovery to space-time systems remains immensely challenging due to the high-dimensional nature of the data. For example, in climate sciences, modern observational temperature records over the past few decades regularly measure thousands of locations around the globe. To address these challenges, we introduce Causal Space-Time Stencil Learning (CaStLe), a novel meta-algorithm for discovering causal structures in complex space-time systems. CaStLe leverages regularities in local space-time dependencies to learn governing global dynamics. This local perspective eliminates spurious confounding and drastically reduces sample complexity, making space-time causal discovery practical and effective. For causal discovery, CaStLe flexibly accepts any appropriately adapted time series causal discovery algorithm to recover local causal structures. These advances enable causal discovery of geophysical phenomena that were previously unapproachable, including non-periodic, transient phenomena such as volcanic eruption plumes. Regularities in local space-time dependencies are transformed into informative spatial replicates, which actually improve CaStLe’s performance when applied to ever-larger spatial grids. We successfully apply CaStLe to discover the atmospheric dynamics governing the climate response to the 1991 Mount Pinatubo volcanic eruption. We provide validation experiments to demonstrate the effectiveness of CaStLe over existing causal-discovery frameworks on a range of geophysics-inspired benchmarks while identifying the method’s limitations and domains where its assumptions may not hold.
@article{Nichol.2025.10.1029/2024jh000546,year={2025},title={{Space-Time Causal Discovery in Earth System Science: A Local Stencil Learning Approach}},author={Nichol, J. Jake and Weylandt, Michael and Fricke, G. Matthew and Moses, Melanie E. and Bull, Diana and Swiler, Laura P.},journal={Journal of Geophysical Research: Machine Learning and Computation},issn={2993-5210},doi={10.1029/2024jh000546},url={https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2024JH000546},number={3},volume={2},}
Dissertation
Seeking Structure in Complex Systems: From Feature Analysis to Space-Time Causal Discovery With Earth Science Applications
J. Jake Nichol
2025
Advisor: Melanie E. Moses. Committee: G. Matthew Fricke, Abdullah Mueen, Tobias P. Fischer, Laura P. Swiler
Complex systems are difficult to study because of their many interacting parts, emergent phenomena, and feedback loops. These systems underpin all life on Earth. We need improved tools for seeking an understanding of them. This body of research presents my investigations into data-driven methods for understanding complex systems, including my invention of a novel causal discovery meta-algorithm for space-time gridded data. I demonstrated machine learning feature importance and causal discovery capabilities for comparing simulated and observed climate data. I developed a new benchmark for modeling space-time dynamics of locally driven phenomena and examined a prominent causal discovery algorithm. Finding that contemporary causal discovery struggles with the high-dimensionality of space-time gridded data, I developed CaStLe, a causal discovery meta-algorithm for recovering the space-time evolution of advective phenomena. Finally, I extended CaStLe to recover multivariate space-time dynamics. This research enhances scientists’ capabilities to explore and understand complex systems in our universe.
@phdthesis{nichol2025thesis,author={Nichol, J. Jake},title={{Seeking Structure in Complex Systems: From Feature Analysis to Space-Time Causal Discovery With Earth Science Applications}},school={The University of New Mexico},year={2025},address={Albuquerque, NM},type={{PhD} dissertation},note={Advisor: Melanie E. Moses. Committee: G. Matthew Fricke, Abdullah Mueen, Tobias P. Fischer, Laura P. Swiler},keywords={causal discovery, machine learning, Earth science, climate, volcano},}
2024
SNL Report
CLimate Impact: Determining Etiology thRough pAthways (CLDERA)
Diana Bull, Kara Peterson, Lyndsay Shand, Laura Swiler, Irina Tezaur, Ben K. Cook, Andrew Salinger, Clare Amann, Bernadette Watts, Rob Leland, Luca Bertagna, Hunter Brown, Meredith Brown, Mauricio Campos, Max Carlson, Kenny Chowdhary, Joseph Crockett, Warren Davis, Thomas Ehrmann, Robert Garrett, Katherine Goode, Mamikon Gulian, Carole Hall, Graham Harper, Joseph Hart, James Hickey, Benjamin Hillman, Brent Houchens, Jose Gabriel Huerta, Daniel Krofcheck, Justin Li, Indu Manickam, Kellie McClernon, Audrey McCombs, J. Jake Nichol, Matthew Peterson, Daniel Ries, Mark A. Smith, Andrea Staid, Andrew Steyer, James Derek Tucker, Benjamin Wagman, Jerry Watkins, Christopher Wentland, Everett Wenzel, Robert Michael Weylandt, and Andrew Yarger
Sandia National Laboratories, Tech. Rep. SAND2024-13423R , 2024
Climate impacts have broad economic, health, political, and national security ramifications. Societally relevant impacts are typically farther downstream, are the product of multiple interacting processes, and can arise over small regions and timeframes because their sources are short-term and localized. Short-term forcings (as can be seen in volcanic eruptions, climatic tipping points (e.g., the collapse of rainforests or the disappearance of sea ice), or in increasingly plausible climate interventions) fundamentally possess low signal-to-noise and could benefit from accounting for the multiple conditional processes through which a downstream impact arises. Under the Grand Challenge LDRD CLDERA (CLimate impacts: Discovering Etiology thRough pAthways), we have developed tools to enable downstream impact attribution from geographically and temporally localized source forcings in the climate. CLDERA developed methods that can distinguish how a localized source drives the climate system to respond with particular impacts. The how is embodied in pathways – the spatio-temporally evolving chain of physical processes that connects a source to a series of increasingly distant impacts. Novel analytic methods in pursuit of downstream impact attribution were developed and demonstrated on simulations and observations of the 1991 eruption of Mt. Pinatubo in the Philippines.
@techreport{Bull2024CLDERA,author={Bull, Diana and Peterson, Kara and Shand, Lyndsay and Swiler, Laura and Tezaur, Irina and Cook, Ben K. and Salinger, Andrew and Amann, Clare and Watts, Bernadette and Leland, Rob and Bertagna, Luca and Brown, Hunter and Brown, Meredith and Campos, Mauricio and Carlson, Max and Chowdhary, Kenny and Crockett, Joseph and Davis, Warren and Ehrmann, Thomas and Garrett, Robert and Goode, Katherine and Gulian, Mamikon and Hall, Carole and Harper, Graham and Hart, Joseph and Hickey, James and Hillman, Benjamin and Houchens, Brent and Huerta, Jose Gabriel and Krofcheck, Daniel and Li, Justin and Manickam, Indu and McClernon, Kellie and McCombs, Audrey and Nichol, J. Jake and Peterson, Matthew and Ries, Daniel and Smith, Mark A. and Staid, Andrea and Steyer, Andrew and Tucker, James Derek and Wagman, Benjamin and Watkins, Jerry and Wentland, Christopher and Wenzel, Everett and Weylandt, Robert Michael and Yarger, Andrew},title={{CLimate Impact: Determining Etiology thRough pAthways (CLDERA)}},institution={Sandia National Laboratories},number={SAND2024-13423R},address={Albuquerque, NM},year={2024},doi={10.2172/2480139},}
2023
SNL Report
Benchmarking the PCMCI Causal Discovery Algorithm for Spatiotemporal Systems
J. Jake Nichol, Michael Weylandt, Mark Smith, and Laura Swiler
Causal discovery algorithms construct hypothesized causal graphs that depict causal dependencies among variables in observational data. While powerful, the accuracy of these algorithms is highly sensitive to the underlying dynamics of the system in ways that have not been fully characterized in the literature. In this report, we benchmark the PCMCI causal discovery algorithm in its application to gridded spatiotemporal systems. Effectively computing grid-level causal graphs on large grids will enable analysis of the causal impacts of transient and mobile spatial phenomena in large systems, such as the Earth’s climate. We evaluate the performance of PCMCI with a set of structural causal models, using simulated spatial vector autoregressive processes in one- and two-dimensions. We develop computational and analytical tools for characterizing these processes and their associated causal graphs. Our findings suggest that direct application of PCMCI is not suitable for the analysis of dynamical spatiotemporal gridded systems, such as climatological data, without significant preprocessing and downscaling of the data. PCMCI requires unrealistic sample sizes to achieve acceptable performance on even modestly sized problems and suffers from a notable curse of dimensionality. This work suggests that, even under generous structural assumptions, significant additional algorithmic improvements are needed before causal discovery algorithms can be reliably applied to grid-level outputs of earth system models.
@techreport{Nichol.2023.10.2172/1991387,year={2023},author={Nichol, J. Jake and Weylandt, Michael and Smith, Mark and Swiler, Laura},title={{Benchmarking the PCMCI Causal Discovery Algorithm for Spatiotemporal Systems}},institution={Sandia National Laboratories},url={https://www.osti.gov/biblio/1991387},}
2021
JCAM
Machine Learning Feature Analysis Illuminates Disparity Between E3SM Climate Models and Observed Climate Change
J. Jake Nichol, Matthew G. Peterson, Kara J. Peterson, G. Matthew Fricke, and Melanie E. Moses
Journal of Computational and Applied Mathematics, 2021
In September of 2020, Arctic sea ice extent was the second-lowest on record. State of the art climate prediction uses Earth system models (ESMs), driven by systems of differential equations representing the laws of physics. Previously, these models have tended to underestimate Arctic sea ice loss. The issue is grave because accurate modeling is critical for economic, ecological, and geopolitical planning. We use machine learning techniques, including random forest regression and Gini importance, to show that the Energy Exascale Earth System Model (E3SM) relies too heavily on just one of the ten chosen climatological quantities to predict September sea ice averages. Furthermore, E3SM gives too much importance to six of those quantities when compared to observed data. Identifying the features that climate models incorrectly rely on should allow climatologists to improve prediction accuracy.
@article{Nichol.2021.10.1016/j.cam.2021.113451,year={2021},title={{Machine Learning Feature Analysis Illuminates Disparity Between E3SM Climate Models and Observed Climate Change}},author={Nichol, J. Jake and Peterson, Matthew G. and Peterson, Kara J. and Fricke, G. Matthew and Moses, Melanie E.},journal={Journal of Computational and Applied Mathematics},issn={0377-0427},doi={10.1016/j.cam.2021.113451},url={https://www.sciencedirect.com/science/article/abs/pii/S0377042721000704},pages={113451},volume={395},}
ICML
Learning Why: Data-Driven Causal Evaluations of Climate Models
J. Jake Nichol, Matthew Peterson, G. Matthew Fricke, and Kara Peterson
In ICML 2021 Workshop: Tackling Climate Change with Machine Learning , 2021
We plan to use nascent data-driven causal discovery methods to find and compare causal relationships in observed data and climate model output. We will look at ten different features in the Arctic climate collected from public databases and from the Energy Exascale Earth System Model (E3SM). In identifying and comparing the resulting causal networks, we hope to find important differences between observed causal relationships and those in climate models. With these, climate modeling experts will be able to improve the coupling and parameterization of E3SM and other climate models.
@inproceedings{Nichol.2021.10.2172/1884401,year={2021},title={{Learning Why: Data-Driven Causal Evaluations of Climate Models}},author={Nichol, J. Jake and Peterson, Matthew and Fricke, G. Matthew and Peterson, Kara},booktitle={ICML 2021 Workshop: Tackling Climate Change with Machine Learning},doi={10.2172/1884401},}
SNL Report
Causal Evaluations for Identifying Differences between Observations and Earth System Models
J. Jake Nichol, Matthew Peterson, and Kara Peterson
@techreport{Nichol.2021.10.2172/1820528,year={2021},title={{Causal Evaluations for Identifying Differences between Observations and Earth System Models}},author={Nichol, J. Jake and Peterson, Matthew and Peterson, Kara},institution={Sandia National Laboratories},doi={10.2172/1820528},url={https://www.osti.gov/biblio/1820528},}
White Paper
Advancing Sea Ice Predictability in E3SM with Machine Learning
Kara Peterson, Warren Davis, Matt Peterson, J. Jake Nichol, Kenny Chowdhary, and Marta D’Elia
To improve predictions of sea ice in E3SM we propose to develop a hierarchy of data-driven models using observational and simulation data to investigate the most important Earth system drivers of sea ice variability and loss, develop surrogates that build on the reduced parameter space of important drivers, and, where appropriate, couple machine learning models with standard PDE models to capture important physical behavior at different scales.
@techreport{osti_1769655,title={{Advancing Sea Ice Predictability in E3SM with Machine Learning}},author={Peterson, Kara and Davis, Warren and Peterson, Matt and Nichol, J. Jake and Chowdhary, Kenny and D'Elia, Marta},institution={Sandia National Laboratories},doi={10.2172/1769655},url={https://www.osti.gov/biblio/1769655},year={2021},}
White Paper
Water Cycle-Driven Infectious Diseases as Multiscale, Reliable, Continuously Updating Water Cycle Sensors
Amy Powell, Erin C. S. Acquesta, Warren L. Davis, J. Jake Nichol, Irina Tezaur, Kara Peterson, Susan Rempe, and Jose Gabriel Huerta
We propose a novel synthesis of observational and simulated data (climatological and biological) to enhance understanding of the real-world interplay between climate (here, the water cycle) and the epidemiology of water cycle-driven infectious disease. Our approach will leverage state-of-the-art in Artificial Intelligence (AI) to measure the degree to which climate change-driven shifts in water cycle can be predicted by supplementing sparse and irregular climate data with water cycle-driven infectious disease resources.
@techreport{osti_1769797,title={{Water Cycle-Driven Infectious Diseases as Multiscale, Reliable, Continuously Updating Water Cycle Sensors}},author={Powell, Amy and Acquesta, Erin C. S. and Davis, Warren L. and Nichol, J. Jake and Tezaur, Irina and Peterson, Kara and Rempe, Susan and Huerta, Jose Gabriel},institution={Sandia National Laboratories},doi={10.2172/1769797},url={https://www.osti.gov/biblio/1769797},year={2021},}
2020
SNL Report
Arctic Tipping Points Triggering Global Change (LDRD Final Report)
Kara J. Peterson, Amy Jo Powell, Irina Kalashnikova Tezaur, Erika Louise Roesler, J. Jake Nichol, Matthew Gregor Peterson, Warren Leon Davis, John Davis Jakeman, David John Stracuzzi, and Diana L. Bull
@techreport{osti_1669210,title={{Arctic Tipping Points Triggering Global Change (LDRD Final Report)}},author={Peterson, Kara J. and Powell, Amy Jo and Tezaur, Irina Kalashnikova and Roesler, Erika Louise and Nichol, J. Jake and Peterson, Matthew Gregor and Davis, Warren Leon and Jakeman, John Davis and Stracuzzi, David John and Bull, Diana L.},institution={Sandia National Laboratories},doi={10.2172/1669210},url={https://www.osti.gov/biblio/1669210},year={2020},}
2018
ICRA
The Swarmathon: An Autonomous Swarm Robotics Competition
Sarah M. Ackerman, G. Matthew Fricke, Joshua P. Hecker, Kastro M. Hamed, Samantha R. Fowler, Antonio D. Griego, Jarett C. Jones, J. Jake Nichol, Kurt W. Leucht, and Melanie E. Moses
In ICRA 2018 Workshop: Swarms — From Biology to Robotics and Back , 2018
The Swarmathon is a swarm robotics programming challenge that engages college students from minority-serving institutions in NASA’s Journey to Mars. Teams compete by programming a group of robots to search for, pick up, and drop off resources in a collection zone. The Swarmathon produces prototypes for robot swarms that would collect resources on the surface of Mars. Robots operate completely autonomously with no global map, and each team’s algorithm must be sufficiently flexible to effectively find resources from a variety of unknown distributions. In the first 2 years, over 1,100 students participated. 63% of students were from underrepresented ethnic and racial groups.
@inproceedings{Ackerman.2018.10.48550/arxiv.1805.08320,year={2018},title={{The Swarmathon: An Autonomous Swarm Robotics Competition}},author={Ackerman, Sarah M. and Fricke, G. Matthew and Hecker, Joshua P. and Hamed, Kastro M. and Fowler, Samantha R. and Griego, Antonio D. and Jones, Jarett C. and Nichol, J. Jake and Leucht, Kurt W. and Moses, Melanie E.},booktitle={ICRA 2018 Workshop: Swarms --- From Biology to Robotics and Back},doi={10.48550/arxiv.1805.08320},}
