Environmental sustainability challenges are fuelling quests for automated solutions to manage energy and critical infrastructure systems (e.g. power grids, telecommunication networks, transportation systems, water networks) in an economically efficient and environmentally resilient way. Artificial Intelligence (AI) techniques have gained prominence in this area, given their ability to process vast amounts of heterogeneous data under uncertainty. However, most AI techniques used to date lack the ability to explain the rationale behind their decisions, hindering their applicability in high-stakes domains. Explainable AI (XAI) techniques have the potential to mitigate these issues and foster the development of supportive AI for energy management systems and critical infrastructure that is efficient and resilient, but also more transparent and socially equitable.

The Bridge will address challenges and promises around the topics above. The target audience includes those interested in bringing together XAI and energy and critical infrastructure innovation research so they can enhance each other. Attendees will walk away with a better, broader sense of where we are and where we should be going, an opportunity to find collaborators, and a strengthened community.

Programme

Time (GMT-5)
08:30 - 09:00 Registration
09:00 - 09:10 Welcome [slides]
9:10 - 9:30 Spotlight talks
9:30 - 10:10 Invited talk: Pascal Van Hentenryck, Georgia Tech
10:10 - 10:40 Break
10:40 - 11:20 Invited talk: Kyri Baker, University of Colorado Boulder [slides]
11:20 - 12:05 Tutorial: Neuromancer, Jan Drgona, Johns Hopkins [slides]
12:05 - 12:30 Poster session
12:30 - 2:00 Lunch break + poster session
2:00 - 2:40 Invited talk: Luis Piloto, DeepMind
2:40 - 3:00 Applications talk: Venkat Tirupati, ERCOT [slides]
3:00 - 3:30 Poster session
3:30 - 4:00 Break + poster session
4:00 - 4:40 Invited talk: Priya Donti, MIT [slides]
4:40 - 5:30 Discussion track
5:30 - 5:35 Closing

Accepted contributions

Causal Forecasting for Robust Explainable Predictions in Smart Buildings Simone Rossato, Daniele Meli, Alessandro Farinelli
Tackling Environment Sustainability Challenges via Reinforcement Learning and Counterfactual Explanations Luca Marzari, Enrico Marchesini
(X)AI in Water Distribution Networks André Artelt
Trustworthiness of Digital-Twin-based Automation Technology in Nuclear Power Plant Operation Paridhi Athe, Nicholas Cittadino, Trang Tran, Jacob Yoder, Nam Dinh, Tran Cao Son
XAInomaly: Explainable, Interpretable and Trustworthy AI for Next Generation Ultra-reliable Low-latency Communications (xURLLC) in 6G Networks Osman Tugay Basaran, Falko Dressler
Diagnosing and Mitigating Infeasbilities in Power Grid Optimization Using Machine Learning and Counterfactual Explanations Mostafa Mohammadian, Anna Van Boven, Kyri Baker
Energy Equity, Infrastructure and Demographic Analysis with XAI Methods Sarahana Shrestha, Aparna S. Varde, Pankaj Lal
Dynamic OPF-Net: Real-Time Stability Constrained AC Optimal Power Flow Vincenzo Di Vito, Mostafa Mohammadian, Kyri Baker, Ferdinando Fioretto
Bridging the Gap – A Grand Challenge for Explainable AI Gregory Gelfond
Human-Centered Decision Making for High-Stakes Applications in the Energy Sector Shixiang (Woody) Zhu

Submission instructions (expired)

Read instructions.

The Bridge accepts submissions to a variety of Tracks, which are described below. Our aim is to maximise opportunities and options for contributing to the Bridge and the Bridge community. Submissions to multiple Tracks are allowed. Further information is provided below on what to submit for each Track.

Submissions need to discuss interactions between XAI, Energy and Critical Infrastructure systems in some fashion. All submissions should keep in mind that Bridge attendees are not necessarily experts in both fields. Presentations should try to bridge potential gaps, and welcome questions and discussion.

Submissions are not anonymous and should be prepared using the AAAI 2025 template available here. Submissions should specify the Track they are submitted to, contain the names, affiliations and contact emails of the authors, and indicate which authors would be expected to attend the Bridge. All accepted contributions must be presented in person. All participants, whether they have an accepted contribution or not, will be required to register to AAAI 2025 using the Bridge, Tutorial and Lab only registration. Additional details for each Track are provided below.

Submission website: https://easychair.org/conferences/?conf=xaieci2025

All accepted submissions will be posted on this website. If a submission is accepted for physical presentation, authors will then be expected to provide any slides used in the presentation for inclusion in the Bridge website as well. These can be directly emailed to: f.leofante@imperial.ac.uk.


Read tracks description.

Introductions Track

The Bridge offers a chance to connect with others and explore potential collaborations. To facilitate this, we are inviting submissions to the Introductions Track from interested participants.

Introductions will consist of a five minute presentation, without slides, where participants will provide basic information about their interests, expectations from the Bridge and potential for collaboration opportunities.

Each submission should include:
  • Name
  • Photo
  • Affiliation
  • E-mail
  • At most 5 key-words to describe your interests
Due to limited time, we may select participants for presentations on a first-come, first-served basis. We encourage interested participants to submit an introduction early.

Short surveys and tutorials Track

This Track invites submission of brief surveys (4 pages max excluding references) covering topics related to the Bridge, as well as tutorials on foundational topics that may facilitate the interaction between different communities. Tutorials will be allowed approximately 30-45 minutes during the Bridge, depending on the number of submissions. Examples include, e.g. tutorials on XAI approaches or surveys on applications of AI in a specific domains where XAI might be required.

Submissions in this Track only require an extended abstract (4 page max excluding references).

Applications, demo, benchmarks Track

This Track invites submissions presenting applications of (X)AI in Energy and Critical Infrastructure Systems, presentation of Benchmark in this area, as well as live Demos of existing tools.

All submissions in this Track only require an extended abstract (1 page max excluding references) describing the application/benchmark/demo. Links to relevant online resourse need to be included in the abstract to facilitate dissemination.

Grand challenges Track

This Track invites submissions that propose, describe and motivate a grand challenge for the Bridge community. Submissions describing concrete roadmaps for pursuing the challenge, as well as quantitative metrics for measuring progress will be given higher priority.

Submissions in this Track only require an extended abstract (2 page max excluding references).

Discussion and community building Track

This Track invites submissions that propose a topic to be discussed during the Bridge. Proponents of accepted topics will be expected to lead discussions at the Bridge. Additionally, this Track will provide an opportunity for attendees to present or solicit collaboration on proposals for special issues, workshops, competitions, tools, libraries, benchmark problems, surveys and other community outreach initiatives to take place after the Bridge.

Submissions in this Track only require an extended abstract (1 page max excluding references).