Extreme weather events, such as hurricanes, tornadoes, and floods, have caused significant damage to power grid systems, affecting critical infrastructures like substations, transmission lines, and generation plants. This damage often results in widespread power outages in disaster-affected areas, disrupting essential services such as healthcare, transportation, and national security. Annually, these power outage events due to extreme weather lead to economic losses ranging from 25 to 70 billion in the United States [1] ). Analyzing and understanding grid resiliency—particularly the dynamics of power outages under various weather events— is crucial for effective resource planning and maintaining reliable grid operations during such events. In this study, we conducted a preliminary analysis to model grid system resiliency under different extreme weather events across various states. Leveraging state-of-the-art deep learning time-series forecasting models, we aim to address the following research questions: • (R1) Can machine learning models predict grid resiliency in advance for a given weather event at a specific location? • (R2) Is it feasible to develop a generalized model to understand resiliency during extreme weather events? • (R3) Is historical data sufficient to model and predict resiliency for future extreme weather events?

Lithium-ion batteries, widely used for their durability and high energy storage, face the risk of internal short circuits leading to catastrophic thermal runaway events. These events, triggered by external stimuli like mechanical loads, pose safety concerns in applications such as electric vehicles. Detecting and understanding thermal runaway events is crucial, but physics-driven models struggle to explain the non-linear evolution of battery temperature during these events, considering factors like material composition and state-of-charge. Due to the rarity of these events and the cost of data collection, we propose a deep learning (DL) model to predict battery temperature responses during thermal runaway. The challenge lies in the scarcity of data, making traditional DL models prone to overfitting and learning low-quality representations of the complex process.Our approach introduces a novel few-shot architecture that incorporates an adversarially governed invariant encoding process. This architecture aims to distill "invariant" relationships by addressing distributional shifts in data across various battery properties, facilitating the detection of thermal runaway events. Specifically, our results demonstrate that deep learning models conditioned on these "invariant" representations outperform state-of-the-art baselines, achieving a remarkable 96.8% performance improvement in terms of the popular metric MAPE. This framework presents a promising direction for enhancing battery safety modeling, particularly in the context of rare and complex events like thermal runaway. Our code and code and dataset used for the paper are public1.

Critical Infrastructures (CIs) such as energy, communication, and transportation compose a complex network that sustains day-to-day commodity flows vital to national security, economic stability, and public safety. Failures caused by an extreme weather event or a man-made incident can trigger widespread cascading failures, sending ripple effects at regional or even national scales. To minimize such impact, emergency responders must identify crucial components within CIs during such stressor events in a systematic and quantifiable manner and take appropriate mitigating actions. Oak Ridge National Laboratory (ORNL) has developed a graph-based analytic system named URBAN-NET, which estimates cascading impact caused by the disruption of critical infrastructure components by leveraging the topology of a critical infrastructure network. Before and during critical events (e.g., hurricanes), the URBAN-NET system generates reports that contain the ranking of the most crucial energy components that have the most downstream impact across infrastructure layers. The developed system has been integrated with the Environment for Analysis of Geo-Located Energy Information (EAGLE-I™) system, which is a situational-awareness system operated by ORNL for the department of energy of the United States.

Li-ion Batteries (LIB), one of the most efficient energy storage devices, are used extensively in many industrial applications. These batteries consist of electrodes that are put together with heterogeneous material compositions. Imaging data of these battery electrodes obtained from X-ray tomography can explain the distribution of material constituents and allow reconstructions to study electron transport pathways. Such reconstructions of material constituents help quantify various associated properties of electrodes (e.g., volume-specific surface area, porosity) which determine the performance of batteries. These images often suffer from low image contrast between multiple material constituents, hence making it difficult for humans to distinguish and characterize these constituents through visual inspection. A minor error in detecting distributions of the material constituents can lead to magnified errors in the calculated parameters of material properties (e.g., porosity). We present MatPhase, a novel hierarchical curriculum learning technique to address the complex task of estimating material constituent distribution in battery electrodes. MatPhase comprises three modules: (i) an uncertainty-aware global model trained to yield inferences conditioned upon global knowledge of material distribution, (ii) a local model to capture relatively more fine-grained (local) distributional signals, (iii) an aggregator model to appropriately fuse the local and global effects towards obtaining the final distribution. On average, MatPhase improves prediction up to 8.5% relative to other sophisticated modeling pipelines and state-of-the-arts (SOTA) object detection models employed in the performance comparison.

Power system components are crucial based on various complex connections inter-connections among them. Crucial power system components cause the vulnerability in the network. Any minor disturbance on one of few crucial power components can lead to massive outages and hence can cripple the entire nation. Traditional power contingency analysis tools are expensive to identify the crucial components. Also, such analysis are not scalable to measure vulnerability at national-scale. In this paper, we develop a real-time scoring module which provides a metric to represent the cruciality of a power system component. Through a case-study in a disaster impacted regions, we show that our scoring module is better than traditional and popular network-centrality measure techniques.

Assessing critical infrastructure vulnerabilities is paramount to arranging efficient plans for their protection. Critical infrastructures are cyber-physical systems that can be represented as a network consisting of nodes and edges and highly interdependent in nature. Given the interdependent nature of critical infrastuctures, failure in one node may cause failure in many others resulting in a cascade of failures. In this paper, we propose a node criticality metric that uses Google’s PageRank algorithm to identify nodes that are likely to fail (are vulnerable), nodes whose failure may cascade to many other sites in the network (are important), and nodes that are both vulnerable and important (are critical). We then present a series of experiments to understand how protecting certain critical nodes can help mitigate massive cascading failures. Simulating failures in a real-world network with and without critical node protections demonstrates the importance of identifying critical nodes in an infrastructure network.

Modeling failure dynamics within a power system is a complex and challenging process due to multiple inter-dependencies and convoluted inter-domain relationships. Subject matter experts (SMEs) are interested in understanding these failure dynamics for reducing the impact from future disasters (i.e., losses or failures of power system components, such as transmission lines). Contingency analysis (CA) tools enable such ’what-if’ scenario analyses to evaluate the impacts on the power system. Analyzing all possible contingencies among N system components can be computationally expensive. An important step for performing CA is identifying a set of k ‘trigger’ components, which when failed initially can significantly impact the overall system by causing multiple failures. Currently SMEs focus on identifying these trigger components by running expensive simulations on all possible subsets, which quickly becomes infeasible. Hence finding a relevant set of trigger components (contingencies) rapidly to enable efficient and useful CA is crucial.In a collaboration between computer scientists and power system experts, we propose an efficient method for performing CA by exploiting network inter-dependencies in power system components. First, we construct a network with multiple electric grid infrastructure components and dependencies as connections among them. We reformulate the problem of finding a set of trigger components as a problem of identifying critical nodes in the network, which can cascade power failures through connected nodes and cause significant damage to the network. To guide the practical CA tools, we develop a network-based model with a probabilistic edge-weights setup using intricate domain rules. Then we conduct an empirical study on real power system data in the US for both regional and national levels. Firstly, we use power system datasets for the US to create a national-scale domain-driven model. Secondly, we demonstrate that network-based model outperforms the outputs from a real CA tool and show on average 25 × improved selection of contingencies, thereby showcasing practical benefits to the power experts.

Multivariate time-series data are gaining popularity in various urban applications, such as emergency management, public health, etc. Segmentation algorithms mostly focus on identifying discrete events with changing phases in such data. For example, consider a power outage scenario during a hurricane. Each time-series can represent the number of power failures in a county for a time period. Segments in such time-series are found in terms of different phases, such as, when a hurricane starts, counties face severe damage, and hurricane ends. Disaster management domain experts typically want to identify the most affected counties (time-series of interests) during these phases. These can be effective for retrospective analysis and decision-making for resource allocation to those regions to lessen the damage. However, getting these actionable counties directly (either by simple visualization or looking into the segmentation algorithm) is typically hard. Hence we introduce and formalize a novel problem RaTSS (Rationalization for time-series segmentation) that aims to find such time-series (rationalizations), which are actionable for the segmentation. We also propose an algorithm Find-RaTSS to find them for any black-box segmentation. We show Find-RaTSS outperforms non-trivial baselines on generalized synthetic and real data, also provides actionable insights in multiple urban domains, especially disasters and public health.

Modern society is increasingly dependent on the stability of a complex system of interdependent infrastructure sectors. Vulnerability in critical infrastructures (CIs) is defined as a measure of system susceptibility to threat scenarios. Quantifying vulnerability in CIs has not been adequately addressed in the literature. This paper presents ongoing research on how the authors model CIs as network-based models and propose a set of metrics to quantify vulnerability in CI systems. The size and complexity of the CIs make this a challenging task. These metrics could be used for planning and efficient decision-making during extreme events.

Recent hurricane events have caused unprecedented amounts of damage on critical infrastructure systems and have severely threatened our public safety and economic health. The most observable (and severe) impact of these hurricanes is the loss of electric power in many regions, which causes breakdowns in essential public services. Understanding power outages and how they evolve during a hurricane provides insights on how to reduce outages in the future, and how to improve the robustness of the underlying critical infrastructure systems. In this article, we propose a novel scalable segmentation with explanations framework to help experts understand such datasets. Our method, CnR (Cut-n-Reveal), first finds a segmentation of the outage sequences based on the temporal variations of the power outage failure process so as to capture major pattern changes. This temporal segmentation procedure is capable of accounting for both the spatial and temporal correlations of the underlying power outage process. We then propose a novel explanation optimization formulation to find an intuitive explanation of the segmentation such that the explanation highlights theculprittime series of the change in each segment. Through extensive experiments, we show that our method consistently outperforms competitors in multiple real datasets with ground truth. We further study real county-level power outage data from several recent hurricanes (Matthew, Harvey, Irma) and show that CnR recovers important, non-trivial, and actionable patterns for domain experts, whereas baselines typically do not give meaningful results.

In this paper, we introduce the concept of "dynamic groups" for Group Trip Planning (GTP) queries and propose a novel query type Dynamic Group Trip Planning (DGTP) queries. The traditional GTP query assumes that the group members remain static or fixed during the trip, whereas in the proposed DGTP queries, the group changes dynamically over the duration of a trip where members can leave or join the group at any point of interest (POI) such as a shopping center, a restaurant or a movie theater. The changes of members in a group can be either predetermined (i.e., group changes are known before the trip is planned) or in real-time (changes happen during the trip). In this paper, we provide efficient solutions for processing DGTP queries in the Euclidean space. A comprehensive experimental study using real and synthetic datasets shows that our efficient approach can compute DGTP query solutions within few seconds and significantly outperforms a naive approach in terms of query processing time and I/O access.