ScAI Lab News

Bharat's work on modeling spatiotemporal chaos with stochastic interpolants has been awarded the 3rd place prize in the Los-Alamos National Labs Theoretical Division lightning talks. Congratulations Bharat!
Bharat Srikishan is off to Los-Alamos National Labs for a summer internship! Good luck Bharat (May 2025)
Nilay Anurag has been awarded the `Outstanding Master's Thesis` award for his thesis titled `Improving Prediction Performance in Physics Informed Machine Learning Through Pretraining and Adaptation`. Congratulations Nilay! (May 2025)
Ali El Sayed has successfully defended his MS thesis titled `LLM-Modulo-Rec: Leveraging Approximate World-Knowledge of LLMs to Improve eCommerce Search Ranking Under Data Paucity`. Ali is starting a Ph.D at Virginia Tech in Fall 2025! Congrats and good luck Ali ! (May 2025)
Bharat's paper published at ICLR 2025! Title: MODEL-AGNOSTIC KNOWLEDGE GUIDED CORRECTION FOR IMPROVED NEURAL SURROGATE ROLLOUT (April 2025)
Paper led by ScAI Lab M.S. student Ali El Sayed accepted & selected for Oral Presentation @ Workshop on GenAI for E-Commerce (2024)! (Oct. 2024)
Paper on Information-Guided Regularization of Language Models, accepted to COLM 2024!! [arXiv link]. Collab. with Sanghani Center@ VT. (July 2024)
Co-organized 1-Day Tutorial at Oak-Ridge National Laboratories on Knowledge-Guided Machine Learning (KGML). [Website link] (July 2024)
Bharat is off for a summer internship at Los Alamos National Labs! (Jun. - Aug. 2024)
Bharat's paper on Parsimonious SciML accepted to AAAI 2024 !! [arXiv link] (Feb. 2024)
Co-organized 3rd KGML Symposium at AAAI 2024 !! [website link] (Feb. 2024)
Ishaan selected as Regeneron Top 300 Scholar for his West-Nile Virus forecasting work conducted @ ScAI Lab (Jan. 2024)!
ScAI Lab Awarded AIRS Summer Fellowship for forecasting flu and Covid19 (Summer 2023)
ScAI Lab Awarded 1 Pinnacle Scholar summer fellowship to work on Disease Modeling (Summer 2023)!
2 papers @ NeurIPS 2022 AI4Science Workshop!
1 paper on numeracy in NLP, accepted @ NeurIPS 2022 MATH-AI Workshop!

Research Focus

Our group at ScAI lab, is especially focused on leveraging scientific domain knowledge to improve model generalization, decision interpretability and reduce the negative effects of data paucity and noise. Most recently, we have been focused on leveraging machine learning techniques to address challenges in physics (specifically computational fluid dynamics) to alleviate the cost of expensive simulations using science-guided machine learning models.

Our other areas of research interest include:

Transfer Learning & Domain Adaptation
Multi-task & Meta Learning
Time-series Forecasting & Anomaly Detection (especially in the context of Cyber-Physical Systems)
Intelligent Disaster Management
Disease Modeling (COVID-19, Influenza-Like-illnesses).

Selected Research Projects

Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback (ICDM 2022)

Anomaly detection is a ubiquitous and challenging task, relevant across many disciplines. With the vital role communication networks play in our daily lives, the security of these networks is imperative for the smooth functioning of society. To this end, we propose a novel self-supervised deep learning framework CAAD for anomaly detection in wireless communication systems. Specifically, CAAD employs contrastive learning in an adversarial setup to learn effective representations of normal and anomalous behavior in wireless networks. We conduct rigorous performance comparisons of CAAD with several state-of-the-art anomaly detection techniques and verify that CAAD yields a mean performance improvement of 92.84%. Additionally, we also augment CAAD enabling it to systematically incorporate expert feedback through a novel contrastive learning feedback loop to improve the learned representations and thereby reduce prediction uncertainty (CAAD-EF ). We view CAADEF as a novel, holistic, and widely applicable solution to anomaly detection. Our source code and data are available online (https://github.com/rgopikrishna-vt/CAAD)

PhyFlow: Physics-Guided Deep Learning for Generating Interpretable 3D Flow Fields

Generating flow fields (such as pressure and velocity fields) in 3D space is a fundamental task in computational fluid dynamics (CFD), with applications across a vast spectrum of science and engineering problems. An important class of fluid flow problems in CFD is multi-phase flow, where dispersed solid particles are present in the fluid flow. Despite recent developments in deep learning (DL) for CFD applications, current state-of-the-art is still unable to model 3D flow fields, especially in multi-phase flow settings.

It is with this goal that we introduce PhyFlow, a novel physics-guided deep learning architecture for modeling 3D multi-phase fluid flows, designed to mimic the popular projection method for solving fluid flows in CFD simulations. We demonstrate that PhyFlow, generates high quality flow fields and yields a 49.61% improvement over other state-of-the-art baselines. We also test the quality of PhyFlow based fields by employing them in downstream tasks like particle drag force prediction and demonstrate state-of-the-art results, improving upon the previous best models by 9.89%. Finally, we demonstrate the consistency of PhyFlow predictions with known underlying physics governing equations. Our source code and data are available online at: tinyurl.com/e5mrerb7 .

Steering a Historical Disease Forecasting Model Under a Pandemic:
Case of Flu and COVID-19

Timely forecasting of diseases like influenza, helps health organizations and policymakers by allowing them adequate preparation time for decision making. However, due to the non-trivial dynamics of influenza seasonal progression, effective influenza forecasting still remains a challenge despite increasing research interest. The forecasting challenge is further heightened amidst the COVID-19 pandemic, when the influenza-like illness (ILI) counts are affected by various factors such as symptomatic similarities with COVID-19 and shift in healthcare seeking patterns of the general population. Hence, historical influenza forecasting models are unable to adapt to this new trend. Therefore, we present CALI-Net, a neural transfer learning architecture, that uses novel knowledge distillation techniques to 'steer' a historical disease forecasting model to new scenarios where flu and COVID-19 co-exist. CALI-Net allows this automatic adaptation of ILI forecasts by learning to emphasize learning from either COVID-related signals or from historical forecasting models at appropriate times. Through our CALI-Net framework, we are able to effectively exploit representations from historical ILI forecasting models and historical ILI data as well as the limited COVID-related signals.

PhyNet: Physics Guided Neural Networks for Particle Drag Force Prediction in Assembly

Physics-based simulations are often used to model and understand complex physical systems in domains like fluid dynamics. Such simulations although used frequently, often suffer from inaccurate or incomplete representations either due to their high computational costs or due to lack of complete physical knowledge of the system. In such situations, it is useful to employ machine learning to fill the gap by learning a model of the complex physical process directly from simulation data. However, as data generation through simulations is costly, we need to develop models being cognizant of data paucity issues. In such scenarios it is helpful if the rich physical knowledge of the application domain is incorporated in the architectural design of machine learning models. We can also use information from physics-based simulations to guide the learning process using aggregate supervision to favorably constrain the learning process. In this paper, we propose PhyNet , a deep learning model using physics-guided structural priors and physics-guided aggregate supervision for modeling the drag forces acting on each particle in a Computational Fluid Dynamics-Discrete Element Method (CFD-DEM). We conduct extensive experiments in the context of drag force prediction and showcase the usefulness of including physics knowledge in our deep learning formulation.

Incorporating Prior Domain Knowledge into Deep Neural Networks

In recent years, the large amount of labeled data available has also helped tend research toward using minimal domain knowledge, e.g., in deep neural network research. However, in many situations, data is still limited and of poor quality. Can domain knowledge be useful in such settings? Here, we propose domain adapted neural networks (DANN) to explore how domain knowledge can be integrated into model training for deep networks. In particular, we incorporate loss terms for knowledge available as monotonicity constraints and approximation constraints. We evaluate our model on both synthetic data generated using the popular Bohachevsky function and a real-world dataset for predicting oxygen solubility in water. In both situations, we find that our DANN model outperforms its domain-agnostic counterpart, yielding an overall mean performance improvement of 19.5%, with a worst and best-case performance improvement of 4% and 42.7% respectively.

Cut-n-Reveal (CnR): Temporal Segmentation with Explanations

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 paper, 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. CnR also provides a novel explanation optimization formulation to find an intuitive explanation of the segmentation, such that the explanation highlights the culprit time-series of the change in each segment. Through extensive experiments, we have demonstrated that our method consistently outperforms competitors in multiple real datasets with ground truth. We further demonstrate results on 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, while baselines typically do not give meaningful results.

illiad: Intelligent Invariant and Anomaly Detection in Cyber-Physical Systems

Cyber physical systems (CPSs) are today ubiquitous in urban environments. Such systems now serve as the backbone to numerous critical infrastructure applications, from smart grids to IoT installations. Scalable and seamless operation of such CPSs requires sophisticated tools for monitoring the time series progression of the system, dynamically tracking relationships, and issuing alerts about anomalies to operators. We present an online monitoring system (illiad) that models the state of the CPS as a function of its relationships between constituent components, using a combination of model-based and data-driven strategies. In addition to accurate inference for state estimation and anomaly tracking,illiad also exploits the underlying network structure of the CPS (wired or wireless) for state estimation purposes. We demonstrate the application of illiad to two diverse settings: a wireless sensor motes application and an IEEE 33-bus microgrid.

Publications

Muralidhar, N., Zubair, A., Weidler, N., Gerdes, R., & Ramakrishnan, N. Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores. In Proceedings of the 14th IEEE International Symposium on Hardware-Oriented Security and Trust (IEEE HOST) 2021.
Muralidhar, N., Bu, J., Cao, Z., Raj, N., Ramakrishnan, N., Tafti, D., & Karpatne, A., “Phyflow: Physics-guided deep learning for generating interpretable 3D flow fields,” In Proceedings of the 21st IEEE International Conference on Data Mining (ICDM), IEEE, 2021.
Rodriguez, A.*,Muralidhar, N.,*, Adhikari, B., Tabassum, A., Ramakrishnan, N., & Prakash B.A. Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19. AAAI 2021
Rodriguez, A.*,Muralidhar, N.,*, Adhikari, B., Tabassum, A., Ramakrishnan, N., & Prakash B.A. Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19. NeurIPS Machine Learning in Public Health (MLPH) Workshop, Virtual Event. December 2020
Muralidhar, N., Mayer, B., Self, N., Kondoju, P., Tonshal, B., Schmotzer, J., & Ramakrishnan,N. RAD: Rapid Automobile Data Analytics Framework for Structured Data. In Proceedings of the 9th SIGKDD International Workshop on Urban Computing (UrbComp 2020).
Muralidhar, N., Bu, J., Cao, Z., He, L., Ramakrishnan, N., Tafti, D., & Karpatne, A. (2020).Physics-Guided Deep Learning for Drag Force Prediction in Dense Fluid-Particulate Systems. BigData, 8(5), 431-449.(Impact Factor: 3.644)
Muralidhar, N., Tabassum, A., Chen, L., Chinthavali, S., Ramakrishnan, N., & Prakash, B. A. (2020). Cut-n-Reveal: Time Series Segmentations with Explanations. ACM Transactions on Intelligent Systems and Technology (TIST), 11(5), 1-26. (Impact Factor: 3.971)
Muralidhar, N., Bu, J., Cao, Z., He, L., Ramakrishnan, N., Tafti, D., & Karpatne, A. "Physics Guided Learning for Particle Drag Force Estimation in Multi Phase Fluid Flow." Proceedings of the 3rd Workshop on Physics Informed Machine Learning 2020.
Muralidhar, N., Bu, J., Cao, Z., He, L., Ramakrishnan, N., Tafti, D., & Karpatne, A. (2020). PhyNet: Physics Guided Neural Networks for Particle Drag Force Prediction in Assembly. In Proceedings of the 2020 SIAM International Conference on Data Mining (pp. 559-567). Society for Industrial and Applied Mathematics. [CODE]
Muralidhar, N., Muthiah, S., Nakayama, K., Sharma, R., & Ramakrishnan, N. (2019, December). Multivariate Long-Term State Forecasting in Cyber-Physical Systems: A Sequence to SequenceApproach. In 2019 IEEE International Conference on Big Data (IEEE Big Data) (pp. 543-552).
Muralidhar, N., Muthiah, S., & Ramakrishnan, N. (2019). DyAt Nets:Dynamic Attention Networks for State Forecasting in Cyber-Physical Systems. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19. International Joint Conferences on Artificial Intelligence Organization, 3180–3186. https://doi.org/10.24963/ijcai.2019/441 [CODE]
Muralidhar, N., Islam, M.R., Marwah, M., Karpatne, A., & Ramakrishnan, N. (2018) Incorporating Prior Domain Knowledge into Deep Neural Networks. In 2018 IEEE International Conference on Big Data (Big Data), pp. 36-45. IEEE, 2018.
Muralidhar, N., Wang, C., Self, N., Momtazpour M., Nakayama, K., Sharma, R., & Ramakrishnan, N. (2018) illiad: Intelligent invariant and anomaly detection in cyber-physical systems. ACM Transactions on Intelligent Systems and Technology (TIST) 9, no. 3 (2018): 35. (Impact Factor: 3.971)
Muralidhar, N., Rangwala H., & Han E.H. Recommending Temporally Relevant News Content from Implicit Feedback Data. In 2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 689-696. IEEE, 2015.

Selected Honors & Awards

First Place Prize COVID-19 Symptom Data Challenge organized by Catalyst Health & Facebook . . . . . 2020
Second Place Prize in COVID-19 Grand Challenge Hosted by C3.ai . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2020
Top 33% Ranking Reviewer Appreciation (International Conference on Machine Learning) . . . . . . . . . . . 2020
Invited Member of τβπ Honor Society (Virginia Tech Chapter) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2020-present
Invited Life Member of ΦKΦ Honor Society (Virginia Tech Chapter) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2017-present
National Science Foundation Urban Computing Fellowship . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2016-2018
Award for Academic Excellence - Dept. of Comp. Sci, George Mason University . . . . . . . . . . . . . . . . . . . 2015

Bharat's work on modeling spatiotemporal chaos with stochastic interpolants has been awarded the 3rd place prize in the Los-Alamos National Labs Theoretical Division lightning talks. Congratulations Bharat!

Bharat Srikishan is off to Los-Alamos National Labs for a summer internship! Good luck Bharat (May 2025)

Nilay Anurag has been awarded the `Outstanding Master's Thesis` award for his thesis titled `Improving Prediction Performance in Physics Informed Machine Learning Through Pretraining and Adaptation`. Congratulations Nilay! (May 2025)

Ali El Sayed has successfully defended his MS thesis titled `LLM-Modulo-Rec: Leveraging Approximate World-Knowledge of LLMs to Improve eCommerce Search Ranking Under Data Paucity`. Ali is starting a Ph.D at Virginia Tech in Fall 2025! Congrats and good luck Ali ! (May 2025)

Bharat's paper published at ICLR 2025! Title: MODEL-AGNOSTIC KNOWLEDGE GUIDED CORRECTION FOR IMPROVED NEURAL SURROGATE ROLLOUT (April 2025)

Paper led by ScAI Lab M.S. student Ali El Sayed accepted & selected for Oral Presentation @ Workshop on GenAI for E-Commerce (2024)! (Oct. 2024)

Paper on Information-Guided Regularization of Language Models, accepted to COLM 2024!! [arXiv link]. Collab. with Sanghani Center@ VT. (July 2024)

Co-organized 1-Day Tutorial at Oak-Ridge National Laboratories on Knowledge-Guided Machine Learning (KGML). [Website link] (July 2024)

Bharat is off for a summer internship at Los Alamos National Labs! (Jun. - Aug. 2024)

Bharat's paper on Parsimonious SciML accepted to AAAI 2024 !! [arXiv link] (Feb. 2024)

Co-organized 3rd KGML Symposium at AAAI 2024 !! [website link] (Feb. 2024)

Ishaan selected as Regeneron Top 300 Scholar for his West-Nile Virus forecasting work conducted @ ScAI Lab (Jan. 2024)!

ScAI Lab Awarded AIRS Summer Fellowship for forecasting flu and Covid19 (Summer 2023)

ScAI Lab Awarded 1 Pinnacle Scholar summer fellowship to work on Disease Modeling (Summer 2023)!

2 papers @ NeurIPS 2022 AI4Science Workshop!

1 paper on numeracy in NLP, accepted @ NeurIPS 2022 MATH-AI Workshop!

Our other areas of research interest include:

Transfer Learning & Domain Adaptation

Multi-task & Meta Learning

Time-series Forecasting & Anomaly Detection (especially in the context of Cyber-Physical Systems)

Intelligent Disaster Management

Disease Modeling (COVID-19, Influenza-Like-illnesses).

Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback (ICDM 2022)

Contact: nmurali1 at stevens dot edu