Modeling dynamical systems is crucial for a wide range of tasks, but it remains challenging due to complex nonlinear dynamics, limited observations, or lack of prior knowledge. Recently, data-driven approaches such as Neural Ordinary Differential Equations (NODE) have shown promising results by leveraging the expressive power of neural networks to model unknown dynamics. However, these approaches often suffer from limited labeled training data, leading to poor generalization and suboptimal predictions. On the other hand, semi-supervised algorithms can utilize abundant unlabeled data and have demonstrated good performance in classification and regression tasks. We propose TS-NODE, the first semi-supervised approach to modeling dynamical systems with NODE. TS-NODE explores cheaply generated synthetic pseudo rollouts to broaden exploration in the state space and to tackle the challenges brought by lack of ground-truth system data under a teacher-student model. TS-NODE employs an unified optimization framework that corrects the teacher model based on the student's feedback while mitigating the potential false system dynamics present in pseudo rollouts. TS-NODE demonstrates significant performance improvements over a baseline Neural ODE model on multiple dynamical system modeling tasks.

As coastal cities are increasingly vulnerable to climate- related flooding, the need for accurate and timely flood predictions is pressing, particularly for emergency response planning. This study presents an approach to predict flood events at high spatial resolution, leveraging inundation maps and 15-minute rainfall data. We employ Fourier Neural Operator (FNO), a method that learns efficient approximations of solutions to parametric partial differential equations. By incorporating multi-modal data types, our FNO model captures the complex dynamics of flood events including water levels in affected areas and long-range spatial and temporal dependencies. This interdisciplinary research contributes to the development of generalizable methods for predicting floods in coastal cities.

Normalizing flows (NF) build upon invertible neural networks and have wide applications in probabilistic modeling. Currently, building a powerful yet computationally efficient flow model relies on empirical fine-tuning over a large design space. While introducing neural architecture search (NAS) to NF is desirable, the invertibility constraint of NF brings new challenges to existing NAS methods whose application is limited to unstructured neural networks. Developing efficient NAS methods specifically for NF remains an open problem. We present AutoNF, the first automated NF architectural optimization framework. First, we present a new mixture distribution formulation that allows efficient differentiable architecture search of flow models without violating the invertibility constraint. Second, under the new formulation, we convert the original NP-hard combinatorial NF architectural optimization problem to an unconstrained continuous relaxation admitting the discrete optimal architectural solution, circumventing the loss of optimality due to binarization in architectural optimization. We evaluate AutoNF with various density estimation datasets and show its superior performance-cost trade-offs over a set of existing hand-crafted baselines.

Many scientific workflows access data derived from specialized instruments. When the data is analyzed, it is accessed over wide area networks, creating bottlenecks from long access latencies. We ask the question: assuming that data must be accessed remotely, can latencies be hidden without application change? We present TAZeR, a remote I/O framework that reduces effective data access latency. TAZeR transparently converts POSIX I/O into operations that interleave application work with data transfer, i.e., read prefetching and write stage-out. TAZeR ensures read data moves directly to application memory without synchronous intervention (soft zero-copy). TAZeR uses distributed bandwidth-aware staging to exploit data reuse across application tasks and to manage the capacity constraints of fast hierarchical storage. We evaluate TAZeR on a High Energy Physics workflow where two 1 Gb/s WAN links request remote data at 48 Gb/s using non-streaming access patterns. TAZeR is 12× and 22× faster than XRootD (state-of-the-art) and file copies (current approach), respectively; and within 7% of optimal. We explore conditions under which TAZeR can hide I/O accesses by showing performance as effective staging sizes change.

In the history of Computer Science, the act of `delegation' has been the greatest multiplier of society's problem-solving ability. A scientist working on detecting anomalies in a phenomenon, does not need to re-invent matrix multiplication techniques to solve her problem. Scientific workflows provide ultimate `delegation' mechanism - where a domain scientist can completely forget the specifics of `how' her program will execute on a large cluster in an efficient and cost-effective manner and can instead focus on the mathematical formulation and theoretical robustness of her solution. We present here an approach that directly aims to make the execution of Scientific Workflows more reliable, robust and efficient. We aim that the work presented in this paper will propel the larger effort, from the scientific workflow community, of making scientific workflow execution as simple, efficient and robust as a JOIN operation in a modern database. Specifically, we apply Deep Learning techniques to develop a mechanism that forecasts the final state (success or failure) of a dynamic job in a large-scale particle physics experiment, with minimal data gathering, and as early as possible in job's life cycle. The key advantage of having a predictive mechanism to identify and anticipate failure-prone jobs is the potential for designing intelligent Fault Tolerance mechanisms to handle anomalous events. We achieve a 14% improvement in computational resources utilization, and an overall classification accuracy of 85% on real tasks executed in a High Energy Physics Computing workflow. To the best of our knowledge, this is the most exhaustive and first of its kind study of neural network architectures in context of a real-dataset profiled from a large-scale scientific workflow.

We present techniques for optimizing the performance of data-intensive workflows that execute on geographically distributed and heterogeneous resources. We optimize for both throughput and response time. Optimizing for throughput, we alleviate data-transfer bottlenecks. To hide access times of accessing remote data, we transparently introduce prefetching (overlapping data transfer and computation), without changing workflow source code. Optimizing for response time, we introduce intelligent scheduling for a set of high-priority tasks. We replace a greedy scheduler that assigns tasks without accounting for differing performance on heterogeneous resources, leading to long latencies. Intelligent scheduling rapidly selects a near-optimal solution for a bi-objective optimization problem. One objective is a good task assignment; the other objective is minimize I/O contention by distributing load across resources and time. To reason about task completion times, we use modeling tools to generate accurate predictions of execution times. We show performance results for Belle II workflow for high energy physics. The combination of these techniques can improve throughput over production Belle II configurations by 20-40%. Our work is general and adaptable to other distributed workflows.

Distributed computing platforms provide a robust mechanism to perform large-scale computations by splitting the task and data among multiple locations, possibly located thousands of miles apart geographically. Although such distribution of resources can lead to benefits, it also comes with its associated problems such as rampant duplication of file transfers increasing congestion, long job completion times, unexpected site crashing, suboptimal data transfer rates, unpredictable reliability in a time range, and suboptimal usage of storage elements. In addition, each sub-system becomes a potential failure node that can trigger system wide disruptions. In this vision paper, we outline our approach to leveraging Deep Learning algorithms to discover solutions to unique problems that arise in a system with computational infrastructure that is spread over a wide area. The presented vision, motivated by a real scientific use case from Belle II experiments, is to develop multilayer neural networks to tackle forecasting, anomaly detection and optimization challenges in a complex and distributed data movement environment. Through this vision based on Deep Learning principles, we aim to achieve reduced congestion events, faster file transfer rates, and enhanced site reliability.

Today's dynamic computing deployment for commercial and scientific applications is propelling us to an era where minor inefficiencies can snowball into significant performance and operational bottlenecks. Data center operations is increasingly relying on sensors based control systems for key decision insights. The increased sampling frequencies, cheaper storage costs and prolific deployment of sensors is producing massive volumes of operational data. However, there is a lag between rapid development of analytical techniques and its widespread practical deployment. We present empirical evidence of the potential carried by analytical techniques for operations management in computing and data centers. Using Machine Learning modeling techniques on data from a real instrumented cluster, we demonstrate that predictive modeling on operational sensor data can directly reduce systems operations monitoring costs and improve system reliability.