An official website of the United States government
Abstract Compound events (CEs) are attracting increased attention due to their significant societal and ecological impacts. However, their inherent complexity can pose challenges for climate scientists and practitioners, highlighting the need for a more approachable and intuitive framework for detecting and visualising CEs. Here, we introduce the Compound Events Toolbox and Dataset (CETD), which provides the first integrated, interactive, and extensible platform for CE detection and visualisation. Employing observations, reanalysis, and model simulations, CETD can quantify the frequency, duration, and severity of multiple CE types: multivariate, sequential, and concurrent events. It can analyse CEs often linked to severe impacts on human health, wildfires, and air pollution, such as hot-dry, wet-windy, and hot-dry-stagnation events. To validate the performance of CETD, we conduct statistical analyses for several high-impact events, such as the 2019 Australian wildfires and the 2022 European heatwaves. The accessibility and extensibility of CETD will benefit the broader community by enabling them to better understand and prepare for the risks and challenges posed by CEs in a warming world.
more »
« less
This content will become publicly available on May 6, 2026
Toward Foundation Models for Online Complex Event Detection in CPS-IoT: A Case Study
Complex events (CEs) play a crucial role in CPS-IoT applications, enabling high-level decision-making in domains such as smart monitoring and autonomous systems. However, most existing models focus on short-span perception tasks, lacking the long-term reasoning required for CE detection. CEs consist of sequences of short-time atomic events (AEs) governed by spatiotemporal dependencies. Detecting them is difficult due to long, noisy sensor data and the challenge of filtering out irrelevant AEs while capturing meaningful patterns. This work explores CE detection as a case study for CPS-IoT foundation models capable of long-term reasoning. We evaluate three approaches: (1) leveraging large language models (LLMs), (2) employing various neural architectures that learn CE rules from data, and (3) adopting a neurosymbolic approach that integrates neural models with symbolic engines embedding human knowledge. Our results show that the state-space model, Mamba, which belongs to the second category, outperforms all methods in accuracy and generalization to longer, unseen sensor traces. These findings suggest that state-space models could be a strong backbone for CPS-IoT foundation models for long-span reasoning tasks.
more »
« less
- Award ID(s):
- 2325956
- PAR ID:
- 10592186
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400716089
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Location:
- Irvine CA USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Sensors are used to monitor various parameters in many real-world applications. Sudden changes in the underlying patterns of the sensors readings may represent events of interest. Therefore, event detection, an important temporal version of outlier detection, is one of the primary motivating applications in sensor networks. This work describes the implementation of a real-time outlier detection that uses an Autoencoder-LSTM neural-network accelerator implemented on the Xilinx PYNQ-Z1 development board. The implemented accelerator consists of a fine-tuned Autoencoder to extract the latent features in sensor data followed by a Long short-term memory (LSTM) network to predict the next step and detect outliers in real-time. The implemented design achieves 2.06 ms minimum latency and 85.9 GOp/s maximum throughput. The low latency and 0.25 W power consumption of the Autoencoder-LSTM outlier detector makes it suitable for resource-constrained computing platforms.more » « less
-
Anomaly detection in time-series data is an integral part in the context of the Internet of Things (IoT). In particular, with the advent of sophisticated deep and machine learning-based techniques, this line of research has attracted many researchers to develop more accurate anomaly detection algorithms. The problem itself has been a long-lasting challenging problem in security and especially in malware detection and data tampering. The advancement of the IoT paradigm as well as the increasing number of cyber attacks on the networks of the Internet of Things worldwide raises the concern of whether flexible and simple yet accurate anomaly detection techniques exist. In this paper, we investigate the performance of deep learning-based models including recurrent neural network-based Bidirectional LSTM (BI-LSTM), Long Short-Term Memory (LSTM), CNN-based Temporal Convolutional (TCN), and CuDNN-LSTM, which is a fast LSTM implementation supported by CuDNN. In particular, we assess the performance of these models with respect to accuracy and the training time needed to build such models. According to our experiment, using different timestamps (i.e., 15, 20, and 30 min), we observe that in terms of performance, the CuDNN-LSTM model outperforms other models, whereas in terms of training time, the TCN-based model is trained faster. We report the results of experiments in comparing these four models with various look-back values.more » « less
-
Driven by the expanse of Internet of Things (IoT) and Cyber-Physical Systems (CPS), there is an increasing demand to process streams of temporal data on embedded devices with limited energy and power resources. Among all potential solutions, neuromorphic computing with spiking neural networks (SNN) that mimic the behavior of brain, have recently been placed at the forefront. Encoding information into sparse and distributed spike events enables low-power implementations, and the complex spatial temporal dynamics of synapses and neurons enable SNNs to detect temporal pattern. However, most existing hardware SNN implementations use simplified neuron and synapse models ignoring synapse dynamic, which is critical for temporal pattern detection and other applications that require temporal dynamics. To adopt a more realistic synapse model in neuromorphic platform its significant computation overhead must be addressed. In this work, we propose an FPGA-based SNN with biologically realistic neuron and synapse for temporal information processing. An encoding scheme to convert continuous real-valued information into sparse spike events is presented. The event-driven implementation of synapse dynamic model and its hardware design that is optimized to exploit the sparsity are also presented. Finally, we train the SNN on various temporal pattern-learning tasks and evaluate its performance and efficiency as compared to rate-based models and artificial neural networks on different embedded platforms. Experiments show that our work can achieve 10X speed up and 196X gains in energy efficiency compared with GPU.more » « less
-
Droughts and heatwaves are rising concerns with regard to the frequent formation of the compound or concurrent extremes (CEs), which can cause greater havoc than an individual event of a higher magnitude. Recently, they have been frequently detected to form CEs together or with other events (e.g., floods, aridity, and humidity events) concurrently or with spatiotemporal lags. Therefore, this systematic review assesses these CEs by reviewing the following aspects: CE hotspots, events, and variable combinations that form CEs; frequently analyzed CE parameters (e.g., frequency and severity); large-scale modes of climate variability (CV) as drivers alongside the approaches to relate them to CEs; and CE impacts (e.g., yield loss and fire risk) alongside the impact integration approaches from 166 screened publications. Additionally, three varied analysis frameworks of CEs are summarized to highlight the different analysis components of drought- and heatwave-associated CEs, which is the novelty of this study. The analysis frameworks vary with regard to the three major assessment objectives: only CE parameters (event–event), driver association (event–driver), and impacts (event–impact). According to this review, the most frequently reported hotspots of these CEs in global studies are southern Africa, Australia, South America, and Southeast Asia. In regional studies, several vital hotspots (e.g., Iberian Peninsula, Balkans, and Mediterranean Basin) have been reported, some of which have not been mentioned in global studies because they usually report hotspots as broader regions. In addition, different event combinations (e.g., drought and heatwave; and heatwave and stagnation) are analyzed by varying the combination of variables, namely, temperature, precipitation, and their derived indices. Thus, this study presents three major analysis frameworks and components of drought- and heatwave-associated CE analysis for prospective researchers.more » « less
