An official website of the United States government
Spatiotemporal systems are ubiquitous in a large number of scientific areas, representing underlying knowledge and patterns in the data. Here, a fundamental question usually arises as how to understand and characterize these spatiotemporal systems with a certain data-driven machine learning framework. In this work, we introduce an unsupervised pattern discovery framework, namely, dynamic autoregressive tensor factorization. Our framework is essentially built on the fact that the spatiotemporal systems can be well described by the time-varying autoregression on multivariate or even multidimensional data. In the modeling process, tensor factorization is seamlessly integrated into the time-varying autoregression for discovering spatial and temporal modes/patterns from the spatiotemporal systems in which the spatial factor matrix is assumed to be orthogonal. To evaluate the framework, we apply it to several real-world spatiotemporal datasets, including fluid flow dynamics, international import/export merchandise trade, and urban human mobility. On the international trade dataset with dimensions {country/region, product type, year}, our framework can produce interpretable import/export patterns of countries/regions, while the low-dimensional product patterns are also important for classifying import/export merchandise and understanding systematical differences between import and export. On the ridesharing mobility dataset with dimensions {origin, destination, time}, our framework is helpful for identifying the shift of spatial patterns of urban human mobility that changed between 2019 and 2022. Empirical experiments demonstrate that our framework can discover interpretable and meaningful patterns from the spatiotemporal systems that are both time-varying and multidimensional.
more »
« less
This content will become publicly available on November 1, 2025
Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering
Mining spatiotemporal mobility patterns is crucial for optimizing urban planning, enhancing transportation systems, and improving public safety by providing useful insights into human movement and behavior over space and time. As an unsupervised learning technique, time series clustering has gained considerable attention due to its efficiency. However, the existing literature has often overlooked the inherent characteristics of mobility data, including high-dimensionality, noise, outliers, and time distortions. This oversight can lead to potentially large computational costs and inaccurate patterns. To address these challenges, this paper proposes a novel neural network-based method integrating temporal autoencoder and dynamic time warping-based K-means clustering algorithm to mutually promote each other for mining spatiotemporal mobility patterns. Comparative results showed that our proposed method outperformed several time series clustering techniques in accurately identifying mobility patterns on both synthetic and real-world data, which provides a reliable foundation for data-driven decision-making. Furthermore, we applied the method to monthly county-level mobility data during the COVID-19 pandemic in the U.S., revealing significant differences in mobility changes between rural and urban areas, as well as the impact of public response and health considerations on mobility patterns.
more »
« less
- Award ID(s):
- 2339174
- PAR ID:
- 10567459
- Publisher / Repository:
- Multidisciplinary Digital Publishing Institute
- Date Published:
- Journal Name:
- ISPRS International Journal of Geo-Information
- Volume:
- 13
- Issue:
- 11
- ISSN:
- 2220-9964
- Page Range / eLocation ID:
- 374
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper introduces a new pattern mining task that considers aligning or joining a set of time series based on an arbitrary number of subsequences (i.e., patterns) with arbitrary lengths. Joining multiple time series along common patterns can be pivotal in clustering and summarizing large time series datasets. An exact algorithm to join hundreds of time series based on multi-length patterns is impractical due to the high computational costs. This paper proposes a fast algorithm named MultiPAL to join multiple time series at interactive speed to summarize large time series datasets. The algorithm exploits Matrix Profiles of the individual time series to enable a greedy search over possible joins. The algorithm is orders of magnitude faster than the exact solution and can utilize hundreds of Matrix Profiles. We evaluate our algorithm for sequential mining on data from various real-world domains, including power management and bioacoustics monitoring.more » « less
-
Objective: Slaughterhouse data has recently been used to enhance animal disease surveillance in many countries, however has been largely underused for syndromic surveillance in the United States. We characterize spatiotemporal patterns and system dynamics of whole carcass swine condemnations in the US. We illustrate the value of data mining and machine learning approaches to more cost-effectively identify: emerging trends by condemnation reason, areas and time periods with higher than predicted condemnation rates, and regions or time periods with similar trends. Methods: Swine slaughter and condemnation data from 2005-2016 were obtained for slaughterhouses inspected by the Food Safety and Inspection Service (FSIS). Time series of condemnation rates by condemnation reason, type of pig, state and month were generated. Data time warping (DTW) and hierarchical clustering methods were used to identify states with similar patterns in the rate of condemnation cases by cause and type of pig. Spatiotemporal scan statistics were used to identify states and months with significantly higher number of condemnation cases than expected. Clusters were compared to historic infectious disease outbreaks in the swine industry. Results: Between 2005-2016, 1,109,300 whole swine carcasses were condemned. The top causes for condemnation were abscess/pyemia, septicemia, pneumonia, icterus, and peritonitis, respectively. DTW and cluster analysis revealed clear spatiotemporal patterns in the rate of condemnations, many with a strong seasonal component. Several clusters were detected in timeframes where widespread outbreaks had occurred. Conclusions: Timely evaluation of spatiotemporal patterns in swine condemnations may provide critical information in predicting disease outbreaks. Identification of spatiotemporal hot spots can direct investigation of primary on-farm risk factors contributing to condemnation. Risk mitigation through targeted decision-making and improved management practices can minimize carcass condemnations and animal losses, improving economic efficiency, profitability and sustainability of the US swine industrymore » « less
-
Transformer-based models are popular for time series forecasting and spatiotemporal prediction due to their ability to infer semantic correlations in long sequences. However, for human mobility prediction, temporal correlations, such as location patterns at the same time on previous days or weeks, are essential. While positional encodings help retain order, the self-attention mechanism causes a loss of temporal detail. To validate this claim, we used a simple approach in the 2nd ACM SIGSPATIAL Human Mobility Prediction Challenge, predicting locations based on past patterns weighted by reliability scores for missing data. Our simple approach was among the top 10 competitors and significantly outperformed the Transformer-based model that won the 2023 challenge.more » « less
-
null (Ed.)Shape expressions (SEs) is a novel specification language that was recently introduced to express behavioral patterns over real-valued signals observed during the execution of cyber-physical systems. An SE is a regular expression composed of arbitrary parameterized shapes, such as lines, exponential curves, and sinusoids as atomic symbols with symbolic constraints on the shape parameters. SEs enable a natural and intuitive specification of complex temporal patterns over possibly noisy data. In this article, we propose a novel method for mining a broad and interesting fragment of SEs from time-series data using a combination of techniques from linear regression, unsupervised clustering, and learning finite automata from positive examples. The learned SE for a given dataset provides an explainable and intuitive model of the observed system behavior. We demonstrate the applicability of our approach on two case studies from different application domains and experimentally evaluate the implemented specification mining procedure.more » « less
