An official website of the United States government
Time series forecasting with additional spatial information has attracted a tremendous amount of attention in recent research, due to its importance in various real-world applications on social studies, such as conflict prediction and pandemic forecasting. Conventional machine learning methods either consider temporal dependencies only, or treat spatial and temporal relations as two separate autoregressive models, namely, space-time autoregressive models. Such methods suffer when it comes to long-term forecasting or predictions for large-scale areas, due to the high nonlinearity and complexity of spatio-temporal data. In this paper, we propose to address these challenges using spatio-temporal graph neural networks. Empirical results on Violence Early Warning System (ViEWS) dataset and U.S. Covid-19 dataset indicate that our method significantly improved performance over the baseline approaches.
more »
« less
(Vision Paper) A Vision for Spatio-Causal Situation Awareness, Forecasting, and Planning
Successfully tackling many urgent challenges in socio-economically critical domains, such as public health and sustainability, requires a deeper understanding of causal relationships and interactions among a diverse spectrum of spatio-temporally distributed entities. In these applications, the ability to leverage spatio-temporal data to obtain causally based situational awareness and to develop informed forecasts to provide resilience at different scales is critical. While the promise of a causally grounded approach to these challenges is apparent, the core data technologies needed to achieve these are in the early stages and lack a framework to help realize their potential. In this article, we argue that there is an urgent need for a novel paradigm of spatio-causal research built on computational advances in spatio-temporal data and model integration, causal learning and discovery, large scale data- and model-driven simulations, emulations, and forecasting, as well as spatio-temporal data-driven and model-centric operational recommendations, and effective causally driven visualization and explanation. We thus provide a vision, and a road map, for spatio-causal situation awareness, forecasting, and planning.
more »
« less
- PAR ID:
- 10544345
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM Transactions on Spatial Algorithms and Systems
- Volume:
- 10
- Issue:
- 2
- ISSN:
- 2374-0353
- Page Range / eLocation ID:
- 1 to 42
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recurrent neural networks (RNNs) are nonlinear dynamical models commonly used in the machine learning and dynamical systems literature to represent complex dynamical or sequential relationships between variables. Recently, as deep learning models have become more common, RNNs have been used to forecast increasingly complicated systems. Dynamical spatio-temporal processes represent a class of complex systems that can potentially benefit from these types of models. Although the RNN literature is expansive and highly developed, uncertainty quantification is often ignored. Even when considered, the uncertainty is generally quantified without the use of a rigorous framework, such as a fully Bayesian setting. Here we attempt to quantify uncertainty in a more formal framework while maintaining the forecast accuracy that makes these models appealing, by presenting a Bayesian RNN model for nonlinear spatio-temporal forecasting. Additionally, we make simple modifications to the basic RNN to help accommodate the unique nature of nonlinear spatio-temporal data. The proposed model is applied to a Lorenz simulation and two real-world nonlinear spatio-temporal forecasting applications.more » « less
-
null (Ed.)In IoT era, the growth of data variety is driven by crossdomain data fusion. In this paper, we advocate that “local production for local consumption (LPLC) paradigm” can be an innovative approach in cross-domain data fusion, and propose a new framework, geolocationcentric information platform (GCIP) that can produce and deliver diverse spatio-temporal content (STC). In the GCIP, (1) infrastructure-based geographic hierarchy edge network and (2) adhoc-based STC retention system are interplayed to provide both of geolocation-awareness and resiliency. Then, we discussed the concepts and the technical challenges of the GCIP. Finally, we implemented a proof-of-concepts of GCIP and demonstrated its ecacy through practical experiments on campus IPv6 network and simulation experiments.more » « less
-
Traffic data forecasting has become an integral part of the intelligent traffic system. Great efforts are spent developing tools and techniques to estimate traffic flow patterns. Many existing approaches lack the ability to model the complex and dynamic spatio-temporal relations in the traffic data, which are crucial in capturing the traffic dynamic. In this work, we propose AJSTGL, a novel adaptive joint spatio-temporal graph learning network for traffic data forecasting. The proposed model utilizes static and adaptive graph learning modules to capture the static and dynamic spatial traffic patterns and optimize the graph learning process. A sequence-to-sequence fusion model is proposed to learn the temporal correlation and combine the output of multiple parallelized encoders. We also develop a spatio-temporal graph transformer module to complement the sequence-to-sequence fusion module by dynamically capturing the time-evolving node relations in long-term intervals. Experiments on three large-scale traffic flow datasets demonstrate that our model could outperform other state-of-the-art baseline methods.more » « less
-
Abstract Long‐lead forecasting for spatio‐temporal systems can entail complex nonlinear dynamics that are difficult to specify a priori. Current statistical methodologies for modeling these processes are often highly parameterized and, thus, challenging to implement from a computational perspective. One potential parsimonious solution to this problem is a method from the dynamical systems and engineering literature referred to as an echo state network (ESN). ESN models usereservoir computingto efficiently compute recurrent neural network forecasts. Moreover, multilevel (deep) hierarchical models have recently been shown to be successful at predicting high‐dimensional complex nonlinear processes, particularly those with multiple spatial and temporal scales of variability (such as those we often find in spatio‐temporal environmental data). Here, we introduce a deep ensemble ESN (D‐EESN) model. Despite the incorporation of a deep structure, the presented model is computationally efficient. We present two versions of this model for spatio‐temporal processes that produce forecasts and associated measures of uncertainty. The first approach utilizes a bootstrap ensemble framework, and the second is developed within a hierarchical Bayesian framework (BD‐EESN). This more general hierarchical Bayesian framework naturally accommodates non‐Gaussian data types and multiple levels of uncertainties. The methodology is first applied to a data set simulated from a novel non‐Gaussian multiscale Lorenz‐96 dynamical system simulation model and, then, to a long‐lead United States (U.S.) soil moisture forecasting application. Across both applications, the proposed methodology improves upon existing methods in terms of both forecast accuracy and quantifying uncertainty.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3672556
