An official website of the United States government
The COVID-19 pandemic represents the most significant public health disaster since the 1918 influenza pandemic. During pandemics such as COVID-19, timely and reliable spatiotemporal forecasting of epidemic dynamics is crucial. Deep learning-based time series models for forecasting have recently gained popularity and have been successfully used for epidemic forecasting. Here we focus on the design and analysis of deep learning-based models for COVID-19 forecasting. We implement multiple recurrent neural network-based deep learning models and combine them using the stacking ensemble technique. In order to incorporate the effects of multiple factors in COVID-19 spread, we consider multiple sources such as COVID-19 confirmed and death case count data and testing data for better predictions. To overcome the sparsity of training data and to address the dynamic correlation of the disease, we propose clustering-based training for high-resolution forecasting. The methods help us to identify the similar trends of certain groups of regions due to various spatio-temporal effects. We examine the proposed method for forecasting weekly COVID-19 new confirmed cases at county-, state-, and country-level. A comprehensive comparison between different time series models in COVID-19 context is conducted and analyzed. The results show that simple deep learning models can achieve comparable or better performance when compared with more complicated models. We are currently integrating our methods as a part of our weekly forecasts that we provide state and federal authorities.
more »
« less
This content will become publicly available on October 21, 2025
Identifying Contemporaneous and Lagged Dependence Structures by Promoting Sparsity in Continuous-time Neural Networks
Continuous-time dynamics models, e.g., neural ordinary differential equations, enable accurate modeling of underlying dynamics in time-series data. However, employing neural networks for parameterizing dynamics makes it challenging for humans to identify dependence structures, especially in the presence of delayed effects. In consequence, these models are not an attractive option when capturing dependence carries more importance than accurate modeling, e.g., in tsunami forecasting. In this paper, we present a novel method for identifying dependence structures in continuous-time dynamics models. We take a two-step approach: (1) During training, we promote weight sparsity in the model’s first layer during training. (2) We prune the sparse weights after training to identify dependence structures. In evaluation, we test our method in scenarios where the exact dependence structures of time-series are known. Compared to baselines, our method is more effective in uncovering dependence structures in data even when there are delayed effects. Moreover, we evaluate our method to a real-world tsunami forecasting, where the exact dependence structures are unknown beforehand. Even in this challenging scenario, our method still effective learns physically-consistent dependence structures and achieves high accuracy in forecasting.
more »
« less
- PAR ID:
- 10568038
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400704369
- Page Range / eLocation ID:
- 2534 to 2543
- Subject(s) / Keyword(s):
- Causality Learning, Neural Ordinary Differential Equations, Tsunami Modeling
- Format(s):
- Medium: X
- Location:
- Boise ID USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The January 1st, 2024, moment magnitude (Mw) 7.5 Noto Peninsula earthquake ruptured in complex ways, challenging timely analysis of the tsunami generation. We present rapid and accurate tsunami models informed by a 6-subevent centroid moment tensor (CMT) model that we obtain by inverting teleseismic and strong motion data and validation against geodetic observations. We identify two distinct bilateral rupture episodes, including six subevents and a re-nucleation episode at its hypocenter 20 seconds after its initiation, likely aided by fault weakening. We construct a complex uplift model that aligns with known fault system geometries and is critical in modeling the observed tsunami. Our tsunami simulation can explain wave amplitude, timing, and polarity of the leading wave, which are crucial for tsunami early warning. Analyzing a 2000 multi-CMT solution ensemble and comparing to alternative rapid source models, we highlight the importance of incorporating complex source effects for realistic tsunami simulations.more » « less
-
We investigate the potential of using Global Navigation Satellite System (GNSS) observations to directly forecast full tsunami waveforms in real time. We train convolutional neural networks to use less than 9 min of GNSS data to forecast the full tsunami waveforms over 6 hr at select locations, and obtain accurate forecasts on a test data set. Our training and test data consists of synthetic earthquakes and associated GNSS data generated for the Cascadia Subduction Zone using the MudPy software, and corresponding tsunami waveforms in Puget Sound computed using GeoClaw. We use the same suite of synthetic earthquakes and waveforms as in earlier work where tsunami waveforms were used for forecasting, and provide a comparison. We also explore varying the number of GNSS stations, their locations, and their observation durations.more » « less
-
null (Ed.)Hydropower is the largest renewable energy source for electricity generation in the world, with numerous benefits in terms of: environment protection (near-zero air pollution and climate impact), cost-effectiveness (long-term use, without significant impacts of market fluctuation), and reliability (quickly respond to surge in demand). However, the effectiveness of hydropower plants is affected by multiple factors such as reservoir capacity, rainfall, temperature and fluctuating electricity demand, and particularly their complicated relationships, which make the prediction/recommendation of station operational output a difficult challenge. In this paper, we present DeepHydro, a novel stochastic method for modeling multivariate time series (e.g., water inflow/outflow and temperature) and forecasting power generation of hydropower stations. DeepHydro captures temporal dependencies in co-evolving time series with a new conditioned latent recurrent neural networks, which not only considers the hidden states of observations but also preserves the uncertainty of latent variables. We introduce a generative network parameterized on a continuous normalizing flow to approximate the complex posterior distribution of multivariate time series data, and further use neural ordinary differential equations to estimate the continuous-time dynamics of the latent variables constituting the observable data. This allows our model to deal with the discrete observations in the context of continuous dynamic systems, while being robust to the noise. We conduct extensive experiments on real-world datasets from a large power generation company consisting of cascade hydropower stations. The experimental results demonstrate that the proposed method can effectively predict the power production and significantly outperform the possible candidate baseline approaches.more » « less
-
We propose heavy ball neural ordinary differential equations (HBNODEs), leveraging the continuous limit of the classical momentum accelerated gradient descent, to improve neural ODEs (NODEs) training and inference. HBNODEs have two properties that imply practical advantages over NODEs: (i) The adjoint state of an HBNODE also satisfies an HBNODE, accelerating both forward and backward ODE solvers, thus significantly reducing the number of function evaluations (NFEs) and improving the utility of the trained models. (ii) The spectrum of HBNODEs is well structured, enabling effective learning of long-term dependencies from complex sequential data. We verify the advantages of HBNODEs over NODEs on benchmark tasks, including image classification, learning complex dynamics, and sequential modeling. Our method requires remarkably fewer forward and backward NFEs, is more accurate, and learns long-term dependencies more effectively than the other ODE-based neural network models. Code is available at https://github.com/hedixia/HeavyBallNODE.more » « less
