SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal
Patterns with an Autoregressive Embedding Loss
- URL: http://arxiv.org/abs/2109.15044v1
- Date: Thu, 30 Sep 2021 12:10:05 GMT
- Title: SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal
Patterns with an Autoregressive Embedding Loss
- Authors: Konstantin Klemmer, Tianlin Xu, Beatrice Acciaio, Daniel B. Neill
- Abstract summary: We propose a novel loss objective combined with -GAN based on an autogressive embedding to reinforce the learning oftemporal dynamics.
We show that our embedding loss improves performance without any changes to the architecture of -GAN, highlighting our model's increased capacity for autocorrelationre structures.
- Score: 4.504870356809408
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: From ecology to atmospheric sciences, many academic disciplines deal with
data characterized by intricate spatio-temporal complexities, the modeling of
which often requires specialized approaches. Generative models of these data
are of particular interest, as they enable a range of impactful downstream
applications like simulation or creating synthetic training data. Recent work
has highlighted the potential of generative adversarial nets (GANs) for
generating spatio-temporal data. A new GAN algorithm COT-GAN, inspired by the
theory of causal optimal transport (COT), was proposed in an attempt to better
tackle this challenge. However, the task of learning more complex
spatio-temporal patterns requires additional knowledge of their specific data
structures. In this study, we propose a novel loss objective combined with
COT-GAN based on an autoregressive embedding to reinforce the learning of
spatio-temporal dynamics. We devise SPATE (spatio-temporal association), a new
metric measuring spatio-temporal autocorrelation by using the deviance of
observations from their expected values. We compute SPATE for real and
synthetic data samples and use it to compute an embedding loss that considers
space-time interactions, nudging the GAN to learn outputs that are faithful to
the observed dynamics. We test this new objective on a diverse set of complex
spatio-temporal patterns: turbulent flows, log-Gaussian Cox processes and
global weather data. We show that our novel embedding loss improves performance
without any changes to the architecture of the COT-GAN backbone, highlighting
our model's increased capacity for capturing autoregressive structures. We also
contextualize our work with respect to recent advances in physics-informed deep
learning and interdisciplinary work connecting neural networks with geographic
and geophysical sciences.
Related papers
- Graph Masked Autoencoder for Spatio-Temporal Graph Learning [38.085962443141206]
In urban sensing applications, effective-temporal prediction frameworks play a crucial role in traffic analysis, human mobility evaluations and crime prediction.
The presence of data noise and sparsity in spatial and temporal data presents significant challenges for existing neural network models in learning robust representations.
We propose a novel self-supervised learning paradigm for effective-temporal data augmentation.
arXiv Detail & Related papers (2024-10-14T07:33:33Z) - Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks [23.613277062707844]
Spiking Neural Networks (SNNs) emulate the integrated-fire-leak mechanism found in biological neurons.
Existing SNNs predominantly rely on the Integrate-and-Fire Leaky (LIF) model.
This paper proposes a novel S-patioTemporal Circuit (STC) model.
arXiv Detail & Related papers (2024-06-01T11:17:27Z) - SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
Weather forecasting plays a critical role in various sectors, driving decision-making and risk management.
Traditional methods often struggle to capture the complex dynamics of meteorological systems.
We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
arXiv Detail & Related papers (2024-05-29T08:00:15Z) - OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive
Learning [67.07363529640784]
We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models.
We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather.
We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
arXiv Detail & Related papers (2023-06-20T03:02:14Z) - An advanced spatio-temporal convolutional recurrent neural network for
storm surge predictions [73.4962254843935]
We study the capability of artificial neural network models to emulate storm surge based on the storm track/size/intensity history.
This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations.
arXiv Detail & Related papers (2022-04-18T23:42:18Z) - Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
We consider the impact of the training set and its structure on the quality of the long-term prediction.
We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
arXiv Detail & Related papers (2021-12-15T20:09:20Z) - Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems [15.923190628643681]
One of the major challenges is to infer the underlying causes, which generate the perceived data stream.
Success of machine learning based predictive models requires massive annotated data for model training.
Our experiments on both synthetic and real-world datasets exhibit that the proposed ST-PCNN with active learning converges to optimal accuracy with substantially fewer instances.
arXiv Detail & Related papers (2021-08-11T18:05:55Z) - Deep Bayesian Active Learning for Accelerating Stochastic Simulation [74.58219903138301]
Interactive Neural Process (INP) is a deep active learning framework for simulations and with active learning approaches.
For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models.
The results demonstrate STNP outperforms the baselines in the learning setting and LIG achieves the state-of-the-art for active learning.
arXiv Detail & Related papers (2021-06-05T01:31:51Z) - Spatio-Temporal Functional Neural Networks [11.73856529960872]
We propose two novel extensions of the Neural Functional Network (FNN), a temporal regression model whose effectiveness has been proven by many researchers.
The proposed models are then deployed to solve a practical and challenging precipitation prediction problem in the meteorology field.
arXiv Detail & Related papers (2020-09-11T21:32:35Z) - Automating Turbulence Modeling by Multi-Agent Reinforcement Learning [4.784658158364452]
We introduce multi-agent reinforcement learning as an automated discovery tool of turbulence models.
We demonstrate the potential of this approach on Large Eddy Simulations of homogeneous and isotropic turbulence.
arXiv Detail & Related papers (2020-05-18T18:45:09Z) - Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence.
This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time.
Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
arXiv Detail & Related papers (2020-02-21T05:00:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.