STACI uses neural nets to estimate spatio-temporal fields with valid uncertainty quantification.
problem Scalable spatio-temporal deep learning models fail to capture underlying correlation structure.
method Variational Bayesian neural network approximation of non-stationary spatio-temporal Gaussian Process (GP) with conformal inference.
result STACI provides accurate prediction intervals for spatio-temporal processes, outperforming competing methods.
Develops a deep non-stationary kernel for non-stationary spatio-temporal point processes.
problem Capturing non-stationary dependencies in point process data.
method Approximates the influence kernel with a novel low-rank decomposition and introduces a log-barrier penalty to maintain non-negativity.
result Demonstrates superior performance and computational efficiency compared to state-of-the-art methods.
New framework predicts urban traffic with high accuracy.
problem Urban traffic prediction challenges.
method Interpretable attention-based neural network combining multiple modules.
result Framework outperforms state-of-the-art alternatives.
Deep models improve spatial and spatio-temporal data analysis.
problem Improving analysis of spatial and spatio-temporal data.
method Hybrid models combining statistical and deep learning approaches.
result Deep models enhance traditional statistical methods for complex data.
Deep learning models improve spatio-temporal data mining.
problem Mining valuable knowledge from spatio-temporal data.
method Application of deep learning techniques (CNN, RNN) in various spatio-temporal data mining tasks.
result Deep learning models enhance performance in spatio-temporal data mining.
Proposes a neural network for estimating traffic density uncertainty.
problem Lack of uncertainty estimates in deep learning traffic prediction models.
method Quantile Graph Wavenet, a Spatio-Temporal neural network trained to estimate density.
result Produces uncertainty estimates efficiently without sampling.
Framework reconstructs missing spatio-temporal data for extreme value prediction.
problem Predicting extreme values from incomplete spatio-temporal data.
method Convolutional deep neural networks and autoencoder-like models for conditional sampling.
result Framework produces accurate reconstructions of missing data for extremal values.
Advances in deep learning for spatio-temporal event modeling.
problem Limitations of traditional parametric models in capturing nonstationary dynamics.
method Integration of deep neural architectures to model conditional intensity function and influence kernels.
result Deep influence kernel approach enhances expressiveness and statistical explainability.
New algorithm for online training of Spiking Neural Networks (SNNs).
problem Training Spiking Neural Networks (SNNs) online with BPTT-equivalent gradients.
method Clear separation of spatial and temporal gradient components, derived from biological insights.
result Online training of SNNs with BPTT-equivalent gradients and low time complexity.
New method uses neural networks to forecast spatial-temporal data.
problem Probabilistic forecasting of spatio-temporal data with causal structure.
method MMAF-guided learning with ensemble of stochastic feed-forward neural networks.
result Forecasting remains calibrated across multiple time horizons.
A new deep learning framework captures multi-scale spatio-temporal dependencies.
problem Designing and analyzing deep learning models for complex spatio-temporal analytics.
method Developed an I2DRNN model with three modules for integrating and learning multi-scale spatio-temporal data. result The I2DRNN model outperforms classical and state-of-the-art models in capturing meaningful multi-scale spatio-temporal dependencies. Spatio-temporal data are ubiquitous in the agricultural, ecological, and environmental sciences, and their study is important for understanding and predicting a wide variety of processes. One of the difficulties with modeling spatial processes that change in time is the complexity of the dependence structures that must…
New method uses MMAF-guided learning for spatio-temporal probabilistic forecasts.
problem Probabilistic forecasting of spatio-temporal data with causal structure.
method Generalized Bayesian methodology, MMAF-guided learning, ensemble of stochastic feed-forward neural networks.
result Forecast performance comparable to, and sometimes better than, deep learning architectures.
DeepKriging uses neural networks for spatio-temporal interpolation and forecasting.
problem Non-Gaussianity and nonstationarity in real-world data.
method Two-stage model: DNN for interpolation, LSTM for forecasting.
result DeepKriging provides probabilistic forecasts without stationarity assumptions.
We present a generic framework for spatio-temporal (ST) data modeling, analysis, and forecasting, with a special focus on data that is sparse in both space and time. Our multi-scaled framework is a seamless coupling of two major components: a self-exciting point process that models the macroscale statistical behaviors …
DeepIST uses CNNs to estimate travel time from path images.
problem Accurately estimating travel time for a path in urban transportation systems.
method Proposes DeepIST, a neural network framework that converts paths into generalized images and uses PathCNN and 1D CNN to capture spatial and temporal patterns.
result DeepIST significantly outperforms existing models in travel time estimation.
PhICNet combines physics and deep learning for forecasting and source identification in dynamical systems.
problem Forecasting and identifying unobservable external sources in spatio-temporal dynamical systems.
method Physics-Incorporated Convolutional Recurrent Neural Network (PhICNet).
result PhICNet can forecast dynamics and identify sources for relatively long periods.
When sensors collect spatio-temporal data in a large geographical area, the existence of missing data cannot be escaped. Missing data negatively impacts the performance of data analysis and machine learning algorithms. In this paper, we study deep autoencoders for missing data imputation in spatio-temporal problems. We…
New framework assesses deep learning models for spatio-temporal data with missing data.
problem Challenges in assessing deep learning models for spatio-temporal data with missing and heterogeneous data.
method Residual correlation analysis framework using spatio-temporal graphs and asymptotically distribution-free summary statistics.
result Identification and localization of regions where predictive performance can be improved.
NeuPDE uses neural networks to model time-dependent data using differential equations.
problem Modeling time-dependent data from dynamic datasets.
method Neural network approach with both shallow multilayer perceptrons and nonlinear differential terms.
result Demonstrated on various dynamical systems, NeuPDE outperforms other methods.
Spatio-temporal RBF neural networks improve chaotic time series prediction.
problem Predicting chaotic time series due to their dynamic nature.
method Proposes an spatio-temporal extension of RBF neural networks.
result Spatio-temporal RBF outperforms standard RBF in chaotic time series prediction.
New neural networks model for spatio-temporal data.
problem Building a mapping from spatially encoded time series covariates to real-valued response data.
method Proposed two novel extensions of Functional Neural Network (FNN) for spatio-temporal regression.
result Demonstrated effectiveness in handling varying spatial correlations through comprehensive simulation studies.
Proposes a new model for complex multivariate event data.
problem Modeling complex multivariate event data with spatio-temporal dynamics.
method Integrates spatial information into latent state evolution through learned temporal and spatial decay dynamics.
result Successfully recovers sensible temporal and spatial intensity structure in multivariate spatio-temporal point patterns.
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. More recently, as deep learning models have become more common, RNNs have been used to forecast increasingl…
Long-lead forecasting for spatio-temporal systems can often entail complex nonlinear dynamics that are difficult to specify it a priori. Current statistical methodologies for modeling these processes are often highly parameterized and thus, challenging to implement from a computational perspective. One potential parsim…
Deep neural networks predict earthquake locations with high accuracy.
problem Predicting the location of earthquakes with high precision.
method Recurrent Convolutional Neural Networks (R-CNN) model that accounts for spatio-temporal dependencies.
result Neural networks model outperforms baseline models in predicting earthquakes with ROC AUC 0.975 and PR AUC 0.0890.
Deep learning model predicts wind-wave relationship.
problem Characterize ocean wave climate for engineering applications.
method Two-stage deep learning model: CNN for spatial features, LSTM for temporal dependencies.
result Predicts spatio-temporal relationship between wind and significant wave height.
Proposes a transformer model with geostatistical inductive bias for spatio-temporal forecasting.
problem Combining probabilistic rigor of geostatistics with flexible deep learning representations.
method Spatially-informed transformer with learnable covariance kernel.
result Successfully recovers spatial decay parameters end-to-end via backpropagation.
A CNN method removes atmospheric distortion from video sequences.
problem Mitigating atmospheric distortion in video sequences.
method End-to-end supervised convolutional neural network (CNN) with residual learning.
result The method outperforms existing techniques in terms of image quality and speed.
Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex task…
Deep learning improves weather modeling for electricity load forecasting.
problem Accurate load and renewable energy forecasting requires complex spatio-temporal weather modeling.
method Automated spatio-temporal feature extraction using deep neural networks.
result Deep learning outperforms traditional methods in French national load forecasting.
Improved RBFNN for nonlinear system identification.
problem Nonlinear system identification problem.
method Spatio-temporal extension of RBFNN with time-space orthogonality.
result Spatio-temporal RBFNN outperforms standard RBFNN in convergence and error reduction.
A deep learning model is applied for predicting block-level parking occupancy in real time. The model leverages Graph-Convolutional Neural Networks (GCNN) to extract the spatial relations of traffic flow in large-scale networks, and utilizes Recurrent Neural Networks (RNN) with Long-Short Term Memory (LSTM) to capture …
Improves CTR prediction by considering spatial and temporal auxiliary ads.
problem Improving CTR prediction in online advertising systems.
method Deep Spatio-Temporal Neural Networks (DSTNs) for CTR prediction.
result DSTNs outperform state-of-the-art methods in CTR prediction.
GNNs improve brain activity forecasting in fMRI studies.
problem Understanding neural dynamics in the brain.
method Comparison of GNN architectures for modeling fMRI data.
result GNNs outperform VAR models in robustly scaling to large network studies.
We propose a mixed deep neural network strategy, incorporating parallel combination of Convolutional (CNN) and Recurrent Neural Networks (RNN), cascaded with deep autoencoders and fully connected layers towards automatic identification of imagined speech from EEG. Instead of utilizing raw EEG channel data, we compute t…
Proposes FairDRL-ST for fair spatio-temporal mobility prediction.
problem Fairness concerns in spatio-temporal AI applications.
method Disentangled representation learning, adversarial learning.
result Achieves fairness in spatio-temporal mobility prediction without performance loss.
DMPP predicts events in cities using rich contextual data.
problem Predicting events in cities with rich contextual factors.
method Deep Mixture Point Processes model with mixture of kernels and deep neural network for context.
result DMPP outperforms existing methods in event prediction.
Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce Spatio-Temporal Deep Graph Infomax (STDGI)---a fully unsupervised node representation learning…
Spatial information is not always necessary for spatio-temporal models.
problem The necessity of including spatial information in spatio-temporal models.
method Comparison of spatial agnostic neural networks with state-of-the-art models on ten datasets.
result Spatial information is not always needed in most spatio-temporal models.
STNN models forecast COVID-19 spread with improved accuracy.
problem Forecasting the spread of COVID-19 worldwide.
method Spatio-temporal Neural Network (STNN) incorporating spatial and temporal data.
result STNN models outperform classical models in accuracy and handling both spatial and temporal data.
HECT tests climate model outputs for reproducibility.
problem Ensuring climate models accurately reflect physical processes.
method Probabilistic classifiers for high-dimensional spatio-temporal data.
result A principled way to assess statistical reproducibility of climate models.
Enhances SNNs for spatio-temporal feature extraction.
problem Insufficient temporal dependencies in existing SNN synaptic structures.
method Integrates temporal convolution and attention mechanisms into synaptic connections.
result Improves SNN performance on classification tasks.
This paper highlights the need for explainable AI in video deep learning models.
problem Lack of explainable AI methods for video deep learning models.
method Illustrates the current state of video deep learning and highlights the need for explainability methods.
result Current explainability methods for video deep learning are insufficient and need improvement.
Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a nove…
A new neural network captures and explains trajectory patterns.
problem Analyzing complex spatial trajectories in urban planning and neuroscience.
method Composite Signal Neural Networks (CompSNN) combining three interpretable ANN modules.
result CompSNN outperforms individual modules and visualizes useful signal parts.
Develops a new model for spatio-temporal data using imitation learning.
problem Capturing complex spatio-temporal dependence in discrete event data.
method NEST point process model with imitation learning for efficient model fitting.
result The imitation learning approach leads to more robust and interpretable results.
Paper presents a spatio-temporal Bayesian model for early detection of COVID-19 hotspots.
problem Understanding spatio-temporal dynamics of COVID-19 hotspots to prevent outbreaks.
method Spatio-temporal Bayesian framework with a zero-mean Gaussian process and non-stationary kernel function enhanced by deep neural networks.
result Model demonstrates superior hotspot-detection performance compared to baseline methods.