GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

• URL: http://arxiv.org/abs/2502.05295v2
• Date: Tue, 28 Oct 2025 16:01:40 GMT
• Title: GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding
• Authors: Miruna Oprescu, David K. Park, Xihaier Luo, Shinjae Yoo, Nathan Kallus,
• Abstract summary: Estimating causal effects from data is essential in public health, environmental science, and policy evaluation.<n>We introduce GST-UNet, a neural framework that combines a U-Net-basedtemporal encoder with regression-based iterative G-mputation.<n>We validate its effectiveness in synthetic experiments and in a real-world analysis of wildfire smoke exposure and respiratory hospitalizations during California Camp Fire.
• Score: 46.46135774964818
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Estimating causal effects from spatiotemporal observational data is essential in public health, environmental science, and policy evaluation, where randomized experiments are often infeasible. Existing approaches, however, either rely on strong structural assumptions or fail to handle key challenges such as interference, spatial confounding, temporal carryover, and time-varying confounding -- where covariates are influenced by past treatments and, in turn, affect future ones. We introduce GST-UNet (G-computation Spatio-Temporal UNet), a theoretically grounded neural framework that combines a U-Net-based spatiotemporal encoder with regression-based iterative G-computation to estimate location-specific potential outcomes under complex intervention sequences. GST-UNet explicitly adjusts for time-varying confounders and captures non-linear spatial and temporal dependencies, enabling valid causal inference from a single observed trajectory in data-scarce settings. We validate its effectiveness in synthetic experiments and in a real-world analysis of wildfire smoke exposure and respiratory hospitalizations during the 2018 California Camp Fire. Together, these results position GST-UNet as a principled and ready-to-use framework for spatiotemporal causal inference, advancing reliable estimation in policy-relevant and scientific domains.

Related papers

• Distributed Dynamic Invariant Causal Prediction in Environmental Time Series [9.779350203438485]
  We propose Distributed Dynamic Invariant Causal Prediction in Time-series (DisDy-ICPT)<n>DisDy-ICPT learns dynamic causal relationships over time while mitigating spatial confounding variables without requiring data communication.<n> Empirical evaluations on synthetic benchmarks and environment-segmented real-world datasets show that DisDy-ICPT achieves superior predictive stability and accuracy compared to baseline methods A and B.
  arXiv  Detail & Related papers  (2026-03-03T11:52:35Z)
• Synthetic Survival Control: Extending Synthetic Controls for "When-If" Decision [14.313335826236722]
  Estimating causal effects on time-to-event outcomes from observational data is challenging due to censoring, limited sample sizes, and non-random treatment assignment.<n>We propose Synthetic Survival Control (SSC) to estimate counterfactual hazard trajectories in a panel data setting.
  arXiv  Detail & Related papers  (2025-11-18T04:36:20Z)
• Predictive Causal Inference via Spatio-Temporal Modeling and Penalized Empirical Likelihood [0.0]
  This study introduces an integrated framework for predictive causal inference designed to overcome limitations in conventional single model approaches.<n> Specifically, we combine a Hidden Markov Model for spatial health state estimation with a Multi Task and Multi Graph Convolutional Network (MTGCN) for capturing temporal outcome trajectories.<n>To demonstrate its utility, we focus on clinical domains such as cancer, dementia, Parkinson disease, where treatment effects are challenging to observe directly.
  arXiv  Detail & Related papers  (2025-07-11T03:11:15Z)
• STOAT: Spatial-Temporal Probabilistic Causal Inference Network [4.973408202277769]
  We propose STOAT (Spatial-Temporal Probabilistic Causal Inference Network), a novel framework for probabilistic forecasting in spatial-temporal time series.<n>The proposed method extends a causal inference approach by incorporating a spatial relation matrix that encodes interregional dependencies.<n> Experiments on COVID-19 data across six countries demonstrate that STOAT outperforms state-of-the-art probabilistic forecasting models.
  arXiv  Detail & Related papers  (2025-06-11T09:25:09Z)
• Do-PFN: In-Context Learning for Causal Effect Estimation [75.62771416172109]
  We show that Prior-data fitted networks (PFNs) can be pre-trained on synthetic data to predict outcomes.<n>Our approach allows for the accurate estimation of causal effects without knowledge of the underlying causal graph.
  arXiv  Detail & Related papers  (2025-06-06T12:43:57Z)
• Topology-Aware Conformal Prediction for Stream Networks [68.02503121089633]
  We propose Spatio-Temporal Adaptive Conformal Inference (textttCISTA), a novel framework that integrates network topology and temporal dynamics into the conformal prediction framework.<n>Our results show that textttCISTA effectively balances prediction efficiency and coverage, outperforming existing conformal prediction methods for stream networks.
  arXiv  Detail & Related papers  (2025-03-06T21:21:15Z)
• ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data [59.78770412981611]
  In real-world applications, most nodes may not possess any available temporal data during training. We propose a principled framework named ST-FiT to handle this problem.
  arXiv  Detail & Related papers  (2024-12-14T17:51:29Z)
• Discovering Latent Causal Graphs from Spatiotemporal Data [23.400027588427964]
  Inferring causal relationships from climate data is a challenging problem with high dimensionality.<n>We present SPACY (tiotemporal CausalY), a novel framework for inference based on latent causal structures.<n> SPACY also identifies key known phenomena from real-world climate data.
  arXiv  Detail & Related papers  (2024-11-08T05:12:16Z)
• Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detection [67.40407388422514]
  We design a conceptual fine-grained causal model named TBN Granger Causality. Second, we propose an end-to-end deep generative model called TacSas, which discovers TBN Granger Causality in a generative manner. We test TacSas on climate benchmark ERA5 for climate forecasting and the extreme weather benchmark of NOAA for extreme weather alerts.
  arXiv  Detail & Related papers  (2024-08-08T06:47:21Z)
• Estimating Direct and Indirect Causal Effects of Spatiotemporal Interventions in Presence of Spatial Interference [0.46052594866569146]
  We first extend the concept of spatial interference in case of time-varying treatment outcomes by extending the potential outcome framework under the assumption of no unmeasured confounding. We then propose our deep learning based potential outcome model fortemporal causal inference. We utilize latent factor modeling to reduce interference due to time-varying confounding while leveraging the power of U-Net architecture to capture global spatial interference in data over time.
  arXiv  Detail & Related papers  (2024-05-13T20:39:27Z)
• Temporal-Spatial Entropy Balancing for Causal Continuous Treatment-Effect Estimation [11.53614718016578]
  In the field of intracity freight transportation, changes in order volume are influenced by temporal and spatial factors. Traditional methods to control confounding variables handle data from a holistic perspective. This study proposes a technique based on flexible temporal-spatial grid partitioning.
  arXiv  Detail & Related papers  (2023-12-14T06:05:13Z)
• Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification [59.81904428056924]
  We introduce SMASH: a Score MAtching estimator for learning markedPs with uncertainty quantification. Specifically, our framework adopts a normalization-free objective by estimating the pseudolikelihood of markedPs through score-matching. The superior performance of our proposed framework is demonstrated through extensive experiments in both event prediction and uncertainty quantification.
  arXiv  Detail & Related papers  (2023-10-25T02:37:51Z)
• Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment [33.4989883914555]
  We propose a novel framework called CaST to tackle temporal out-of-distribution issues and dynamic spatial causation. Experiments results on three real-world datasets demonstrate the effectiveness and practicality of CaST.
  arXiv  Detail & Related papers  (2023-09-23T13:51:09Z)
• Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders [15.41689729746877]
  Real-world time series can include large-scale, irregular, and intermittent time series observations. existence of hidden confounders can lead to biased treatment estimates. In continuous time settings with irregular samples, it is challenging to directly handle the dynamics of causality.
  arXiv  Detail & Related papers  (2023-03-04T04:55:34Z)
• Understanding the Impact of Competing Events on Heterogeneous Treatment Effect Estimation from Time-to-Event Data [92.51773744318119]
  We study the problem of inferring heterogeneous treatment effects (HTEs) from time-to-event data in the presence of competing events. We take an outcome modeling approach to estimating HTEs, and consider how and when existing prediction models for time-to-event data can be used as plug-in estimators for potential outcomes. We theoretically analyze and empirically illustrate when and how these challenges play a role when using generic machine learning prediction models for the estimation of HTEs.
  arXiv  Detail & Related papers  (2023-02-23T14:28:55Z)
• DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models [53.67562579184457]
  This paper focuses on probabilistic STG forecasting, which is challenging due to the difficulty in modeling uncertainties and complex dependencies. We present the first attempt to generalize the popular denoising diffusion models to STGs, leading to a novel non-autoregressive framework called DiffSTG. Our approach combines the intrinsic-temporal learning capabilities STNNs with the uncertainty measurements of diffusion models.
  arXiv  Detail & Related papers  (2023-01-31T13:42:36Z)
• Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations [84.42837346400151]
  Estimating counterfactual outcomes over time has the potential to unlock personalized healthcare. Existing causal inference approaches consider regular, discrete-time intervals between observations and treatment decisions. We propose a controllable simulation environment based on a model of tumor growth for a range of scenarios.
  arXiv  Detail & Related papers  (2022-06-16T17:15:15Z)
• Latent State Inference in a Spatiotemporal Generative Model [3.7525506486107267]
  We focus on temperature and weather processes, including wave propagation dynamics, for which we assume that universal causes apply throughout space and time. A recently introduced DIsed Stemporal graph graph artificial Neural Architecture (DISTANA) is used and enhanced to learn such processes. We show that DISTANA, when combined with a retrospective latent state inference principle called active tuning, can reliably derive location-respective hidden causal factors.
  arXiv  Detail & Related papers  (2020-09-21T12:59:40Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)

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.