AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery

2026/07/31 by Marco Ruiz, Miguel Arana-Catania, David R. Ardila +1
Computer Science · #cs.LG

paper · pdf

33 pages, 10 figures. Submitted to Environmental Modelling & Software

arxiv created 2026/07/31 · arxiv updated 2026/08/04

Abstract

Environmental time-series causal discovery requires expert decisions about method choice, conditional-independence tests, lag horizons, sample-size adequacy, multiple-testing control, and evidence interpretation. Applied inconsistently across datasets, these choices yield graphs that cannot be compared, reproduced, or audited. We present AutoCause, an open-source Python workflow that records each decision, derives defaults from an extended causal-audit module, and admits domain-informed overrides. The workflow wraps four established causal-discovery methods from three families, adds non-causal reference models, and grades links by method-count support. On 145 datasets from DGP-Atlas, TimeGraph, and a topology-derived CausalRivers reference, the methods recover complementary parts of the reference graphs. Majority-supported links are more precise than single-method links on the synthetic benchmarks but not against river topology. AutoCause converts inconsistent expert practice into an auditable, repeatable analysis; causal interpretation remains with the analyst. Available at https://github.com/marcoruizrueda/autocause.

Citations

• TimeGraph: Synthetic Benchmark Datasets for Robust Time-Series Causal Discovery
• CausalDynamics: A large-scale benchmark for structural discovery of dynamical causal models
• CausalRivers -- Scaling up benchmarking of causal discovery for real-world time-series
• Are you doing better than random guessing? A call for using negative controls when evaluating causal discovery algorithms
• The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
• Robust Time Series Causal Discovery for Agent-Based Model Validation
• LOCAL: Learning with Orientation Matrix to Infer Causal Structure from Time Series Data
• Comprehensive Review and Empirical Evaluation of Causal Discovery Algorithms for Numerical Data
• Causal discovery in a complex industrial system: A time series benchmark
• CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery
• Causal discovery for time series from multiple datasets with latent contexts
• Enhancing Causal Discovery from Robot Sensor Data in Dynamic Scenarios
• CIPCaD-Bench: Continuous Industrial Process datasets for benchmarking Causal Discovery methods
• gCastle: A Python Toolbox for Causal Discovery
• Causal Inference for Time series Analysis: Problems, Methods and Evaluation
• High-recall causal discovery for autocorrelated time series with latent confounders
• Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets
• DYNOTEARS: Structure Learning from Time-Series Data
• Review of Causal Discovery Methods Based on Graphical Models
• DAGs with NO TEARS: Continuous Optimization for Structure Learning
• Conditional independence testing based on a nearest-neighbor estimator of conditional mutual information
• To Explain or to Predict?
• Measuring and testing dependence by correlation of distances
• Statistical inference in vector autoregressions with possibly integrated processes