4 papers
DCD: Decomposition-based Causal Discovery from Autocorrelated and Non-Stationary Temporal Data
Muhammad Hasan Ferdous, Md Osman Gani
Multivariate time series in domains such as finance, climate science, and healthcare often exhibit long-term trends, seasonal patterns, and short-term fluctuations, complicating ca…
Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift
Emam Hossain, Muhammad Hasan Ferdous, Devon Dunmire +2
Causal modeling offers a principled foundation for uncovering stable, invariant relationships in time-series data, thereby improving robustness and generalization under distributio…
TimeGraph: Synthetic Benchmark Datasets for Robust Time-Series Causal Discovery
Muhammad Hasan Ferdous, Emam Hossain, Md Osman Gani
Robust causal discovery in time series datasets depends on reliable benchmark datasets with known ground-truth causal relationships. However, such datasets remain scarce, and exist…
Correlation to Causation: A Causal Deep Learning Framework for Arctic Sea Ice Prediction
Emam Hossain, Muhammad Hasan Ferdous, Jianwu Wang +2
Traditional machine learning and deep learning techniques rely on correlation-based learning, often failing to distinguish spurious associations from true causal relationships, whi…