Feb
01
Signal processing plays a foundational role in modern technologies that acquire, structure, and interpret data. Yet, as these systems increasingly operate under uncertainty, interventions, and distributional shifts, statistical correlation is no longer sufficient. Causal inference provides a structured framework for intervention analysis, distributional generalization, and counterfactual reasoning. These capabilities are essential in domains such as biomedicine, communication, climate science, and robotics.
This special issue will present recent methodological developments at the intersection of signal processing and causal inference in a tutorial style as is standard with special issues of the magazine. We seek contributions examining how signal processing techniques, including filtering, transform domain analysis, sparse representations, and spatiotemporal models, support causal structure estimation in complex, high dimensional signals. We also welcome demonstrations of how causal reasoning informs the design of signal processing systems, including strategies for inference, robustness, adaptivity, and experimental
control.
TOPICS
Topics of interest include, but are not limited to:
- Signal-based approaches to causal inference
- Causal structure estimation from high-dimensional and multimodal signals
- Spatiotemporal modeling for causal analysis
- Causal discovery in networked and distributed systems
- Causal graph learning from nonstationary signals
- Causality in physical and generative signal models
- Causal representation learning from signals
- Interventional and counterfactual signal modeling
- Causal generalization and robustness in signal processing pipelines
- Theoretical limits and identifiability in causal signal processing
- Uncertainty quantification in the estimation of causal relationships
- Design of experiments and active sensing for causal inference
- Integration of causal modeling with learning architectures (e.g., neural or probabilistic models)
- Domain-specific applications in biomedical imaging, neuroscience, geophysics, etc.
- Benchmarking, datasets, and evaluation for causal signal processing
SUBMISSION PROCESS
White papers are required, and full articles will follow only after review of the white papers. Each white paper may have up to four pages and must include the proposed title, the motivation and significance of the topic, an outline of the tutorial contribution, representative references, and an author list with contact information and short bios. All invited articles must take the form of tutorial, overview, or survey papers that address a broad audience and remain fully accessible to readers across the signal processing community, with clear relevance to the scope of the special issue. All invited papers will undergo the standard peer review process of IEEE Signal Processing Magazine to maintain technical quality and editorial consistency.
IMPORTANT DATES
- February 1, 2026: White paper due
- March 1, 2026: Invitation notifications sent
- May 1, 2026: Full-length manuscripts due
- July 1, 2026: First reviews returned to authors
- September 1, 2026: Revisions due
- November 1, 2026: Final decisions sent
- December 1, 2026: Final production files due
- March 1, 2027: Publication date
GUEST EDITORS
Prof. Petar M. Djuric
Stony Brook University, USA
Prof. Sotirios A. Tsaftaris
University of Edinburgh, UK
Prof. Prof. Qi Dou
The Chinese University of Hong Kong, Hong Kong
Prof. Urbashi Mitra
University of Southern California, USA
Prof. Efstratios Gavves
University of Amsterdam, Netherlands
