SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.20443 · 2026

Topological Data Analysis for High-Dimensional Dynamic Process Monitoring

Tyler Soderstrom, Angan Mukherjee, Michael Kurtz, Victor Zavala

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
zavalab/ML canonical 9 of 10
FunctionStatusWhere it lives
biomarker_data Ran zavalab/ML/Asthma/src/result_utils.py
pointer only (licence: NONE) · get_code("a9124c8aaaf659e9")
compute_gradients Ran zavalab/ML/Asthma/src/saliency.py
pointer only (licence: NONE) · get_code("94132dc246945836")
get_cnn_result Ran zavalab/ML/Asthma/src/result_utils.py
pointer only (licence: NONE) · get_code("91a4a9e4f671fe99")
get_data Ran zavalab/ML/Asthma/src/train_cnn.py
pointer only (licence: NONE) · get_code("523cf7d200ff0e50")
get_metrics Ran zavalab/ML/Asthma/src/result_utils.py
pointer only (licence: NONE) · get_code("7b0ae182cdf4004f")
integral_approximation Ran zavalab/ML/Asthma/src/saliency.py
pointer only (licence: NONE) · get_code("b23a1eeb1fce1111")
interpolate_data Ran zavalab/ML/Asthma/src/saliency.py
pointer only (licence: NONE) · get_code("0c8f6b39addeea0b")
nll Ran zavalab/ML/AUTOGNNUQ/gnn_uq/gnn_model.py
pointer only (licence: NONE) · get_code("375315f53b291d52")
reduce Ran zavalab/ML/CMC_GCN/code/model_GNN.py
pointer only (licence: NONE) · get_code("0d5fd0c9a54335f2")
list_string_to_list Not yet run zavalab/ML/Asthma/src/aux_utils.py
pointer only (licence: NONE) · get_code("c4c7865f3905bf67")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Real-time process monitoring requires methods that extract actionable information from highdimensional time-series data. In this work, we present a new approach for process monitoring that combines tools of topological data analysis (TDA) and machine learning. In the proposed approach, we represent multivariate time-series data as manifolds and use topological descriptors to summarize the structure of such data; we then use a neural ordinary differential equation to learn the dynamic evolution of the topological structure of the system. Using real data from an industrial process, we show that this trajectory-based event detection approach is effective at detecting diverse types of events. We contrast this approach against reconstruction-based approaches such as principal component analysis and autoencoders and against a trajectory-based approach that uses Koopman autoencoders.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2606.20443")
get_code_for_paper("2606.20443")
have("2606.20443")

Connect an agent — have() is free.