{"id":22728739,"url":"https://github.com/keichi/kedm","last_synced_at":"2025-08-22T05:32:44.008Z","repository":{"id":41833945,"uuid":"260696522","full_name":"keichi/kEDM","owner":"keichi","description":"A high-performance implementation of Empirical Dynamic Modeling (EDM)","archived":false,"fork":false,"pushed_at":"2024-09-03T22:17:47.000Z","size":566,"stargazers_count":15,"open_issues_count":8,"forks_count":5,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-12-10T17:17:22.544Z","etag":null,"topics":["empirical-dynamic-modeling","high-performance-computing","nonlinear-dynamics","time-series"],"latest_commit_sha":null,"homepage":"https://kedm.readthedocs.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/keichi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-05-02T13:48:10.000Z","updated_at":"2024-11-21T10:52:38.000Z","dependencies_parsed_at":"2023-02-17T14:15:23.178Z","dependency_job_id":null,"html_url":"https://github.com/keichi/kEDM","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keichi%2FkEDM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keichi%2FkEDM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keichi%2FkEDM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/keichi%2FkEDM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/keichi","download_url":"https://codeload.github.com/keichi/kEDM/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230561014,"owners_count":18245324,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["empirical-dynamic-modeling","high-performance-computing","nonlinear-dynamics","time-series"],"created_at":"2024-12-10T17:17:32.785Z","updated_at":"2024-12-20T09:07:42.438Z","avatar_url":"https://github.com/keichi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# kEDM\n\n[![build](https://github.com/keichi/kEDM/workflows/build/badge.svg)](https://github.com/keichi/kEDM/actions?query=workflow%3Abuild) [![Documentation Status](https://readthedocs.org/projects/kedm/badge/?version=latest)](https://kedm.readthedocs.io/en/latest/?badge=latest) [![PyPI version](https://badge.fury.io/py/kedm.svg)](https://badge.fury.io/py/kedm)\n\nkEDM (Kokkos-EDM) is a high-performance implementation of the [Empirical\nDynamical Modeling (EDM)](https://sugiharalab.github.io/EDM_Documentation/)\nframework. The goal of kEDM is to provide an optimized and parallelized\nimplementation of EDM algorithms for high-end CPUs and GPUs, while ensuring\ncompatibility with the original reference implementation\n([cppEDM](https://github.com/SugiharaLab/cppEDM)).\n\nFollowing EDM algorithms are currently implemented in kEDM:\n\n- Simplex projection [1]\n- Sequential Locally Weighted Global Linear Maps (S-Map) [2]\n- Convergent Cross Mapping (CCM) [3]\n\n## Installation\n\nCPU (Linux and macOS)\n\n```\npip3 install kedm\n```\n\nNVIDIA GPU (CUDA 11.2 or later)\n\n```\npip3 install kedm-11x\n```\n\nNVIDIA GPU (CUDA 12.0 or later)\n\n```\npip3 install kedm-12x\n```\n\n## Citing\n\nPlease cite the following papers if you find kEDM useful:\n\n- Keichi Takahashi, Kohei Ichikawa, Joseph Park, Gerald M. Pao, “Scalable Empirical Dynamic Modeling\n  with Parallel Computing and Approximate k-NN Search,” IEEE Access, vol. 11, pp. 68171–68183,\n  Jun. 2023. [10.1109/ACCESS.2023.3289836](https://doi.org/10.1109/ACCESS.2023.3289836)\n- Keichi Takahashi, Wassapon Watanakeesuntorn, Kohei Ichikawa, Joseph Park,\n  Ryousei Takano, Jason Haga, George Sugihara, Gerald M. Pao, \"kEDM: A\n  Performance-portable Implementation of Empirical Dynamical Modeling,\" Practice\n  \u0026 Experience in Advanced Research Computing (PEARC 2021), Jul. 2021.\n  [10.1145/3437359.3465571](https://doi.org/10.1145/3437359.3465571)\n\n## References\n\n1. George Sugihara, Robert May, \"Nonlinear forecasting as a way of\n   distinguishing chaos from measurement error in time series,\" Nature, vol.\n   344, pp. 734–741,  1990. [10.1038/344734a0](https://doi.org/10.1038/344734a0)\n2. George Sugihara, \"Nonlinear forecasting for the classification of natural\n   time series. Philosophical Transactions,\" Physical Sciences and Engineering,\n   vol. 348, no. 1688, pp. 477–495, 1994.\n   [10.1098/rsta.1994.0106](https://doi.org/10.1098/rsta.1994.0106)\n3. George Sugihara, Robert May, Hao Ye, Chih-hao Hsieh, Ethan Deyle, Michael\n   Fogarty, Stephan Munch, \"Detecting Causality in Complex Ecosystems,\"\n   Science, vol. 338, pp. 496–500, 2012.\n   [10.1126/science.1227079](https://doi.org/10.1126/science.1227079)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeichi%2Fkedm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkeichi%2Fkedm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeichi%2Fkedm/lists"}