{"id":50501915,"url":"https://github.com/worldbank/eca-resilience","last_synced_at":"2026-06-02T12:30:43.144Z","repository":{"id":359595617,"uuid":"1130608155","full_name":"worldbank/eca-resilience","owner":"worldbank","description":"GPS-based analysis of human mobility and urban space usage during atypical events.","archived":false,"fork":false,"pushed_at":"2026-06-01T22:16:19.000Z","size":24266,"stargazers_count":0,"open_issues_count":15,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-02T00:15:46.199Z","etag":null,"topics":["datapartnership","disaster-response","gps-data","mobility"],"latest_commit_sha":null,"homepage":"https://worldbank.github.io/eca-resilience/README.html","language":"Jupyter Notebook","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/worldbank.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"docs/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-08T18:42:15.000Z","updated_at":"2026-06-01T22:16:23.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/worldbank/eca-resilience","commit_stats":null,"previous_names":["worldbank/eca-resilience"],"tags_count":0,"template":false,"template_full_name":"worldbank/template","purl":"pkg:github/worldbank/eca-resilience","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbank%2Feca-resilience","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbank%2Feca-resilience/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbank%2Feca-resilience/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbank%2Feca-resilience/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/worldbank","download_url":"https://codeload.github.com/worldbank/eca-resilience/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbank%2Feca-resilience/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33822812,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-02T02:00:07.132Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["datapartnership","disaster-response","gps-data","mobility"],"created_at":"2026-06-02T12:30:41.997Z","updated_at":"2026-06-02T12:30:43.134Z","avatar_url":"https://github.com/worldbank.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ECA Resilience\n\n*[GitHub](https://github.com/worldbank/eca-resilience) · [Documentation](https://worldbank.github.io/eca-resilience/README.html) · [Development Data Partnership](https://datapartnership.org/)*\n\nThis project leverages large-scale GPS mobility data to study human activity and urban space usage in response to atypical events. Using the **Urban Space Usage Index**, a normalized measure of relative human presence derived from anonymized mobile device location pings, the project quantifies deviations from typical mobility patterns and examines how cities respond to a range of shocks, from sudden natural disasters to planned public events and slow-onset climate stressors.\n \nCase studies span two countries and four distinct event types: the **2023 Turkey-Syria earthquakes**, **Republic Day celebrations in Istanbul**, **heatwaves in Metro Manila**, and **monsoon-driven flooding in Manila amplified by Typhoon Doksuri**.\n\n## Project Overview\n \n### Data Source\n \nThe analysis is based on the [Veraset Movement dataset](https://datapartnership.org/), provided as part of the Mobility Data collection from the [Development Data Partnership](https://datapartnership.org/). The dataset consists of anonymized, high-frequency GPS pings collected through a network of mobile applications and SDKs. Each record includes geographic coordinates, a UTC timestamp, and an anonymized device identifier.\n \nMobility observations are spatially aggregated using the [Uber H3 hierarchical spatial index](https://h3geo.org/) at resolutions 7 and 8 (average cell areas of ~5 km² and ~0.74 km², respectively).\n \n### Methodology\n \nThe analytical framework follows three steps:\n \n**1. Define a measure.** The **Urban Space Usage Index** (*I*) is defined as the daily share of total active users visiting each H3 hexagon, normalizing for day-to-day fluctuations in overall data volume:\n \n\u003e *I(h, d) = U(h, d) / U(d)*\n \nwhere *U(h, d)* is the number of unique users in hexagon *h* on day *d*, and *U(d)* is the total number of active users on that day.\n \n**2. Quantify deviations.** Deviations from typical conditions are measured through **Z-scores** computed relative to a stable baseline period:\n \n\u003e *Z(h, d) = (I(h, d) − μ(h)) / σ(h)*\n \n**3. Interpret deviations.** Z-scores are analyzed temporally and spatially, and stratified by land-use category and functional layer (POI-based), enabling characterization of *where* and *how* urban activity changes in response to events.\n \nFull methodological details are available in the [Methodological Framework](https://worldbank.github.io/eca-resilience/notebooks/Methodology.html) and [Spatial Characterization of Urban Units](https://worldbank.github.io/eca-resilience/notebooks/Methodology_land_usage.html) notebooks.\n \n### Geographies\n \n| Country | Area of Interest | Resolution |\n|---|---|---|\n| Philippines | Metro Manila | H3 resolution 8 (~0.74 km²) |\n| Turkey | Istanbul | H3 resolution 8 (~0.74 km²) |\n| Turkey | 11 earthquake-affected provinces | H3 resolution 8 (~0.74 km²) |\n \n### Case Studies\n \nA key design feature of this project is that the four case studies deliberately span **four distinct event typologies**, each presenting different challenges for mobility analysis and policy response:\n \n| Event | Location | Typology | Period |\n|---|---|---|---|\n| [Republic Day](https://worldbank.github.io/eca-resilience/notebooks/Republic_day_report.html) | Istanbul, Turkey | Planned public event | Oct 2023 |\n| [2023 Turkey-Syria Earthquake](https://worldbank.github.io/eca-resilience/notebooks/Earthquake_report.html) | Southern Turkey (11 provinces) | Sudden, unpredictable natural disaster | Feb 2023 |\n| [Flooding (Typhoon Doksuri)](https://worldbank.github.io/eca-resilience/notebooks/Floods_report.html) | Metro Manila, Philippines | Foreseeable natural disaster (typhoon-driven) | Jul 2023 |\n| [Heatwaves](https://worldbank.github.io/eca-resilience/notebooks/Heatwaves_report.html) | Metro Manila, Philippines | Slow-onset climate shock | Apr 2023 |\n \nThis typology-driven structure allows the framework to be tested across events with fundamentally different warning horizons, impact profiles, and behavioral responses:\n \n- **Planned events** (Republic Day) produce sharp, predictable spikes in activity that amplify existing spatial patterns city-wide.\n- **Sudden disasters** (earthquake) generate delayed but extreme anomalies driven by emergency response, displacement, and humanitarian operations, with no anticipatory behavioral signal.\n- **Foreseeable disasters** (typhoon-driven flooding) show a characteristic two-phase pattern: a pre-event increase in activity consistent with anticipatory behaviors (stocking, relocation), followed by a sharp collapse during peak impact.\n- **Slow-onset shocks** (heatwaves) produce weaker aggregate signals but reveal systematic spatial and functional redistributions of activity, with people shifting toward climate-controlled or shaded environments rather than reducing mobility altogether.\n### Data Quality Assessments\n \nPrior to analysis, comprehensive Exploratory Data Analysis and Quality Assessments (EDA+QA) were conducted for each country dataset, documenting temporal coverage, spatial distribution, regime shifts, and user-level heterogeneity.\n \n| Report | Key findings |\n|---|---|\n| [EDA+QA Turkey](https://worldbank.github.io/eca-resilience/notebooks/Turkey_EDA_QA.html) | ~1.1B GPS points, 18.9M users; 96.7% temporal coverage; three anomalous regimes identified |\n| [EDA+QA Metro Manila](https://worldbank.github.io/eca-resilience/notebooks/Manila_EDA_QA.html) | ~4.4B GPS points, 27.2M users; 96.6% temporal coverage; structural break on 10 July 2023 |\n\n\n\n## Getting Started\n\n### Prerequisites\n\n- Python 3.8 or higher\n- Jupyter Lab for running notebooks\n\n### Installation\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/worldbank/eca-resilience.git\n   cd eca-resilience\n   ```\n\n2. Create and activate the conda environment:\n   ```bash\n   conda env create -f environment.yml\n   conda activate eca-resilience\n   ```\n\n### Usage\n\nFor detailed documentation and analysis notebooks, visit the [project documentation](https://worldbank.github.io/eca-resilience/README.html).\n\n## Contact \n\nFor questions, feedback, or contributions, please contact the Development Data Partnership at datapartnership@worldbank.org.\n\nYou can also open an issue in the [GitHub repository](https://github.com/worldbank/eca-resilience/issues).\n\n## License\n\nThis project is licensed under the MIT License together with the World Bank IGO Rider. The Rider is purely procedural: it reserves all privileges and immunities enjoyed by the World Bank, without adding restrictions to the MIT permissions. Please review both files before using, distributing or contributing.\n\n## Code of Conduct\n\nThis project maintains a [Code of Conduct](docs/CODE_OF_CONDUCT.md) to ensure an inclusive and respectful environment for everyone. Please adhere to it in all interactions within our community.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fworldbank%2Feca-resilience","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fworldbank%2Feca-resilience","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fworldbank%2Feca-resilience/lists"}