Replication data and code for: Built environment and taxi peak-commuting carbon emissions in central Shanghai

Derived data and analysis code supporting the manuscript "Built environment and taxi peak-commuting carbon emissions in central Shanghai" (submitted to Transportation Research Part D: Transport and Environment). CONTENTS data/ — 500 m grid-level derived layers for the central districts of Shanghai (n = 1,494 cells): 29 built-environment indicators; commuting carbon outcomes (all-day occupied, morning peak, evening peak); empty-cruising (deadheading) carbon; commuting trip counts, per-trip carbon and short-trip carbon shares; opportunity-accessibility layers; multi-scale (250 m / 1 km) MAUP aggregates; robustness outputs (alternative centre sets, disjoint commuting definitions); external-validation summaries; and the 500 m grid geometry (GeoPackage). code/ — Tier-A analysis scripts that run entirely from the released data with relative paths: OLS/Moran's I/LISA, spatial Durbin model, GWR/MGWR, XGBoost with spatial-block cross-validation, SHAP, ALE, single-variable counterfactual scan, and NSGA-II bi-objective optimisation. code_restricted/ — Tier-B provenance scripts that require the restricted raw inputs (GPS trajectories, mobile-signalling OD, raw POI) and therefore cannot be re-executed from this package. Their aggregated outputs are included in data/. output/ — Trained models, hyperparameters, spatial fold assignment and cross-validation metrics, enabling byte-level model reproduction. MANIFEST.csv — Full 32-character MD5 checksums and file sizes for every file.README_ZENODO.md — Data dictionary, units, reproduction instructions, and an explicit statement of what can and cannot be reproduced from this package. IMPORTANT — EMISSION FACTORThe released carbon fields are computed with the reference emission factor EF = 2.98. The manuscript reports carbon with the corrected factor EF = 2.31 (Appendix H). Multiply the released carbon by the rounded factor 0.775 (2.31/2.98 ≈ 0.7752) to obtain the manuscript's absolute values, or use the ready-made grid_500m_carbon_ef231.csv. All scale-invariant quantities (percentages, SHAP values, ALE, correlations, Moran's I, accessibility, exchange rates) are unaffected. DATA AVAILABILITY AND RESTRICTIONSThe underlying taxi GPS trajectories and the mobile-signalling job–housing OD data are provided by third parties under authorisation and cannot be redistributed. Only de-identified, aggregate 500 m (and 250 m / 1 km) grid-level derivatives are released here. Consequently, the derivation of carbon from raw trajectories cannot be re-executed from this package; the released grid carbon can, however, be verified for internal consistency and used to reproduce every statistical and modelling result reported in the manuscript. ACCESSFiles are restricted during peer review. Editors and reviewers may request access, or use the access link provided in the cover letter.