Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.23935200This dataset and code package supports the manuscript “Divergent trajectories following cropland abandonment in Inner Mongolia: Satellite evidence and socioeconomic predictability.” It contains processed county-level socioeconomic data, derived county–cohort statistics, and reproducible analysis code for examining persistence and return to cultivation after confirmed cropland abandonment. The primary analytical sample comprises 195 county–cohort observations from 71 counties, covering first-confirmation cohorts in 2019–2021 with two-year follow-up. Socioeconomic predictors refer to 2018–2020 and include registered population, urban disposable income, rural or pastoral disposable income, road length, and fiscal expenditure per registered resident. The package provides the source values used in analysis, their natural-log transformations, and the final common modeling sample. A broader inventory contains 522 county–cohort records across 87 spatial units for 2018–2023, including cohorts with incomplete follow-up. The code implements XGBoost modeling with nested spatial cross-validation, sensitivity analyses, temporal-transfer evaluation, and held-out TreeSHAP interpretation. It also includes scripts for reconstructing sample eligibility and generating descriptive statistics. English documentation, a variable dictionary, source information, and file checksums are provided. Original remote-sensing rasters, pixel-level cultivation histories, and intermediate verification files are excluded. The underlying ARCC10-IM dataset is available separately at https://doi.org/10.6084/m9.figshare.25687278.v4. This package supports reproduction of the county-level tabular analyses and predictive interpretation; it does not reproduce the original remote-sensing classification.
Keyword(s):
Cropland abandonment; Cultivation trajectories; Return to cultivation; County-level socioeconomic data; Inner Mongolia; XGBoost; SHAP; Spatial cross-validation; Remote sensing.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)