Replication Data and Code for “Added Predictive Value and Temporal Transferability of MODIS and ERA5-Land Data for District-Level Wheat Yield Forecasting”
Year: 2026
Type: dataset
Abstract: This dataset contains the reproducibility materials supporting the manuscript “Added Predictive Value and Temporal Transferability of MODIS and ERA5-Land Data for District-Level Wheat Yield Forecasting.” It includes the processed district-year analytical panel for 17 districts of Akmola Region, Kazakhstan (2015–2025), administrative boundary data, reproducible Python scripts, complete expanding-window out-of-sample predictions for 2020–2025, Random Forest model outputs, M1–M5 data-source ablation results, paired district-cluster and observation-level bootstrap analyses, yield-history benchmarks, permutation-importance results, cropland-mask sensitivity and 2025 robustness analyses, all main manuscript tables and figures, supplementary Tables S1–S6, metadata, a reproducibility README, and a SHA-256 file manifest.
Source: Harvard Dataverse
DOI: 10.7910/dvn/utejgw
Institutions: Astana IT University, Universiti Putra Malaysia
Language: English
Subfield: Ecology
Field: Environmental Science
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W7212134941