Dataset · Harvard Dataverse · September 6, 2026
Replication Data and Code for “Added Predictive Value and Temporal Transferability of MODIS and ERA5-Land Data for District-Level Wheat Yield Forecasting”
A. A. Pyagay, Dulat Kali, Nurzhamal Kashkimbayeva, Razali Yaakob
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.
More by Nurzhamal Kashkimbayeva
- Evidence-Linked Measurement of Indirect Prompt Injection in Web Security Agents: Paired Trials and Application-Specific Evidence AuditsTechnologies · 2026
- Kazakhstan Agri Recommender — Data Collection PipelineZenodo · 2026
- Multimodal Data Fusion for District-Scale Crop Yield Prediction in Northern KazakhstanIEEE International Conference on Smart Information Systems and Technologies · 2026
- Development of an Intelligent Software Platform for Forecasting Market Trends and Stock Prices Based on the Analysis of Big Financial Data and News FeedsIEEE International Conference on Smart Information Systems and Technologies · 2026