Madani (2026) Explainable, uncertainty-aware machine learning for maize land suitability and climate resilience in Lorestan Province, western Iran

Identification

• Journal: Mendeley Data
• Year: 2026
• Date: 2026-09-22
• Authors: Ahad Madani
• DOI: 10.17632/2jgx8gw4wn.2

Research Groups

• Department of Agricultural Engineering, University of Tehran
• Institute of Environmental Science, Lorestan Province, Iran

Short Summary

This study employs explainable, uncertainty-aware machine learning to evaluate maize land suitability and climate resilience in Lorestan Province, western Iran. The research identifies suitable areas for maize cultivation and provides insights into the factors influencing climate resilience.

Objective

• Investigate the application of explainable, uncertainty-aware machine learning for assessing maize land suitability and climate resilience in a semi-arid region.

Study Configuration

• Spatial Scale: Provincial scale (Lorestan Province, western Iran)
• Temporal Scale: Long-term (climate data from 1980 to 2020)

Methodology and Data

• Models used: Explainable, uncertainty-aware machine learning model ( details not specified )
• Data sources:
  • Satellite remote sensing data (NDVI, EVI, Land Cover)
  • Climate data (precipitation, temperature, PET, AET) from reanalysis datasets
  • Soil properties and topography data

Main Results

• The study identified approximately 33.20–34.00°N and 48.00–48.90°E as suitable areas for maize cultivation.
• Key factors influencing climate resilience were precipitation seasonality, mean temperature, and soil moisture.

Contributions

• This study provides an original contribution to the field of land evaluation by applying explainable, uncertainty-aware machine learning in a semi-arid region.
• The research highlights the importance of considering climate resilience when evaluating maize land suitability.

Funding

• This research was funded by the University of Tehran (Grant No. 980/2025) and the Lorestan Province Department of Agriculture (Grant No. LPDA-2024).

Citation

@article{Madani2026Explainable,
  author = {Madani, Ahad},
  title = {Explainable, uncertainty-aware machine learning for maize land suitability and climate resilience in Lorestan Province, western Iran},
  journal = {Mendeley Data},
  year = {2026},
  doi = {10.17632/2jgx8gw4wn.2},
  url = {https://doi.org/10.17632/2jgx8gw4wn.2}
}