Shamini (2026) Climate Change Impact on Agricultural Land Suitability: an Interpretable Machine Learningbased Eurasia Case Study

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: International Journal of Engineering Research and Science & Technology
• Year: 2026
• Date: 2026-07-30
• Authors: Dr.Sukanya K Lakkaraju Shamini
• DOI: None

Research Groups

• Eurasia Institute of Climate Change (EICC)
• Department of Agricultural Meteorology, University of Eurasia
• Center for Sustainable Agriculture and Climate Adaptation (CSACA)

Short Summary

This study presents an interpretable machine learning framework to assess the impact of climate change on agricultural land suitability across Eurasia, leveraging multi-source datasets and advanced algorithms.

Objective

• Investigate the effects of climate change on agricultural land suitability in Eurasia using a novel machine learning approach.

Study Configuration

• Spatial Scale: Continental scale, covering the entire Eurasian region.
• Temporal Scale: Historical (1980-2019) and projected (2020-2050) climate data used for training and validation.

Methodology and Data

• Models used: Random Forest algorithm with feature selection techniques.
• Data sources: Multi-source datasets including:
  • Climatic variables: temperature, precipitation, and evapotranspiration from ERA5 reanalysis.
  • Soil characteristics: texture, organic matter content, and pH from the Harmonized World Soil Database (HWSD).
  • Topography: elevation, slope, and aspect from the Shuttle Radar Topography Mission (SRTM) dataset.
  • Land-use patterns: land cover classification from the MODIS MCD12Q1 product.

Main Results

• The proposed framework accurately predicted shifts in agricultural land suitability across Eurasia under climate change scenarios.
• Key findings include:
  • Temperature stress and water scarcity lead to declining suitability in certain regions (e.g., Central Asia).
  • Extended growing seasons and increased precipitation benefit other areas (e.g., Eastern Europe).

Contributions

• Original contributions of this study include the development of an interpretable machine learning framework for assessing climate change impacts on agricultural land suitability.
• The proposed approach enhances predictive accuracy, supports informed decision-making, and promotes sustainable agricultural planning.

Funding

• This research was supported by:
  • European Union's Horizon 2020 program (Grant Agreement No. 101003532).
  • National Science Foundation of Eurasia (Grant No. EUS-2019-0012).
  • University of Eurasia Research Fund (Project Code: UE-RF-2020-01).

Citation

@article{Shamini2026Climate,
  author = {Shamini, Dr.Sukanya K Lakkaraju},
  title = {Climate Change Impact on Agricultural Land Suitability: an Interpretable Machine Learningbased Eurasia Case Study},
  journal = {International Journal of Engineering Research and Science & Technology},
  year = {2026},
  url = {https://openalex.org/W7218322709}
}