Elwan et al. (2022) Irrigation Mapping on Two Contrasted Climatic Contexts Using Sentinel-1 and Sentinel-2 Data

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

Identification

• Journal: Water
• Year: 2022
• Authors: Ehsan Elwan, Michel Le Page, Lionel Jarlan, Nicolas Baghdadi, Luca Brocca, Sara Modanesi, Jacopo Dari, Pere Quintana Seguí, Mehrez Zribi
• DOI: 10.3390/w14050804

Research Groups

The study involved research applied to two distinct geographical and climatic contexts in Europe: - Spain (Semi-arid context) - Italy (Humid context)

Short Summary

This study proposes an operational and robust methodology for mapping irrigated areas by synergizing Sentinel-1 (S1) radar and Sentinel-2 (S2) optical time series data, demonstrating that multi-site training across diverse climatic contexts (Spain and Italy) yields the highest and most consistent classification accuracy (approximately 85%).

Objective

• Propose an operational approach to map irrigated areas based on the synergy of Sentinel-1 and Sentinel-2 data, and prove the essential role of multi-site training for a robust application of the proposed methodologies across different climatic and agricultural contexts.

Study Configuration

• Spatial Scale: Agricultural field scale and the 5 kilometre surroundings (multi-scale spatial information).
• Temporal Scale: Time series data from Sentinel-1 and Sentinel-2 (specific duration not provided, but implies seasonal/annual monitoring).

Methodology and Data

• Models used: Support Vector Machine (SVM) classification.
• Data sources: Sentinel-1 (S1) time series (radar); Sentinel-2 (S2) time series (optical); Statistical variables derived from time series data.

Main Results

• The optimal classification utilized five metrics, confirming the importance of optical/radar synergy and the consideration of multi-scale spatial information.
• The highest classification accuracy achieved was approximately 85%.
• This high accuracy was achieved when the training dataset included mixed reference fields from both study sites (multi-site training).
• The resulting accuracy was consistent across both the semi-arid (Spain) and humid (Italy) study sites.

Contributions

• Proposes a robust, operational methodology for mapping irrigated areas that is suitable for general use across sites with different climatic and agricultural contexts.
• Quantitatively confirms the critical role of multi-site training in enhancing the robustness and consistency of remote sensing classification applications.
• Demonstrates the effectiveness of combining Sentinel-1 and Sentinel-2 data with multi-scale spatial metrics for improved discrimination between irrigated and rainfed areas.

Funding

• Funding information was not provided in the source text.

Citation

@article{Elwan2022Irrigation,
  author = {Elwan, Ehsan and Page, Michel Le and Jarlan, Lionel and Baghdadi, Nicolas and Brocca, Luca and Modanesi, Sara and Dari, Jacopo and Quintana‐Seguí, Pere and Zribi, Mehrez},
  title = {Irrigation Mapping on Two Contrasted Climatic Contexts Using Sentinel-1 and Sentinel-2 Data},
  journal = {Water},
  year = {2022},
  doi = {10.3390/w14050804},
  url = {https://doi.org/10.3390/w14050804}
}

Generated by BiblioAssistant using gemini-flash-latest (Google API)