Tefera et al. (2025) Satellite-Based Machine Learning for Soil Moisture Prediction and Land Conservation Practice Assessment in West African Drylands

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

Identification

• Journal: Remote Sensing
• Year: 2025
• Date: 2025-11-05
• Authors: Meron Lakew Tefera, Ethiopia B. Zeleke, Mario Pirastru, Assefa M. Melesse, Giovanna Seddaiu, Hassan Awada
• DOI: 10.3390/rs17213651

Research Groups

Not explicitly stated in the provided text.

Short Summary

This study integrated remote sensing, in situ data, and machine learning to predict soil moisture and evaluate the impact of land conservation practices in northern Ghana, finding that stone bunds increased soil moisture by 4–6% compared to non-bunded fields.

Objective

• To predict soil moisture and evaluate the impact of land conservation practices using integrated remote sensing, in situ data, and machine learning.

Study Configuration

• Spatial Scale: 222 field sites in northern Ghana; fine-scale resolution.
• Temporal Scale: Not explicitly stated in the provided text.

Methodology and Data

• Models used: Long Short-Term Memory (LSTM) model combined with Random Forest gap-filling.
• Data sources: Remote sensing data, in situ observation data.

Main Results

• The LSTM model with Random Forest gap-filling achieved strong predictive performance for soil moisture (R² = 0.84; RMSE = 0.103 cm³ cm⁻³).
• The model outperformed SMAP satellite estimates by approximately 30% across key accuracy metrics.
• Fields with stone bunds maintained 4–6% higher moisture than non-bunded fields.
• The positive impact of stone bunds was particularly evident on steep slopes and in areas with low to moderate topographic wetness.

Contributions

• Demonstrates the capability of combining remote sensing and deep learning for fine-scale soil moisture prediction.
• Provides quantitative evidence of how nature-based solutions (stone bunds) enhance water retention and climate resilience in dryland agricultural systems.

Funding

Not explicitly stated in the provided text.

Citation

@article{Tefera2025SatelliteBased,
  author = {Tefera, Meron Lakew and Zeleke, Ethiopia B. and Pirastru, Mario and Melesse, Assefa M. and Seddaiu, Giovanna and Awada, Hassan},
  title = {Satellite-Based Machine Learning for Soil Moisture Prediction and Land Conservation Practice Assessment in West African Drylands},
  journal = {Remote Sensing},
  year = {2025},
  doi = {10.3390/rs17213651},
  url = {https://doi.org/10.3390/rs17213651}
}