EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

Retrieval of rice biophysical parameters from Sentinel‑2 using parsimonious multi‑output machine learning

Joseph Kagotho Muriithi, Collins Mito, Giovanni Laneve, John Buers, Elijah Cheruiyot, Jephter Ondieki

Agrosystems, Geosciences & Environment · 2026-06 · 9 (2)

DOI: 10.1002/agg2.70381 ↗

At a glance

Journal article in Agrosystems, Geosciences & Environment, published online on 2026-06-01. Written by Joseph Kagotho Muriithi and 5 co-authors. Cited 1 times so far (Crossref); 85 references. The full text is freely available (open access, CC BY 4.0). Funded by: European Space Agency.

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Rice ( Oryza sativa L.) crop monitoring in Africa requires efficient retrieval of biophysical parameters such as leaf area index (LAI) and leaf chlorophyll content (LCC), which are essential for crop stress detection and nutrient management. This study aimed at developing a parsimonious modeling approach that overcomes the limitations of existing single‐ and multi‐target models. We developed a novel multi‐output framework that integrates Pareto optimization with adaptive stopping rules to simultaneously retrieve LAI and LCC from Sentinel‐2 imagery. Model performance was evaluated using in situ data ( n = 177) collected from rice farms in Kenya's Ahero irrigation scheme using coefficient of determination ( R 2 ) and root mean square error (RMSE) metrics. The parsimonious XGBoost (eXtreme gradient boosting) model trained on 11 vegetation indices achieved high accuracies ( R 2 = 0.76 and RMSE = 0.766 m 2 m − 2 for LAI; R 2 = 0.74 and RMSE = 3.590 µg cm − 2 for LCC). These results represent gains of up to 32% for LAI and 47% for LCC compared to prior Sentinel‐2‐based multi‐target retrieval approaches. Notably, the model achieved these improvements with a 54% reduction in vegetation indices and a 28% smaller model size relative to a 24‐vegetation indices baseline model. Therefore, our innovative design results in improved stability, generalization, and computational efficiency. By reducing complexity while improving accuracy, the framework offers a practical pathway for scalable crop monitoring and productivity improvement using freely available satellite data.

Funding

  • European Space Agency

Cite

APA

Muriithi, J. K., Mito, C., Laneve, G., Buers, J., Cheruiyot, E., & Ondieki, J. (2026). Retrieval of rice biophysical parameters from Sentinel‑2 using parsimonious multi‑output machine learning. Agrosystems, Geosciences & Environment, 9(2). https://doi.org/10.1002/agg2.70381

Vancouver

Muriithi JK, Mito C, Laneve G, Buers J, Cheruiyot E, Ondieki J. Retrieval of rice biophysical parameters from Sentinel‑2 using parsimonious multi‑output machine learning. Agrosystems, Geosciences & Environment. 2026;9(2). doi:10.1002/agg2.70381

BibTeX
@article{Muriithi2026,
  author = {Muriithi, Joseph Kagotho and Mito, Collins and Laneve, Giovanni and Buers, John and Cheruiyot, Elijah and Ondieki, Jephter},
  title = {Retrieval of rice biophysical parameters from Sentinel‑2 using parsimonious multi‑output machine learning},
  journal = {Agrosystems, Geosciences & Environment},
  year = {2026},
  volume = {9},
  number = {2},
  doi = {10.1002/agg2.70381}
}
Start for free →