A novel ordinal multi-view aggregation scheme for oak defoliation

Authors

Francisco Bérchez-Moreno

Ricardo Enrique Hernández Lambraño

David Guijo-Rubio

Víctor Manuel Vargas-Yun

Francisco José Ruiz-Gómez

Juan Carlos Fernández

Pablo González-Moreno

Published in Journal

arXiv preprint arXiv:2605.28151

Abstract

Forest decline driven by climate and biotic stressors threatens ecosystem functioning, making accurate monitoring of tree health essential. In this work, we address tree defoliation estimation as an ordinal classification problem using ground-level imagery. We propose a novel multi-view ensemble framework that aggregates predictions from Convolutional Neural Networks (CNNs) trained on different perspectives of individual trees (north, south, and crown). This approach leverages complementary visual information while preserving modelling consistency through a homogeneous ensemble design. A comprehensive evaluation is conducted by comparing multiple ordinal classification methods and analysing the contribution of each view and their combinations. Results show that modelling the ordinal structure of defoliation levels improves performance over nominal approaches, while the proposed multi-view ensemble consistently outperforms single-view and pairwise configurations. In particular, the three-view ensemble achieves the most robust and accurate predictions across all evaluation metrics. These findings highlight the potential of combining Deep Learning (DL), Ordinal Classification (OC), and multi-view aggregation for scalable, consistent, and objective forest health assessment in complex ecosystems such as Mediterranean dehesas.

BibTex Citation

@article{Berchez2026novel,
	author = {B{\' e}rchez-Moreno, Francisco and Hern{\' a}ndez Lambra{\~ n}o, Ricardo Enrique and Guijo-Rubio, David and Vargas-Yun, V{\' i}ctor Manuel and Ruiz-G{\' o}mez, Francisco Jos{\' e} and Fern{\' a}ndez, Juan Carlos and Gonz{\' a}lez-Moreno, Pablo},
	journal = {arXiv preprint arXiv:2605.28151},
	year = {2026},
	title = {A novel ordinal multi-view aggregation scheme for oak defoliation},
	url = {https://arxiv.org/abs/2605.28151},
	howpublished = {https://arxiv.org/abs/2605.28151},
}

BibTex Unicode Citation

@article{Berchez2026novel,
	author = {Bérchez-Moreno, Francisco and Hernández Lambraño, Ricardo Enrique and Guijo-Rubio, David and Vargas-Yun, Víctor Manuel and Ruiz-Gómez, Francisco José and Fernández, Juan Carlos and González-Moreno, Pablo},
	journal = {arXiv preprint arXiv:2605.28151},
	year = {2026},
	title = {A novel ordinal multi-view aggregation scheme for oak defoliation},
	url = {https://arxiv.org/abs/2605.28151},
	howpublished = {https://arxiv.org/abs/2605.28151},
}

APA Citation

Bérchez-Moreno, F., Hernández Lambraño, R. E., Guijo-Rubio, D., Vargas-Yun, V. M., Ruiz-Gómez, F. J., Fernández, J. C., & González-Moreno, P. (2026). A novel ordinal multi-view aggregation scheme for oak defoliation. arXiv Preprint arXiv:2605.28151. https://arxiv.org/abs/2605.28151

RIS Citation

TY  - JOUR
AU  - Bérchez-Moreno, Francisco
AU  - Hernández Lambraño, Ricardo Enrique
AU  - Guijo-Rubio, David
AU  - Vargas-Yun, Víctor Manuel
AU  - Ruiz-Gómez, Francisco José
AU  - Fernández, Juan Carlos
AU  - González-Moreno, Pablo
DA  - 2026///
PY  - 2026
ID  - temp_id_442843862909
T2  - arXiv preprint arXiv:2605.28151
TI  - A novel ordinal multi-view aggregation scheme for oak defoliation
UR  - https://arxiv.org/abs/2605.28151
ER  -

CV Citation

F. Bérchez-Moreno, R.E. Hernández Lambraño, D. Guijo-Rubio, V.M. Vargas-Yun (CA), F.J. Ruiz-Gómez, J.C. Fernández, P. González-Moreno (4/7). "A novel ordinal multi-view aggregation scheme for oak defoliation". arXiv preprint arXiv:2605.28151, 2026.