# A novel ordinal multi-view aggregation scheme for oak defoliation

Source: [A novel ordinal multi-view aggregation scheme for oak defoliation](<https://www.sota2.com/research/paper/6a17cc03dbd7150506f8125d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-29T05:00:05.519Z

Authors: Francisco B\\'erchez-Moreno, Ricardo Enrique Hern\\'andez-Lambra\\~no, David Guijo-Rubio, V\\'ictor Manuel Vargas, Francisco Jos\\'e Ruiz-G\\'omez, Juan Carlos Fern\\'andez, Pablo Gonz\\'alez-Moreno

Published: 2026-05-27T08:33:44.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Ordinal Classification on oak Crown (test)](<https://www.sota2.com/research/sota/ordinal-classification-on-oak-crown-test.md>): Ordinal Classification; oak Crown (test); QWK: 0.454.

- [Ordinal Classification on oak North (test)](<https://www.sota2.com/research/sota/ordinal-classification-on-oak-north-test.md>): Ordinal Classification; oak North (test); QWK: 0.483.

- [Ordinal Classification on oak South (test)](<https://www.sota2.com/research/sota/ordinal-classification-on-oak-south-test.md>): Ordinal Classification; oak South (test); QWK: 48.3.

- [Ordinal Classification on oak Crown+North (test)](<https://www.sota2.com/research/sota/ordinal-classification-on-oak-crown-plus-north-test.md>): Ordinal Classification; oak Crown+North (test); QWK: 0.555.

- [Ordinal Classification on oak Crown+South (test)](<https://www.sota2.com/research/sota/ordinal-classification-on-oak-crown-plus-south-test.md>): Ordinal Classification; oak Crown+South (test); QWK: 0.573.

- [Ordinal Classification on oak North+South (test)](<https://www.sota2.com/research/sota/ordinal-classification-on-oak-north-plus-south-test.md>): Ordinal Classification; oak North+South (test); QWK: 0.568.

- [Ordinal Classification on oak Crown+North+South (test)](<https://www.sota2.com/research/sota/ordinal-classification-on-oak-crown-plus-north-plus-south-test.md>): Ordinal Classification; oak Crown+North+South (test); QWK: 0.613.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.28151>)

[PDF](<https://arxiv.org/pdf/2605.28151.pdf>)
