Communication Dans Un Congrès Année : 2025

Hybrid Phenology Modeling for Predicting Temperature Effects on Tree Dormancy

Résumé

Biophysical models offer valuable insights into climatephenology relationships in both natural and agricultural settings. However, there are substantial structural discrepancies across models which require site-specific recalibration, often yielding inconsistent predictions under similar climate scenarios. Machine learning methods offer data-driven solutions, but often lack interpretability and alignment with existing knowledge. We present a phenology model describing dormancy in fruit trees, integrating conventional biophysical models with a neural network to address their structural disparities. We evaluate our hybrid model in an extensive case study predicting cherry tree phenology in Japan, South Korea and Switzerland. Our approach consistently outperforms both traditional biophysical and machine learning models in predicting blooming dates across years. Additionally, the neural network's adaptability facilitates parameter learning for specific tree varieties, enabling robust generalization to new sites without site-specific recalibration. This hybrid model leverages both biophysical constraints and data-driven flexibility, offering a promising avenue for accurate and interpretable phenology modeling.

Fichier principal
Vignette du fichier
AAAI2025_CameraReady.pdf (756.01 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05196296 , version 1 (01-08-2025)

Licence

Identifiants

Citer

Ron van Bree, Diego Marcos, Ioannis Athanasiadis. Hybrid Phenology Modeling for Predicting Temperature Effects on Tree Dormancy. AIAA 2025 - 39. Annual AAAI Conference on Artificial Intelligence, Feb 2025, Philadelphia, United States. pp.28458-28466, ⟨10.1609/aaai.v39i27.35068⟩. ⟨hal-05196296⟩
133 Consultations
103 Téléchargements

Altmetric

Partager

  • More