Hybrid Phenology Modeling for Predicting Temperature Effects on Tree Dormancy

TL;DR

This paper introduces a hybrid phenology model combining biophysical and neural network approaches to improve temperature effect predictions on tree dormancy, achieving better accuracy and adaptability across diverse sites.

Contribution

The study presents a novel hybrid model that integrates biophysical knowledge with machine learning, enhancing prediction accuracy and generalization without site-specific recalibration.

Findings

Outperforms traditional models in predicting cherry tree blooming dates.

Enables parameter learning for specific tree varieties.

Generalizes well to new sites without recalibration.

Abstract

Biophysical models offer valuable insights into climate-phenology 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.