Data-driven forecasting of tropical cloud forest phenology: A dynamical systems and machine learning hybrid approach

Pedro Garcia; Saul Flores

cs.LGOct 18, 2026

Data-driven forecasting of tropical cloud forest phenology: A dynamical systems and machine learning hybrid approach

Authors: Pedro Garcia, Saul Flores

Organizations: Departamento de Física, Facultad de Ingeniería, Universidad Católica Andrés Bello, Caracas, Venezuela · Laboratorio de Ecología de Suelos, Centro de Ecología, Instituto Venezolano de Investigaciones Científicas, Caracas, Venezuela

Abstract

Forecasting how species and ecosystems respond to climate change is a critical challenge in ecology, particularly in hyper-diverse tropical biomes. While traditional phenological models often rely on preconceived functional forms, this study introduces a data-driven hybrid approach that integrates dynamical systems theory with machine learning to forecast flowering and fruiting cycles. Using a robust 35-year dataset from a Venezuelan tropical cloud forest, we reconstruct the system's state-space using delay vectors inspired by Takens' theorem, incorporating climate forcing variables such as temperature and precipitation. The model was trained using Gaussian Process Regression, providing both point predictors and explicit uncertainty estimates. Our results clearly suggest that the synergy between dynamical systems and machine learning effectively captures the non-linear complexities of ecological time series. Specifically, the model achieved higher predictive accuracy for flowering and fruiting. This hybrid framework offers a scalable tool for anticipating phenological mismatches and informing conservation strategies in the face of global environmental change.

Figures & tables

No.	Family	Species	GBIF link	Growth form	Reproductive density
					(4m -2 )
1	Apocynaceae	Aspidosperma fendleri Woodson	3618540	Tree	0.25 $\pm$ 0.18
2	Burseraceae	Protium tovarense Pittier	3992944	Tree	0.29 $\pm$ 0.21
3	Phyllanthaceae	Hieronyma fendleri Briq.	3079076	Tree	0.20 $\pm$ 0.16
4	Phyllanthaceae	Richeria grandis Vahl	3079144	Tree	0.23 $\pm$ 0.27
5	Marcgraviaceae	Ruyschia tremadena (Ernst) Lundell	3915996	Climber	0.10 $\pm$ 0.01

Table 1: Focal study species.

Figure 1: State space of the system forest-clima.

Panel of Figure 3 — Figure 3: GPR flowering and fruiting prediction for each specie vs. actual data with confidence interval.

Species	Flowering	Fruiting
A.fendleri	0.444	0.581
B.reticulata	0.503	0.495
C.tremadena	0.444	0.478
E.amazonicum	0.455	0.637
E.americanus	0.705	0.546
G.latifolia	0.449	0.482

Table 2: Root-mean-square error of GPR by species.

Figure 4: K-Means Clustering of species based on RMSE.

Time Series Forecasting

Time series forecasting predicts future values from ordered observations using statistical, neural, and probabilistic models to support decisions under uncertainty.

See all 839 papers

Calibrating Biophysical Models for Grape Phenology Prediction via Multi-Task Learning
Aug 5, 2025William Solow, Sandhya SaisubramanianMulti-Task Learning Model Calibration
Oregon State University
A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning
Mar 16, 2026William Solow, Paola Pesantez-Cabrera, Markus Keller +3Precision Agriculture
Oregon State University · Washington State University
MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning
Apr 1, 2026Yuchang Jiang, Jan Dirk Wegner, Vivien Sainte Fare GarnotDomain Adaptation Domain-Adversarial Learning
DM3L, UZH, Zurich, Switzerland

Aug 5, 2025J/K move · Enter open · S save

Calibrating Biophysical Models for Grape Phenology Prediction via Multi-Task Learning

William Solow, Sandhya Saisubramanian

Oregon State University

Multi-Task Learning Model Calibration

Open paper AskPDF arXiv

Accurate prediction of grape phenology is essential for timely vineyard management decisions, such as scheduling irrigation and fertilization, to maximize crop yield and quality. While traditional biophysical models calibrated on historical field data can be used for season-long predictions, they lack the precision required for fine-grained vineyard management. Deep learning methods are a compelling alternative but their performance is hindered by sparse phenology datasets, particularly at the cultivar level. We propose a hybrid modeling approach that combines multi-task learning with a recurrent neural network to parameterize a differentiable biophysical model. By using multi-task learning to predict the parameters of the biophysical model, our approach enables shared learning across cultivars while preserving biological structure, thereby improving the robustness and accuracy of predictions. Empirical evaluation using real-world and synthetic datasets demonstrates that our method significantly outperforms both conventional biophysical models and baseline deep learning approaches in predicting phenological stages, as well as other crop state variables such as cold-hardiness and wheat yield.

Abstract

Time Series Forecasting

Explore similar work

Calibrating Biophysical Models for Grape Phenology Prediction via Multi-Task Learning

A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning

MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning