Zero-Shot Transfer Capabilities of the Sundial Foundation Model for Leaf Area Index Forecasting

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Peining, Qin, Hongchen, Zhang, Haochen, Guo, Ziqi, Wang, Guiling, Bi, Jinbo
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909991856766976
author Zhang, Peining
Qin, Hongchen
Zhang, Haochen
Guo, Ziqi
Wang, Guiling
Bi, Jinbo
author_facet Zhang, Peining
Qin, Hongchen
Zhang, Haochen
Guo, Ziqi
Wang, Guiling
Bi, Jinbo
contents This work investigates the zero-shot forecasting capability of time series foundation models for Leaf Area Index (LAI) forecasting in agricultural monitoring. Using the HiQ dataset (U.S., 2000-2022), we systematically compare statistical baselines, a fully supervised LSTM, and the Sundial foundation model under multiple evaluation protocols. We find that Sundial, in the zero-shot setting, can outperform a fully trained LSTM provided that the input context window is sufficiently long-specifically, when covering more than one or two full seasonal cycles. We show that a general-purpose foundation model can surpass specialized supervised models on remote-sensing time series prediction without any task-specific tuning. These results highlight the strong potential of pretrained time series foundation models to serve as effective plug-and-play forecasters in agricultural and environmental applications.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Transfer Capabilities of the Sundial Foundation Model for Leaf Area Index Forecasting
Zhang, Peining
Qin, Hongchen
Zhang, Haochen
Guo, Ziqi
Wang, Guiling
Bi, Jinbo
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
This work investigates the zero-shot forecasting capability of time series foundation models for Leaf Area Index (LAI) forecasting in agricultural monitoring. Using the HiQ dataset (U.S., 2000-2022), we systematically compare statistical baselines, a fully supervised LSTM, and the Sundial foundation model under multiple evaluation protocols. We find that Sundial, in the zero-shot setting, can outperform a fully trained LSTM provided that the input context window is sufficiently long-specifically, when covering more than one or two full seasonal cycles. We show that a general-purpose foundation model can surpass specialized supervised models on remote-sensing time series prediction without any task-specific tuning. These results highlight the strong potential of pretrained time series foundation models to serve as effective plug-and-play forecasters in agricultural and environmental applications.
title Zero-Shot Transfer Capabilities of the Sundial Foundation Model for Leaf Area Index Forecasting
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20004