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

TL;DR

This paper demonstrates that the Sundial foundation model can effectively forecast Leaf Area Index in agriculture without task-specific training, often outperforming traditional supervised models when given sufficient input context.

Contribution

It shows that a general-purpose foundation model can surpass specialized models in remote-sensing time series forecasting without task-specific tuning.

Findings

Sundial outperforms fully trained LSTM with enough seasonal context.

Zero-shot Sundial achieves competitive forecasting accuracy.

Foundation models have strong potential in agricultural remote sensing.

Abstract

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.