aiqbench analysis
This study applies sequence-to-sequence Convolutional LSTM models to generate high-resolution, 30-day forecasts of Leaf Area Index across the South-Central United States using meteorological forcing and historical sequences. By achieving a significantly lower RMSE than persistence baselines at a 1-km grid scale, this work demonstrates that deep learning can effectively bridge gaps in subseasonal land surface modeling for diverse vegetation types. The approach offers a robust methodological advance for integrating machine learning into climate models where traditional data-driven estimation has previously fallen short of prognostic requirements.
A Sequence-to-Sequence ConvLSTM Approach for Leaf Area Index Forecasting over the South-Central United States
arXiv:2608.00879v1 Announce Type: cross Abstract: Leaf Area Index (LAI) is a fundamental biophysical variable governing land-atmosphere interactions; however, LAI forecasting at high spatial resolution remains an unsolved challenge. While recent machine learning approaches have demonstrated LAI estimation at point or regional scales, none provides a gridded, meteorology-driven prognostic forecast suitable for subseasonal land surface and climate modeling applications. Here we present a sequence-to-sequence Convolutional LSTM (ConvLSTM) framework that generates daily 1-km LAI forecasts up to 30 days ahead, driven by historical LAI sequences and daily meteorological forcing including temperature and precipitation. Trained and evaluated over the South-Central United States -- a region of strong climate gradients and diverse vegetation -- the model achieves a domain-averaged RMSE of 0.36 at a 30-day lead time, more than a third lower than the persistence baseline. Forecast skill remains robust across seasons, geographic distributions, and plant functional types, including forests, grasslands, shrublands, and croplands. To our knowledge, this is the first demonstration of skillful LAI forecasting at a 30-day horizon at 1-km resolution.
Abstract:Leaf Area Index (LAI) is a fundamental biophysical variable governing land-atmosphere interactions; however, LAI forecasting at high spatial resolution remains an unsolved challenge. While recent machine learning approaches have demonstrated LAI estimation at point or regional scales, none provides a gridded, meteorology-driven prognostic forecast suitable for subseasonal land surface and climate modeling applications. Here we present a sequence-to-sequence Convolutional LSTM (ConvLSTM) framework that generates daily 1-km LAI forecasts up to 30 days ahead, driven by historical LAI sequences and daily meteorological forcing including temperature and precipitation. Trained and evaluated over the South-Central United States -- a region of strong climate gradients and diverse vegetation -- the model achieves a domain-averaged RMSE of 0.36 at a 30-day lead time, more than a third lower than the persistence baseline. Forecast skill remains robust across seasons, geographic distributions, and plant functional types, including forests, grasslands, shrublands, and croplands. To our knowledge, this is the first demonstration of skillful LAI forecasting at a 30-day horizon at 1-km resolution.
Atmospheric and Oceanic Physics (physics.ao-ph); Machine Learning (cs.LG)
arXiv:2608.00879 [physics.ao-ph]
(or arXiv:2608.00879v1 [physics.ao-ph] for this version)
https://doi.org/10.48550/arXiv.2608.00879 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 263 words
Related coverage
Links #5: 2026/07
LessWrong · Jul 31, 2026
Turning spectra into images improves plant trait retrieval with 2D-CNNs
arXiv · Aug 19, 2026
ORBIT-2 based Weather and Climate Downscaling and Downscaled Global Forecasts on AMD Instinct
AMD · Jun 8, 2026
Dialogue with Eliezer Yudkowsky on Neural Networks
LessWrong · Oct 2, 2026