Update README.md
Browse files
README.md
CHANGED
|
@@ -13,8 +13,20 @@ tags:
|
|
| 13 |
|
| 14 |
# VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting
|
| 15 |
|
| 16 |
-
This is the official pretrained model weights for the paper [arXiv:2508.03589](https://arxiv.org/abs/2508.03589)
|
| 17 |
|
| 18 |
## Overview
|
| 19 |
|
| 20 |
-
VITA addresses the data asymmetry problem in agricultural AI: pretraining uses 31 meteorological variables from NASA POWER satellite data, while deployment relies on only 6 basic weather features. Through variational pretraining with a seasonality-aware sinusoidal prior, VITA achieves state-of-the-art performance in predicting corn and soybean yields across 763 U.S. Corn Belt counties, particularly during extreme weather years.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
# VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting
|
| 15 |
|
| 16 |
+
This is the official pretrained model weights for the paper [arXiv:2508.03589](https://arxiv.org/abs/2508.03589). VITA is a variational pretraining framework that learns weather representations from rich satellite data and transfers them to yield prediction tasks with limited ground-based measurements.
|
| 17 |
|
| 18 |
## Overview
|
| 19 |
|
| 20 |
+
VITA addresses the data asymmetry problem in agricultural AI: pretraining uses 31 meteorological variables from NASA POWER satellite data, while deployment relies on only 6 basic weather features. Through variational pretraining with a seasonality-aware sinusoidal prior, VITA achieves state-of-the-art performance in predicting corn and soybean yields across 763 U.S. Corn Belt counties, particularly during extreme weather years.
|
| 21 |
+
|
| 22 |
+
## Citation
|
| 23 |
+
|
| 24 |
+
```bibtex
|
| 25 |
+
@inproceedings{hasan2026vita,
|
| 26 |
+
title={VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting},
|
| 27 |
+
author={Hasan, Adib and Roozbehani, Mardavij and Dahleh, Munther},
|
| 28 |
+
booktitle={Proceedings of the 40th AAAI Conference on Artificial Intelligence},
|
| 29 |
+
year={2026},
|
| 30 |
+
url={https://arxiv.org/abs/2508.03589},
|
| 31 |
+
}
|
| 32 |
+
```
|