English
weather,
agriculture,
notadib commited on
Commit
5617f12
·
verified ·
1 Parent(s): 88e4ad5

Update README.md

Browse files

# VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting

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. This is the official pretrained model. Code: https://github.com/Neehan/VITA

**Paper**: [arXiv:2508.03589](https://arxiv.org/abs/2508.03589) | **AAAI 2026**

## Overview

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.

Files changed (1) hide show
  1. README.md +12 -3
README.md CHANGED
@@ -1,3 +1,12 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - notadib/NASA-Power-Daily-Weather
5
+ language:
6
+ - en
7
+ metrics:
8
+ - r_squared
9
+ tags:
10
+ - weather,
11
+ - agriculture,
12
+ ---