Learning county from pixels: corn yield prediction with attention-weighted multiple instance learning

TL;DR

This paper introduces an attention-weighted multiple instance learning approach for county-level corn yield prediction using pixel-level remote sensing data, effectively handling mixed pixels and outperforming existing models.

Contribution

The study presents a novel pixel-level yield prediction method employing attention mechanisms to address mixed pixel issues, improving accuracy over traditional county aggregation methods.

Findings

Achieved R2 of 0.84 and RMSE of 0.83 in 2022.

Outperformed four other machine learning models over five years.

Effectively filtered noise from mixed pixels using attention.

Abstract

Remote sensing technology has become a promising tool in yield prediction. Most prior work employs satellite imagery for county-level corn yield prediction by spatially aggregating all pixels within a county into a single value, potentially overlooking the detailed information and valuable insights offered by more granular data. To this end, this research examines each county at the pixel level and applies multiple instance learning to leverage detailed information within a county. In addition, our method addresses the "mixed pixel" issue caused by the inconsistent resolution between feature datasets and crop mask, which may introduce noise into the model and therefore hinder accurate yield prediction. Specifically, the attention mechanism is employed to automatically assign weights to different pixels, which can mitigate the influence of mixed pixels. The experimental results show that the developed model outperforms four other machine learning models over the past five years in the U.S. corn belt and demonstrates its best performance in 2022, achieving a coefficient of determination (R2) value of 0.84 and a root mean square error (RMSE) of 0.83. This paper demonstrates the advantages of our approach from both spatial and temporal perspectives. Furthermore, through an in-depth study of the relationship between mixed pixels and attention, it is verified that our approach can capture critical feature information while filtering out noise from mixed pixels.