Bayesian Machine Learning Approach for Corn Yield Prediction Using Satellite Imagery and Topographic Data

Aug 5, 2026

Upload by Levi

In an era of climate change and growing global food demand, accurate crop yield prediction is pivotal for enabling data-driven crop management and sustainability. This study compares several Bayesian machine learning methods using high-resolution PlanetScope satellite imagery and topographic data. Bayesian Linear Regression, Bayesian Random Forest, Bayesian Splines, Bayesian Additive Regression Trees, and Bayesian Neural Network models are developed to incorporate uncertainty quantification while targeting improved predictive accuracy. Results indicate that Bayesian Random Forest achieves the strongest yield prediction performance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages1

Reading Time3 min

AccessFree to download

Abstract

Methods

Results

Keywords

FAQs

Which Bayesian machine learning models are used for corn yield prediction?

The study develops Bayesian Linear Regression, Bayesian Random Forest, Bayesian Splines, Bayesian Additive Regression Trees, and Bayesian Neural Network models.

What input data sources drive the yield prediction?

The models use high-resolution PlanetScope imagery together with topographic data.

Which method performs best for predicting corn yield?

Bayesian Random Forest outperforms the other compared models in corn yield prediction performance.

Aug 5, 2026

Upload by Levi