Open accessPeer reviewed
Symposium on Machine Learning for Development 202412 December 2024CC-BY-4.0PDFID 8x447
Cite this

Beatrice Njoroge and Kevin Mutiso (2024) Satellite-based crop-yield nowcasting for smallholder maize in the Rift Valley. Symposium on Machine Learning for Development 2024. https://quorumpress.org/papers/satellite-based-crop-yield-8x447

BibTeXRISRIS opens in Zotero, Mendeley and EndNote.

Published in Symposium on Machine Learning for Development 2024. This article was peer reviewed before publication.

Symposium on Machine Learning for Development 2024Abstract No. AEDWF7
Kigali Institute of Applied AI
Abstract

Satellite-based crop-yield nowcasting for smallholder maize in the Rift Valley

Beatrice Njoroge1*, Kevin Mutiso1

1 Highland AgriTech Institute, Addis Ababa, Ethiopia
* Corresponding author
Published 12 December 2024CC-BY-4.0

Abstract

We describe a machine-learning pipeline that combines Sentinel-2 imagery, rainfall estimates, and soil data to nowcast smallholder maize yields at sub-county resolution. Trained on three seasons of ground-truth harvest measurements, the model explained 71 percent of yield variance and flagged drought-stressed zones four to six weeks before harvest. We discuss how such early signals can inform anticipatory action by county agriculture offices.

Keywords: Remote sensing, Crop yield, Smallholder agriculture, Nowcasting

Cite as: Beatrice Njoroge & Kevin Mutiso (2024). Satellite-based crop-yield nowcasting for smallholder maize in the Rift Valley. Symposium on Machine Learning for Development 2024. https://quorumpress.org/papers/satellite-based-crop-yield-8x447

© 2024 Njoroge and Mutiso. Open access under CC BY 4.0.

An abstract submission. There is no manuscript body.

Cite this paper

Beatrice Njoroge, Kevin Mutiso. Satellite-based crop-yield nowcasting for smallholder maize in the Rift Valley. Symposium on Machine Learning for Development 2024, 2024. https://quorumpress.org/papers/satellite-based-crop-yield-8x447

Publication ID: 8x447