From reflectance to yield: Understanding corn production metrics

Authors: RAM SAPKOTA, BALA - Texas A&M University; BAATH, GURJINDER - Texas Agrilife Research; Flynn, Kyle; Adhikari, Kabindra; Hajda, Chad; Smith, Douglas; MURRAY, SETH - Texas A&M University

Submitted to: Meeting Abstract
Publication Type: Abstract Only
Publication Acceptance Date: 8/29/2024
Publication Date: N/A
Citation: N/A

Interpretive Summary: n/a - abstract only.

Technical Abstract: This study investigates the use of machine learning algorithms and multispectral imaging for predicting corn yield. It aims to enhance traditional yield prediction methods by incorporating reflectance bands and vegetation indices. The research compares the performance of five different machine learning algorithms across various growth stages. It uses an extensive dataset from experimental corn plots planted at different times across three distinct field locations. The Extra Trees Regressor consistently outperforms other models, with calibrated reflectance band values proving more effective predictors than vegetation indices alone. The study finds that yield prediction accuracy varies with growth stages, with the mid-vegetative stage being less accurate due to lower canopy cover. The study concludes that integrating spectral bands and vegetation indices can enhance yield prediction models, providing a more reliable alternative to relying solely on historical data. This has significant implications for optimizing agricultural practices and resource allocation.