Prediction of ratoon sugarcane family yield and selection using remote imagery

Authors: Todd, James; Johnson, Richard

Submitted to: Agronomy
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/18/2021
Publication Date: 6/23/2021
Citation: Todd, J.R., Johnson, R.M. 2021. Prediction of ratoon sugarcane family yield and selection using remote imagery. Agronomy. 11(7):Article 1273. https://doi.org/10.3390/agronomy11071273.
DOI: https://doi.org/10.3390/agronomy11071273

Interpretive Summary: Sugarcane selection efficiency could be increased if selection is done early in the breeding process by family; however, this would require a significant addition in time and resources. Remote sensing techniques have been utilized to predict crop performance in many other crops and potentially could also be used to predict sugarcane seedling family performance. Sugarcane is a perennial crop that may be harvested multiple years after the initial plant-cane crop. Subsequent crops (ratoons) are harvested each year until yields decline to an unacceptable level. Sugarcane seedling selection is typically performed on the first ratoon crop. Traditionally, family selection plots are weighed in plant cane and this data is used to predict family performance and make selections in first ratoon. It would be preferable to make selections in later ratoon crops to help identify varieties with superior ratooning ability (regrowth) but this not possible due to resource limitations. In this study we found that remote sensing data was more effective at predicting second ratoon family performance than yield data from the plant cane crop. These results demonstrate that remote sensing could potentially replace weighed plot yields as a selection tool, thus increasing breeding efficiency in development of high yielding sugarcane.

Technical Abstract: Remote sensing techniques and the use of Unmanned Aerial Systems (UAS) have simplified the estimation of yield and plant health in many crops. Family selection in sugarcane breeding programs relies on weighed plots at harvest, which is a labor-intensive process. In this study we utilized UAS-based remote sensing imagery of plant-cane and first-ratoon crops to estimate family yields for a second ratoon crop. Multiple families from the commercial breeding program were planted in a randomized complete block design by family. Standard red, green, and blue imagery was acquired with a commercially available UAS equipped with a Red-Green-Blue (RGB) camera. Color indices using the CIELab color space model were estimated from imagery for each plot. Cane was mechanically harvested with a sugarcane combine harvester and plot weights were obtained (kg) with a field wagon equipped with load cells. Stepwise regression, correlations, and variance inflation factors were used to identify the best multiple linear regression model to estimate second ratoon cane yield (kg). A multiple regression model which included family, and five different color indices produced a significant R2 of 0.88. This indicates that it is possible to make family selection predictions of cane weight without collecting plot weights. The adoption of this technology has the potential decrease labor requirements and increase breeding efficiency.