257-5 Reducing Farmer Uncertainty in Spring Forage Harvests: Digital Image Analysis and Artificial Intelligence to Predict Alfalfa-Grass Stand Composition.

Poster Number 706

See more from this Division: C06 Forage and Grazinglands
See more from this Session: Forage and Grazinglands
Tuesday, October 23, 2012
Duke Energy Convention Center, Exhibit Hall AB, Level 1
Share |

Keenan C. McRoberts1, Jerome H. Cherney2, Brent M. Benson3 and Debbie Jeannine Ray J. Cherney1, (1)Department of Animal Science, Cornell University, Ithaca, NY
(2)Department of Crop and Soil Sciences, Cornell University, Ithaca, NY
(3)Benson Consulting, Pasadena, MD
Poster Presentation
  • ASA Poster 2012 Final.pdf (651.0 kB)
  • There is a small range in optimal fiber content (NDF) for lactating dairy cows, making quality-related harvest management decisions critical. The aim of this project is to improve the timing and nutritive value of spring forage harvests for dairy operations by reducing uncertainty in stand composition. Accurate prediction equations exist for estimating NDF content of mixed alfalfa-grass stands in spring, and estimating the optimal harvest date. The weak link is estimating the proportion grass in a stand. In spring 2011 we acquired 580 digital images of alfalfa-grass stands in farmer’s fields and determined alfalfa and grass dry matter percentages for vegetation in each image. A program was designed to estimate alfalfa-grass proportions. The program uses digital image processing to filter 64 x 64 pixel tiles. These tiles were transformed to the frequency spectrum using the Fast Fourier algorithm, and selected frequencies were aggregated and supplemented by alfalfa maximum height and grass canopy height information from original images for artificial intelligence processing. Tiles in a subset of selected images were classified as predominately grass, alfalfa, or non-classifiable. Predicted stand composition by Support Vector Machine trained with 1000 to 8000 tiles significantly predicted actual values (p<0.0001, n=548) when all grass species were pooled. Best results were obtained with a set of 4000 training tiles (r2=0.39). Species-specific predictions were better than overall results for timothy (r2=0.5) and reed canarygrass (r2=0.44). The next step is to attempt grass species-specific training and prediction. When satisfactory predictive capacity is achieved, the only required inputs to an Internet program accessible by computer or smart phone include an image of the stand and agronomic measures (e.g., maximum alfalfa height). Farmers and consultants could use this technology to prioritize the order of harvest of alfalfa-grass fields to maximize chances of obtaining optimal forage NDF for lactating dairy cow diets.
    See more from this Division: C06 Forage and Grazinglands
    See more from this Session: Forage and Grazinglands