Author Identifier
David M. Cook: https://orcid.org/0000-0002-2264-8719
Leisa J. Armstrong: https://orcid.org/0000-0002-9634-016X
Document Type
Conference Proceeding
Publication Title
BIO Web of Conferences
Volume
167
Publisher
EDP Sciences
School
School of Science
Publication Unique Identifier
10.1051/bioconf/202516705001
RAS ID
78460
Abstract
The ability to predict and estimate the harvest production is of vital significance to the food security and financial value of global agriculture. The use of synthetic inference in determining crop yield estimations cannot be underestimated. L-systems uses high-level estimation dependent upon inference techniques through sources ranging from real to synthetic data. This paper combines intelligent and highly visual features to infer crop characteristics. It provides a method of assembling superior synthetic datasets that reduce the reliance upon time-consuming fully trained neural networks. It demonstrates a mature approach to using synthetic inference that provides cost-effective reliable crop yield estimations. This model allows for scalable and affordable application of synthetic inference as part of an optimised yield-positive farming enterprise in crops such as wheat. By leveraging synthetic inference, digital twins, and visualization, scientists, agronomists, and farmers can gain deeper insights into improved crop management.
DOI
10.1051/bioconf/202516705001
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Comments
Napier, C. C., Cook, D. M., & Armstrong, L. J. (2025). An efficient yield prediction model using synthetic inference from L-systems. In 5th International Conference on Smart and Innovative Agriculture (ICoSIA 2024), BIO Web of Conferences. https://doi.org/10.1051/bioconf/202516705001