2021-04-22, 13:30–14:00, Track 2
SEGES, a Danish agricultural knowledge and innovation centre, developed and productionized in 2020 a crop yield prognosis model. We present the utilized ML methods, EO data, de-facto Python GIS packages, experiment results, and DevOps solutions.
We present the within-field crop yield prognosis model developed by SEGES using machine learning (ML) methods and earth observation (EO) data. Our model and its prognoses were released to the Danish farmers in 2020 via our WebUI solution called CropManager, where the prognosis maps of a 10x10 meter resolution are visualized. This presentation will drill into the specifics of the utilized ML algorithm, ground truth yield data, and the other EO data sources used for creating the prognosis model. Additionally, we also present our use of DevOps solutions, like TeamCity, Octopus, Azure Machine Learning, and Kubernetes, to productionize the ML model.
SEGES is the leading agricultural knowledge and innovation centre in Denmark. We offer sustainable products and services for the agriculture and food sector, by collaborating with international customers, clients and farmers, to build a bridge between research and practical farming.