AI-based optimization of greenhouse horticulture
| Reference number | |
| Coordinator | SVEGRO AB - Svegro AB, Torslunda |
| Funding from Vinnova | SEK 300 000 |
| Project duration | April 2020 - October 2020 |
| Status | Completed |
| Venture | AI - Competence, ability and application |
| Call | Start your AI-journey! For businesses |
Important results from the project
The purpose of this project was to investigate how AI can be used to support and optimize the growing process of herbs in greenhouses. Of particular interest was to investigate whether AI can be used to optimize energy use and reduce the number of pots that need to be discarded due to quality deficiencies.
Expected long term effects
AI models were created to continuously estimate plant size and plant quality from image data captured by surveillance cameras. The results from these models are fed into machine learning models that calculate the expected size of the plants at harvest. The end result shows that AI can be used to effectively monitor cultivation beds and assess size and other quality factors. The project also led to insights into which data is relevant and how it should be used to find further connections to reduce energy needs and cultivation waste.
Approach and implementation
The project has been carried out as a close collaboration between Svegro and a consulting company that specializes in AI and machine learning. The direct results from the project have been turned into a web-based product. In addition to this, Svegro has also decided to continue investing in AI as part of its development and innovation work.