Machine learning and artificial intelligence within precision agriculture

Technology for efficiently collecting large amounts of data, combined with machine learning and artificial intelligence, enables us to extract valuable information that can optimize various aspects of agriculture.

At the Center for Precision Agriculture, we primarily work with data from imaging sensors that provide spectral data across different parts of the electromagnetic spectrum. We use this to develop models for tasks such as estimating crop yield, crop quality, fertilizer requirements, weed detection, and berry counting.

Since the outcome of a model is only as good as the quality of the data fed into it, we strive for the best possible data quality and the highest quality analyses. This includes implementing rigorous procedures for field trials, data collection, and data processing before modeling.

We recognize that models often need to be adjusted to account for specific geographic and climatic conditions. Therefore, we work to ensure that high-quality models tailored to Norwegian conditions can be used effectively by Norwegian farmers.

Through initiatives such as the PRESIS project, we are working on developing a digital infrastructure that makes these models accessible to all Norwegian farmers who wish to use them.