One of the main challenges facing precision agriculture is to find the most effective ways to explore the vast amounts of data that are being generated by different types of sensors. With the remarkable evolution of artificial intelligence techniques observed since the beginning of 2010, boosted by the development of deep learning (LeCun et al. 2015), it has become possible to extract useful information from the data more rapidly and efficiently. However, many agricultural problems pose challenges that no single source of data can fully characterize (Barbedo 2022). This is exacerbated by the fact that the agricultural environment has many more variables than are found in other environments (Barbedo 2018). Thus, exploring two or more sources of data is often the only viable option if more assertive answers are required. This is not a trivial task, though, especially when dealing with vastly different types of data, e.g. digital images and meteorological data. Fortunately, there are many different strategies generally known as data fusion techniques that can be used to make the best use of different types of data.