The purpose of the detection would be to determine if the tree is infected by X.F. For this, there is a method called PCR (Polymerase Chain Reaction) that can detect the presence of viruses or measure viral loads. However, this is a complex method that requires DNA sampling on the tree, which will undergo various treatments in the laboratory, so it is not a way to detect X.F. on the field.

Therefore, this project focuses on detecting the drying of the tree which is one of the first symptoms of X.F. In the case of the olive tree, this method is relevant because the olive tree is an evergreen tree, its leaves will not dry naturally if the tree is healthy. However, the drying of the tree can be caused by other factors than XF, the solution presented here serves primarily as a warning device, it is appropriate after detecting the drying of a tree to take a sample and to ensure that it is XF which infects the tree before injecting the remedy developed by the team.

You can see below a diagram representing a chain of data transmission that would allow you to observe the status of one or more trees in real time. This report relates mainly on the sensor and the data processing part.

To observe the dryness of the tree, we use NDVI (Normalized Difference Vegetation Index) images, this allows to detect the level of photosynthesis of the leaves of a tree.

You can see on the diagram below that healthy leaves return more infrared light, there is an index, the NDVI, which allows to determine this level of photosynthesis of a plant.

$$\text{Index NDVI} = \frac{\text{NIR}-\text{RED}}{\text{NIR}+\text{RED}}$$

The calculated index is between -1 and 1 and it is associated with a color scale that allows you to observe easily and quickly if the tree is healthy or not, you can see an example of NDVI image below.