The merging and comparing of the collected data is still in progress. The most recent data addition has been from the Indian River location. In August, more new data from the South Florida area will be incorporated. Using neural networks to analyze the data is underway and a few compelling results have been obtained and need further validations. Objective 1: Leaf nutrient thresholds At this point, we have just begun to analyze the combined data using the neural network software Easy-NN, including the Indian River Data set with the Ridge data set, which is complete through May 2017. We are looking at the sample dates as snapshots in time and combined for any possible connection or correlation with HLB severity. Continuing from our previous leads using mean leaf perimeter and leaf area as outputs in generating neural networks, we have found that along with calcium and magnesium, iron and copper are looking like important variables to watch with severity of HLB infection. When we run the neural network with soil parameters from the Ridge and Indian River area, we find that the organic matter content still plays a key role as well as soil pH and soil Mg concentration. Another vital variable to explore further is the L* parameter (lightness in color of the soil). As L* increases, the mean leaf area decreases. However, on its own, this variable is not well suited for predicting HLB incidence or severity; it does help to show the importance of organic matter in tree health. Looking further into the soil parameters as inputs and using leaf thickness (grams of leaf dry mass / meter square leaf area) as an output, we find the most important soil variables to be the soil magnesium content, as well as the lightness of the soil (L*), potassium content, and soil organic matter content. These are only preliminary results and more investigation is necessary as well as increasing the data set over the next few quarters. In the next quarterly report, we hope to be able to include data from the South Florida Region. A preliminary set of samples was just delivered for image analysis and soil samples should be forthcoming. Objective 2: Determine soil conditions that favor root hair and VAM proliferation i. We have discussed further soil analysis that we would like to work on, including data about permanent wilting points as well as possibly quantifying the silicon content of the soil. Soils from the South Florida area will be included into the data set and will be measured for all of variables the other two regions have been measured for, including organic matter content, and color analysis. ii. We are investigating a new system for root hair development using Valencia and Murcott seedlings in a nutrient solution. Test runs of seedlings exposed to nutrient fog is underway.