Imaging systems mounted to ground vehicles are used to image fruit tree canopies for estimation of fruit load, but frequently need correction for fruit occluded by branches, foliage or other fruits. This can be achieved using an orchard ‘occlusion factor’, estimated from a manual count of fruit load on a sample of trees (referred to as the reference method). It was hypothesised that canopy images could hold information related to the number of occluded fruit. Five approaches to correct for occluded fruit based on canopy images were compared using data of three mango orchards in two seasons. However, no attribute correlates to the number of hidden fruit were identified. Several image features obtained through segmentation of fruit and canopy areas, such as the proportion of fruit that were partly occluded, were used in training Random forest and multi-layered perceptron (MLP) models for estimation of a correction factor per tree. In another approach, deep learning convolutional neural networks (CNNs) were directly trained against harvest fruit count on trees. The supervised machine learning methods for direct estimation of fruit load per tree delivered an improved prediction outcome over the reference method for data of the season/orchard from which training data was acquired. For a set of 2017 season tree images (n=98 trees), a R2 of 0.98 was achieved for the correlation of the number of fruits predicted by a Random forest model and the ground truth fruit count on the trees, compared to a R2 of 0.68 for the reference method. The best prediction of whole orchard (n = 880 trees) fruit load, in the season of the training data, was achieved by the MLP model, with an error to packhouse count of 1.6% compared to the reference method error of 13.6%. However, the performance of these models on new season data (test set images) was at best equivalent and generally poorer than the reference method. This result indicates that training on one season of data was insufficient for the development of a robust model. This outcome was attributed to variability in tree architecture and foliage density between seasons and between orchards, such that the characters of the canopy visible from the interrow that relate to the proportion of hidden fruit are not consistent. Training of these models across several seasons and orchards is recommended.

Bioprospecting native Australian plants offers potential discovery of latent and novel bioactive compounds. Promising cytotoxic and antibacterial activity of methanolic extracts of Pittosporum angustifolium and Terminalia ferdinandiana led to further fractionation and isolation using our laboratory’s bioassay guided fractionation protocol. Hence, the aim of this study was to further evaluate the bioactivity of the fractions and subfractions and characterize bioactive compounds using liquid chromatography mass spectroscopy (LC-MS/MS) and gas chromatography MS (GC-MS). Compounds tentatively identified in P. angustifolium Fraction 1 using LC-ESI-QTOF-MS/MS were chlorogenic acid and/or neochlorogenic acid, bergapten, berberine, 8’-epitanegool and rosmarinic acid. GC-MS analysis data showed the presence of around 100 compounds, mainly comprising of carboxylic acids, sugars, sugar alcohols, amino acids, and monoalkylglycerols. Furthermore, the fractions obtained from T. ferdinandiana flesh extracts showed no cytotoxicity, except against HT29 cell lines, and only Fraction 2 exhibited some antibacterial activity. The reduced bioactivity observed in the T. ferdinandiana fractions could be attributed to the potential loss of synergy as compounds become separated within the fractions. As a result, further fractionation, and separation of compounds in these samples were not pursued. However, additional dose-dependent studies are warranted to validate the bioactivity of T. ferdinandiana flesh fractions, particularly since this is an understudied species. Moreover, LC-MS/GC-MS studies confirm the presence of bioactive compounds in P. angustifolium Fraction 1/subfractions which helps to explain the significant acute anti-cancer activity of this plant. The screening process designed in this study has the potential to pave the way for developing scientifically validated phytochemical/bioactivity information on ethnomedicinal plants, thereby facilitating further bioprospecting efforts, and supporting the discovery of novel drugs in modern medicine.