The Potential for Hyperspectral Imaging and Machine Learning to Classify Internal Quality Defects in Macadamia Nuts
Tree nuts are rich in nutrients, and global production and consumption have doubled during the last decade. However, nuts have a range of quality defects that must be detected and removed during post-harvest processing. Tree nuts can develop hidden internal discoloration, and current sorting methods are prone to subjectivity and human error. Therefore, non-destructive, real-time methods to evaluate internal nut quality are needed. This study explored the potential for VNIR (400–1000 nm) hyperspectral imaging to classify brown center disorder in macadamias. This study compared the accuracy of classifiers developed using images of kernels imaged in face-up and face-down orientations. Classification accuracy was excellent using face-up (>97.9%) and face-down (>94%) images using ensemble and linear discriminate models before and after wavelength selection. Combining images to form a pooled dataset also provided high accuracy (>90%) using artificial neural network and support vector machine models. Overall, HSI has great potential for commercial application in nut processing to detect internal brown centers using images of the outside kernel surface in the VNIR range. This technology will allow rapid and non-destructive evaluation of intact nut products that can then be marketed as a high-quality, defect-free product, compared with traditional methods that rely heavily on representative sub-sampling.
https://doi.org/10.3390/horticulturae10111129
Trend Analysis of Different Climate Parameters and Watering Requirements for Hazelnut in Central Italy Related to Climate Change
In this study, the effects of climate change on the irrigation water requirement of hazelnut trees were investigated in Central Italy. The meteorological variables considered were precipitation, temperature, chilling units, and the Standardized Precipitation Index (SPI) in Central Italy. The hydrological variables were the reference evapotranspiration (ET0) and the water requirement based on soil water balance. Climate data were collected from eight meteorological stations for the period 1974–2021, and ET0 was estimated by the Hargreaves and Samani equation. The SPI index was calculated for a four-month time scale corresponding to the hazelnut growing season (April–August). A statistical analysis of the trends of the variables considered was conducted. The results showed an increasing trend for temperature, ET0, and water requirements, while a decreasing trend was shown for the chilling units. No significant trends were detected for precipitation and SPI. https://doi.org/10.3390/horticulturae9050593
Fruit Phenology of Two Hazelnut Cultivars and Incidence of Damage by Halyomorpha halys in Treated and Untreated Hazel Groves
Over the past decade, Halyomorpha halys has become one of the main threats to hazelnut production. Its trophic activity makes kernels inedible due to strongly detrimental effects on the organoleptic quality. Its management in Italy is still tricky due to the lack of effective native biocontrol agents and authorized and effective insecticides. A field test was performed on San Giovanni (SG) and Tonda Romana (TR) cultivars (early and late ripening, respectively) to assess the intensity of cimiciato damage with different pest management approaches (no insecticide and integrated pest management, IPM). Moreover, phenological analysis of fruits and the monitoring of stink bug species by traps and plant beating were carried out. In the untreated plots, the SG cv showed a higher cimiciato incidence with respect to the late TR cv (40% SG–NI vs. 23% TR–NI). This was probably due to the different phenological phases in which stink bugs injured the fruits. In fact, stink bug bites provoke different kinds of injuries (blanks, shriveled, and cimiciato) according to the fruit’s development period. Indeed, in the period of highest insect occurrence in the field, the fruits of the early cv (SG) were in kernel expansion, a phenological phase in which bug injuries are more likely in cimiciato defects. Lastly, the IPM did not provide sufficient fruit protection (19% SG–IPM vs. 11% TR–IPM). The interaction between the phenological development of hazelnuts and the brown marmorated stink bug represents a critical aspect in understanding and implementing effective strategies for controlling this key pest on hazelnut trees. https://doi.org/10.3390/horticulturae9060727