Changes in GC-MS metabolite profile, antioxidant capacity and anthocyanins content during fermentation of fine-flavor cacao beans from Ecuador

The fermentation of fine-flavor cacao beans is a key process contributing to the enhancement of organoleptic attributes and monetary benefits for cacao farmers. This work aimed to describe the dynamics of the gas chromatography-mass spectrometry (GC-MS) metabolite profile as well as the antioxidant capacity and anthocyanin contents during fermentation of fine-flavor cacao beans. Samples of Nacional x Trinitario cacao beans were obtained after 0, 24, 48, 72, 96, and 120 hours of spontaneous fermentation. Total phenolic content (TPC), ferric reducing antioxidant power (FRAP), and total anthocyanin content were measured by ultraviolet-visible (UV-Vis) spectrophotometry. Volatiles were adsorbed by headspace solid phase microextraction (HS-SPME) while other metabolites were assessed by an extraction-derivatization method followed by gas chromatography-mass spectrometry (GC-MS) detection and identification. Thirty-two aroma-active compounds were identified in the samples, including 17 fruity, and 9 floral-like volatiles as well as metabolites with caramel, chocolate, ethereal, nutty, sweet, and woody notes. Principal components analysis and Heatmap-cluster analysis of volatile metabolites grouped samples according to the fermentation time. Additionally, the total anthocyanin content declined during fermentation, and FRAP-TPC values showed a partial correlation. These results highlight the importance of fermentation for the improvement of the fine-flavor characteristics of cacao beans.

Effective Methods Based on Distinct Learning Principles for the Analysis of Hyperspectral Images to Detect Black Sigatoka Disease

Current chemical methods used to control plant diseases cause a negative impact on the environment and increase production costs. Accurate and early detection is vital for designing effective protection strategies for crops. We evaluate advanced distributed edge intelligence techniques with distinct learning principles for early black sigatoka disease detection using hyperspectral imaging. We discuss the learning features of the techniques used, which will help researchers improve their understanding of the required data conditions and identify a method suitable for their research needs. A set of hyperspectral images of banana leaves inoculated with a conidial suspension of black sigatoka fungus (Pseudocercospora fijiensis) was used to train and validate machine learning models. Support vector machine (SVM), multilayer perceptron (MLP), neural networks, N-way partial least square-discriminant analysis (NPLS-DA), and partial least square-penalized logistic regression (PLS-PLR) were selected due to their high predictive power. The metrics of AUC, precision, sensitivity, prediction, and F1 were used for the models' evaluation. The experimental results show that the PLS-PLR, SVM, and MLP models allow for the successful detection of black sigatoka disease with high accuracy, which positions them as robust and highly reliable HSI classification methods for the early detection of plant disease and can be used to assess chemical and biological control of phytopathogens.