Models for predicting coffee yield from chemical characteristics of soil and leaves using machine learning

BACKGROUND

Coffee farming constitutes a substantial economic resource, representing a source of income for several countries due to the high consumption of coffee worldwide. Precise management of coffee crops involves collecting crop attributes (characteristics of the soil and the plant), mapping, and applying inputs according to the plants' needs. This differentiated management is precision coffee growing and it stands out for its increased yield and sustainability.

RESULTS

This research aimed to predict yield in coffee plantations by applying machine learning methodologies to soil and plant attributes. The data were obtained in a field of 54.6 ha during two consecutive seasons, applying varied fertilization rates in accordance with the recommendations of soil attribute maps. Leaf analysis maps also were monitored with the aim of establishing a correlation between input parameters and yield prediction. The machine-learning models obtained from these data predicted coffee yield efficiently. The best model demonstrated predictive fit results with a Pearson correlation of 0.86. Soil chemical attributes did not interfere with the prediction models, indicating that this analysis can be dispensed with when applying these models.

CONCLUSION

These findings have important implications for optimizing coffee management and cultivation, providing valuable insights for producers and researchers interested in maximizing yield using precision agriculture. © 2024 Society of Chemical Industry.

Optimizing adjuvant inhaled chemotherapy: Synergistic enhancement in paclitaxel cytotoxicity by flubendazole nanocrystals in a cycle model approach

Lung cancer is the leading cause of cancer-related death. In addition to new innovative approaches, practical strategies that improve the efficacy of already available drugs are urgently needed. In this study, an inhalable dry powder formulation is used to repurpose flubendazole, a poorly soluble anthelmintic drug with potential against a variety of cancer lineages. Flubendazole nanocrystals were obtained through nanoprecipitation, and dry powder was produced by spray drying. Through fractional factorial design, the spray drying parameters were optimized and the impact of formulation on aerolization properties was clarified. The loading limitations were clarified through response surface methodology, and a 15% flubendazole loading was feasible through the addition of 20% L-leucine, leading to a flubendazole particle size of 388.6 nm, median mass aerodynamic diameter of 2.9 μm, 50.3% FPF, emitted dose of 83.2% and triple the initial solubility. Although the cytotoxicity of this formulation in A549 cells was limited, the formulation showed a synergistic effect when associated with paclitaxel, leading to a surprising 1000-fold reduction in the IC50. Compared to 3 cycles of paclitaxel alone, a 3-cycle model combined treatment increased the threshold of cytotoxicity by 25% for the same dose. Our study suggests, for the first time, that orally inhaled flubendazole nanocrystals show high potential as adjuvants to increase cytotoxic agents' potency and reduce adverse effects.