Examinando por Materia "machine learning"

Mostrando 1 - 2 de 2

A Comparison of Classification Algorithms for Predicting Distinctive Characteristics in Fine Aroma Cocoa Flowers Using WEKA Modeler
(2024-09-24) Tineo Flores, Daniel; Murillo, Yuriko S.; Marin, Mercedes; Gomez Fernandez, Darwin; Taboada, Víctor H.; Goñas Goñas, Malluri; Quiñonez Huatangari, Lenin
The expression of crop functional traits is influenced by environmental and management conditions, which in turn is reflected in genetic diversity. This study employed a data mining approach to determine the functional traits of flowers that influence cocoa diversity. A total of 1,140 flowers from 228 trees were utilized in this study, with 177 representing fine aroma cocoa trees and 51 trees belonging to other commercial cultivars. Three attribute evaluators (InfoGainAttributeEval, CorrelationAttributeEval and GainRatioAttributeEval), and six algorithms (Naive Bayes, Multinomial Logistic Regression, J48, Random Forest, LTM and Simple Logistic) were employed in this study. The findings indicated that the GainRatioAttributeEval attribute generator was the most efficacious in discerning the functional trait in cocoa diversity flowers. The algorithms Simple Logistic and LMT were the most accurate and specific, while Naive Bayes was the most efficient in terms of computational complexity for model building. This research provides a comprehensive overview of the use of machine learning to analyze functional traits of flowers that most influence cocoa genetic diversity. It also highlights the need to further improve these models by integrating additional techniques to increase their efficiency and extend the data mining approach to other agricultural sectors.
Vis-NIR spectroscopy and machine learning for prediction of soil fertility indicators and fertilizer recommendation in Andean highland and rainforest agroecosystems
(MDPI, 2026-04-26) Pizarro Carcausto, Samuel Edwin; Ccopi Trucios, Dennis; Ortega Quispe, Kevin Abner; Contreras Pino, Duglas Lenin; Ñaupari, Javier; Cano, Deyvis; Patricio Rosales , Solanch Rosy; Loayza, Hildo; Apolo Apolo, Orly Enrique
This study evaluated the use of visible and near-infrared (Vis-NIR) spectroscopy combined with machine learning (ML) algorithms to predict soil fertility-related properties in two contrasting agroecological regions of Peru: the Highlands and the Rainforest. A total of 297 soil samples were analyzed using portable spectroradiometers covering a spectral range of 350–2500 nm, applying transformations such as Savitzky–Golay smoothing, first derivative, and band depth. Predictive models were developed using PLSR, Random Forest, Support Vector Machines, and neural networks. Results show variable predictive performance across soil properties and ecosystems. Organic matter in Highland soils and calcium in Rainforest soils achieved the strongest test-set accuracy (R2 > 0.70), while pH and texture fractions showed moderate performance (R2 = 0.42–0.67), and mobile nutrients including phosphorus, potassium, and sodium showed limited predictive accuracy due to their weak spectral expression. Spectral predictions were further integrated into a structured nutrient balance framework to assess agronomic reliability. Nitrogen fertilizer recommendations showed the strongest agreement between observed and predicted values across both ecosystems, whereas K2O and CaO recommendations in Highland soils were substantially underestimated, demonstrating that property-level statistical performance does not guarantee agronomic reliability. These findings confirm that Vis-NIR spectroscopy combined with ML represents a fast, cost-effective, and sustainable alternative to conventional soil analysis, especially in rural areas with limited laboratory infrastructure. Expanding regional calibration datasets and exploring mid-infrared FTIR spectroscopy as a complementary technology are identified as priority directions for improving predictions of agronomically critical nutrients.