Examinando por Materia "Yield prediction"

Mostrando 1 - 2 de 2

Agronomic variables outperform multispectral indices for individual plant yield prediction in Andean quinoa
(Elsevier B.V., 2026-04-18) Pizarro Carcausto, Samuel Edwin; García Seguil, Erika Janina; Gavino Lulo, Esthefany Irene; Requena Rojas, Edilson Jimmy; Ortega Quispe, Kevin Abner; Cccopi Trucios, Dennis
Accurate pre-harvest yield estimation is essential for decision-making in high-altitude agriculture. This study evaluated agronomic and multispectral UAV variables for near-harvest prediction of individual quinoa grain weight, with data collected across six phenological stages to identify when predictors achieve reliable performance, under Andean conditions. A total of 374 plants were monitored across six phenological stages at Santa Ana Experimental Station (Huancayo, Peru, 3280 m a.s.l.) during 2024. OLS, Random Forest, Support Vector Machine, and Neural Network models were trained using agronomic-only (AGRO), spectral-only (IND), and combined (COMP) predictor sets, evaluated through 5-fold cross-validation reporting mean ± standard deviation. Agronomic and combined models achieved moderate performance (R² = 0.22–0.25, RPD = 1.10–1.15), suitable for relative plant ranking in breeding programs, while spectral-only models failed across all algorithms (R² ≤ 0.044, CCC ≤ 0.080), constrained by saturation, phenological decoupling, and canopy heterogeneity. Variable importance analysis confirmed that late-season structural traits dominated predictions, while spectral indices contributed marginally despite including red-edge bands. These results challenge spectral-only approaches for individual plant phenotyping in heterogeneous canopies, demonstrating that integrating simple ground measurements with UAV spectral data is essential for reliable quinoa yield estimation.
Yield estimation based on agronomic traits in vegetables under different biochar levels
(Elsevier B.V., 2025-09-29) Ccopi Trucios, Dennis; Requena Rojas, Edilson Jimmy; Arias Arredondo, Alberto; Taipe Crispin, Maglorio; Marcelo Matero, Jhonny Demis; Pizarro Carcausto, Samuel Edwin
Biochar, a carbon-rich material produced through oxygen-limited pyrolysis of organic biomass, demonstrates exceptional potential as a soil amendment due to its porous structure and stability. This research investigated the impact of guinea pig manure biochar on three vegetable species cultivated in high Andean conditions: spinach (Spinacia oleracea L.), cabbage (Brassica oleracea var.), and chard (Beta vulgaris var.). The study implemented four biochar application rates (0, 10, 20, and 30 t/ha) and measured comprehensive agronomic parameters including leaf count, leaf length, and fresh/dry biomass of both leaves and roots. Simultaneously, UAV-captured multispectral imagery provided spectral indices that were integrated with agronomic data into machine learning models: linear regression, support vector machines (SVM), and regression trees (CART). Results demonstrated significant vegetative growth enhancement and yield increases across all crops, with the 30 t ha-1 application rate producing optimal outcomes. Predictive modeling exhibited remarkable accuracy: spinach analysis via SVM achieved R² = 0.94 and RMSE = 0.32 g; chard analysis through CART delivered R² = 0.92 and RMSE = 0.35 g; and cabbage assessment using CART yielded R² = 0.91 and RMSE = 0.38 g. This research substantiates biochar’s effectiveness as an organic amendment while establishing a reliable framework for crop yield prediction using machine learning algorithms integrated with spectral data. These findings position biochar as a valuable component in sustainable agricultural systems, particularly for vegetable production in challenging high-altitude environments.