Yield estimation based on agronomic traits in vegetables under different biochar levels

• Autores: Ccopi Trucios, Dennis, Requena Rojas, Edilson Jimmy, Arias Arredondo, Alberto, Taipe Crispin, Maglorio, Marcelo Matero, Jhonny Demis, Pizarro Carcausto, Samuel Edwin
• Formato: artículo
• Fecha de Publicación: 2025
• Institución: Instituto Nacional de Innovación Agraria
• Repositorio: INIA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.inia.gob.pe:20.500.12955/2935
• Enlace del recurso: http://hdl.handle.net/20.500.12955/2935; https://doi.org/10.1016/j.scienta.2025.114425
• Nivel de acceso: acceso abierto
• Materia: Biochar; Vegetables; Machine learning; Spectral índices; Sustainable agricultura; Yield prediction; Biocarbón; Hortalizas; Aprendizaje automático; Índices espectrales; Agricultura sostenible; Predicción de rendimiento.; https://purl.org/pe-repo/ocde/ford#4.01.01; Espinaca; Basella alba; Repollo; Cabbages; Acelga; Chard; Rendimiento de cultivos; Crop yield; Región andina; Andean region

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.