A study by Dennis Ccopi and colleagues, published in Scientia Horticulturae, investigated a sustainable solution for vegetable cultivation in the challenging high Andean conditions: using biochar derived from guinea pig manure. The research not only confirmed biochar’s effectiveness but also developed a highly accurate system for predicting crop yields by integrating data from drones and machine learning.

The experiment tested four different application rates of biochar (0,10,20, and 30 t/ha) on three important leafy greens: spinach, cabbage, and chard. The biochar, created through the process of slow pyrolysisPyrolysis is a thermochemical process that converts waste biomass into bio-char, bio-oil, and pyro-gas. It offers significant advantages in waste valorization, turning low-value materials into economically valuable resources. Its versatility allows for tailored products based on operational conditions, presenting itself as a cost-effective and efficient More (thermal decomposition of organic biomass under oxygen-limited conditions) , is rich in carbon and is known for improving soil properties like aeration, water-holding capacity, and nutrient retention. Specifically, manure-derived biochar is recognized for its exceptional ability to enhance phosphorus availabilityPhosphorus is another essential nutrient for plant growth, but it can sometimes be locked up in the soil and unavailable to plants. Biochar can help release phosphorus from the soil and make it more accessible to plants, reducing the need for chemical fertilizers.   More and nutrient retention.

The results demonstrated a clear dose-dependent response. The highest application rate, 30 t/ha (T4), consistently delivered the most significant enhancements in vegetative growth and maximized dry biomass accumulation across all three crops. For all three species, T4 produced superior shoot biomass and root elongation compared to the control treatment (0 t/ha) at the 102 days after sowing (DAS) final measurement. This substantial improvement supports biochar’s potential as an organic amendment, particularly in low-input agricultural systems.

To overcome the labor-intensive and error-prone nature of traditional yield measurement, the researchers leveraged digital agriculture. They integrated manually recorded agronomic parameters (like leaf count and length) with spectral indices (like NDVI, SAVI, and NDRE) derived from UAV-captured multispectral imagery. This combined dataset was then used to train three machine learning models: Linear Regression (MLR), Support Vector Machines (SVM), and Classification and Regression Trees (CART).

The predictive modeling achieved remarkable accuracy for all crops. The successful integration of UAV remote sensing and advanced machine learning algorithms validates a powerful and reliable framework for precise crop yield estimation. This technological approach not only confirms the positive effect of the biochar treatment but also enables the spatial visualization of yield potential (Fig. 7), providing a valuable, data-driven tool for optimizing fertilization strategies in real-time. These findings position guinea pig manure biochar as a key component in creating resilient, ecologically sustainable agricultural systems, especially for vegetable production in the central Andean region.

Source: Ccopi, D., Requena-Rojas, E., Arias-Arredondo, A., Taipe, M., Marcelo, J., & Pizarro, S. (2025). Yield estimation based on agronomic traits in vegetables under different biochar levels. Scientia Horticulturae, 352, 114425 . Sources