This study aims to assess the carbon stock in a pasture area and fragment of forest in natural regeneration, given the importance of agroforestry systems in mitigating gas emissions which contribute to the greenhouse effect, as well as promoting the maintenance of agricultural productivity. Our other goal was to predict the carbon stock, according to different land use systems, from physical and chemical soil variables using the Random Forest algorithm. We carried out our study at an Entisols Quartzipsamments area with a completely randomized experimental design: four treatments and six replites. The treatments consisted of the following: (i) an agroforestry system developed for livestock, (ii) an agroforestry system developed for fruit culture, (iii) a conventional pasture, and (iv) a forest fragment. Deformed and undeformed soil samples were collected in order to analyze their physical and chemical properties across two consecutive agricultural years. The response variable, carbon stock, was subjected to a boxplot analysis and all the databases were used for a predictive modeling which in turn used the Random Forest algorithm. Results led to the conclusion that the agroforestry systems developed both for fruit culture and livestock, are more efficient at stocking carbon in the soil than the pasture area and forest fragment undergoing natural regeneration. Nitrogen stock and land use systems are the most important variables to estimate carbon stock from the physical and chemical variables of soil using the Random Forest algorithm. The predictive models generated from the physical and chemical variables of soil, as well as the Random Forest algorithm, presented a high potential for predicting soil carbon stock and are sensitive to different land use systems.

Gratidão a Deus pela vida e pelas oportunidades que ela traz para o meu desenvolvimento. Ao Mestre Gabriel, Estrela que me guia.Ao Raul Monteiro Júnior pelo convite para fazer parte deste projeto, por alimentar o sonho de um mundo melhor e por proporcionar a parceria com a Fazenda da Toca.Ao professor Zigomar Menezes de Souza pelo incentivo e confiança para a realização deste mestrado. Pela orientação, amizade e especialmente pela compreensão e acolhimento durante a minha gestação e licença maternidade.À Fazenda da Toca, por disponibilizar as áreas para o experimento e pelo apoio para a realização das coletas em campo. Ao Ernst Götsch, pelas incríveis aulas em campo. Ao pesquisador Everton Lemos, por todas as horas despendidas nessa parceria.Ao CNPq, pela bolsa concedida.

The need to put into practice sustainable agricultural production systems has been supported by agroecology science that seeks to optimize land use to food production with the lowest impact on soil. This study evaluated soil quality, based on physical and chemical attributes, in agroforestry (AGF) and silvopastoral (SILVP) systems developed for large-scale food production. The study was carried out in the municipality of Itirapina, state of São Paulo, in two areas with AGF and SILVP system, compared to an area with a forest fragment and another with pasture in a Quartzipisamment Sand Neosol. The soil collections were carried out in the layers of 0.00–0.05, 0.05–0.10, 0.10–0.20, and 0.20–0.40 m, where physical soil attributes were evaluated (total porosity, microporosity, and microporosity, density, mean diameter of aggregates) as well as chemical attributes (macro- and micronutrients), in addition to carbon and nitrogen storage. To interpret the data, Tukey’s test was applied to compare means, and principal component analysis was used to better characterize the study environments. The results showed that agroforestry and silvopastoral systems developed for large-scale production are efficient in improving chemical and physical attributes that reflect on soil quality, especially in the superficial layers of the soil, overcoming pasture and the natural regeneration process. Carbon and nitrogen storage were the main variables that differentiated the production systems, highlighting the importance of the AGF and SILVP systems as more sustainable agricultural intensification strategies, even in soils of low agricultural suitability.