DMDiego Fernandes Terra Machado

Diego Fernandes Terra Machado

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Diego Fernandes Terra Machado has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Accelerated pedogenesis in technogenic deposits in humid tropical area

    by Érika Cristina Nesta Silva, Francisco Sérgio Bernardes Ladeira, Diego Fernandes Terra Machado, Caio Augusto Marques dos Santos

    The growing human influence on soils can degrade or improve their properties, as seen in anthropogenic black earths, which are known for their high fertility. This study aimed to compare two soil profiles in the same watershed in a humid tropical area, specifically in Rondonópolis-MT (Brazil), to understand the physical and chemical transformations resulting from human activity by evaluating a profile with less anthropogenic influence and another developed on technogenic deposits. Thus, the approach to the formation and characterization of soils developed from technogenic deposition becomes relevant as negative human changes in soils intensify. Morphological, physical, and chemical analyses of the profiles were performed, including particle size, pH, exchangeable cations, organic carbon, and trace elements. The least impacted profile (Profile 1) was classified as Neossolo Quartzarênico Órtico típico (Arenosol), whereas the profile with the greatest anthropogenic influence (Profile 2) presented a sequence of horizons indicative of multiple deposition and pedogenesis events and was classified as a Neossolo Flúvico Psamítico gleissólico (Fluvisol). Profile 2 showed greater chemical variability and the presence of technogenic materials, such as plastics and ferrirete fragments, in addition to high levels of chromium, indicating possible contamination. Anthropic soils, although not yet officially classified in the Brazilian Soil Classification System, show pedogenetic processes acting rapidly even in recent deposits. This study highlights the importance of understanding the evolution of these soils in urban environments, both for classifying and understanding their genesis and for proper management, with the aim of mitigating the risks of environmental and population contamination.

  • Open Access

    Dinâmica Hídrica do Solo de Campo de Murundus do Parque Nacional da Serra da Canastra - MG

    by Jefferson Gomes Confesssor, Lara Luíza Silva, Diego Fernandes Terra Machado, Idelvone Mendes Ferreira, Francisco Sergio Bernardes Ladeira, Silvio Carlos Rodrigues

    O Cerrado apresenta ao longo de sua área de ocorrência diferentes fitofisionomias, destacando-se entre estas as áreas de Campos de Murundus. Devido a crescente substituição do Cerrado por atividades agropecuárias, torna-se necessário o estudo destas áreas para garantir a proteção de suas funcionalidades biogeográficas. Este estudo objetivou compreender as características físico-hídricas de uma área de Murundus inserida no Parque Nacional da Serra da Canastra, utilizando-se para tal um simulador de chuvas e um infiltrômetro de inundação, correlacionando os dados produzidos com as condições paisagísticas do ambiente. Os dados coletados revelaram que o Campo de Murundus apresenta alta capacidade de infiltração, exibindo altos valores de velocidade básica de infiltração-VIB (115,44mm/h), estando estes volumes intimamente ligados à presença atuante da pedofauna no solo, caracterizada principalmente pela ação das térmitas, as quais através de seus hábitos de vida imprimiram sobre os solos características singulares, incrementando sua porosidade através da densa rede de tuneis escavados, selecionando materiais e estratificando camadas de alta porosidade próximas a superfície. A alta incorporação de água na área estudada indica que os Campos de Murundus comportam-se como grandes áreas de captação de água das chuvas, consolidando-os como áreas estratégicas de proteção, visto sua importância ecológica e de segurança hídrica.


  • Open Access

    Soil type spatial prediction from Random Forest: different training datasets, transferability, accuracy and uncertainty assessment

    by Diego Fernandes Terra Machado, Sérgio Henrique Godinho Silva, Nilton Curi, Michele Duarte de Menezes

    Different uses of soil legacy data such as training dataset as well as the selection of soil environmental covariables could drive the accuracy of machine learning techniques. Thus, this study evaluated the ability of the Random Forest algorithm to predict soil classes from different training datasets and extrapolate such information to a similar area. The following training datasets were extracted from legacy data: a) point data composed of 53 soil samples; b) 30 m buffer around the soil samples, and soil map polygons excluding: c) 20 m; and d) 30 m from the boundaries of polygons. These four datasets were submitted to principal component analysis (PCA) to reduce multidimensionality. Each dataset derived a new one. Different combinations of predictor variables were tested. A total of 52 models were evaluated by means of error of models, prediction uncertainty and external validation for overall accuracy and Kappa index. The best result was obtained by reducing the number of predictors with the PCA along with information from the buffer around the points. Although Random Forest has been considered a robust spatial predictor model, it was clear it is sensitive to different strategies of selecting training dataset. Effort was necessary to find the best training dataset for achieving a suitable level of accuracy of spatial prediction. To identify a specific dataset seems to be better than using a great number of variables or a large volume of training data. The efforts made allowed for the accurate acquisition of a mapped area 15.5 times larger than the reference area.