Morro de Seis Lagos, a region in the Brazilian Amazon, contains a small (less than 1%) formation of siderite carbonatites which is considered to be one of the world’s largest niobium reserves. This highly weathered geological and pedological occurrence makes the site ideal for studying the pedogenetic process of lateralization and the spatial variability of chemical elements. The aim of this study was to investigate the influences of various sampling combinations (scenarios) derived from three sampling designs on the spatial predictions associated with chemical compounds (Al₂O₃, Fe₂O₃, MnO, Nb₂O₅, TiO₂, and SiO₂), using multiple machine learning algorithms combined with remotely sensed imagery. The dataset comprised 341 samples from the Geological Survey of Brazil (CPRM). Covariates included remotely sensed data collected from Sentinel-2 MSI, Sentinel-1A, and the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), and topographic attributes were calculated from a 20 m digital elevation model derived from hydrologic data (HC-DEM). The machine learning algorithms (Generalized Linear Models with Elastic Net Regularization (GLMNET), Nearest Neighbors (KNN), Neural Network (NNET), Random Forest (RF) and Support Vector Machine (SVMRadial) were used in combination with covariates and measured elements at point locations to spatially map the concentrations of these chemical elements. The optimal covariates for modeling were selected using Recursive Feature Elimination (RFE), processing 10 runs for each chemical element. The RF, SVMRadial, and KNN models performed best, followed by the models from the Neural Network group (NNET). The sampling scenarios were not significantly different, based on root mean square error (F = 1.7; p-value = 0.15) and mean absolute error (F = 0.4; p-value = 0.79); however, significant differences were observed in the coefficient of determination (F = 41.2; p-value < 0.00) across all models. Overall, the models performed poorly for all elements, with R² ranging from 0.07 to 0.27, regardless of sampling scenario (F = 1.6; p-value = 0.08). Relatively, RF, GLMET, and KNN performed better, compared to other models. The terrain attributes were significantly more successful as to the spatial predictions of the elements contained in laterites than were the remote sensing spectral indices, likely due to the fact that the underlying spatial structures of the two formations (laterite and talus) occur at different elevations.

Concepts in pedometrics and Machine Learning techniques are increasingly used in the execution of soil surveys, employing digital soil mapping procedures. The objective of the study was to evaluate the performance of Multivariate Adaptive Regression Spline (MARS), Radial Support Vector Machine (SVMRadial) and Random Forest (RF) models, for spatial prediction of Fe2O3 , MnO, Nb and TiO2 , in the Morro dos Seis Lagos-AM, Brazil.The methodology consisted of: Thematic review; Compilation of geochemical data; Treatment and analysis of data (input data); Selection of covariates; Application of algorithms for prediction of elements; obtaining the maps, analysis of results and interpretations.The results showed greater accuracy for the prediction of iron oxide (Fe2O3), manganese (MnO) and niobium (Nb) contents, with the RF model, while for titanium (TiO2), better performance was observed with the SVMRadial model. Morphometric covariates were more relevant than covariates derived from spectral indices. Conceitos em pedometria e técnicas de Machine Learning são cada vez mais utilizados na execução de levantamentos de solos, empregando procedimentos de mapeamento digital de solos. O objetivo do estudo foi avaliar o desempenho de modelos Multivariate Adaptive Regression Spline (MARS), Radial Support Vector Machine (SVMRadial) e Random Forest (RF), para predição espacial de Fe2O3 , MnO, Nb e TiO2 , em Morro dos Seis Lagos-AM, Brasil. A metodologia consistiu em: Revisão bibliográfica; Compilação dos dados geoquímicos; Tratamento e análise dos dados (input data); Seleção de covariáveis; Aplicação de algoritmos para predição de elementos; Obtenção dos mapas, análise dos resultados e interpretações. Os resultados demonstraram maior acurácia para a predição de teores de óxido de ferro (Fe2O3), manganês (MnO) e nióbio (Nb) com o modelo RF, já para titânio (TiO2), melhor desempenho foi observado com o modelo SVMRadial. As covariáveis morfométricas foram mais relevantes do que covariáveis derivadas de índices espectrais.

The study goal was the preliminary mapping of Fe2O3, Nb and TiO2 contents to support of the classification of outcropping materials (focused on laterite types), in “Morro dos Seis Lagos”, in Brazilian Amazon. The methodological procedures were based on machine learning tools, gathering Sentinel-2 MSI and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) sensor data, numerical terrain models (all with 20 m spatial resolution), and geochemical legacy dataset from the Geological Survey of Brazil (CPRM). The input geochemical dataset was subdivided in training dataset (341 samples) and validation dataset (85 samples) to apply the Random Forest (RF), in 60 loops of iteration, and the model’s performance were evaluated through the average values of the metrics (R2, RMSE and MAE). Subsequently, the resulting average maps were combined using cluster analysis (k-means) via unsupervised classification, performed at the R environment through the Vegan package, where the number of resulting classes was optimized taking into account the “Simple Structure Index” (SSI) criterion. Different cluster grouping was tested considering classes number (6 to 10) and interactions (0 to 8000), and the resulting classes (zones) were contrasted with available geological map.  The results showed the best performance in modeling via the Random Forest (RF) model associated with Recursive Feat Elimination (RFE) for the elements Nb (R2=0.08, RMSE = 0.86, MAE = 0.66), TiO2 (R2=0.14, RMSE = 3.90, MAE= 2.56) and Fe2O3 (R2=0.23, RMSE =19.77, MAE = 14.12). Based on the results obtained via preliminary cluster analysis, the best optimization was achieved grouping in 9 classes, according to SSI criterion. The results showed agreement when compared to the classes of the geological map available for the area, but with better detailing of the laterite facies. The conclusions of the preliminary study pointed out that advances regarding the scale detail provided better understanding the behavior of the variability in laterite and talus deposits with the support of machine-learning tools and covariates from remote sensing data. However, improvement in the cluster classification can be achieve by adding other geochemical compounds and testing different predictive models.

Nas últimas décadas, as intervenções antrópicas têm alterado o ciclo dos processos naturais que ocorrem na superfície terrestre, com impactos que configuram o meio físico. O objetivo da pesquisa foi identificar e analisar geoindicadores (geoquímicos) de mudanças ambientais antropogênicas nos compartimentos ambientais (água e sedimentos) na bacia hidrográfica do rio Botas. A metodologia foi baseada na seleção de cinco pontos no perfil longitudinal do rio e análises laboratoriais (sedimento de leito e planície e água) para determinação dos elementos-traço: Cr, Cu, Ni, Cd, Pb e Zn. Os resultados indicaram a poluição da água e sedimentos pelos elementos Cr, Cu, Pb e Zn, com base nos valores de referência da National Oceanic and Atmospheric Administration (NOAA) (BUCHMAN, 2008) e CONAMA (2005). Observou-se uma variabilidade de 0,1 a 1,5 (Cr), 0 a 0,2 (Pb) e 0 a 0,2 (Zn) para água (mg/l); em sedimentos de leito (mg/kg) de 5,8 a 42,2 (Cr), 2,7 a 12,4 (Pb), 1,3 a 15 (Cu) e 22,9 a 69 (Zn); e, para sedimentos de planície (mg/kg) obteve-se a variação de 5,2 a 24,6 (Cr), 2 a 36,5 (Pb), 5,7 a 17,3 (Cu) e 20 a 242,2 (Zn), com indicação de aumento gradativo em direção à jusante do rio. Considera-se que os pontos poluídos têm interferência de esgoto industrial e doméstico in natura, associados aos diversos usos e cobertura da terra, que corroboram com o aumento de elementos-traço. Tais resultados indicam a degradação antropogênica em sistema fluvial associado ao longo histórico de degradação ambiental.

Introducion: Changes in land cover caused by open-pit mining have resulted in significant transformations in landscape structure and environmental balance. In the semiarid region of Paraíba, the extraction of ornamental rocks is a strategic economic activity, but it also generates direct impacts on local ecosystems, such as vegetation loss. Objective: The general objective of the study was to analyze the dynamics of land use and occupation in ornamental rock mining areas in the Sertão region of Paraíba, using NDVI in a time-space approach. Method: The Normalized Difference Vegetation Index (NDVI) was applied as a remote sensing tool to assess environmental changes that occurred between 2017 and 2024 in municipalities in the Sertão region of Paraíba, where mining operations are active. Data were obtained from a public database for the months of November 2017 and November 2024. For each year analyzed, two scenes were required to cover the entire study area. Results and Discussion: The results revealed a dual pattern: while part of the area showed a sharp decrease in NDVI, indicating environmental degradation associated with anthropogenic pressure, other sectors showed an increase in NDVI values, evidencing natural regeneration processes or sustainable management actions. NDVI was found to be an efficient and low-cost indicator for monitoring environmental changes over time, supporting impact assessments, public land use planning policies, and practices for restoring degraded areas. Research Implications: The application of geotechnologies proves essential to reconcile the development of ornamental rock mining with the conservation of natural resources in the Paraíba semiarid region. Originality/Value: The article addresses the use of geotechnologies for the control and monitoring of mining areas, specifically ornamental rock mining in the state of Paraíba, a topic that has been little explored and has scarcely been studied.