https://www.alice.cnptia.embrapa.br/alice/handle/item/36 Embrapa Solos (CNPS) Thu, 04 Jun 2026 22:36:27 GMT 2026-06-04T22:36:27Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186938 Título: Spectrally-based soil carbon models to support the National Forest Inventory of Rio de Janeiro, Brazil. Autoria: VASQUES, G. M.; LUZ, L. B.; BALIEIRO, F. de C.; MAGALHÃES, M. A. F.; SILVEIRA FILHO, T. B.; ANDRADE, M. T. de Conteúdo: Methods for assessing soil carbon must be fast and accurate to support soil health and security evaluation, measurement, reporting and verification of carbon stocks. Visible-near infrared (Vis-NIR) spectroscopy minimizes the costs and time required for assessing soil carbon. Soil samples were obtained at 189 sites from the National Forest Inventory (NFI) of Rio de Janeiro state (∼​​43,782 km²), Brazil, between 2013 and 2016, at 0–20 and 30–50 cm, with a total of 373 recovered samples. The objective was to compare different preprocessing transformations of spectral curves, and calibration methods to predict soil carbon contents from soil Vis-NIR spectral curves in NFI samples from Rio de Janeiro state. Soil carbon contents were measured by dry combustion in a CHNS elemental analyzer, and soil spectral curves were obtained in the laboratory. Cubist combined with log(1/reflectance) preprocessing emerged as the optimal combination to predict soil carbon content (root mean square error of cross-validation of 5.1 g kg-1), whereas elastic net obtained good soil carbon content predictions consistently in both cross-validation and external validation. Partial least squares regression, random forest, support vector machines, and model ensemble produced poorer results. The results agree with previous studies comparing calibration methods for soil carbon content prediction, and stress the importance of preprocessing soil spectral curves, as well as testing different methods to produce robust results. Soil Vis-NIR spectroscopy can be used to assess soil carbon contents in Rio de Janeiro, supporting expedited and accurate soil carbon stock, and stock change assessments in future phases of the NFI. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186938 2026-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186904 Título: A novel methodological framework for predicting and mapping agriculture-related soil attributes using Euclidean distance, regular grids, and machine learning algorithms. Autoria: VELOSO, G. V.; MELLO, D. C. de; FERNANDES-FILHO, E. I.; SOUZA, C. M. P. de; SILVA, L. A. P. da; ESPIRITO SANTO, M. M.; VASQUES, G. M.; COELHO, M. R.; DEMATTÊ, J. A. M. Conteúdo: Recent advances in statistical and machine learning (ML) methods have improved the prediction of soil attributes at fine spatial scales, yet the comparative performance and reliability of these techniques remain unclear. This study compared Ordinary Kriging (OK), Inverse Distance Weighting (IDW), and ML algorithms in predicting and spatializing soil attributes, while also evaluating prediction uncertainty and com- putational processing time. Conducted in Minas Gerais State (Brazil), the analysis used Euclidean distance based predictors derived from X-Y coordinates and regular grids with 5, 7, and 10 divisions. Soil attribute maps (CEC, phosphorus, sand, and clay) were generated using OK, IDW, Random Forest (RF), Cubist, Support Vector Machine (SVM), and Earth. Model performance was assessed using R2, RMSE, MAE, and the coefficient of variation. IDW and OK showed the lowest predictive accuracy (R2 = 0.52–0.58), whereas ML methods, especially RF and SVM achieved superior performance (R2 = 0.62–0.70). Among ML algorithms, Earth performed worst, while RF produced the highest accuracy for all attributes except sand, for which SVM performed best. Processing time was shortest for IDW, followed by OK; among ML models, Earth was fastest, followed by RF, SVM, and Cubist. Larger regular grids improved ML prediction and spatialization but increased computational cost. ML methods thus outperform traditional geostatistical interpolators, benefiting from the use of numerous covariates and flexible algorithmic structures, although requiring greater computational time. These findings demonstrate the robustness and practical potential of ML approaches for soil attribute mapping. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186904 2026-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186745 Título: Soybean performance as affected by lime and gypsum incorporation through tillage versus surface application in pasture-to-cropland conversion areas in Southeast Brazil. Autoria: RODRIGUES, P. P.; BATISTA, J. N.; GUARESCHI, R. F.; JANTALIA, C. P.; ALVES, B. J. R.; URQUIAGA, S.; LIMA, E. S. A.; SOUZA FILHO, B. F. de; ZILLI, J. E. Conteúdo: Lime and gypsum are widely used to correct soil acidity and improve grain yields in Brazilian agricultural systems. However, limited information is available on their effectiveness and application practices in degraded sandy soils typical of older agricultural frontiers, such as those in Rio de Janeiro State. This study evaluated the effects of surface application versus the incorporation of lime and gypsum into the soil through tillage operations on soil chemical properties, nodulation, and grain yield of soybean cultivars grown in low-fertility Fluvisols. The experiment was conducted during the 2021/2022 growing season in Campos dos Goytacazes, Rio de Janeiro, using a strip-plot design with four soybean cultivars and two soil amendment placement strategies: surface application without tillage and incorporation through tillage. Soil chemical attributes, nodulation, nutrient uptake, and yield components were assessed. Incorporated application significantly increased soil pH, reduced Al3+ toxicity, and enhanced Ca2+, Mg2+, P, and K+ availability compared to surface application. Nodulation responses varied among cultivars, with incorporated treatments promoting up to 40% greater nodule biomass. Although primary root length was not affected, incorporation stimulated secondary root development and nutrient uptake, leading to approximately 50% higher pod number and grain yield. Overall, incorporating lime and gypsum through soil tillage was more effective than surface application in improving soil fertility, enhancing nodulation, and increasing soybean productivity under the conditions evaluated in this study. These findings suggest that lime and gypsum incorporation can represent an important management strategy for improving soybean production in degraded sandy soils. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186745 2026-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186744 Título: Response of corn to potassic organomineral fertilizer in an Oxisol. Autoria: OLIVEIRA, C. de F.; TEZOTTO, T.; BENITES, V. de M.; ALLEONI, L. R. F. Conteúdo: Purpose: Corn (Zea mays L.) requires an adequate supply of potassium (K) to achieve high productivity. Potassium chloride (KCl) is the main fertilizer source used, but its excessive application can increase soil salinity and production costs. Organomineral fertilizers (OMF) have emerged as an alternative, as they improve soil attributes and supply nutrients. In this study, the effects of an OMF fertilizer were compared with KCl, based on the external critical level (CL) of K for corn in a sandy loam Typic Hapludox. Method: The experiment was conducted in a greenhouse using a randomized complete block design with five treatments and four replications. The applied K rates ranged from 40% below to 20% above the CL. Biometric and plant tissue data were evaluated. Results: OMF showed equivalent or superior efficacy compared to KCl, especially at rates suitable for the crop. The use of OMF enhanced calcium and magnesium uptake and exhibited the highest agronomic efficiency of K use across all evaluated rates, with an average value 24% higher than that of KCl. Both fertilizers had similar K uptake efficiency, while apparent recovery efficiency ranged from 55 to 70% for OMF and 77 to 94% for KCl. Conclusion: Both fertilizers exhibited similar efficacy, and the choice should consider availability and cost. In addition to being a viable alternative, OMF offers environmental benefits and contributes to organic waste management, promoting more sustainable agricultural practices and aligning with the United Nations Sustainable Development Objectives. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1186744 2026-01-01T00:00:00Z