Satellite remote sensing data expedite crop yield estimation, offering valuable insights for farmers’ decision making. Recent forecasting methods, particularly those utilizing machine learning algorithms like Random Forest and Artificial Neural Networks, show promise. However, challenges such as validation performances, large volume of data, and the inherent complexity and inexplicability of these models hinder their widespread adoption. This paper presents a simpler approach, employing linear regression models fitted from vegetation indices (VIs) extracted from MODIS sensor data on the Terra and Aqua satellites. The aim is to forecast cotton yields in key areas of the Brazilian Cerrado. Using data from 281 commercial production plots, models were trained (167 plots) and tested (114 plots), relating seed cotton yield to nine commonly used VIs averaged over 15-day intervals. Among the evaluated VIs, Enhanced Vegetation Index (EVI) and Triangular Vegetation Index (TVI) exhibited the lowest root mean square errors (RMSE) and the highest determination coefficients (R²). Optimal periods for in-season yield prediction fell between 90 and 105 to 135 and 150 days after sowing (DAS), corresponding to key phenological phases such as boll development, open boll, and fiber maturation, with the lowest RMSE of about 750 kg ha⁻¹ and R² of 0.70. The best forecasts for early crop stages were provided by models at the peaks (maximum value of the VI time series) for EVI and TVI, which occurred around 80–90 DAS. The proposed approach makes the yield predictability more inferable along the crop time series just by providing sowing dates, contour maps, and their respective VIs.

Soil bulk density (ρ_b) is vital for assessing soil organic carbon (SOC) and nutrient stocks, as well as for modeling soil processes. Although ρ_b can be measured using traditional methods, these are labor-intensive and time-consuming. Consequently, there is a growing interest in developing pedotransfer functions (PTFs) to predict ρ_b based on more easily measured soil properties. The vast Brazilian territory, with different climates and biomes, presents a challenge for development of national-scale PTFs, particularly for ρ_b. In this study, a comprehensive dataset was compiled from various sources to develop ρ_b PTFs across Brazil. The dataset includes particle size distribution (PSD), SOC, ρ_b, sampling depth, soil order, land use, and geographic coordinates, allowing for the incorporation of additional numerical and categorical variables. Rigorous data preprocessing ensured quality and reliability. PTFs were developed using multiple linear regression (MLR) and Random Forest (RF) models. Model accuracy was evaluated using mean absolute error, bias, root mean square error (RMSE), and coefficient of determination. Both MLR and RF models accurately predicted ρ_b, with log-transformed PSD and SOC emerging as key predictors. The RF model slightly outperformed the MLR model (RMSE = 0.12 vs. 0.13 g cm⁻³) on the test dataset, underscoring the importance of environmental and categorical variables in predicting ρ_b. The developed PTFs, along with other PTFs for Brazil, were applied to estimate SOC stocks across different biomes and land uses. Best estimations were obtained with the RF model, with an R² of 0.97, emphasizing the value of categorical variables in improving SOC stock estimations.

Most studies about soil organic carbon stock changes in the Cerrado (Brazilian Savanna) biome are either related to field data collected in clayey Ferralsols or different land uses, as if they were in equilibrium. This study aimed to evaluate the effect of tillage systems and crop sequences on the soil organic carbon stock and crop yield, in a sandy Ferralsol from Bahia, Brazil. The experimental design was randomized blocks, with four replicates. Soil samples were collected after fve years of cotton, soybean and maize monocropping under heavy disk harrow and leveling harrow (conventional tillage), and of crop rotation of cotton, soybean and maize with green manure or cover crop (no-tillage). Additional samples were collected from a non-cultivated site (Neotropical Savanna, Cerrado sensu stricto). Soil conservation practices such as no-tillage and crop rotation with cover crop and green manure favored the soil organic carbon stock at the 0-40 cm layer, with the highest values reaching 36.03 Mg ha−1. The accrued soil carbon stock under conventional tillage and monoculture of cotton, maize and soybean was lower than under no-tillage, which ranged from 30.9 to 54.9 %, with the soil organic carbon stock increasing at the annual rate of 2.36 Mg ha−1 during fve years. The no-tillage, with the soybean-maize-cotton rotation, in combination with cover crop and green manure, increased the cotton and soybean yields, with a simultaneous organic carbon accumulation in the sandy soil.

Este trabalho objetivou avaliar parâmetros físicos e hídricos de um Latossolo de textura franco-arenosa, cultivado com milho sob plantio convencional (PC) e sistema plantio direto (SPD) no Cerrado do Oeste da Bahia, Brasil. O estudo foi conduzido em área experimental situada no município de Luís Eduardo Magalhães, Bahia (BA). Os tratamentos foram, T1: Milho (M) sob Plantio Convencional (PC); T2: M sob Sistema Plantio Direto (SPD) em consórcio com Braquiária (B); T3: M sob SPD em consórcio com B em sucessão à Soja (S), Milheto (Mt) e Algodão (A); e T4: M sob SPD em consórcio com Crotalária (C), utilizando como referência uma área de Cerrado Nativo (CN), de fitofisionomia de Campo Sujo. As amostras foram coletadas nas camadas 0,00 a 0,05 m; 0,05 a 0,10 m e 0,10 a 0,20 m e foram utilizadas para determinar a porosidade total (Pt); a macroporosidade (Ma); a microporosidade (Mi); a densidade do solo (Ds) e a disponibilidade de água (AD) por meio da curva de retenção de água no solo (CRA); as frações granulométricas e os teores de carbono orgânico total (COT). A diferença dos valores dos atributos medidos nos tratamentos foi, primeiramente, utilizada para verificar o incremento (+) ou a redução (-) do atributo em relação ao CN (Δref, %). Em seguida, os tratamentos foram submetidos à análise de variância e as médias comparadas pelo teste de Duncan ao nível de 5% significância, bem como à análise de correlação de Pearson para avaliação das relações entre os atributos. O SPD promoveu a qualidade do solo, pelo aumento do carbono orgânico total, do grau de floculação, do conteúdo de água disponível e da microporosidade, além de ter reduzido o teor de argila dispersa em água. Contudo, apresentou maior densidade e resistência a penetração, menor macroporosidade e porosidade total, sem prejuízos para o crescimento e o desenvolvimento das plantas. Assim sendo, conclui-se que o SPD é capaz de promover a estruturação, a qualidade e as funções do solo enquanto recurso natural essencial à vida.

Assessing soil quality under different cover crops or different management systems is essential to its conservation. This study aimed to evaluate an Oxisol cultivated with corn and cotton, after different crop successions and under no-tillage system (NTS) and conventional tillage system (CT), through the soil quality index (SQI), using an area of native Cerrado as reference. The study was carried out in the municipality of Luís Eduardo Magalhães, Western Bahia, Brazil. Soil samples with the preserved and non-preserved structure were collected in the layers of 0-0.05 m, 0.05-0.10 m, and 0.10-0.20 m to determine the macroporosity, the soil bulk density, the available water, the levels of total organic carbon, the clay dispersed in water, and the degree of flocculation. The averages of the attributes measured in the treatments and the soil quality index, which was elaborated by the method of deviations of the values of the attributes measured in the treatments concerning the reference area, followed by normalization, were compared by the Duncan test (p ≤ 0.05). The soil under CT, in all treatments, had its quality reduced when compared to the NTS. Also, the SQI used was sensitive to detect the changes caused by the management systems and assign consistent scores to the evaluated soil quality.