Search

Abstract Food production is extremely dependent on the soil. Brazil plays an important role in the global food production chain. Although only 30% of the total Brazilian agricultural areas are used for crop and livestock, the full soil production potential needs to be evaluated due to the environmental and legal impossibility to expand agriculture to new areas. A novel approach to assess the productive potential of soils, called “SoilPP” and based on soil analysis (0–100 cm) - which express its pedological information - and machine learning is presented. Historical yields of sugarcane and soybeans were analyzed, allowing to identify where it is still possible to improve crop yields. The soybean yields were below the estimated SoilPP in 46% of Brazilian counties and could be improved by proper management practices. For sugarcane, 38% of areas can be improved. This technique allowed us to understand and map the food yield situation over large areas, which can support farmers, consultants, industries, policymakers, and world food security planning.

Abstract The pressure for food production has expanded agriculture frontiers worldwide, posing a threat to water resources. For instance, placing crop systems over hydromorphic soils (HS), have a direct impact on groundwater and influence the recharge of riverine ecosystems. Environmental regulations improved over the past decades, but it is difficult to detect and protect these soils. To overcome this issue, we applied a temporal remote sensing strategy to generate a synthetic soil image (SYSI) associated with random forest (RF) to map HS in an 735,953.8 km2 area in Brazil. HS presented different spectral patterns from other soils, allowing the detection by satellite sensors. Slope and SYSI contributed the most for the prediction model using RF with cross validation (accuracy of 0.92). The assessments showed that 14.5% of the study area represented HS, mostly located inside agricultural areas. Soybean and pasture areas had up to 14.9% while sugar cane had just 3%. Here we present an advanced remote sensing technique that may improve the identification of HS under agriculture and assist public policies for their conservation.

There was an error in the original publication [...]

Although many Soil Spectral Libraries (SSLs) have been created globally, these libraries still have not been operationalized for end-users. To address this limitation, this study created an online Brazilian Soil Spectral Service (BraSpecS). The system was based on the Brazilian Soil Spectral Library (BSSL) with samples collected in the Visible–Near–Short-wave infrared (vis–NIR–SWIR) and Mid-infrared (MIR) ranges. The interactive platform allows users to find spectra, act as custodians of the data, and estimate several soil properties and classification. The system was tested by 500 Brazilian and 65 international users. Users accessed the platform (besbbr.com.br), uploaded their spectra, and received soil organic carbon (SOC) and clay content prediction results via email. The BraSpecS prediction provided good results for Brazilian data, but performed variably for other countries. Prediction for countries outside of Brazil using local spectra (External Country Soil Spectral Libraries, ExCSSL) mostly showed greater performance than BraSpecS. Clay R2 ranged from 0.5 (BraSpecS) to 0.8 (ExCSSL) in vis–NIR–SWIR, but BraSpecS MIR models were more accurate in most situations. The development of external models based on the fusion of local samples with BSSL formed the Global Soil Spectral Library (GSSL). The GSSL models improved soil properties prediction for different countries. Nevertheless, the proposed system needs to be continually updated with new spectra so they can be applied broadly. Accordingly, the online system is dynamic, users can contribute their data and the models will adapt to local information. Our community-driven web platform allows users to predict soil attributes without learning soil spectral modeling, which will invite end-users to utilize this powerful technique.

ABSTRACT The elaboration of maps to characterize the spatial variability of soil attributes assists in the strategic planning and decision making of agricultural managers. Precision and accuracy of maps are related to the ideal sampling density to characterize the variability pattern. This study was conducted with the aim of identifying the sampling density to represent the variability of soil physical quality using attributes with different magnitudes of variation in an area cultivated with coffee. Three approaches were used to find the most adequate sampling density (geostatistical analysis, percentage of error associated with the sampling density, and coefficient of variation). A total of 145 soil samples were collected at a depth of 0-0.20 m at the crossing points of a regular grid with a spacing of 50 m. The percentage of clay, silt, and sand, macroporosity, microporosity, total pore volume, and soil density were determined. The data were submitted to descriptive statistical analysis. For elaborating the variability maps with up to 15% error and soil attributes with a coefficient of variation close to 50%, a sampling density of 3 points ha−1 is suggested.