Fine-scale soil mapping with Earth Observation data: a multiple geographic level comparison

Abstract

Multitemporal collections of satellite images and their products have recently been explored in digital soil mapping. This study aimed to produce a bare soil image (BSI) for the São Paulo State (Brazil) to perform a pedometric analysis for different geographical levels. First, we assessed the potential of the BSI for predicting the surface (0.00-0.20 m) and subsurface (0.80-1.00 m) clay, iron oxides (Fe 2 O 3 ), aluminum (m%) and bases saturation (V%) contents at the state level, which are important properties for soil classification. In this task, legacy soil samples, the BSI and terrain attributes were employed in machine learning. In a second moment, we evaluated the capacity of the BSI for clustering the landscape at the regional level, comparing the predicted patterns with a legacy semi-detailed soil map from a smaller reference site. In the final stage, the predicted soil maps from the state level were investigated at the farm level considering several sites distributed across the São Paulo state. Our results demonstrated that clay and Fe 2 O 3 reached the best prediction performance for both depths at the state level, reaching a RMSE of less than 10 %, RPIQ higher than 1.6 and R 2 of at least 0.41. Additionally, the predicted landscape clusters had a significant association with the main pedological classes, subsurface color, soil mineralogy and texture from the legacy semi-detailed soil map. Illustrative examples at the farm level indicated great capacity of BSI in detecting the variations of soils, which were linked to several soil properties, such as texture, iron content, drainage network, among others. Therefore, this study demonstrates that BSI is valuable information derived from optical Earth Observation data that can contribute to the future of soil survey and mapping in Brazil (PronaSolos).

An Interlaboratory Comparison of Mid-Infrared Spectra Acquisition: Instruments and Procedures Matter

“…K-means clustering was first performed on raw spectra compressed by principal component analysis by testing up to 20 clusters. The optimal number of clusters was determined using the Elbow method with the Akaike Information Criterion (Dotto et al, 2020;Safanelli et al, 2021). The proportion of samples belonging to a cluster was estimated for each instrument and the cluster with the majority was defined as representing the instrument.…”

Fine scale mapping of phosphorus stocks in brazilian soils by geotechnologies: implications for a sustainable agriculture

“…It was not possible to use the factors as climate, parental material, time and organisms, due to low spatial resolution or lack of information. To represent the relief factor, we consider environmental covariates that were previously used to predict soil attributes with satisfactory results in Safanelli et al (2021b). These terrain attributes were as follows: slope, altitude, north and east slope, horizontal curvature, vertical curvature, and a relief shape index.…”

“…Among the environmental covariates, the most commonly used ones are digital elevation models, vegetation indices, climate covariates, geological maps, and surface reflectance obtained by satellites . In addition to these covariates, recent studies propose using environmental covariates that represent bare soil reflectance (Rosin et al, 2023;Safanelli et al, 2021b). Despite the great potential of bare soil reflectance in DSM, obtaining this reflectance is a major challenge due to the vegetation present on soils most of the time.…”

Soil degradation determined by temporal satellite images and environmental variables in São Paulo State, Brazil

“…The soil attributes were spatialized using the same methodology as Safanelli et al (2021). The Random Forest algorithm was applied in this study.…”