With the growing availability of environmental covariates, feature selection (FS) is becoming an essential task for applying machine learning (ML) in digital soil mapping (DSM). In this study, the effectiveness of six types of FS methods from four categories (filter, wrapper, embedded, and hybrid) were compared. These FS algorithms chose relevant covariates from an exhaustive…
In the history of alluvium and colluvium, the definitions have been shifted and rearranged several times, and this evolution is ongoing. Although field books, textbooks, and dictionaries provide standardized references, the authors of those definitions must wrestle with a wide variety of previous definitions, especially for colluvium. Contributing to this challenge is the need for…
This study examines three soil classification systems – Buganda, World Reference Base, and US Soil Taxonomy – in order to evaluate their relative strengths and feasibility for making linkages between them. Nine field sites and 16 pedons were considered across the soil landscapes of the Buganda catena. Each identified field pedon diagnostic horizons and characteristics…
Digital soil mapping (DSM) increasingly makes use of machine learning algorithms to identify relationships between soil properties and multiple covariates that can be detected across landscapes. Selecting the appropriate algorithm for model building is critical for optimizing results in the context of the available data. Over the past decade, many studies have tested different machine…
The geography of soil is more important today than ever before. Models of environmental systems and myriad direct field applications depend on accurate information about soil properties and their spatial distribution. Many of these applications play a critical role in managing and preparing for issues of food security, water supply, and climate change. The capability…
Hillslope elements have considerable potential in predicting soil properties and types in the landscape, making them likely to be a useful basis for detailed soil mapping. The goal of this research was to apply a previously developed digital hillslope position (DHP) model, calibrate it as needed to a Brazilian landscape, and test its utility as…
This landscape was originally interpreted as loess mixed with underlying sands. This paper re-evaluates this landscape through a spatial analysis of data from auger samples and soil pits. To better estimate the loamy sediment’s initial textures, we utilized “filtered” laser diffraction data, which remove much of the coarser sand data. Our new model for the…
Despite the soil science discipline in the USA hitting hard times in the 1980s and 1990s, there were still many positive advances within soil science in the USA during these two decades. There was an increased use of geophysical instrumentation, remote sensing, geographic information systems (GIS), and global positioning systems (GPS), and research began in…
This study examines the spatial patterns and accuracies of predictions made by different spatial modelling methods on sample sets taken at two different scales. These spatial models are then tested on independent validation sets taken at three different scales. Each spatial modelling method produced similar, but unique, maps of soil organic carbon content (SOC%). Kriging…
Soil mapping, classification, and pedologic modelling have been important drivers in the advancement of our understanding of soil. Advancement in one of these highly interrelated areas tend to lead to corresponding advances in the others. Traditionally, soil maps have been desirable for purposes of land valuation, agronomic planning, and even in military operations. The expansion…
