Abstract

Geophysical sensors combined with machine learning algorithms have been used to understand the pedosphere system, landscape processes and to model soil attributes. In this research, we used parent material, terrain attributes and data from geophysical sensors in different combinations, to test and compare different and novel machine learning algorithms to model soil attributes. Also, we analyzed the importance of pedoenvironmental variables in predictive models. For that, we collected soil physico-chemical and geophysical data (gamma-ray emission from uranium, thorium and potassium, magnetic susceptibility and apparent electric conductivity) by three sensors, gamma-ray spectrometer – RS 230, susceptibilimeter KT10 – Terraplus and Conductivimeter – EM38 Geonics) at 75 points and, we performed soil analysis afterwards. The results showed varying models with the best performance (R2 > 0.2) for clay, sand, Fe2O3, TiO2, SiO2 and Cation Exchange Capacity prediction. Modeling with selection of covariates at three phases (variance close to zero, removal by correction and removal by importance), demonstrated to be adequate to increase the parsimony. The prediction of soil attributes by machine learning algorithms demonstrated adequate values for field collected data, without any sample preparation, for most of the tested predictors (R2 ranging from 0.20 to 0.50). Also, the use of four regression algorithms proved important, since at least one of the predictors used one of the tested algorithms. The performances of the best algorithms for each predictor were higher than the use of a mean value for the entire area comparing the values of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The best combination of sensors that reached the best model performance to predict soil attributes were gamma-ray spectrometer and susceptibilimeter. The most important variables were parent material, digital elevation model, standardized height and magnetic susceptibility for most predictions. We concluded that soil attributes can be efficiently modelled by geophysical data using machine learning techniques and geophysical sensors combinations. The technique can bring light for future soil mapping with gain of time and environment friendly.

Highlights

  • The pedosphere is composed by soils and their connections with hydrosphere, lithosphere, atmosphere and biosphere (Targulian et al, 2019)

  • The worst performance in modeling soil attributes occurred excluding the use of geophysical sensors, where only parent material and terrain attributes were used (Table 2)

  • The results show that for 5 soil properties, the best results did not occur with a greater number of sensors, showing that increasing number of covariables can lead to lower performance (Fig. 9)

Read more

Summary

Introduction

The pedosphere is composed by soils and their connections with hydrosphere, lithosphere, atmosphere and biosphere (Targulian et al, 2019). The main soil processes are weathering and pedogenesis (Breemen and Buurman, 2003; Schaetzl and Anderson, 2005), while the soil-forming factors are parent material, relief, climate, organisms and time (Jenny, 1994) Their interactions during soil genesis results in different soil attributes such as texture, mineralogy, color, structure, base saturation, clay activity and others. New geotechnologies have emerged in the last decades, allowing the acquisition of data at shorter times, with non-invasive and accurate methods, such as reflectance spectroscopy, satellite imagery and geophysical techniques (Mello et al, 2020; Demattê et al, 2017, 2007; Fioriob, 2013; Fongaro et al, 2018; Mello et al, 2021; Terra et al, 2018a, 2018b) Among these 55 technologies, geophysical sensors have been recently used in pedology to understand pedogenesis and the relationship between these processes and soil attributes (Son et al, 2010; Schuler et al, 2011; Beamish, 2013; McFadden and Scott, 2013; Sarmast et al, 2017; Reinhardt and Herrmann, 2019). Gamma-ray spectrometry can provide important information for comprehension of soil processes and attributes (Reinhardt and Herrmann, 2019), soil texture (Taylor et al, 2002a), mineralogy (Wilford and Minty 2006; 65 Barbuena et al 2013), pH (Wong and Harper, 1999) and organic carbon (Priori et al, 2016) and others

Methods
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call