Predicting soil aggregate stability using readily available soil properties and machine learning techniques

Rivera, Javier I.; Bonilla, Carlos A.

doi:10.1016/j.catena.2019.104408

Cited by 86 publications

(34 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, it can be determined that soil properties contribute significantly to predicting MWD, specifically organic matter. This can be supported by previous studies, which showed the high correlation between OM and SAS (Abiven et al, 2009;Chaplot and Cooper, 2015) and that OM represents a significant contributor in the prediction of MWD (Bieganowski et al, 2018;Rivera and Bonilla, 2020). Also, Annabi et al (2017) reported the significant weight of clays in the pedotransfer-function of MWDfw, which confirms the current study's results on the contribution of clay in the prediction of different SAS tests.…”

Section: Determining the Relative Importance Of Variablessupporting

confidence: 91%

“…Overall, this technique achieves its effectiveness due to the availability of many important factors, such as the significant progress of machine learning algorithms and their widespread applications in several fields (Wadoux et al, 2020), including soil science, and their contribution to the prediction and mapping of different continuous soil propreties such as organic carbon (Lamichhane et al, 2019), soil plasticity (Al Masmoudi et al, 2021), soil aggregate stability (Rivera and Bonilla, 2020;Bouslihim et al, 2021) and texture (Barman and Choudhury, 2020). It is also involved in the prediction of discontinuous soil characteristics such as soil classes and soil horizons (Zeraatpisheh et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Soil Aggregate Stability Mapping Using Remote Sensing and GIS-Based Machine Learning Technique

Bouslıhım

Rochdi

Aboutayeb³

et al. 2021

Front. Earth Sci.

View full text Add to dashboard Cite

Soil aggregate stability (SAS) is a critical parameter of soil quality and its mapping can help determine erosion hotspots. Despite this importance, SAS is less documented in available literature due to limited number of analyzes besides being a time consuming. For this reason, many researchers have turned to alternative methods that often use readily available variables such as soil parameters or remote sensing indices to estimate this variable. In that framework, the aim of the present study focused on the investigation of the feasibile use of adapted Leo Breiman’s random forest algorithm (RF) to mapping different mean weight diameter (MWD) tests as an index of SAS (mechanical breakdown (MWDmb), slow wetting (MWDsw), fast wetting (MWDfw) and the mean of the three tests (MWDmean)). The model was built with 77 samples distributed in the three watersheds of the study area located at Settat Ben-Ahmed, in Morocco and with the use of several environmental variables such as soil parameters (organic matter and clay), remote sensing indices (band 2, band 3, band 4, band 5, normalized difference vegetation index (NDVI) and transformed normalized difference vegetation index (TNDVI)), topography (elevation, slope, curvature plane and the topographic wetness index (TWI)) along with additional categorical variables as geological maps, land use and soil classes. The results showed a good level of accuracy for the training phase (75% of samples) for the different tests (R2 > 0.92, RMSE and MAE < 0.15) and were satisfactory for the testing phase (25% of samples, R2 > 0.65, RMSE and MAE < 0.31). Also, organic matter, topography and geology were the most important parameters in the spatial prediction of SAS. Finally, the maps build during this study could be of great use to identify areas of less stable soils in the perspective for taking the necessary measures to improve their quality.

show abstract

Section: Determining the Relative Importance Of Variablessupporting

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Soil Aggregate Stability Mapping Using Remote Sensing and GIS-Based Machine Learning Technique

Bouslıhım

Rochdi

Aboutayeb³

et al. 2021

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

“…In the process of land reclamation, it is important to select optimal management strategies to create not only the desired vegetation cover, but also to promote the preservation of macroaggregate structure in soils to improve long-term nutrient supply and physical properties of the soil (Klimkina et al, 2018;Wick et al, 2009Wick et al, , 2016. Aggregation processes in soil are the result of interaction of a number of physical, chemical and biological factors with the complex feedback mechanisms (Oades and Waters, 1991;Rivera and Bonilla, 2020;Sodhi et al, 2009). The soil aggregation is considered as a process regulated by the biota (Duchicela et al, 2013;Rillig and Mummey, 2006;Tisdall and Oades, 1982).…”

Section: Discussionmentioning

confidence: 99%

Spatial Organization of the Micromollusc Community under Recreational Load

et al. 2021

View full text Add to dashboard Cite

The recreational load is an important factor in transforming the living conditions of living organisms in the urban environment. This article examines the role of recreation as a driver of the changing habitat of soil micromolluscs in the park environment in an urban landscape. The hypothesis that recreational exposure changes the hierarchical organization of the spatial distribution of the micromollusc community was tested. An experimental polygon was located in Novooleksandrivskiy Park (Melitopol, Ukraine) and represented 7 transects with 18 test points in each. The set of soil properties explained 24.7% of the variation in the mollusc community. The distance from trees was able to explain 6.8% of mollusc community variation. The distance from recreational pathways was able to explain 12.2% of the variation in the mollusc community. The spatial eigenfunctions were able to explain 54.2% of mollusc community variation. The spatial patterns of variation in the structure of the assemblage of molluscs were found to be due to various causes. Thus, the broad-scale component was due to the distance from trees and the distance fro m the recreational pathways and was associated with the variability of soil penetration resistance, aggregate structure, electrical conductivity, soil moisture and density. The recreational load is the cause of this pattern formation. In turn, the medium-scale component reflected the influence of soil aggregate composition on the mollusс community and components independent of soil properties. The fine-scale component reflected the variability of the mollusc community, which was independent of soil properties.

show abstract

“…Following the K sat measurements, the samples were analyzed for soil bulk density, particle density (Blake & Hartge, 1986), texture (Day, 1965), and water holding capacity as described in Burt (2004). Also, undisturbed soil samples were taken at each sampling point from the top 5 soil cm and used to estimate aggregates stability using a wet sieving apparatus (Eijkelkamp ®) following the methodology described by Kemper & Rosenau (1986) and the adaptation described in Rivera & Bonilla (2020) for the Eijkelkamp wet sieving apparatus.…”

Section: Soil Sampling and Laboratory Analysismentioning

confidence: 99%

Livestock Grazing Reduces Soil Quality and Threatens Recovery of a Degraded Andean Araucaria Forest.

Crovo

Costa-Reidel

Rodrı́guez

et al. 2021

Preprint

View full text Add to dashboard Cite

Araucaria araucana is an iconic long-lived endangered tree species exclusively distributed in Southern Chile and Argentina. Araucaria forest ecosystems provide a myriad of ecosystem benefits to local aboriginal Mapuche-Pehuenche communities. Among the main current threats for Araucaria forests are the increasing frequency and severity of wildfires and overgrazing. This study evaluates the effect of uncontrolled livestock grazing on soil quality indicators linked to critical functions relevant to forest regeneration and ecosystem service provision. We also aim to determine a set of soil quality indicators that are sensitive enough to grazing pressure, so they are useful as early indicators of degradation or the effectiveness of restoration practices. This study evaluated twenty soil quality indicators in two contiguous degraded forest areas with contrasting grazing pressure. We observed a substantial shift in forest structure, a reduction in tree coverage on the overgrazed sites. Overgrazing has produced significant deterioration of most soil physical, chemical, and biological quality indicators making soil conditions less suitable for seed germination and sapling establishment. We also observed an alteration in C, N, and P biogeochemical pools. Besides, soil physical indicators alterations suggest changes in these soils’ hydrological behavior, potentially reducing water storage, availability, and increasing runoff. We show that uncontrolled grazing in native protected areas degrades soils and forest health, restricting forest regeneration and potentially accelerating erosive processes. Our results emphasized the need for an improved conservation plan for these forests that systematically evaluates and monitors livestock grazing and all its direct and indirect effects, including soil quality.

show abstract

Predicting soil aggregate stability using readily available soil properties and machine learning techniques

Cited by 86 publications

References 59 publications

Soil Aggregate Stability Mapping Using Remote Sensing and GIS-Based Machine Learning Technique

Soil Aggregate Stability Mapping Using Remote Sensing and GIS-Based Machine Learning Technique

Spatial Organization of the Micromollusc Community under Recreational Load

Livestock Grazing Reduces Soil Quality and Threatens Recovery of a Degraded Andean Araucaria Forest.

Contact Info

Product

Resources

About