scholarly journals Conversion between Soil Texture Classification Systems using the Random Forest Algorithm

2015 ◽  
Vol 8 ◽  
pp. ASWR.S31924 ◽  
Author(s):  
Milan Cisty ◽  
Lubomir Celar ◽  
Peter Minaric
Keyword(s):  
Random Forest ◽  
Soil Texture ◽  
Classification System ◽  
Texture Classification ◽  
Hybrid Approach ◽  
Soil Classification ◽  
Classification Systems ◽  
Statistical Indicators ◽  
Better Than ◽  
Different Soils

This study focuses on the reclassification of a soil texture system following a hybrid approach in which the conventional particle-size distribution (PSD) models are coupled with a random forest (RF) algorithm for achieving more generally applicable and precise outputs. The existing parametric PSD models that could be used for this purpose have various limitations; different models frequently show unequal degrees of precision in different soils or under different environments. The authors present in this article a novel ensemble modeling approach in which the existing PSD models are used as ensemble members. An improvement in precision was proved by better statistical indicators for the results obtained, and the article documents that the ensemble model worked better than any of its constituents (different existing parametric PSD models). This study is verified by using a soil dataset from Slovakia, which was originally labeled by a national texture classification system, which was then transformed to the USDA soil classification system. However, the methodology proposed could be used more generally, and the information provided is also applicable when dealing with the soil texture classification systems used in other countries.

Computerized Cone Penetration Test for Soil Classification

2008 ◽  
Vol 2053 (1) ◽  
pp. 47-64 ◽  
Author(s):  
Murad Y. Abu-Farsakh ◽  
Zhongjie Zhang ◽  
Mehmet Tumay ◽  
Mark Morvant
Keyword(s):  
Classification System ◽  
Soil Classification ◽  
Cone Penetration Test ◽  
Classification Systems ◽  
Fuzzy Classification ◽  
Classification Methods ◽  
Penetration Test ◽  
Cone Penetration ◽  
Cone Tip Resistance ◽  
Tip Resistance

Computerized MS-Windows Visual Basic software of a cone penetration test (CPT) for soil classification was developed as part of an extensive effort to facilitate the implementation of CPT technology in many geotechnical engineering applications. Five CPT soil engineering classification systems were implemented as a handy, user-friendly, software tool for geotechnical engineers. In the probabilistic region estimation and fuzzy classification methods, a conformal transformation is first applied to determine the profile of soil classification index (U) with depth from cone tip resistance (qc) and friction ratio (Rf). A statistical correlation was established in the probabilistic region estimation method between the U index and the compositional soil type given by the Unified Soil Classification System. Conversely, the CPT fuzzy classification emphasizes the certainty of soil behavior. The Schmertmann and Douglas and Olsen methods provide soil classification charts based on cone tip resistance and friction ratio. However, Robertson et al. proposed a three-dimensional classification system that is presented in two charts: one chart uses corrected tip resistance (qt) and friction ratio (Rf); the other chart uses qt and pore pressure parameter (Bq) as input data. Five sites in Louisiana were selected for this study. For each site, CPT tests and the corresponding soil boring results were correlated. The soil classification results obtained using the five different CPT soil classification methods were compared.

A multivariate method for matching soil classification systems, with an Australian example

Soil Research ◽  
2020 ◽  
Vol 58 (6) ◽  
pp. 519
Author(s):  
H. F. Teng ◽  
R. A. Viscarra Rossel ◽  
R. Webster
Keyword(s):  
Vector Space ◽  
Classification System ◽  
Near Infrared ◽  
Soil Classification ◽  
Classification Systems ◽  
Near Infrared Reflectance ◽  
Local Systems ◽  
Soil Units ◽  
International Systems ◽  
Australian Soil

Differences between local systems of soil classification hinder the communication between pedologists from different countries. The FAO–UNESCO Soil Map of the World, as a fruit of world-wide collaboration between innumerable soil scientists, is recognised internationally. Ideally, pedologists should be able to match whole classes in their local systems to those in an international soil classification system. The Australian Soil Classification (ASC) system, created specifically for Australian soil, is widely used in Australia, and Australian pedologists wish to translate the orders they recognise into the FAO soil units when writing for readers elsewhere. We explored the feasibility of matching soil orders in the ASC to units in the FAO legend using a multivariate analysis. Twenty soil properties, variates, of 4927 profiles were estimated from their visible–near infrared reflectance (vis–NIR) spectra. We arranged the profiles in a Euclidean 20-dimensional orthogonal vector space defined by standardised variates. Class centroids were computed in that space, and the Euclidean distances between the centroids of the ASC orders and units in the FAO scheme were also computed. The shortest distance between a centroid of any ASC order and one of units in the FAO classification was treated as a best match. With only one exception the best matches were those that an experienced pedologist might expect. Second and third nearest neighbours in the vector space provided additional insight. We conclude that vis–NIR spectra represent sufficiently well the essential characters of the soil and so spectra could form the basis for the development of a universal soil classification system. In our case, we could assign with confidence the orders of the ASC to the units of the FAO scheme. A similar approach could be applied to link other national classification systems to one or other international systems of soil classification.

scholarly journals Laser Diffraction as An Innovative Alternative to Standard Pipette Method for Determination of Soil Texture Classes in Central Europe

Water ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 1232
Author(s):  
Dušan Igaz ◽  
Elena Aydin ◽  
Miroslava Šinkovičová ◽  
Vladimír Šimanský ◽  
Andrej Tall ◽  
...  
Keyword(s):  
Particle Size ◽  
Particle Size Distribution ◽  
Size Distribution ◽  
Soil Texture ◽  
Polynomial Regression ◽  
Texture Classification ◽  
Size Fraction ◽  
Laser Diffraction ◽  
Classification Systems ◽  
Particle Size Fraction

The paper presents the comparison of soil particle size distribution determined by standard pipette method and laser diffraction. Based on the obtained results (542 soil samples from 271 sites located in the Nitra, Váh and Hron River basins), regression models were calculated to convert the results of the particle size distribution by laser diffraction to pipette method. Considering one of the most common soil texture classification systems used in Slovakia (according to Novák), the emphasis was placed on the determination accuracy of particle size fraction <0.01 mm. Analysette22 MicroTec plus and Mastersizer2000 devices were used for laser diffraction. Polynomial regression model resulted in the best approximation of measurements by laser diffraction to values obtained by pipette method. In the case of particle size fraction <0.01 mm, the differences between the measured values by pipette method and both laser analyzers ranged in average from 3% up to 9% and from 2% up to 11% in the case of Analysette22 and Mastersizer2000, respectively. After correction, the differences decreased to average 3.28% (Analysette22) and 2.24% (Mastersizer2000) in comparison with pipette method. After recalculation of the data, laser diffraction can be used alongside the sedimentation methods.

Origin of the soil texture classification system used in Japan

2015 ◽  
Vol 61 (4) ◽  
pp. 688-697 ◽  
Author(s):  
Hirotatsu Murano ◽  
Yusuke Takata ◽  
Toshiyuki Isoi
Keyword(s):  
Soil Texture ◽  
Classification System ◽  
Texture Classification

scholarly journals Analysis of Agronomic Categories in Different Soil Texture Classification Systems

2017 ◽  
Vol 49 (1) ◽  
pp. 61 ◽  
Author(s):  
Jan Jadczyszyn ◽  
Jacek Niedźwiecki ◽  
Guillaume Debaene
Keyword(s):  
Soil Texture ◽  
Texture Classification ◽  
Classification Systems

scholarly journals Guideline for the description of soils in the Berlin metropolitan area: an extension for surveying and mapping anthropogenic and natural soils in urban environments within the German soil classification system

2020 ◽  
Author(s):  
Mohsen Makki ◽  
Kolja Thestorf ◽  
Sabine Hilbert ◽  
Michael Thelemann ◽  
Lutz Makowsky
Keyword(s):  
Metropolitan Area ◽  
Classification System ◽  
Urban Areas ◽  
Urban Soil ◽  
Urban Soils ◽  
Soil Classification ◽  
Urban Environments ◽  
Soil Mapping ◽  
Classification Systems ◽  
Anthropogenic Soils

Abstract Purpose In urban areas, humans shape the surface, (re-)deposit natural or technogenic material, and thus become the dominant soil formation factor. The 2015 edition of the World Reference Base for Soil Resources (WRB) describes anthropogenic urban soils as Anthrosols or Technosols, but the methodological approaches and classification criteria of national soil classification systems are rather inconsistent. Stringent criteria for describing and mapping anthropogenic soils in urban areas and their application are still lacking, although more than half (53%) of the urban soils in Berlin are built-up by or contain anthropogenic material. Materials and methods On behalf of the Berlin Senate Department for the Environment, Transport and Climate Protection and in close cooperation with the German Working Group for Urban Soils, a comprehensive guideline for soil description in the Berlin metropolitan area (BMA), with special regard to anthropogenic/technogenic parent material and anthropogenic soils, has been developed. Our approach includes all previous standard works for soil description and mapping and is based on studies that have been conducted in the BMA over the last five decades. Special emphasis was placed on the integration of our manual into the classification system of the German soil mapping guideline (KA5). Results and discussion The extension of existing data fields (e.g., the further subdivision of land use types) as well as the creation of new data fields (e.g., pH value) adapted to the requirements of urban soil mapping has been carried out. Additional technogenic materials that occur in urban environments have been added to the list of anthropogenic parent materials. Furthermore, we designed appendices that clearly characterize typical soil profiles of the BMA and depict technogenic materials, their physical and chemical characteristics, as well as their origin and distribution. Our approach will set new benchmarks for soil description and mapping in urban environments, which will improve the quality of urban soil research in the BMA. It is expected that our approach will provide baselines for urban soil mapping in other metropolitan areas. Conclusions Our guideline is a comprehensive manual for the description of urban soils within a national soil classification system. This mapping guideline will be the future standard work for soil surveys and soil mapping in the federal state of Berlin. Currently, representatives from federal and state authorities are reviewing our guideline, with a view to potentially integrating key components into the classification system of the forthcoming 6th edition of the German soil mapping guideline (KA6).

Major Arable Soils of the Tropics :A Descriptive Grouping Based on Clay Mineralogy

2003 ◽  
Author(s):  
Anthony S. R. Juo ◽  
Kathrin Franzluebbers
Keyword(s):  
Classification System ◽  
Clay Mineralogy ◽  
Soil Management ◽  
Soil Classification ◽  
Classification Systems ◽  
Soil Survey ◽  
Arable Soils ◽  
Soil Taxonomy ◽  
Detailed Interpretation ◽  
The Tropics

Several pedological soil classification schemes have been developed to classify soils worldwide based on morphological features, stage of weathering, and to some extent their chemical and physical properties. Three soil classification systems are commonly used as research and teaching tools in the tropics, namely, the USDA Soil Taxonomy classification, the FAO/UNESCO World Soil Legends, and the French soil classification system. Brazil, the country with the largest land area in the tropics, has its own national soil classification system. However, soil survey, classification, and interpretation are costly and time-consuming, and few countries in the tropics have completed soil maps that are at a scale detailed enough to be useful to farmers and land users. In the absence of soil information at state, county or farm level, the authors propose a simple descriptive grouping of major soils in the tropics based on clay mineralogy to facilitate discussion on soil management and plant production in the subsequent chapters of this book. Reference to the Soil Taxonomy classification will be made when such information is available. It should be pointed out that the main purpose of this technical grouping is to provide field workers, especially those who are less familiar with the various soil classification systems, with a simple framework for planning soil management strategies. It by no means replaces the national and international soil taxonomy and classification systems that are designed for communication among soil scientists and for more detailed interpretation of soil survey data and land-use planning. This technical scheme classifies major arable soils in the tropics into four groupings according to their dominant clay mineralogy. They are • kaolinitic soils • oxidic soils • allophanic soils • smectitic soils Kaolinitic soils are deeply weathered soils with a sand, loamy sand, or sandy loam texture in the surface horizon and a clayey B horizon (20-60%). Silt content is low (< 20%) throughout the profile. Kaolinite (> 90%) is the dominant mineral in the clay fraction. These soils have an effective CEC of less than 12 cmol/kg of clay in the lower B horizon. Kaolinitic soils have a relatively high bulk density, especially in the clayey subsoil horizons (> 1.40 Mg/m3). The structure of the subsoil horizons is usually massive or blocky.

scholarly journals Machine learning model for automation of soil texture classification

2019 ◽  
Author(s):  
K. Radhika ◽  
D. Madhavi Latha
Keyword(s):  
Soil Texture ◽  
Texture Classification ◽  
Critical Role ◽  
Soil Classification ◽  
Kappa Coefficient ◽  
Classification Model ◽  
Available Phosphorus ◽  
Available Nitrogen ◽  
Linear Discriminant ◽  
Physico Chemical

Abstract Soil formation is a long term process and diverse soils are formed in different localities due to various soil forming factors over the landscape. Soil classification plays critical role in various aspects of agricultural engineering. Physico-chemical parameters play an important role in soil classification. In this paper, we present a comprehensive classification model for soil texture classification by using Linear Discriminant Analysis (LDA). We took the Physico-chemical properties of the soil, which include soil moisture, temperature, electrical conductivity, pH, organic carbon, available nitrogen, available phosphorus and potassium as independent variables, while the soil type was taken as the dependent variable. Feature selection is employed using Boruta algorithm. The performance of the proposed classification model is evaluated and expressed in terms of overall accuracy and kappa coefficient. Results show that the average prediction accuracy and kappa coefficient of the proposed model are 96.3% and 0.944 respectively, indicating that the model can be used effectively for soil classification for a set of suitable dependent variables.

scholarly journals Do Andosols occur in the Czech Republic?

2010 ◽  
Vol 5 (No. 4) ◽  
pp. 161-171 ◽  
Author(s):  
P. Novák ◽  
T. Khel ◽  
J. Vopravil ◽  
J. Lagová
Keyword(s):  
Czech Republic ◽  
Classification System ◽  
Humus Horizon ◽  
Volcanic Glass ◽  
Soil Classification ◽  
Classification Systems ◽  
Necessary Condition ◽  
The Czech Republic ◽  
Diagnostic Characteristics ◽  
The Hill

The aim of this contribution was either to confirm or refuse the supposition that there are soils on the volcanic effusive rocks in the Brunt&aacute;l district which can be assigned to the referential group of Andosols. The conditions for the genesis of Andosols are described and the diagnostic criteria of the andic process are defined both according to the principles of the WBR/FAO 2006 classification and according to the Slovak MKSPS 2000 classification system. In the Czech classification system, the diagnostics of Andosols has not yet been described or defined because their occurrence on the territory of the Czech Republic has not been confirmed till now. On the Velk&yacute; Roudn&yacute; volcanic dome (780 m), samples from two profiles were taken and described: one from below the summit as a sample of forest soil, and the other from the terraced, grass-covered foot of the hill, formerly used as a ploughed land. The samples from the two profiles were processed, and analyses were carried out according to both the classification systems mentioned above. The results of the analyses were subsequently evaluated. It was discovered that both evaluated profiles conformed to most of the diagnostic characteristics of andic development according to both WRB 2006 and the Slovak 2000 classification systems. Both evaluated profiles could be then classified &ndash; according to WRB 2006 &ndash; as Vitric Andosol (Dystric) and Vitric &ndash; Umbric Andosol (Dystric, Colluvic), respectivelly; according to Slovak Classification System as Andic Cambisols. The occurrence of soils with andic development in the Czech Republic was thus confirmed. The conclusion drawn by some authors (eg. in US Taxonomy) that a higher content of volcanic glass and a substrate of andesite type are not an indispensable condition for the creation of soils classified as Andosols was also confirmed. Likewise, according to the WRB criteria, a melanic humus horizon is not a necessary condition. Because of the difficulties in distinguishing the types, the Czech classification system recommends that a humic andic horizon should be evaluated as molic. We assume that in some cases it could be better classified as umbric. A preliminary proposal has been put forward to insert the Andozem soil types in Taxonomic Soil Classification System of the Czech Republic: Haplic Andosol, Vitric Andosol, Lithic Andosol, Umbric Andosol, but the properties and criteria of those soils will have to be defined precisely. One problem which will also have to be resolved is how to allocate the profiles displaying andic properties either to the proposed subtype of Cambic Andosol or to the subtype of Andic Cambisol (outside the referential class of Andsols). This issue is, indeed, not dealt with satisfactorily either by the Slovak system or the worldwide WRB 2006 classification, either.

scholarly journals Learning soil classification with the Kayapó indians

2005 ◽  
Vol 62 (6) ◽  
pp. 604-606 ◽  
Author(s):  
Miguel Cooper ◽  
Edson Roberto Teramoto ◽  
Pablo Vidal-Torrado ◽  
Gerd Sparovek
Keyword(s):  
Classification System ◽  
Soil Classification ◽  
Logical Structure ◽  
Classification Systems ◽  
Amazon Forest ◽  
Language And Culture ◽  
Modern Agriculture ◽  
Modern Soil ◽  
Modern Classification ◽  
Morphological Variables

The Kayapó Xicrin do Cateté (Xicrin) indigenous reserve is located within the Amazon forest in Pará (Brazil). The Xicrins have developed a soil classification system that is incorporated in their language and culture. The etymology of their classification system and its logical structure makes it similar and comparable with modern soil classification. The etymology of the Xicrin's language is based on the junction of radicals to form words for different soil names. The name of the soil is formed by the main noun radical "puka", to which adjectives referring to soil morphological attributes are added. Modern classification systems are also based on similar morphological variables, and analytical support for defining boundaries of chemical or physical soil attributes are important only in lower hierarchical levels. Soil scientists have developed a soil classification system that is sensitive for the restrictions and potentialities the soil will show for modern agriculture. The Xicrins classify soils for what is important for their life style, i.e. a harmonic and friendly life with the resources they gain from the forest.

Sign in / Sign up

Export Citation Format

Share Document