Tree-based techniques to predict soil units

Soil Research ◽  
2017 ◽  
Vol 55 (8) ◽  
pp. 788 ◽  
Author(s):  
H. S. K. Pinheiro ◽  
P. R. Owens ◽  
L. H. C. Anjos ◽  
W. Carvalho Júnior ◽  
C. S. Chagas
Keyword(s):  
Vegetation Index ◽  
Soil Classification ◽  
Base System ◽  
Reference Base ◽  
Landscape Models ◽  
Statistical Indices ◽  
Normalised Difference Vegetation Index ◽  
World Reference Base ◽  
Kappa Value ◽  
Soil Units

Quantitative soil–landscape models offer a method for conducting soil surveys that use statistical tools to predict natural patterns in the occurrence of particular map units across a landscape. The aim of the present study was to predict soil units in a watershed with wide variation in landscape conditions. The approach relied on a modelling of soil-forming factors in order to understand the variability of the landscape components in the region. Models were generated for landscape attributes related to pedogenesis, specifically elevation, slope, curvature, compound topographic index, Euclidean distance from stream networks, landforms map, clay minerals index, iron oxide index and normalised difference vegetation index, along with an existing geology map. The soil classification was adapted from the World Reference Base System for Soil Resources, and the predominant soil taxonomic orders observed were Ferrasols, Acrisols, Gleysols, Cambisols, Fluvisols and Regosols. The algorithms used to predict the soil units were based on decision tree (DT) and random forest (RF) methods. The criteria used to evaluate the models’ performance were statistical indices, coherence between predicted units and the legacy map, as well as accuracy checks based on control samples. The best performing model was found to be the RF algorithm, with resulting statistical indices considered excellent (overall=0.966, kappa=0.962). The accuracy of the map as determined by control points was 67.89%, with a kappa value of 61.39%.

scholarly journals Characteristics of Rendzina soils in Serbia and their WRB classification

2020 ◽  
Vol 65 (3) ◽  
pp. 251-261
Author(s):  
Svjetlana Radmanovic ◽  
Maja Gajic-Kvascev ◽  
Vesna Mrvic ◽  
Aleksandar Djordjevic
Keyword(s):  
Fractional Composition ◽  
Soil Depth ◽  
Chemical Properties ◽  
Principal Component ◽  
Soil Classification ◽  
Soil Profiles ◽  
Total N ◽  
Reference Base ◽  
World Reference Base ◽  
Soil Units

According to the Serbian official soil classification system, Rendzina is a soil type with an A-AC-C-R profile, developed on parent rock containing more than 20% of calcareous material (except soils with an A-R profile on hard pure limestone or dolomite). Previous investigations have shown that 29 Rendzina soil profiles from Serbia belong to the reference soil groups (RSGs) of Leptosols, Regosols and Phaeozems according to the World Reference Base for Soil Resources (WRB 2015). The present study addresses the correlations among three WRB RSGs in terms of soil texture, mean weight diameter (MWD), total N content, and humus fractional composition using Principal Component Analysis (PCA). The objective is to better understand the mutual relationship between the classification soil units used in Serbia and the international WRB system. The results show that PCA cannot unequivocally distinguish between these three RSGs. Leptosols and Regosols are highly incoherent groups while the group of Phaeozems is highly coherent, leading to the conclusion that the physical and chemical properties of the soil profiles of Phaoeozems are specific. It is obvious that soil depth and color, which are the overriding factors in the differentiation of Rendzina soils into three WRB RSGs, had no significant effect on these properties. The results further show that soil properties such as texture, MWD, humus fractional composition, etc. cannot be used to correlate Rendzina soils from Serbia with WRB. Instead, careful correlation of individual soil profiles is needed based on quantitative soil data analysis as required by WRB.

scholarly journals Correlation between the Polish Soil Classification (2011) and international soil classification system World Reference Base for Soil Resources (2015)

2016 ◽  
Vol 67 (2) ◽  
pp. 88-100 ◽  
Author(s):  
Cezary Kabała ◽  
Marcin Świtoniak ◽  
Przemysław Charzyński
Keyword(s):  
International Society ◽  
Working Group ◽  
Soil Classification ◽  
Soil Resources ◽  
Reference Base ◽  
The World ◽  
World Reference Base ◽  
Recent Edition ◽  
Soil Units ◽  
Correlation Table

AbstractThe recent editions of the Polish Soil Classification (PSC) have supplied the correlation table with the World Reference Base for Soil Resources (WRB), which is the international soil classification most commonly used by Polish pedologists. However, the latest WRB edition (IUSS Working Group WRB 2015) has introduced significant changes and many of the former correlations became outdated. The current paper presents the closest equivalents of the soil orders, types and subtypes of the recent edition of the PSC (2011) and WRB (IUSS Working Group WRB 2015). The proposals can be used for general correlation of soil units on maps and in databases, and may support Polish soil scientists to establish the most appropriate equivalents for soils under study, as well as make PSC more available for an international society.

scholarly journals ЦИФРОВАЯ ПОЧВЕННАЯ КАРТА ВОДОСБОРА РЕКИ СОКОЛОВКА (ТЕРРИТОРИЯ ВЕРХНЕУССУРИЙСКОГО СТАЦИОНАРА ФНЦ БИОРАЗНООБРАЗИЯ ДВО РАН)

2019 ◽  
Author(s):  
A.A. Tereshkina ◽  
N.F. Pshenichnikova ◽  
A.N. Bugaets ◽  
O.M. Golodnaya ◽  
S.M. Krasnopeev
Keyword(s):  
Soil Classification ◽  
Soil Resources ◽  
Reference Base ◽  
Experimental Station ◽  
Digital Soil Map ◽  
Modern Soil ◽  
World Reference Base ◽  
The Russian Federation ◽  
The Right

В работе приведены предварительные результаты создания цифровой почвенной карты для бассейна р. Правая Соколовка, территории Верхнеуссурийского стационара (ВУС) ФНЦ Биоразнообразия наземной биоты Восточной Азии ДВО РАН 1: 50 000. По природным условиям территория типична для среднегорного пояса, представляет собой характерный низкосреднегорный участок южного СихотэАлиня. Климат района формируется под влиянием восточноазиатского муссона. В качестве топографической основы использована цифровая модель рельефа с пространственным разрешением 30 м (SRTM30), план лесонасаждений Верхнеуссурийского стационара, геологическая карта М 1: 200 000. Основными единицами карты являются почвенные подтипы. Номенклатура почв дана по региональной классификации Г. И. Иванова, выполнена адаптация к современной почвенной классификации Российской Федерации и проведена корреляция с номенклатурой почв Всемирной реферативной базой почвенных ресурсов (WRB). Каждый почвенный ареал включает данные по условиям формирования почв на уровне подтипа. Всего выделено десять подтипов. Показано, что в почвеннорастительном покрове четко выражена вертикальная зональность, представленная двумя почвеннорастительными поясами: горных буротаежных и горноподзолистых почв темнохвойных лесов и поясом горнолесных бурых почв хвойношироколиственных лесов. В поясе темнохвойных лесов в пределах высот 800 1000 м распространены горные ржавоземы грубогумусовые иллювиальногумусированные, составляющие 23,8 от общей площади бассейна. В поясе хвойношироколиственных лесов в основном распространены буроземы (70 от общей площади водосбора). Среди почв пойменных ландшафтов преобладают аллювиальные серогумусовые (дерновые) типичные. На основе информации по генетическим горизонтам создана база данных гидрофизических характеристик почв. По литературным источникам создана база данных физических характеристик почв (гранулометрический состав, глубина, вес, содержание гумуса) по генетическим горизонтам почвенных профилей (45 разрезов). С помощью алгоритмов обработки пространственных данных выполнен анализ численных характеристик морфометрии рельефа (средняя высота, уклон, площадь) почвенных ареалов.The digital soil map (1: 50 000) of the Right Sokolovka River basin the territory of the Upper Ussurian experimental station of the Centre of Biodiversity of the terrestrial biota of East Asia, FEB RAS. The main map units are soil subtypes. The soil nomenclature is given according to the regional classification, the adaptation to the modern soil classification of the Russian Federation was carried out and correlation with the soil nomenclature by the World Reference Base of Soil Resources was made. The calculation and preliminary analysis of the numerical characteristics of the morphometry of the topography of the soil areas has been performed.

scholarly journals Soil environment grouping system based on spectral, climate, and terrain data: a quantitative branch of soil series

SOIL ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. 163-177
Author(s):  
Andre Carnieletto Dotto ◽  
Jose A. M. Demattê ◽  
Raphael A. Viscarra Rossel ◽  
Rodnei Rizzo
Keyword(s):  
Soil Classification ◽  
Empirical Knowledge ◽  
Soil Series ◽  
Soil Environment ◽  
Data Set ◽  
Reference Base ◽  
Automated Measurements ◽  
World Reference Base ◽  
Soil Information ◽  
New System

Abstract. Soil classification has traditionally been developed by combining the interpretation of taxonomic rules that are related to soil information with the pedologist's tacit knowledge. Hence, a more quantitative approach is necessary to characterize soils with less subjectivity. The objective of this study was to develop a soil grouping system based on spectral, climate, and terrain variables with the aim of establishing a quantitative way of classifying soils. Spectral data were utilized to obtain information about the soil, and this information was complemented by climate and terrain variables in order to simulate the pedologist knowledge of soil–environment interactions. We used a data set of 2287 soil profiles from five Brazilian regions. The soil classes of World Reference Base (WRB) system were predicted using the three above-mentioned variables, and the results showed that they were able to correctly classify the soils with an overall accuracy of 88 %. To derive the new system, we applied the spectral, climatic, and terrain variables, which – using cluster analysis – defined eight groups; thus, these groups were not generated by the traditional taxonomic method but instead by grouping areas with similar characteristics expressed by the variables indicated. They were denominated as “soil environment groupings” (SEGs). The SEG system facilitated the identification of groups with equivalent characteristics using not only soil but also environmental variables for their distinction. Finally, the conceptual characteristics of the eight SEGs were described. The new system has been designed to incorporate applicable soil data for agricultural management, to require less interference from personal/subjective/empirical knowledge (which is an issue in traditional taxonomic systems), and to provide more reliable automated measurements using sensors.

scholarly journals A Comparative Analysis of a Detailed and Semi-Detailed Soil Mapping for Sustainable Land Management Using Conventional and Currently Applied Methodologies in Greece

Land ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 154 ◽  
Author(s):  
Orestis Kairis ◽  
Vassiliki Dimitriou ◽  
Chrysoula Aratzioglou ◽  
Dionisios Gasparatos ◽  
Nicholas Yassoglou ◽  
...  
Keyword(s):  
Soil Classification ◽  
Botanical Garden ◽  
Soil Mapping ◽  
Classification Systems ◽  
Soil Survey ◽  
Sustainable Land Use ◽  
Soil Taxonomy ◽  
Reference Base ◽  
World Reference Base ◽  
Soil Surveys

Two soil mapping methodologies at different scales applied in the same area were compared in order to investigate the potential of their combined use to achieve an integrated and more accurate soil description for sustainable land use management. The two methodologies represent the main types of soil mapping systems used and still applied in soil surveys in Greece. Diomedes Botanical Garden (DBG) (Athens, Greece) was used as a study area because past cartographic data of soil survey were available. The older soil survey data were obtained via the conventional methodology extensively used over time since the beginnings of soil mapping in Greece (1977). The second mapping methodology constitutes the current soil mapping system in Greece recently used for compilation of the national soil map. The obtained cartographic and soil data resulting from the application of the two methodologies were analyzed and compared using appropriate geospatial techniques. Even though the two mapping methodologies have been performed at different mapping scales, using partially different mapping symbols and different soil classification systems, the description of the soils based on the cartographic symbols of the two methodologies presented an agreement of 63.7% while the soil classification by the two taxonomic systems namely Soil Taxonomy and World Reference Base for Soil Resources had an average coincidence of 69.5%.

The World Reference Base for Soils (WRB) and Soil Taxonomy: an appraisal of their application to the soils of the Northern Rivers of New South Wales

Soil Research ◽  
2013 ◽  
Vol 51 (3) ◽  
pp. 167 ◽  
Author(s):  
David T. Morand
Keyword(s):  
New South ◽  
New South Wales ◽  
Soil Classification ◽  
Soil Taxonomy ◽  
Reference Base ◽  
South Wales ◽  
The World ◽  
World Reference Base ◽  
Northern Rivers ◽  
Soil Surveys

Few soil surveys in New South Wales have utilised international soil classifications. Extensive morphological and laboratory data collected during soil surveys in the Northern Rivers region provided a strong basis for correlation with the World Reference Base for Soil Resources (WRB), Soil Taxonomy (ST), and the Australian Soil Classification (ASC). Of the 32 reference soil groups comprising the WRB, 20 were present locally; nine of the 12 ST orders were present. After re-classification of soils, correlation of the ASC with the WRB and ST was undertaken. Soils not requiring extensive laboratory analysis for classification and sharing similar central concepts were the more straightforward to correlate. Several ASC orders have unique central concepts and were therefore difficult to correlate with any one WRB reference soil group or ST order/suborder. Other soils were difficult to correlate due to differences in definitions of similar diagnostic criteria. This is most applicable to soils with strong texture-contrast and those with natric conditions. Such soils are not adequately differentiated to suit the Northern Rivers conditions. Of the two international schemes, the WRB was easier to apply locally due to the relative simplicity of the scheme. Considering certain aspects of Australian soils would improve the applicability of the WRB as a truly international framework for soil classification and correlation. Amendments to both the ASC and WRB are suggested.

Diversity and main properties of soils of the Gronfjord area (Svalbard archipelago)

2018 ◽  
Vol 8 (1) ◽  
pp. 43-59 ◽  
Author(s):  
Elizaveta Iaroslavovna Iavid ◽  
Veronika Nikolaevna Kondakova ◽  
Vyacheslav Igorevich Polyakov ◽  
Evgeny Vasilyevic Abakumov
Keyword(s):  
Soil Cover ◽  
Morphological Structure ◽  
Soil Formation ◽  
Soil Classification ◽  
Svalbard Archipelago ◽  
Climate Conditions ◽  
Reference Base ◽  
Relative Air Humidity ◽  
World Reference Base ◽  
Russian Soil

Svalbard archipelago is characterized by specific climate conditions, high air temperature and relative air humidity, which are not typical for high latitudes. Such conditions affect soil-forming processes. Classification and morphological structure of the soil cover on the Spitsbergen archipelago are still poorly understood. The aim of current research was to reveal diverse soil taxons in the Gronfjord area and characterize framework of its formation. As the results of this work, the authors provide the description of the investigated soils and their taxonomy in accordance with World Reference Base for Soil Resources (IUSS Working Group 2015) and the new Russian soil classification system. Chemical parameters of the soil, as well and the data on soil horizons properties were measured using vertical electric resistivity sounding method. In total, 15 soil profiles were made and the studied soils were referred to six Soil Reference Groups with domination of Leptosols and Regosols. The profiles were made in different landscapes that allowed to determine the similarities and differences in soil cover of the area. The main factors affected soil formation are cryogenic processes combined with gleyfication and cambic alteration of soil material.

Sign in / Sign up

Export Citation Format

Share Document