Comparing traditional and digital soil mapping at a district scale using residual maximum likelihood analysis

Soil Research ◽  
2018 ◽  
Vol 56 (5) ◽  
pp. 535 ◽  
Author(s):  
E. Zare ◽  
M. F. Ahmed ◽  
R. S. Malik ◽  
R. Subasinghe ◽  
J. Huang ◽  
...  
Keyword(s):  
Maximum Likelihood ◽  
Soil Profile ◽  
Traditional Approach ◽  
Clay Content ◽  
Soil Mapping ◽  
Classification Systems ◽  
Digital Soil Mapping ◽  
Likelihood Method ◽  
Ancillary Data ◽  
Residual Maximum Likelihood

Conventional soil mapping uses field morphological observations to classify soil profiles into predefined classification systems and extrapolates the classified soils to make a map based on aerial photographs and the experience of the surveyor. A criticism of this approach is that the subjectivity of the surveyor leads to non-reproducible maps. Advances in computing and statistical analysis, and an increased availability of ancillary data have cumulatively led to an alternative, referred to as digital soil mapping (DSM). In this research, two agriculturally productive areas (i.e. Warren and Trangie) located in central New South Wales, Australia, were considered to evaluate whether pedoderms and soil profile classes defined according to the traditional approach can also be recognised and mapped using a DSM approach. First, we performed a fuzzy k-means analysis to look for clusters in the ancillary data, which include data from remote-sensed gamma-ray (γ-ray) spectrometry and proximal-sensed electromagnetic (EM) induction. We used the residual maximum likelihood method to evaluate the maps for various numbers of classes (k = 2–10) to minimise the mean square prediction error (σ2p,C) of soil physical (i.e. clay content, field capacity (FC), permanent wilting point (PWP) and available water content (AWC)) and chemical (pH, EC of 1 : 5 soil water extract (EC1:5) and cation exchange capacity (CEC)) properties of topsoil (0–0.3 m) and subsoil (0.6–0.9 m). In terms of prediction, the calculated σ2p,C was locally minimised for k = 8 when accounting for topsoil clay, FC, PWP, pH and CEC, and subsoil FC, EC1:5 and CEC. A comparison of σ2p,C of the traditional (seven pedoderm components) and DSM approach (k = 8) indicated that only topsoil EC1:5 and subsoil pH was better accounted for by the traditional approach, whereas topsoil clay content, and CEC and subsoil clay, EC1:5 and CEC were better resolved using the DSM approach. The produced DSM maps (e.g. k = 3, 6 and 8) also reflected the pedoderm components identified using the traditional approach. We concluded that the DSM maps with k = 8 classes reflected the soil profile classes identified within the pedoderms and that soil maps of similar accuracy could be developed from the EM data independently.

Digital soil mapping of compositional particle-size fractions using proximal and remotely sensed ancillary data

Geophysics ◽  
2012 ◽  
Vol 77 (4) ◽  
pp. WB201-WB211 ◽  
Author(s):  
S. Buchanan ◽  
J. Triantafilis ◽  
I. O. A. Odeh ◽  
R. Subansinghe
Keyword(s):  
Particle Size ◽  
High Resolution ◽  
Soil Mapping ◽  
Additive Models ◽  
Digital Soil Mapping ◽  
Unbiased Estimation ◽  
Ancillary Data ◽  
Size Fractions ◽  
Particle Size Fractions ◽  
Log Ratio

The soil particle-size fractions (PSFs) are one of the most important attributes to influence soil physical (e.g., soil hydraulic properties) and chemical (e.g., cation exchange) processes. There is an increasing need, therefore, for high-resolution digital prediction of PSFs to improve our ability to manage agricultural land. Consequently, use of ancillary data to make cheaper high-resolution predictions of soil properties is becoming popular. This approach is known as “digital soil mapping.” However, most commonly employed techniques (e.g., multiple linear regression or MLR) do not consider the special requirements of a regionalized composition, namely PSF; (1) should be nonnegative (2) should sum to a constant at each location, and (3) estimation should be constrained to produce an unbiased estimation, to avoid false interpretation. Previous studies have shown that the use of the additive log-ratio transformation (ALR) is an appropriate technique to meet the requirements of a composition. In this study, we investigated the use of ancillary data (i.e., electromagnetic (EM), gamma-ray spectrometry, Landsat TM, and a digital elevation model to predict soil PSF using MLR and generalized additive models (GAM) in a standard form and with an ALR transformation applied to the optimal method (GAM-ALR). The results show that the use of ancillary data improved prediction precision by around 30% for clay, 30% for sand, and 7% for silt for all techniques (MLR, GAM, and GAM-ALR) when compared to ordinary kriging. However, the ALR technique had the advantage of adhering to the special requirements of a composition, with all predicted values nonnegative and PSFs summing to unity at each prediction point and giving more accurate textural prediction.

Comparing digital soil mapping techniques for organic carbon and clay content: Case study in Burundi's central plateaus

CATENA ◽  
2017 ◽  
Vol 156 ◽  
pp. 161-175 ◽  
Author(s):  
Anicet Sindayihebura ◽  
Sam Ottoy ◽  
Stefaan Dondeyne ◽  
Marc Van Meirvenne ◽  
Jos Van Orshoven
Keyword(s):  
Organic Carbon ◽  
Clay Content ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Mapping Techniques

Digital soil mapping of a coastal acid sulfate soil landscape

Soil Research ◽  
2014 ◽  
Vol 52 (4) ◽  
pp. 327 ◽  
Author(s):  
Jingyi Huang ◽  
Terence Nhan ◽  
Vanessa N. L. Wong ◽  
Scott G. Johnston ◽  
R. Murray Lark ◽  
...  
Keyword(s):  
Spatial Distribution ◽  
Traditional Approach ◽  
Management Strategies ◽  
Error Variance ◽  
Optimal Number ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Acid Sulfate ◽  
Soil Landscape ◽  
Number Of Classes

Coastal floodplains are commonly underlain by sulfidic sediments and coastal acid sulfate soils (CASS). Oxidation of sulfidic sediments leads to increases in acidity and mobilisation of trace metals, resulting in an increase in the concentrations of conducting ions in sediment and pore water. The distribution of these sediments on floodplains is highly heterogeneous. Accurately identifying the distribution of CASS is essential for developing targeted management strategies. One approach is the use of digital soil mapping (DSM) using ancillary information. Proximal sensing instruments such as an EM38 can provide data on the spatial distribution of soil salinity, which is associated with CASS, and can be complemented by digital elevation models (DEM). We used EM38 measurements of the apparent soil electrical conductivity (ECa) in the horizontal and vertical modes in combination with a high resolution DEM to delineate the spatial distribution of CASS. We used a fuzzy k-means algorithm to cluster the data. The fuzziness exponent, number of classes (k) and distance metric (i.e. Euclidean, Mahalanobis and diagonal) were varied to determine a set of parameters to identify CASS. The mean-squared prediction error variance of the class mean of various soil properties (e.g. EC1:5 and pH) was used to identify which of these metrics was suitable for further analysis (i.e. Mahalanobis) and also determine the optimal number of classes (i.e. k = 4). The final map is consistent with previously defined soil–landscape units generated using traditional soil profile description, classification and mapping. The DSM approach is amenable for evaluation on a larger scale and in order to refine CASS boundaries previously mapped using the traditional approach or to identify CASS areas that remain unmapped.

scholarly journals Standardised soil profile data to support global mapping and modelling (WoSIS snapshot 2019)

2019 ◽  
Author(s):  
Niels H. Batjes ◽  
Eloi Ribeiro ◽  
Ad van Oostrum
Keyword(s):  
Soil Profile ◽  
Soil Property ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Total Carbon ◽  
System Modelling ◽  
Profile Data ◽  
Wide Range ◽  
Global Soil ◽  
Soil Information

Abstract. The World Soil Information Service (WoSIS) provides quality-assessed and standardised soil profile data to support digital soil mapping and environmental applications at broad scale levels. Since the release of the first WoSIS snapshot, in July 2016, many new soil data were shared with us, registered in the ISRIC data repository, and subsequently standardised in accordance with the licences specified by the data providers. Soil profile data managed in WoSIS were contributed by a wide range of data providers, therefore special attention was paid to measures for soil data quality and the standardisation of soil property definitions, soil property values (and units of measurement), and soil analytical method descriptions. We presently consider the following soil chemical properties (organic carbon, total carbon, total carbonate equivalent, total Nitrogen, Phosphorus (extractable-P, total-P, and P-retention), soil pH, cation exchange capacity, and electrical conductivity) and physical properties (soil texture (sand, silt, and clay), bulk density, coarse fragments, and water retention), grouped according to analytical procedures (aggregates) that are operationally comparable. Further, for each profile, we provide the original soil classification (FAO, WRB, USDA, and version) and horizon designations insofar as these have been specified in the source databases. Measures for geographical accuracy (i.e. location) of the point data as well as a first approximation for the uncertainty associated with the operationally defined analytical methods are presented, for possible consideration in digital soil mapping and subsequent earth system modelling. The latest (dynamic) set of quality-assessed and standardised data, called wosis_latest, is freely accessible via an OGC-compliant WFS (web feature service). For consistent referencing, we also provide time-specific static snapshots. The present snapshot (September 2019) comprises 196,498 geo-referenced profiles originating from 173 countries. They represent over 832 thousand soil layers (or horizons), and over 5.8 million records. The actual number of observations for each property varies (greatly) between profiles and with depth, this generally depending on the objectives of the initial soil sampling programmes. In the coming years, we aim to fill gradually gaps in the geographic and feature space, this subject to the sharing of a wider selection of soil profile data for so far under-represented areas and properties by our existing and prospective partners. Part of this work is foreseen in conjunction within the Global Soil Information System (GloSIS) being developed by the Global Soil Partnership (GSP). The WoSIS snapshot – September 2019 is archived and freely accessible at https://doi.org/10.17027/isric-wdcsoils.20190901 (Batjes et al., 2019).

scholarly journals Standardised soil profile data to support global mapping and modelling (WoSIS snapshot 2019)

2020 ◽  
Vol 12 (1) ◽  
pp. 299-320 ◽  
Author(s):  
Niels H. Batjes ◽  
Eloi Ribeiro ◽  
Ad van Oostrum
Keyword(s):  
Soil Profile ◽  
Soil Property ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Total Carbon ◽  
System Modelling ◽  
Profile Data ◽  
Wide Range ◽  
Global Soil ◽  
Soil Information

Abstract. The World Soil Information Service (WoSIS) provides quality-assessed and standardised soil profile data to support digital soil mapping and environmental applications at broadscale levels. Since the release of the first “WoSIS snapshot”, in July 2016, many new soil data were shared with us, registered in the ISRIC data repository and subsequently standardised in accordance with the licences specified by the data providers. Soil profile data managed in WoSIS were contributed by a wide range of data providers; therefore, special attention was paid to measures for soil data quality and the standardisation of soil property definitions, soil property values (and units of measurement) and soil analytical method descriptions. We presently consider the following soil chemical properties: organic carbon, total carbon, total carbonate equivalent, total nitrogen, phosphorus (extractable P, total P and P retention), soil pH, cation exchange capacity and electrical conductivity. We also consider the following physical properties: soil texture (sand, silt, and clay), bulk density, coarse fragments and water retention. Both of these sets of properties are grouped according to analytical procedures that are operationally comparable. Further, for each profile we provide the original soil classification (FAO, WRB, USDA), version and horizon designations, insofar as these have been specified in the source databases. Measures for geographical accuracy (i.e. location) of the point data, as well as a first approximation for the uncertainty associated with the operationally defined analytical methods, are presented for possible consideration in digital soil mapping and subsequent earth system modelling. The latest (dynamic) set of quality-assessed and standardised data, called “wosis_latest”, is freely accessible via an OGC-compliant WFS (web feature service). For consistent referencing, we also provide time-specific static “snapshots”. The present snapshot (September 2019) is comprised of 196 498 geo-referenced profiles originating from 173 countries. They represent over 832 000 soil layers (or horizons) and over 5.8 million records. The actual number of observations for each property varies (greatly) between profiles and with depth, generally depending on the objectives of the initial soil sampling programmes. In the coming years, we aim to fill gradually gaps in the geographic distribution and soil property data themselves, this subject to the sharing of a wider selection of soil profile data for so far under-represented areas and properties by our existing and prospective partners. Part of this work is foreseen in conjunction within the Global Soil Information System (GloSIS) being developed by the Global Soil Partnership (GSP). The “WoSIS snapshot – September 2019” is archived and freely accessible at https://doi.org/10.17027/isric-wdcsoils.20190901 (Batjes et al., 2019).

Digital soil mapping: the challenge to obtain the best soil dataset and create a precise environmental model to support land use management at a national level (Ecuador).

2020 ◽  
Author(s):  
Daphne Armas ◽  
Mário Guevara ◽  
Fernando Bezares ◽  
Rodrigo Vargas ◽  
Pilar Durante ◽  
...  
Keyword(s):  
Land Use ◽  
Information System ◽  
Soil Properties ◽  
Soil Profile ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Land Use Management ◽  
National Scale ◽  
Global Soil ◽  
Soil Information

<p>One of the biggest challenges for digital soil mapping is the limited of field soil information (e.g., soil profile descriptions, soil sample analysis) for representing soil variability across scales. Global initiatives such as the Global Soil Partnership (GSP) and the development of a <strong>Global Soil Information System</strong> (GloSIS), World Soil Information Service (WoSis) or SoilGrids250m for global pedometric mapping highlight new opportunities but the crescent need of new and better soil datasets across the world. Soil datasets are increasingly required for the development of soil monitoring baselines, soil protection and sustainable land use strategies, and to better understand the response of soils to global environmental change.  However, soil surveys are a very challenging task due to their high acquisition costs such data and operational complexity. The use of legacy soil data can reduce these sampling efforts.</p><p>The main objective of this research was the rescue, synthesis and harmonization of legacy soil profile information collected between 2009 and 2015 for different purposes (e.g., soil or natural resources inventory) across Ecuador. This project will support the creation of a soil information system at the national scale following international standards for archiving and sharing soil information (e.g., GPS or the GlobalSoilMap.net project). This new information could be useful to increase the accuracy of current digital soil information across the country and the future development of digital soil properties maps.</p><p>We provided an integrated framework combining multiple data analytic tools (e.g., python libraries, pandas, openpyxl or pdftools) for the automatic conversion of text in paper format (e.g., pdf, jpg) legacy soil information, as much the qualitative soil description as analytical data,  to usable digital soil mapping inputs (e.g., spatial datasets) across Ecuador. For the conversion, we used text data mining techniques to automatically extract the information. We based on regular expressions using consecutive sequences algorithms of common patterns not only to search for terms, but also relationships between terms. Following this approach, we rescued information of 13.696 profiles in .pdf, .jpg format and compiled a database consisting of 10 soil-related variables.</p><p>The new database includes historical soil information that automatically converted a generic tabular database form (e.g., .csv) information.</p><p>As a result, we substantially improved the representation of soil information in Ecuador that can be used to support current soil information initiatives such as the WoSis, Batjes et al. 2019, with only 94 pedons available for Ecuador, the Latin American Soil Information System (SISLAC, http://54.229.242.119/sislac/es),  and the United Nations goals  towards increasing soil carbon sequestration areas or decreasing land desertification trends.  In our database there are almost 13.696 soil profiles at the national scale, with soil-related (e.g., depth, organic carbon, salinity, texture) with positive implications for digital soil properties mapping. </p><p>With this work we increased opportunities for digital soil mapping across Ecuador. This contribution could be used to generate spatial indicators of land degradation at a national scale (e.g., salinity, erosion).</p><p>This dataset could support new knowledge for more accurate environmental modelling and to support land use management decisions at the national scale.</p><p> </p>

Global soil mapping with Neural Networks 

2021 ◽  
Author(s):  
Giulio Genova ◽  
Luis de Sousa ◽  
Tanja Mimmo ◽  
Luigi Borruso ◽  
Laura Poggio
Keyword(s):  
Neural Networks ◽  
Prediction Models ◽  
Traditional Approach ◽  
Contextual Information ◽  
Water Security ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Environmental Covariates ◽  
Complex Architectures ◽  
Global Soil

<p>High quality global soil maps are crucial to face several challenges such as reducing soil erosion, climate change adaptation and mitigation, ensuring food and water security, and biodiversity conservation planning. To obtain accurate and robust soil properties maps, research and development are necessary to identify the most appropriate prediction models and to develop efficient and robust workflows. A few recent studies used Artificial Neural Networks (ANN) in Digital Soil Mapping, in some cases improving the accuracy of the predicted maps compared to other methods like Random Forest (RF). In this study we tested different ANN architectures on a global top-soil dataset of ca. 110 000 samples, comparing the results for the different architectures with the more traditional approach of RF. The target variables considered are pH, Soil Organic Carbon, Sand, Silt, and Clay. We selected 40 environmental covariates from a pool of over 400 to represent the most important soil forming factors. We tried simpler architectures (single input – single target) using point observations for one target variable with corresponding raster cell values for spatially explicit environmental covariates. We also used more complex architectures (multi input - multi target) incorporating contextual information surrounding an observation (convolutional) and with multiple target variables. Preliminary results show that increasing the number of hidden layers in the neural network does not significantly influence the results, while changing the type of architecture can play a bigger role in the overall accuracy of the model. The overall prediction accuracy of the ANN was comparable with the RF model. We conclude that ANN are a promising, relatively new, approach for Global Digital Soil Mapping and that further research is needed to improve performance.</p>

scholarly journals Digital soil mapping from conventional field soil observations

2013 ◽  
Vol 8 (No. 1) ◽  
pp. 13-25 ◽  
Author(s):  
J. Balkovič ◽  
Z. Rašeková ◽  
V. Hutár ◽  
J. Sobocká ◽  
R. Skalský
Keyword(s):  
Soil Profile ◽  
Soil Mapping ◽  
Digital Soil Mapping ◽  
Estimation Methods ◽  
Linear Regression Method ◽  
Regression Kriging ◽  
Field Methods ◽  
Leave One Out ◽  
Relative Differences ◽  
Conventional Field

We tested the performance of a formalized digital soil mapping (DSM) approach comprising fuzzy k-means (FKM) classification and regression-kriging to produce soil type maps from a fine-scale soil observation network in Ri&scaron;ňovce, Slovakia. We examine whether the soil profile descriptions collected merely by field methods fit into the statistical DSM tools and if they provide pedologically meaningful results for an erosion-affected area. Soil texture, colour, carbonates, stoniness and genetic qualifiers were estimated for a total of 111 soil profiles using conventional field methods. The data were digitized along semi-quantitative scales in 10-cm depth intervals to express the relative differences, and afterwards classified by the FKM method into four classes A&ndash;D: (i) Luvic Phaeozems (Anthric), (ii)&nbsp;Haplic Phaeozems (Anthric, Calcaric, Pachic), (iii) Calcic Cutanic Luvisols, and (iv) Haplic Regosols (Calcaric). To parameterize regression-kriging, membership values (MVs) to the above A&ndash;D class centroids were regressed against PCA-transformed terrain variables using the multiple linear regression method (MLR). MLR yielded significant relationships with R<sup>2</sup> ranging from 23% to 47% (P &lt; 0.001) for classes A, B and D, but only marginally significant for Luvisols of class C (R<sup>2</sup> = 14%, P &lt; 0.05). Given the results, Luvisols were then mapped by ordinary kriging and the rest by regression-kriging. A &ldquo;leave-one-out&rdquo; cross-validation was calculated for the output maps yielding R<sup>2</sup> of 33%, 56%, 22% and 42% for Luvic Phaeozems, Haplic Phaeozems, Luvisols and also Regosols, respectively (all P &lt; 0.001). Additionally, the pixel-mixture visualization technique was used to draw a synthetic digital soil map. We conclude that the DSM model represents a fully formalized alternative to classical soil mapping at very fine scales, even when soil profile descriptions were collected merely by field estimation methods. Additionally to conventional soil maps it allows to address the diffuse character in soil cover, both in taxonomic and geographical interpretations.

Estimating the Cost of Car Warranty in Indonesia using the Gertsbakh-Kordonsky Method

2020 ◽  
Vol 2 (1) ◽  
pp. 33-40
Author(s):  
Anggis Sagitarisman ◽  
Aceng Komarudin Mutaqin
Keyword(s):  
Maximum Likelihood ◽  
Likelihood Estimation ◽  
Type A ◽  
Claim Data ◽  
Likelihood Method ◽  
Selling Price ◽  
One Dimensional ◽  
Warranty Period ◽  
Kolmogorov Smirnov ◽  
Warranty Costs

AbstractCar manufacturers in Indonesia need to determine reasonable warranty costs that do not burden companies or consumers. Several statistical approaches have been developed to analyze warranty costs. One of them is the Gertsbakh-Kordonsky method which reduces the two-dimensional warranty problem to one dimensional. In this research, we apply the Gertsbakh-Kordonsky method to estimate the warranty cost for car type A in XYZ company. The one-dimensional data will be tested using the Kolmogorov-Smirnov to determine its distribution and the parameter of distribution will be estimated using the maximum likelihood method. There are three approaches to estimate the parameter of the distribution. The difference between these three approaches is in the calculation of mileage for units that do not claim within the warranty period. In the application, we use claim data for the car type A. The data exploration indicates the failure of car type A is mostly due to the age of the vehicle. The Kolmogorov-Smirnov shows that the most appropriate distribution for the claim data is the three-parameter Weibull. Meanwhile, the estimated using the Gertsbakh-Kordonsky method shows that the warranty costs for car type A are around 3.54% from the selling price of this car unit without warranty i.e. around Rp. 4,248,000 per unit.Keywords: warranty costs; the Gertsbakh-Kordonsky method; maximum likelihood estimation; Kolmogorov-Smirnov test.                                   AbstrakPerusahaan produsen mobil di Indonesia perlu menentukan biaya garansi yang bersifat wajar tidak memberatkan perusahaan maupun konsumen. Beberapa pendekatan statistik telah dikembangkan untuk menganalisis biaya garansi. Salah satunya adalah metode Gertsbakh-Kordonsky yang mereduksi masalah garansi dua dimensi menjadi satu dimensi. Pada penelitian ini, metode Gertsbakh-Kordonsky akan digunakan untuk mengestimasi biaya garansi untuk mobil tipe A pada perusahaan XYZ. Data satu dimensi hasil reduksi diuji kecocokan distribusinya menggunakan uji kecocokan Kolmogorov-Smirnov dan taksiran parameter distribusinya menggunakan metode penaksir kemungkinan maksimum. Ada tiga pendekatan yang digunakan untuk menaksir parameter distribusi. Perbedaan dari ketiga pendekatan tersebut terletak pada perhitungan jarak tempuh untuk unit yang tidak melakukan klaim dalam periode garansi. Sebagai bahan aplikasi, kami menggunakan data klaim unit mobil tipe A. Hasil eksplorasi data menunjukkan bahwa kegagalan mobil tipe A lebih banyak disebabkan karena faktor usia kendaraan. Hasil uji kecocokan distribusi untuk data hasil reduksi menunjukkan bahwa distribusi yang cocok adalah distribusi Weibull 3-parameter. Sementara itu, hasil perhitungan taksiran biaya garansi menunjukan bahwa taksiran biaya garansi untuk unit mobil tipe A sekitar 3,54% dari harga jual unit mobil tipe A tanpa garansi, atau sekitar Rp. 4.248.000,- per unit.Kata Kunci: biaya garansi; metode Gertsbakh-Kordonsky; penaksiran kemungkinan maksimum; uji Kolmogorov-Smirnov.

Sign in / Sign up

Export Citation Format

Share Document