Chemometric Study on the Forensic Discrimination of Soil Types Using Their Infrared Spectral Characteristics

Baron, Mark; Gonzalez-Rodriguez, Jose; Croxton, Ruth; Gonzalez, Rafael; Jiménez‐Pérez, Rebeca

doi:10.1366/10-06197

Cited by 20 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used variable importance in project (VIP) scores to identify the features that were most important for characterizing each soil type. We defined VIP scores ≥1 as indicative of particularly important features for the model 17 . Among the 66 features selected by GA, there were 28, 30, 29, 32 and 28 with VIP scores ≥1 (solid points in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Although the method of maximum distance we used to classify individual samples is straightforward and easily implemented, other methods such as centroids or Mahalanobis distances between soil types might lead to improvements in classification accuracy. Alternative methods, such as nonlinear iterative partial least squares followed by linear discriminant analysis (NIPALS-LDA), may also perform better 17 . Data mining should always be explored to improve the accuracy and predictive models for soil type recognition, especially if more spectral data are available for the continued development across larger spatial scales.…”

Section: Resultsmentioning

confidence: 99%

“…For both methods, we used percentage classification accuracy as the metric of model performance. Variable importance in projection (VIP) scores were used to estimate the importance of each variable in the projection used in a PLS model 17 .…”

Section: Methodsmentioning

confidence: 99%

“…Pattern recognition methods were developed to explore similarity among groups of multivariate data 11 and have been employed to identify soil samples using mid-infrared photoacoustic spectroscopy (MIR-PAS) 4 and near-infrared spectroscopy (NIR) 3 . Chemometrics methods used in identification and classification of soils include principal component analysis (PCA) 4 12 13 , partial least squares (PLS) and artificial neural networks (ANN) 14 , cluster analysis 15 , linear discriminant analysis (LDA) 16 , soft independent modeling of class analogy (SIMCA) 16 and partial least squares discriminant analysis (PLSDA) 17 . Among these methods, PLSDA is particularly effective at classification tasks 18 19 and has the capacity to deal with data multicollinearity 20 .…”

mentioning

confidence: 99%

See 3 more Smart Citations

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis

Xie

Zhao

Wang

et al. 2015

Sci Rep

View full text Add to dashboard Cite

Soil types have traditionally been determined by soil physical and chemical properties, diagnostic horizons and pedogenic processes based on a given classification system. This is a laborious and time consuming process. Near infrared (NIR) spectroscopy can comprehensively characterize soil properties, and may provide a viable alternative method for soil type recognition. Here, we presented a partial least squares discriminant analysis (PLSDA) method based on the NIR spectra for the accurate recognition of the types of 230 soil samples collected from farmland topsoils (0–10 cm), representing 5 different soil classes (Albic Luvisols, Haplic Luvisols, Chernozems, Eutric Cambisols and Phaeozems) in northeast China. We found that the PLSDA had an internal validation accuracy of 89% and external validation accuracy of 83% on average, while variable selection with the genetic algorithm (GA and GA-PLSDA) improved this to 92% and 93%. Our results indicate that the GA variable selection technique can significantly improve the accuracy rate of soil type recognition using NIR spectroscopy, suggesting that the proposed methodology is a promising alternative for recognizing soil types using NIR spectroscopy.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis

Xie

Zhao

Wang

et al. 2015

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Its implementation in the field and laboratory offers the possibility of repeating measurements and estimating the ranges of various soil properties such as OM content, texture and CaCO 3 (Lagacherie et al 2008, Liu et al 2017. Several research studies have confirmed the high potentiality of the VIS-NIR spectroscopy to determine and discriminate between soil profiles and to provide information about the influence of soil properties on soil reflectance (Zeng et al 2016, andBaron et al 2011) but at present, few or even no, confirmatory studies have been conducted to discriminate between topsoils of different soil types using the data of the VIS-NIR spectroscopy acquired in the field.…”

Section: Introductionmentioning

confidence: 99%

Potential of VIS-NIR spectroscopy to characterize and discriminate topsoils of different soil types in the Triffa plain (Morocco)

Lazaar¹,

Mahyou²,

Gholizadeh³

et al. 2019

Soil Science Annual

View full text Add to dashboard Cite

This study aims to identify the influence of soil organic matter (OM) content and calcium carbonates (CaCO3) on soil reflectance and select the optimum spectral bands for discriminating between topsoils of different soil types situated in the irrigated perimeter of the Triffa plain (Morocco) using VIS-NIR reflectance spectroscopy. Soil samples were collected from the plow layer in 26 sampling sites. The spectral measurements were conducted in the field using an ASD Fieldspec portable spectroradiometer (350–2500 nm), while the soil samples were analyzed in the laboratory. The spectral data were pre-processed to remove the noise effects and then analyzed with the CovSel (selected covariance) method, validated by linear discriminant analysis in order to select the most optimal spectral variables to discriminate between topsoils of different soil types in the plain. The results of the soils reflectance curves showed that low reflectance intensity marked the soils with high OM contents throughout the VIS spectrum. The influence of the soil OM content was very apparent in the VIS range (between 580–750 nm). Regarding the CaCO3 content, it was noted that the soil samples with a high percentage of CaCO3 increase the reflectance in all spectral domains situated between 350 and 2500 nm. The spectral bands of 1999, 686, 1280, 2340 and 1951 nm were the most optimal for the soil discrimination in the Triffa plain. This study concluded that the VIS-NIR spectroscopy demonstrates an excellent ability to characterize and discriminate between topsoils in the Triffa plain.

show abstract

Forensic Applications

Guerreiro

Lopez‐López

Ossa

et al. 2015

Analytical Separation Science

View full text Add to dashboard Cite

The forensic process encompasses many stages from the initial investigation of a crime scene to the presentation of witness testimony in court. Most of the current analytical techniques used to analyze forensic evidence require a sample preparation prior to the analytical stage. This chapter provides an overview of the novel sample preparation modes, published up to date, for samples of forensic interest. This information has been grouped into the three following themes: explosives and related samples, drugs and toxicological analysis, and other forensic samples. The identification of explosives and related samples has become a heightened priority in recent years for homeland security and counterterrorism applications. The chapter also discusses drug analyses and forensic toxicology. A transition to noninvasive and nondestructive analysis avoiding any sample treatment is expected in the near future for most forensic evidence.

show abstract

Chemometric Study on the Forensic Discrimination of Soil Types Using Their Infrared Spectral Characteristics

Abstract: 14Soil has been utilized in criminal investigations for some time because of its prevalence and 15 transferability. It is usually the physical characteristics that are studied, however the research

Cited by 20 publications

References 18 publications

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis

Potential of VIS-NIR spectroscopy to characterize and discriminate topsoils of different soil types in the Triffa plain (Morocco)

Forensic Applications

Contact Info

Product

Resources

About