scholarly journals A Comparison of Feature-Based MLR and PLS Regression Techniques for the Prediction of Three Soil Constituents in a Degraded South African Ecosystem

2012 ◽  
Vol 2012 ◽  
pp. 1-20 ◽  
Author(s):  
Anita Bayer ◽  
Martin Bachmann ◽  
Andreas Müller ◽  
Hermann Kaufmann
Keyword(s):  
Reference Data ◽  
Imaging Spectroscopy ◽  
Clay Content ◽  
Absorption Feature ◽  
Least Squares Regression ◽  
Soil Constituent ◽  
Feature Based ◽  
Regression Techniques ◽  
Soil Constituents ◽  
Land Changes

The accurate assessment of selected soil constituents can provide valuable indicators to identify and monitor land changes coupled with degradation which are frequent phenomena in semiarid regions. Two approaches for the quantification of soil organic carbon, iron oxides, and clay content based on field and laboratory spectroscopy of natural surfaces are tested. (1) A physical approach which is based on spectral absorption feature analysis is applied. For every soil constituent, a set of diagnostic spectral features is selected and linked with chemical reference data by multiple linear regression (MLR) techniques. (2) Partial least squares regression (PLS) as an exclusively statistical multivariate method is applied for comparison. Regression models are developed based on extensive ground reference data of 163 sampled sites collected in the Thicket Biome, South Africa, where land changes are observed due to intensive overgrazing. The approaches are assessed upon their prediction performance and significance in regard to a future quantification of soil constituents over large areas using imaging spectroscopy.

Sodium-fluoride pH of South-Western Australian soils as an indicator of P-sorption

Soil Research ◽  
1994 ◽  
Vol 32 (4) ◽  
pp. 755 ◽  
Author(s):  
RJ Gilkes ◽  
JC Hughes
Keyword(s):  
Clay Minerals ◽  
Iron Oxides ◽  
Sorption Capacity ◽  
Sodium Fluoride ◽  
Secondary Importance ◽  
P Sorption ◽  
Soil Constituent ◽  
Western Australian ◽  
Soil Constituents ◽  
Measuring Ph

Phosphate sorption by the surface horizon of 228 acid to neutral Western Australian (W.A.) soils is more closely related (r(2) = 0.76) to the content of oxalate-extractable aluminium than to any other soil constituent. This fraction corresponds to poorly ordered inorganic and organic Al compounds that release considerable amounts of OH- to NaF solution. Thus the abundance of these compounds in soil may be estimated by measurement of the pH of a NaF extract (pH((NaF)) This association enables the rapid and moderately accurate prediction in the field of the P-sorption capacity of soils (r(2) = 0.72) by measuring pH(NaF) With a. simple, portable pH meter. For many W.A. soils, it is probable that well crystalline aluminium and iron oxides, clay minerals and other soil constituents are of secondary importance in determining P-sorption and that most P-sorption is due to poorly ordered and organically complexed forms of Al.

Sulfide detection in drill core from the Stillwater Complex using visible/near‐infrared imaging spectroscopy

Geophysics ◽  
2003 ◽  
Vol 68 (5) ◽  
pp. 1561-1568 ◽  
Author(s):  
Brock J. Bolin ◽  
Thomas S. Moon
Keyword(s):  
Metal Ion ◽  
Imaging Spectroscopy ◽  
Visible Region ◽  
Sulfide Minerals ◽  
Absorption Feature ◽  
Drill Core ◽  
Mining Operations ◽  
Stillwater Complex ◽  
Imaging Spectrometer ◽  
Point Count

This feasibility study examines the potential of imaging spectroscopy to estimate sulfide percentage in drill core from the Stillwater Complex, Montana. The Stillwater Complex is a layered mafic to ultramafic intrusion hosting ore‐grade platinum group elements within the zone known as the JM Reef. Stillwater Mine geologists indirectly infer the platinum/palladium grade by the presence and abundance of sulfide minerals. In order to discriminate between waste and ore rock, geologists visually inspect the core and working faces for minerals such as chalcopyrite, pentlandite, and pyrrhotite. Iron sulfide minerals have a strong ultraviolet absorption that blends into the blue portion of the visible region and produces their yellow luster. The spectral differences between these pathfinder minerals and the accessory minerals are sufficiently distinct to allow classification of this mineralogy using imaging spectroscopy even in the absence of a particular absorption feature. Five different sections of split core from the JM Reef were chosen for their representative mineralogical character. The surface of each sample was scanned with Montana Tech's prototype Airborne and Laboratory Imaging Spectrometer (ALIS) and the images were analyzed for sulfides. For validation, the amount of sulfides was independently determined visually with counting grids. The imaging spectrometer results correlate well with the point‐count percentage, although all five samples consistently fall below the point‐count average. This underestimation is possibly due to metal ion substitution, linear mixing at mineral boundaries, or anisotropic scattering due to the high spatial resolution of the spectrometer. The success of this experiment suggests possible machine vision applications in future mining operations, such as automation of core logging and downhole instrumentation.

Quantitative measurement of complex substances dissolved in an ionic liquid using IR spectroscopy and chemometrics

2017 ◽  
Vol 84 (1) ◽  
Author(s):  
Johannes Kiefer ◽  
Andreas Bösmann ◽  
Peter Wasserscheid
Keyword(s):  
Principal Component Analysis ◽  
Ionic Liquid ◽  
Principal Component Regression ◽  
Principal Component ◽  
Component Analysis ◽  
Least Squares Regression ◽  
Catalytically Active ◽  
Regression Techniques ◽  
Active Substances ◽  
Better Than

AbstractIn the past two decades, ionic liquids have found many applications as solvents for complex solutes. Prominent examples are the dissolution of biomass and carbohydrates as well as catalytically active substances. The chemical analysis of such solutions, however, is still a challenge due to the molecular complexity. In the present work, the use of infrared spectroscopy for quantifying the concentration of different solutes dissolved in an imidazolium-based ionic liquid is investigated. Binary solutions of glucose, cellubiose, and Wilkinson's catalyst in 1-ethyl-3-methylimidazolium acetate are studied as examples. For this purpose, different chemometric approaches (principal component analysis (PCA), partial least-squares regression (PLSR), and principal component regression (PCR)) for analyzing the spectra are tested. Principal component analysis was found to be suitable for classifying the different solutions. Both regression techniques were capable of deriving accurate concentration values. The performance of PLSR was slightly better than that of PCR for the same number of components.

scholarly journals Civil war and the spread of AIDS in Central Africa

1991 ◽  
Vol 107 (1) ◽  
pp. 69-80 ◽  
Author(s):  
M. R. Smallman-Raynor ◽  
A. D. Cliff
Keyword(s):  
Geographical Distribution ◽  
Central Africa ◽  
Subsequent Development ◽  
Ordinary Least Squares ◽  
Least Squares Regression ◽  
African Countries ◽  
Regression Techniques ◽  
And Control ◽  
First Time ◽  
Hiv 1

SUMMARYUsing ordinary least squares regression techniques this paper demonstrates, for the first time, that the classic association of war and disease substantially accounts for the presently observed geographical distribution of reported clinical AIDS cases in Uganda. Both the spread of HIV 1 infection in the 1980s, and the subsequent development of AIDS to its 1990 spatial pattern, are shown to be significantly and positively correlated with ethnic patterns of recruitment into the Ugandan National Liberation Army (UNLA) after the overthrow of Idi Amin some 10 years earlier in 1979. This correlation reflects the estimated mean incubation period of 8–10 years for HIV 1 and underlines the need for cognizance of historical factors which may have influenced current patterns of AIDS seen in Central Africa. The findings may have important implications for AIDS forecasting and control in African countries which have recently experienced war. The results are compared with parallel analyses of other HIV hypotheses advanced to account for the reported geographical distribution of AIDS in Uganda.

scholarly journals X-ray AGN; The View from ASCA

1995 ◽  
Vol 10 ◽  
pp. 513-516 ◽  
Author(s):  
Hideyo Kunieda
Keyword(s):  
Imaging Spectroscopy ◽  
High Sensitivity ◽  
Low Energy ◽  
Absorption Feature ◽  
X Rays ◽  
Considerable Contribution ◽  
X Ray ◽  
Multiple Components ◽  
X Ray Imaging ◽  
Broad Energy

ASCA capability of X-ray imaging spectroscopy up to 10 keV. allows us to examine the emission and absorption feature from AGN. Warm absorber, low energy lines and broad iron K lines are confirmed from Sy I’s. High sensitivity in broad energy band makes it possible to distinguish multiple components emerged by different processes. Detection of X-rays from faint sources tells us various galaxies may harbor AGN sometimes with obscuration tori. They might have considerable contribution to CXB.

Using Inquiry-Based Methods to Teach Spatial Statistics

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Andrew J. Gregory ◽  
Emma S. Spence
Keyword(s):  
Spatial Statistics ◽  
Spatial Regression ◽  
Ordinary Least Squares ◽  
Data Sets ◽  
Least Squares Regression ◽  
Data Set ◽  
Higher Level Thinking ◽  
Interesting Approach ◽  
Regression Techniques ◽  
Undergraduate Statistics

Spatial statistics and experimental design are among the most important topics students in the environmental and ecological sciences learn and utilize throughout their careers. These topics are also among the most difficult for students to learn, often due to the use of contrived data sets that present simplified and unrealistic scenarios that fail to engage students in higher level thinking. One way to engage students in higher level thinking is to use an inquiry-based pedagogical framework. The use of inquiry as a pedagogical approach should be instinctive for most scientists, as it mimics how science is conducted, yet most instructors continue to use lecture-based, textbook-driven instructional formats. This type of approach is efficient in covering material, but it suffers in its ability to engage students or enhance learning. Using a Bigfoot data set in an inquiry-based framework, students in a cross-listed graduate/undergraduate statistics class learned ordinary least squares regression and geographically weighted regression techniques. These techniques are among the most frequently applied analyses in the natural sciences. The use of a Bigfoot data set engaged students’ interest, rendering the prospect of learning regression topics as an emergent property of their interest and engagement. This approach also has an additional benefit in that students learned not only key statistical concepts but also learn how to self-diagnose deficiencies with their models as well as how to identify strategies to overcome these deficiencies. We hope that both instructors and students in graduate and undergraduate statistics or spatial modeling courses find this case study, and included data sets, a useful and interesting approach to teach and learn regression and spatial regression.

scholarly journals Wavelet geographically weighted regression for spectroscopic modelling of soil properties

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yongze Song ◽  
Zefang Shen ◽  
Peng Wu ◽  
R. A. Viscarra Rossel
Keyword(s):  
Organic Carbon ◽  
Soil Properties ◽  
Geographically Weighted Regression ◽  
Near Infrared ◽  
Linear Models ◽  
Spatial Information ◽  
Clay Content ◽  
Weighted Regression ◽  
Organic Carbon Content ◽  
Least Squares Regression

AbstractSoil properties, such as organic carbon, pH and clay content, are critical indicators of ecosystem function. Visible–near infrared (vis–NIR) reflectance spectroscopy has been widely used to cost-efficiently estimate such soil properties. Multivariate modelling, such as partial least squares regression (PLSR), and machine learning are the most common methods for modelling soil properties with spectra. Often, such models do not account for the multiresolution information presented in the vis–NIR signal, or the spatial variation in the data. To address these potential shortcomings, we used wavelets to decompose the vis–NIR spectra of 226 soils from agricultural and forested regions in south-western Western Australia and developed a wavelet geographically weighted regression (WGWR) for estimating soil organic carbon content, clay content and pH. To evaluate the WGWR models, we compared them to linear models derived with multiresolution data from a wavelet decomposition (WLR) and PLSR without multiresolution information. Overall, validation of the WGWR models produced more accurate estimates of the soil properties than WLR and PLSR. Around 3.5–49.1% of the improvement in the estimates was due to the multiresolution analysis and 1.0–5.2% due to the integration of spatial information in the modelling. The WGWR improves the modelling of soil properties with spectra.

scholarly journals Estimation of effective calibration sample size using visible near infrared spectroscopy: deep learning vs machine learning

2019 ◽  
Author(s):  
Wartini Ng ◽  
Budiman Minasny ◽  
Wanderson de Sousa Mendes ◽  
José A. M. Demattê
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Soil Properties ◽  
Sample Size ◽  
Near Infrared ◽  
Model Performance ◽  
Clay Content ◽  
Least Squares Regression ◽  
Soil Attributes ◽  
Calibration Dataset

Abstract. The number of samples used in the calibration dataset affects the quality of the generated predictive models using visible, near and shortwave infrared (VIS-NIR-SWIR) spectroscopy for soil attributes. Recently, convolutional neural network (CNN) is regarded as a highly accurate model for predicting soil properties on a large database, however it has not been ascertained yet how large the sample size should be for CNN model to be effective. This paper aims at providing an estimate of how much calibration samples are needed to improve the model performance of soil properties predictions with CNN. It is hypothesized that the larger the amount of data, the more accurate is the CNN model. The performance of two commonly used machine learning models (Partial least squares regression (PLSR) and Cubist) are compared against the CNN model. A VIS-NIR-SWIR spectral library from Brazil containing 4251 unique sites, with averages of 2–3 samples per depth (a total of 12,044 samples), was divided into calibration (3188 sites) and validation (1063 sites) sets. A subset of the calibration dataset was then created to represent smaller calibration dataset ranging from 125, 300, 500, 1000, 1500, 2000, 2500 and 2700 unique sites, or equivalent to sample size approximately 350, 840, 1400, 2800, 4200, 5600, 7000, and 7650. All three models (PLSR, Cubist, and CNN models) were generated for each sample size of the unique sites for the prediction of five different soil properties, i.e. cation exchange capacity, organic matter, sand, silt and clay content. These calibration subset sampling processes and modelling were repeated ten times to provide a better representation of the model performances. Similar results were observed when the performances of both PLSR and Cubist model were compared to the CNN model where the performance of CNN outweighed the PLSR and Cubist model at sample size of 1500 and 1800 respectively. It can be recommended that deep learning is most efficient for spectral modelling for sample size above 2000. The accuracy of the PLSR and Cubist model seemed to reach a plateau above sample size of 4200 and 5000 respectively. A sensitivity analysis was performed on the CNN model to determine important wavelengths region that affected the predictions of various soil attributes.

Sign in / Sign up

Export Citation Format

Share Document