Spectral regionalization of tropical soils in the estimation of soil attributes

Demattê, José Alexandre Melo; Bellinaso, Henrique; Araújo, Suzana Romeiro; Rizzo, Rodnei; Souza, Arnaldo Barros e

doi:10.5935/1806-6690.20160071

Cited by 18 publications

(14 citation statements)

References 21 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the bands from 2,100 to 2,200 nm (Viscarra Rossel, 2011; Demattê et al, 2016), valleys that are characteristic of kaolinite (Kt) were observed in the spectral curves, and, in the band at 2,265 nm (Demattê et al, 2000;Pizarro et al, 2001), valleys that are typical of gibbsite (Gb). All the studied soils showed valleys in the spectral curves that are characteristic of Kt (Figure 1), but only some had valleys characteristic of Gb.…”

Section: Resultsmentioning

confidence: 99%

“…Understanding soils, considering all their attributes and processes of formation, is essential to monitor them (Viscarra Rossel et al, 2016). However, laboratory analyses are generally costly and time-consuming, restricting the number of samples representative of a region (Viscarra Rossel, 2011;Bahia et al, 2015;Demattê et al, 2016). In this context, the use of spectral signature emerges as an alternative methodology for this task.…”

Section: Introductionmentioning

confidence: 99%

“…Diffuse reflectance spectroscopy (DRS) and magnetic susceptibility (MS) are alternative techniques that can be used to estimate soil properties such as: iron oxides (Viscarra Rossel et al, 2010;Bahia et al, 2015); silicate minerals, including kaolinite, illite, and smectite (Viscarra Rossel, 2011;Mulder et al, 2013); chemical attributes and grain size Demattê et al, 2016;Viscarra Rossel et al, 2016); phosphorus adsorption (Camargo et al, 2015;Peluco et al, 2015); and soil color (Aquino et al, 2016;Carmo et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

“…Demattê et al (2016) assessed models for the prediction of soil attributes that were generated using a spectral database from multiple locations. According to these authors, the more complete and broad a spectral library of soils is in a given region, the better will be the quality of the evaluation of the attributes, processes, and management of such soils.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Magnetic and spectral signatures of Cerrado soils in the state of Goiás, Brazil

Fernandes

Ribon

Marques

et al. 2017

Pesq. agropec. bras.

View full text Add to dashboard Cite

-The objective of this work was to estimate the iron oxide contents (hematite and goethite) and to characterize the color and the spectral and magnetic signatures of Cerrado soils in the state of Goiás, Brazil. Six Oxisols and one Inceptisol were studied. Spectral and magnetic signatures were determined by diffuse reflectance spectroscopy (DRS) and magnetic susceptibility, respectively. Then, the spectral curves and the second derivative calculations were used to determine hematite and goethite contents, as well as soil color after conversion into tristimulus values. Hematite and goethite contents were also obtained by x-ray diffractometry, and soil color was also defined in the field (Munsell color chart). The values for the isomorphic substitution of iron by aluminum and the degree of redness were also determined. DRS can be used to estimate hematite and goethite contents, as well as the color of Cerrado soils in the state of Goiás. The spectral signature can point out the main soil properties related to the contents of organic matter, iron oxides, kaolinite, and gibbsite. The magnetic signature, characteristic of soils rich in iron oxides (hematite and goethite), shows the predominance of pedogenic minerals.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Magnetic and spectral signatures of Cerrado soils in the state of Goiás, Brazil

Fernandes

Ribon

Marques

et al. 2017

Pesq. agropec. bras.

View full text Add to dashboard Cite

show abstract

“…For example, Local regression is a promising modeling strategy especially for diverse datasets with large soil variations [40,42,51]. Testing the applicability of the SSR to large diverse and heterogeneous soil spectral dataset [52,53] would be a meaningful task in the future. Moreover, investigating the compatibility of SSR with these modeling strategies and techniques might be meaningful for further studies.…”

Section: Discussionmentioning

confidence: 99%

Improving Spectral Estimation of Soil Organic Carbon Content through Semi-Supervised Regression

et al. 2017

View full text Add to dashboard Cite

Visible and near infrared (VIS-NIR) spectroscopy has been applied to estimate soil organic carbon (SOC) content with many modeling strategies and techniques, in which a crucial and challenging problem is to obtain accurate estimations using a limited number of samples with reference values (labeled samples). To solve such a challenging problem, this study, with Honghu City (Hubei Province, China) as a study area, aimed to apply semi-supervised regression (SSR) to estimate SOC contents from VIS-NIR spectroscopy. A total of 252 soil samples were collected in four field campaigns for laboratory-based SOC content determinations and spectral measurements. Semi-supervised regression with co-training based on least squares support vector machine regression (Co-LSSVMR) was applied for spectral estimations of SOC contents, and it was further compared with LSSVMR. Results showed that Co-LSSVMR could improve the estimations of SOC contents by exploiting samples without reference values (unlabeled samples) when the number of labeled samples was not excessively small and produce better estimations than LSSVMR. Therefore, SSR could reduce the number of labeled samples required in calibration given an accuracy threshold, and it holds advantages in SOC estimations from VIS-NIR spectroscopy with a limited number of labeled samples. Considering the increasing popularity of airborne platforms and sensors, SSR might be a promising modeling technique for SOC estimations from remotely sensed hyperspectral images.

show abstract

Calibration set optimization and library transfer for soil carbon estimation using soil spectroscopy—A review

Dorantes

Fuentes

Miller

2022

Soil Science Soc of Amer J

View full text Add to dashboard Cite

Resource-efficient techniques for accurate soil property estimation are necessary to satisfy the increasing demand for soil data to support environmental monitoring, precision agriculture, and spatial modeling. Over the last 30 yr, infrared soil spectroscopy has developed into a rapid, robust, and cost-effective technique for soil carbon analysis. Ongoing global efforts to make soil spectroscopy operational require the development of soil spectral libraries, which are the main source of data for the construction of calibration models. Understanding calibration optimization is important to ensure the efficient use of soil spectral libraries for the accurate estimation of soil carbon. Moreover, spectral library transfer can benefit new data collection, soil monitoring, and modeling efforts. This review presents techniques for optimization of calibration models and library transfer. Selection of calibration set size and subsetting are presented as current calibration optimization techniques. Moreover, spiking is discussed as an effective technique for spectral library transfer. Overall, studies have suggested that an increase in calibration size improves model performance and this continues until an optimal size is reached. Additionally, subsetting can improve model performance if the resulting subsets reduce the variability of spectrally active components. Studies have also suggested that spiking is effective when used in conjunction with subsetting techniques. These findings denote the current applicability and potential of optimization and library transfer techniques for the accurate estimation of soil carbon with soil spectroscopy. Future efforts should focus on refining

show abstract

Spectral regionalization of tropical soils in the estimation of soil attributes

Cited by 18 publications

References 21 publications

Magnetic and spectral signatures of Cerrado soils in the state of Goiás, Brazil

Magnetic and spectral signatures of Cerrado soils in the state of Goiás, Brazil

Improving Spectral Estimation of Soil Organic Carbon Content through Semi-Supervised Regression

Calibration set optimization and library transfer for soil carbon estimation using soil spectroscopy—A review

Contact Info

Product

Resources

About