Nontronite mineral identification in nilgiri hills of tamil nadu using hyperspectral remote sensing

M, Vignesh Kumar; Yarakkula, Kiran

doi:10.1088/1757-899x/263/3/032001

Cited by 7 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although spectral detection technology is widely used, it also has some difficulties. (1) The detection accuracy is very high when the internal structure of the object is simple, similar to the consistent forms of inorganic matter, such as petroleum [25] and minerals [26]; however, for organic substances (such as seeds) with complex and unevenly distributed internal chemical components, it is difficult to detect substantial differences among varieties. (2) Spectra contain a high amount of information, but they also contain a high amount of interference information, such as redundancy and noise, which further increases the difficulty of identification.…”

Section: Introductionmentioning

confidence: 99%

Identification of Soybean Seed Varieties Based on Hyperspectral Imaging Technology

Zhu

Chao

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

Hyperspectral imaging is a nondestructive testing technology that integrates spectroscopy and iconology technologies, which enables us to quickly obtain both internal and external information of objects and identify crop seed varieties. First, the hyperspectral images of ten soybean seed varieties were collected and the reflectance was obtained. Savitzky-Golay smoothing (SG), first derivative (FD), standard normal variate (SNV), fast Fourier transform (FFT), Hilbert transform (HT), and multiplicative scatter correction (MSC) spectral reflectance pretreatment methods were used. Then, the feature wavelengths and feature information of the pretreated spectral reflectance data were extracted using competitive adaptive reweighted sampling (CARS), the successive projections algorithm (SPA), and principal component analysis (PCA). Finally, 5 classifiers, Bayes, support vector machine (SVM), k-nearest neighbor (KNN), ensemble learning (EL), and artificial neural network (ANN), were used to identify seed varieties. The results showed that MSC-CARS-EL had the highest accuracy among the 90 combinations, with training set, test set, and 5-fold cross-validation accuracies of 100%, 100%, and 99.8%, respectively. Moreover, the contribution of spectral pretreatment to discrimination accuracy was higher than those of feature extraction and classifier selection. Pretreatment methods determined the range of the identification accuracy, feature-selective methods and classifiers only changed within this range. The experimental results provide a good reference for the identification of other crop seed varieties.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Soybean Seed Varieties Based on Hyperspectral Imaging Technology

Zhu

Chao

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…With the help of remote sensing the radiations can be sensed outside the visible range of 400 nm to 700 nm. The variety of applications of remote sensing are land use and land cover mapping, mineral mapping [1], agriculture mapping, change detection with respect to land cover, vegetation analysis, water table applications, mineral identification [2] and lithological mapping [3], fault fracture analysis, snow analysis and many more.…”

Section: Introductionmentioning

confidence: 99%

Unearthing the Lonar Crater Using Hyperspectral Remote Sensing and Validating Through Non-destructive Approach

Gore¹,

Mishra²,

Deshmukh³

et al. 2023

Advances in Computer Science Research

View full text Add to dashboard Cite

Remote Sensing is a prominent technology, applied at all fields of earth science. It is useful in the identification and mapping of minerals, vegetation, different materials and backgrounds by capturing the electromagnetic energy reflected from them. The analysis of remote places or structures is possible with the help of remote sensing with economic and timely manner. So, the proposed work focuses on exploring the Lonar crater with the help of remote sensing. The earth surface is enriched with number of useful minerals. Minerals are very important resources contributing in the wealth of a country. So, this work focused on mineral mapping and mineral identification at Lonar Crater by using high resolution hyperspectral images acquired by Hyperion sensor. The validation of minerals identified with hyperspectral imaging was completed by the use of nondestructive approach of spectroradiometer.The various minerals are identified by imaging analysis and validated through non-destructive approach. The significant results of the proposed methodology are: i) the type of rock at the Lonar crater is identified as basaltic igneous rocks, ii) the origin of Lonar crater is due to the extrusive volcanic activity and iii) The Lonar lake is saline in nature. The Spectral Classification using SAM gave accuracy of 89.01% with 0.8753 kappa coefficient and SVM technique, gave the accuracy of 97.25% with 0.9688 kappa coefficient indicating more match with the ground truth.

show abstract

Unsupervised Learning Method for Mineral Identification from Hyperspectral Data

Prabhavathy

Tripathy

Venkatesan

2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Nontronite mineral identification in nilgiri hills of tamil nadu using hyperspectral remote sensing

Cited by 7 publications

References 9 publications

Identification of Soybean Seed Varieties Based on Hyperspectral Imaging Technology

Identification of Soybean Seed Varieties Based on Hyperspectral Imaging Technology

Unearthing the Lonar Crater Using Hyperspectral Remote Sensing and Validating Through Non-destructive Approach

Unsupervised Learning Method for Mineral Identification from Hyperspectral Data

Contact Info

Product

Resources

About