Continuous wavelets for the improved use of spectral libraries and hyperspectral data

Abstract. Classification of urban materials using remote sensing data, in particular hyperspectral data, is common practice. Spectral libraries can be utilized to train a classifier since they provide spectral features about selected urban materials. However, urban materials can have similar spectral characteristic features due to high inter-class correlation which can lead to misclassification. Spectral libraries rarely provide imagery of their samples, which disables the possibility of classifying urban materials with additional textural information. Thus, this paper conducts material classification comparing the benefits of using close-range acquired spectral and textural features. The spectral features consist of either the original spectra, a PCA-based encoding or the compressed spectral representation of the original spectra retrieved using a deep autoencoder. The textural features are generated using a deep denoising convolutional autoencoder. The spectral and textural features are gathered from the recently published spectral library KLUM. Three classifiers are used, the two well-established Random Forest and Support Vector Machine classifiers in addition to a Histogram-based Gradient Boosting Classification Tree. The achieved overall accuracy was within the range of 70–80% with a standard deviation between 2–10% across all classification approaches. This indicates that the amount of samples still is insufficient for some of the material classes for this classification task. Nonetheless, the classification results indicate that the spectral features are more important for assigning material labels than the textural features.

Download Full-text

A solar optical hyperspectral library of rare-earth-bearing minerals, rare-earth oxide powders, copper-bearing minerals and Apliki mine surface samples

Earth System Science Data ◽

10.5194/essd-13-923-2021 ◽

2021 ◽

Vol 13 (3) ◽

pp. 923-942

Author(s):

Friederike Koerting ◽

Nicole Koellner ◽

Agnieszka Kuras ◽

Nina Kristin Boesche ◽

Christian Rogass ◽

...

Keyword(s):

Rare Earth ◽

Near Infrared ◽

Spectral Characteristics ◽

Hyperspectral Data ◽

Reflectance Spectra ◽

High Tech ◽

Oxide Powders ◽

Surface Samples ◽

Copper Gold ◽

Spectral Libraries

Abstract. Mineral resource exploration and mining is an essential part of today's high-tech industry. Elements such as rare-earth elements (REEs) and copper are, therefore, in high demand. Modern exploration techniques from multiple platforms (e.g., spaceborne and airborne), to detect and map the spectral characteristics of the materials of interest, require spectral libraries as an essential reference. They include field and laboratory spectral information in combination with geochemical analyses for validation. Here, we present a collection of REE- and copper-related hyperspectral spectra with associated geochemical information. The libraries contain reflectance spectra from rare-earth element oxides, REE-bearing minerals, copper-bearing minerals and mine surface samples from the Apliki copper–gold–pyrite mine in the Republic of Cyprus. The samples were measured with the HySpex imaging spectrometers in the visible and near infrared (VNIR) and shortwave infrared (SWIR) range (400–2500 nm). The geochemical validation of each sample is provided with the reflectance spectra. The spectral libraries are openly available to assist future mineral mapping campaigns and laboratory spectroscopic analyses. The spectral libraries and corresponding geochemistry are published via GFZ Data Services with the following DOIs: https://doi.org/10.5880/GFZ.1.4.2019.004 (13 REE-bearing minerals and 16 oxide powders, Koerting et al., 2019a), https://doi.org/10.5880/GFZ.1.4.2019.003 (20 copper-bearing minerals, Koellner et al., 2019), and https://doi.org/10.5880/GFZ.1.4.2019.005 (37 copper-bearing surface material samples from the Apliki copper–gold–pyrite mine in Cyprus, Koerting et al., 2019b). All spectral libraries are united and comparable by the internally consistent method of hyperspectral data acquisition in the laboratory.

Download Full-text

Hyperspectral data influenced by sample matrix: the importance of building relevant reference spectral libraries to map materials of interest

Microscopy Research and Technique ◽

10.1002/jemt.22816 ◽

2017 ◽

Vol 80 (5) ◽

pp. 462-470 ◽

Cited By ~ 5

Author(s):

James C. K. Dillon ◽

Leonardo Bezerra ◽

María del Pilar Sosa Peña ◽

Nicole M. Neu-Baker ◽

Sara A. Brenner

Keyword(s):

Hyperspectral Data ◽

Sample Matrix ◽

Relevant Reference ◽

Spectral Libraries

Download Full-text

Frost Damage Assessment in Wheat Using Spectral Mixture Analysis

Remote Sensing ◽

10.3390/rs11212476 ◽

2019 ◽

Vol 11 (21) ◽

pp. 2476 ◽

Cited By ~ 2

Author(s):

Glenn J. Fitzgerald ◽

Eileen M. Perry ◽

Ken C. Flower ◽

J. Nikolaus Callow ◽

Bryan Boruff ◽

...

Keyword(s):

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Crop Protection ◽

Frost Damage ◽

Hyperspectral Data ◽

Spectral Mixture Analysis ◽

Mixture Analysis ◽

Data Set ◽

Spectral Libraries ◽

Spectral Mixture

Frost damage to broadacre crops can cause up to an 85% loss in productivity. Although growers have few options for crop protection from frost, a rapid method for assessing frost-induced sterility would allow for timely management decisions (e.g., cutting for hay and altering marketing strategies). Spectral mixture analysis (SMA) has shown success in mapping landscape components and was used with hyperspectral data collected on the canopy, heads, and leaves of wheat at different sites to determine if this could quantify frost damage. Spectral libraries were assembled from canopy components collected from local field sites to generate spectral libraries for SMA from which a series of fraction sets was derived. The frost (Fr) fraction was then used to estimate final yield as a means of measuring frost damage. The best-fitting Fr fractions to yield were derived from the same data set as the source Fr spectra, and these ranged over R2 = 0.58–0.75 at the canopy scale. It was clear that spectral signatures need to be collected at scale to assess frost damage. While Fr fractions were able to estimate yield there was no “universal” endmember set from which a Fr fraction could be derived. The normalized difference vegetation index (NDVI) was not able to estimate frost damage consistently. Future work requires determining whether there is a “universal” set of endmembers and a minimum set of targeted wavebands that could lead to multispectral instruments for frost assessment for use in ground and aerial sensors.

Download Full-text

Automatic tumor tissue classification of oncological esophageal resectates based on hyperspectral data

10.1055/s-0039-1695116 ◽

2019 ◽

Author(s):

M Maktabi ◽

H Köhler ◽

R Thieme ◽

JP Takoh ◽

SM Rabe ◽

...

Keyword(s):

Tumor Tissue ◽

Hyperspectral Data ◽

Tissue Classification

Download Full-text

AN AUTOMATIC APPROACH TO LOSSY COMPRESSION OF AVIRIS HYPERSPECTRAL DATA

Telecommunications and Radio Engineering ◽

10.1615/telecomradeng.v69.i6.80 ◽

2010 ◽

Vol 69 (6) ◽

pp. 537-563 ◽

Cited By ~ 1

Author(s):

N. N. Ponomarenko ◽

M. S. Zriakhov ◽

A. Kaarna

Keyword(s):

Lossy Compression ◽

Hyperspectral Data

Download Full-text

Estimating nitrogen contents of apple leaves based on hyperspectral parameter models at different phenophases

JOURNAL OF ADVANCES IN AGRICULTURE ◽

10.24297/jaa.v6i2.5377 ◽

2016 ◽

Vol 6 (2) ◽

pp. 942-952

Author(s):

Xicun ZHU ◽

Zhuoyuan WANG ◽

Lulu GAO ◽

Gengxing ZHAO ◽

Ling WANG

Keyword(s):

Neural Network ◽

Network Model ◽

Neural Network Model ◽

Bp Neural Network ◽

Shoot Growth ◽

Hyperspectral Data ◽

Estimation Model ◽

Apple Leaves ◽

Bp Neural Network Model ◽

Nitrogen Contents

The objective of the paper is to explore the best phenophase for estimating the nitrogen contents of apple leaves, to establish the best estimation model of the hyperspectral data at different phenophases. It is to improve the apple trees precise fertilization and production management. The experiments were done in 20 orchards in the field, measured hyperspectral data and nitrogen contents of apple leaves at three phenophases in two years, which were shoot growth phenophase, spring shoots pause growth phenophase, autumn shoots pause growth phenophase. The study analyzed the nitrogen contents of apple leaves with its original spectral and first derivative, screened sensitive wavelengths of each phenophase. The hyperspectral parameters were built with the sensitive wavelengths. Multiple stepwise regressions, partial least squares and BP neural network model were adopted in the study. The results showed that 551 nm, 716 nm, 530 nm, 703 nm; 543 nm, 705 nm, 699 nm, 756 nm and 545 nm, 702 nm, 695 nm, 746 nm were sensitive wavelengths of three phenophases. R551+R716, R551*R716, FDR530+FDR703, FDR530*FDR703; R543+R705, R543*R705, FDR699+FDR756, FDR699*FDR756and R545+R702, R545*R702, FDR695+FDR746, FDR695*FDR746 were the best hyperspectral parameters of each phenophase. Of all the estimation models, the estimated effect of shoot growth phenophase was better than other two phenophases, so shoot growth phenophase was the best phenophase to estimate the nitrogen contents of apple leaves based on hyperspectral models. In the three models, the 4-3-1 BP neural network model of shoot growth phenophase was the best estimation model. The R2 of estimated value and measured value was 0.6307, RE% was 23.37, RMSE was 0.6274.

Download Full-text