Hyperspectral Analysis Techniques Research Articles

A novel framework to assess apple leaf nitrogen content: Fusion of hyperspectral reflectance and phenology information through deep learning

Rapid and accurate assessment of apple-tree leaf nitrogen content (LNC) plays an important role in smart orchards for accurate fertilization. Hyperspectral remote sensing technology provides a reliable, economical, and fast method to estimate LNC. However, high-dimensional spectral data contain redundant information that is irrelevant to the target parameters, necessitating the development of robust hyperspectral analysis techniques to estimate apple-tree LNC. Additionally, the role of phenological information in improving LNC estimates across multiple growth stages remains uncertain. The present study thus proposes a novel hyperspectral data-processing framework (Boruta-Iteration-DNN) to optimize estimates of apple-tree LNC and investigates the potential of phenological information to improve LNC estimates of multi-fertility apple trees. The proposed framework incorporates the Boruta feature-selection method for identifying important spectral bands and assessing how they affect model performance through iterative feature analysis. A deep neural network (DNN) regression model is then developed for LNC estimation. In addition, a widely used Pearson-DNN method is used for comparison to demonstrate the superiority of the proposed approach. Furthermore, the potential of incorporating phenological information (Day After Anthesis, DAA) into the estimation models is examined to evaluate its ability to better estimate LNC. The results demonstrate that the proposed framework not only enhances the accuracy of apple-tree LNC estimates with respect to the full-spectrum model (without DAA: validation R2 improved from 0.69 to 0.75, NRMSE reduced from 11.92 % to 9.97 %; with DAA: validation R2 improved from 0.72 to 0.79, NRMSE reduced from 11.09 % to 9.06 %), but also reduces the complexity and dimensionality of the models by eliminating 96 % of the redundant spectral bands (2015 bands). Moreover, the inferior results of the Pearson-Iteration-DNN framework further underscore the effectiveness of the Boruta method in selecting relevant spectral bands. Additionally, including the DAA phenological information enhances the accuracy of all models (the total R2 of training and validation increased by 0.05 ∼ 0.12, and the total NRMSE reduced by 1.49 % ∼ 1.93 %). These findings highlight the ability of DNN models integrated with hyperspectral data and phenological information to accurately assess LNC in apple trees, thereby offering valuable guidance to orchard management for developing precise fertilization strategies.

Towards the Concurrent Execution of Multiple Hyperspectral Imaging Applications by Means of Computationally Simple Operations

The on-board processing of remotely sensed hyperspectral images is gaining momentum for applications that demand a quick response as an alternative to conventional approaches where the acquired images are off-line processed once they have been transmitted to the ground segment. However, the adoption of this on-board processing strategy brings further challenges for the remote-sensing research community due to the high data rate of the new-generation hyperspectral sensors and the limited amount of available on-board computational resources. This situation becomes even more stringent when different time-sensitive applications coexist, since different tasks must be sequentially processed onto the same computing device. In this work, we have dealt with this issue through the definition of a set of core operations that extracts spectral features useful for many hyperspectral analysis techniques, such as unmixing, compression and target/anomaly detection. Accordingly, it permits the concurrent execution of such techniques reusing operations and thereby requiring much less computational resources than if they were separately executed. In particular, in this manuscript we have verified the goodness of our proposal for the concurrent execution of both the lossy compression and anomaly detection processes in hyperspectral images. To evaluate the performance, several images taken by an unmanned aerial vehicle have been used. The obtained results clearly support the benefits of our proposal not only in terms of accuracy but also in terms of computational burden, achieving a reduction of roughly 50% fewer operations to be executed. Future research lines are focused on extending this methodology to other fields such as target detection, classification and dimensionality reduction.

Satellite-based spectral mapping (ASTER and landsat data) of mineralogical signatures of beach sediments: a precursor insight

Detailed investigation on texture and mineralogy of beach sediments helps to understand their nature of deposition and potential targets of strategic mineral deposits. The beach sediments from the coast of Thiruvananthapuram, the southernmost district of Kerala, India, have been studied to understand the variation in grain size by using the spectral indices as derived from the visible-NIR-TIR bands of Landsat and ASTER remote sensing data. Further, an attempt has been made to map the distribution of strategic minerals present in beach sands using standardized hyperspectral analysis techniques. The grain size shows a remarkable variation from medium sand to fine sand. The THM (Total Heavy Minerals) content was estimated to about 80.04% and 52.33% along the coast of Kovalam and Varkala, respectively. The ilmenite mineral predominantly exists in these areas, followed by monazite, sillimanite, rutile, zircon, garnet, leucoxene, and Kyanite. The hyperspectral analysis extracts two endmembers of ilmenite and light minerals from the Landsat and ASTER imagery, which could be successfully, mapped using the SAM classification algorithm. The satellite-derived map showing texture and mineralogy has been validated with the results of laboratory analysis and shows strong correlation almost in all locations. This study illustrates the potential use of satellite remote sensing techniques for the mapping of natural resources, especially mineral resources.

HYPERSPECTRAL ANALYSIS OF ASTER AND LANDSAT 8 DATA TO CHARACTERIZE EL-MISSIKAT URANIUM BEARING SILICEOUS VEINS AND THEIR ANALOGY TO EL-ERADIYA AND GATTAR GRANITES, EASTERN DESERT, EGYPT

This work aims to apply spectral image processing techniques that have been used often to processhyperspectral data to analyze multispectral ASTER (Advanced Spaceborne Thermal Emission andReflection Radiometer) and Landsat 8 data for mapping uranium-bearing siliceous rocks within El-Missikat granite. These techniques succeeded effectively in recognition of the same features at El-Eradiyaand Gattar granites. Siliceous materials (siliceous sinter), as used here, is a spectral group of SiO2 mineralsincluding opal, chalcedony and cristobalite derived from hydrothermal fluids and/or the decomposition ofgranite. The spectral identification of such minerals depend mainly on the uses a hydration absorptionfeature that characterize some hydrated silica at wavelength region of 2.2- to 2.4-μm.The effectiveness of the hyperspectral analysis techniques used to compare a pixel spectrum with thespectra of known pure materials, extracted from the spectral end member selection procedures, includingminimum noise fraction (MNF), pixel purity index (PPI) and n-dimensional visualization. Among thoseof the spectral analysis algorithms employed, spectral angle mapping (SAM) and matched filtering (MF)produced accurate classifications that were close to the ground reference data. The hyperspectralanalysis of an ASTER and Landsat 8 dataset covering the studied areas, has successfully effective indetecting lithological units than traditional multispectral analysis procedures.Field validation and laboratory investigation were carried out to prove and support the resultsobtained from ASTER and Landsat 8 processing. These results succeeded to delineate additional sitesof siliceous materials that could be a promising areas to host the uranium mineralization.

Mapping Pure Mangrove Patches in Small Corridors and Sandbanks Using Airborne Hyperspectral Imagery

Taijiang National Park (TNP) of Taiwan is the northernmost geographical position of mangrove habitats in the Northern Hemisphere. Instead of occupying a vast region with a single species, the mangroves in TNP are usually mingled with other plants in a narrow corridor along the water or in groups on a small sandbank. The multi-spectral images acquired from the spaceborne platforms are therefore limited in mapping the abundance and distribution of the mangrove species in TNP. We report the work of mapping pure mangrove patches in small corridors and sandbanks in TNP using airborne Compact Airborne Spectrographic Imager (CASI) hyperspectral imagery. Bu considering the similarity of spectral reflectance among three species of mangrove and other plants, we followed the concept of supervised classification to select a few training areas with known mangrove trees, where the training areas are determined from the detailed map of mangrove distribution derived from the field investigation. The Hourglass hyperspectral analysis technique was employed to identify the endmembers of pure mangrove in the training areas. The results are consistent with the current distribution of mangrove trees, and the remarkable feature of a “mangrove desert” highlights a fact that biodiversity can be easily and quickly destroyed if no protection is provided. Some remnant patches located by this research are very important to the management of mangrove trees.

Unsupervised Clustering and Active Learning of Hyperspectral Images With Nonlinear Diffusion

The problem of unsupervised learning and segmentation of hyperspectral images is a significant challenge in remote sensing. The high dimensionality of hyperspectral data, presence of substantial noise, and overlap of classes all contribute to the difficulty of automatically clustering and segmenting hyperspectral images. We propose an unsupervised learning technique called spectral-spatial diffusion learning (DLSS) that combines a geometric estimation of class modes with a diffusion-inspired labeling that incorporates both spectral and spatial information. The mode estimation incorporates the geometry of the hyperspectral data by using diffusion distance to promote learning a unique mode from each class. These class modes are then used to label all the points by a joint spectral-spatial nonlinear diffusion process. A related variation of DLSS is also discussed, which enables active learning by requesting labels for a very small number of well-chosen pixels, dramatically boosting overall clustering results. Extensive experimental analysis demonstrates the efficacy of the proposed methods against benchmark and state-of-the-art hyperspectral analysis techniques on a variety of real data sets, their robustness to choices of parameters, and their low computational complexity.

Shortwave infrared (1.0–2.5 μm) hyperspectral imaging of the Athabasca West Grand Rapids Formation oil sands

Previous work on the reflectance spectroscopy of oil sands has focused exclusively on the McMurray Formation of the Athabasca deposit. However, as industrial development expands into other formations, spectral research on Alberta’s other bitumen reservoirs is warranted. This study presents the first investigation of shortwave infrared (SWIR; 1.0–2.5 μm) hyperspectral imaging of Grand Rapids Formation oil sands. Comparing the spectral properties of Grand Rapids oil sands to that of the McMurray Formation reveals some key differences. Grand Rapids oil sands have lower overall reflectance and deeper 1.4- and 1.9-μm absorption features than McMurray oil sands of the same ore grade. At ore grades greater than 10 wt. %, Grand Rapids oil sands also have shallower bitumen absorption features. These spectral differences may be attributed to the mineralogical differences between the two formations, namely, structural water in K-feldspar. Hyperspectral analysis techniques that have been previously developed for McMurray oil sands were tested on a Grand Rapids Formation core. Using contrast stretching and the three-band combination of R e 2.05 μm, G e 2.13 μm, and B e 2.28 μm (where R, G, and B refer to red, green, and blue channels), the visibility of sedimentological features was enhanced in SWIR imagery. With a simple recalibration, an established spectral model for the estimation of total bitumen content (TBC) produced results in close agreement with Dean–Stark analysis data (coefficient of determination [R2] e 0.92, ±1.1 wt. %) and of similar accuracy to what has been previously demonstrated for the McMurray Formation. The results of this study suggest that with minor adjustments, oil sands spectral analysis techniques are transferable between different geological formations.

Hyperspectral monitoring of fructose content in marzipan

In our research marzipan samples of different sugar to almond paste ratios (1:1, 2:1, 3:1) were stored at 17 °C. Reducing sugar content was measured by analytical method, texture analysis was done by penetrometry, electric characteristics were measured by conductometry and hyperspectral images were taken 6–8 times during the 16 days of storage. For statistical analyses (discriminant analysis, principal component analysis) SPSS program was used. According to our findings with the hyperspectral analysis technique, it is possible to identify how long the samples were stored (after production), and to which class (ratio of sugar to almond) the sample belonged. The main wavelengths which gave the best discrimination results among the days of storage were between 960 and 1100 nm. The type of the marzipan was easy to distinguish with the hyperspectral data; the biggest differences were observed at 1200 and 1400 nm, which are connected to the first overtone of C-H bound, therefore correlate with the oil content. The spatial distribution of penetrometric, electric and spectral properties were also characteristic to fructose content. The fructose content of marzipan is difficult to measure by usual optical ways (polarimetry, spectroscopy), but since fructose is hygroscopic, the spatial distribution of spectral properties can be characteristic.

Integrating spatial and spectral information for enhancing spatial features in the Gough map of Great Britain

Abstract The Gough map has been recognized as the earliest surviving map of Great Britain. The map, dated to late 14th or early 15th century, depicts many and sophisticated cartographical local details, which was unusual in European medieval maps. Moreover, the rewriting and re-inking of some names or areas could indicate the map was re-touched after its original production. The Gough map, today with restricted access and in a conservation environment, was displayed for some time at the Bodleian Library in Oxford, where it was frequently in contact with scholars. Despite this familiarization, the Gough map has not been widely researched and inquiries about the original purpose of the map or the context in which it was made remain unknown. Recent interest in the map has lead to the use of new technologies to image the map and produce sophisticated data that allows scholars and scientists to examine it taking advantage of the new information. In this paper, a technique for Pan-sharpening hyperspectral images (HSI) is introduced to the cultural heritage community. The Pan-sharpening process is applied specifically to HSI images of the Gough map of Great Britain with the purpose of using relatively low spatial resolution hyperspectral analysis techniques on its very fine features. The Pan-sharpening technique is based on Nearest-neighbor diffusion (NNDiffuse) and the spatial enhancing is aimed at faded features such as handwriting and some distinctive details that are only visible in high-resolution conservation photographs. It is shown here that the use of the NNDiffuse Pan-sharpening improves spatial features in HSI of historical artifacts without impacting the spectral fidelity, and that the findings in the analysis of these features could contribute to the understanding of the Gough map and its importance in the historical context of Great Britain.

Evaluation of wavelet spectral features in pathological detection and discrimination of yellow rust and powdery mildew in winter wheat with hyperspectral reflectance data

Hyperspectral absorption features are important indicators of characterizing plant biophysical variables for the automatic diagnosis of crop diseases. Continuous wavelet analysis has proven to be an advanced hyperspectral analysis technique for extracting absorption features; however, specific wavelet features (WFs) and their relationship with pathological characteristics induced by different infestations have rarely been summarized. The aim of this research is to determine the most sensitive WFs for identifying specific pathological lesions from yellow rust and powdery mildew in winter wheat, based on 314 hyperspectral samples measured in field experiments in China in 2002, 2003, 2005, and 2012. The resultant WFs could be used as proxies to capture the major spectral absorption features caused by infestation of yellow rust or powdery mildew. Multivariate regression analysis based on these WFs outperformed conventional spectral features in disease detection; meanwhile, a Fisher discrimination model exhibited considerable potential for generating separable clusters for each infestation. Optimal classification returned an overall accuracy of 91.9% with a Kappa of 0.89. This paper also emphasizes the WFs and their relationship with pathological characteristics in order to provide a foundation for the further application of this approach in monitoring winter wheat diseases at the regional scale.

Changes in hyperspectral reflectance signatures of lettuce leaves in response to macronutrient deficiencies

The adaptation of specific remote sensing and hyperspectral analysis techniques for the determination of incipient nutrient stress in plants could allow early detection and precision supplementation for remediation, important considerations for minimizing mass of advanced life support systems on space station and long term missions. This experiment was conducted to determine if hyperspectral reflectance could be used to detect nutrient stress in Lactuca sativa L. cv. Black Seeded Simpson. Lettuce seedlings were grown for 90 days in a greenhouse or growth chamber in vermiculite containing modified Hoagland’s nutrient solution with key macronutrient elements removed in order to induce a range of nutrient stresses, including nitrogen, phosphorus, potassium, calcium, and magnesium. Leaf tissue nutrient concentrations were compared with corresponding spectral reflectances taken at the end of 90 days. Spectral reflectances varied with growing location, position on the leaf, and nutrient deficiency treatment. Spectral responses of lettuce leaves under macronutrient deficiency conditions showed an increase in reflectance in the red, near red, and infrared wavelength ranges. The data obtained suggest that spectral reflectance shows the potential as a diagnostic tool in predicting nutrient deficiencies in general. Overlapping of spectral signatures makes the use of wavelengths of narrow bandwidths or individual bands for the discrimination of specific nutrient stresses difficult without further data processing.

Identification and mapping of minerals in drill core using hyperspectral image analysis of infrared reflectance spectra

Abstract A Portable Infrared Mineral Analyzer II (PIMA II) field spectrometer was used to measure infrared reflectance spectra (1·3-2·5 μm) of split drill core at 1 cm intervals in both the along-core and cross-core directions. These data were formatted into an image cube similar to that acquired by an imaging spectrometer with 600 spectral channels, and multi-spectral and hyperspectral analysis techniques were used for analysis. Colour images and enhancements provided visual displays of the spectral information, while real-time digital extraction of individual spectra allowed identification of minerals. Absorption band-depth mapping and spectral classification were used to map the spatial distribution of specific minerals in the core. Linear spectral unmixing provided estimated mineral abundances. Analysis results demonstrate that multi-spectral and hyperspectral image analysis methods can be used to produce detailed mineralogical maps of drill core. They suggest that the concepts and analytical techniqu...