NIR Hyperspectral Imaging for Advanced Identification and Quantification of Materials in PV Recycling Fractions

Renewable energy, particularly solar energy, has experienced remarkable growth in recent years. However, the integrity of solar photovoltaic (PV) cells can degrade over time, necessitating non-destructive testing and evaluation (NDT-NDE) for quality control during production and in-service inspection. Hyperspectral (HS) imaging has emerged as a promising technique for defect identification in PV cells based on their spectral signatures. This study utilizes a HS imager to establish a diffuse reflectance spectra signature for two groups of PV cells: working and non-working. A non-contact photoluminescence imaging-based methodology is employed, using a halogen lamp as an illumination source to replicate sunlight. Our findings reveal that non-working PV regions can be differentiated from working regions within the 400–600 nm wavelength range, with an optimal candidate peak frequency of 450 nm. To accurately group active PV regions in the constructed HS images at 450 nm, we employ an image processing strategy that combines K-means clustering (K-mc) with contour delineation. Specifically, K-mc with K = 8 is used to efficiently and precisely group active PV regions. We demonstrate the effectiveness of this proposed approach and compare it with traditional infrared (IR) imaging techniques. This imaging clustering approach can be implemented using a conventional camera and a 450 nm wavelength filter for NDT-NDE on exterior-mounted PV panels. Overall, the proposed HS imaging technique, coupled with K-mc, offers a rapid and effective means of identifying defects in PV cells, outperforming conventional IR imaging techniques. This advancement contributes to increased efficiency and extended lifespan of solar PV panels.

n/a.

The present work is a demonstration of how near infrared (NIR) hyperspectral photoluminescence imaging can be used to detect defects in silicon wafers and solar cells. Chemometric analysis techniques such as multivariate curve resolution (MCR) and partial least squares discriminant analysis (PLS-DA) allow various types of defects to be classified and cascades of radiative defects in the samples to be extracted. It is also demonstrated how utilising a macro lens yields a spatial resolution of 30 µm on selected regions of the samples, revealing that some types of defect signals originate in grain boundaries of the silicon crystal, whereas other signals show up as singular spots. Combined with independent investigation techniques, hyperspectral imaging is a promising tool for determining origins of defects in silicon samples for photovoltaic applications.

Management of phosphate mine waste rock piles (PWRPs) is a critical challenge in the mining industry, particularly in regions like Morocco, which holds the world’s largest phosphate reserves. To this end, there is a need for an approach that focuses on real-time monitoring of waste rock heterogeneity, enabling more efficient resource recovery and environmental management. This study proposes a novel, multi-scale approach that integrates hyperspectral imaging, field spectroscopy, and explainable machine learning (XML) to characterize and map the mineralogical diversity of PWRPs at the Benguerir mine.  A total of 103 samples were collected from waste rock piles across an area of approximately 60 km², representing the full spectrum of mineralogical variability. Handheld X-ray fluorescence (XRF) analysis was conducted on the all the samples and revealed the dominance of SiO₂ (29.51 wt% ± 12.42), CaO (30.16 wt% ± 10.17), and P₂O₅ (7.23 wt% ± 4.21). These XRF analyses indicated the presence of silicate, carbonate, and phosphate-bearing materials. These findings were complemented by both PRISMA hyperspectral imaging, which captured spectral data across the visible to shortwave infrared (VSWIR) range. precise calibration and validation of the remote sensing outputs were conducted using field spectroscopy using the ASD FieldSpec 4 spectroradiometer.To address the complexity of the spectral data, we developed an explainable machine learning framework based on SHapley Additive exPlanations (SHAP) and Convolutional Neural Networks (CNN). This framework not only improved classification accuracy (achieving 0.92 overall accuracy) but also provided interpretable insights into the spectral features driving mineral identification. Our results showed that the used model successfully differentiated four main waste rock categories: carbonate-rich, phosphate-rich, clay-dominated, and siliceous materials. The resulting maps offer a practical tool for real-time waste management and resource recovery. For instance, carbonate-rich materials, characterized by high CaO content, can be identified or used for construction applications, while phosphate-rich zones, with elevated P₂O₅ levels, can be flagged for potential recovery and further processing. This targeted approach ensures that waste materials are repurposed efficiently, aligning with circular economy principles. The study highlights the potential for automated, spectroscopy-based monitoring systems to support sustainable mining practices. Overall, this study demonstrates the power of combining cutting-edge remote sensing technologies with explainable machine learning to address the challenges of phosphate waste rock characterization. The methodology provides a scalable, cost-effective solution for mining operations worldwide, with significant implications for environmental sustainability, resource efficiency, and circular economy initiatives.Keywords: Phosphate mine waste, Hyperspectral imaging, Field spectroscopy, Explainable machine learning (XML), Sustainable mining.

Near infrared (NIR) hyperspectral imaging and hyperspectral image analysis were evaluated for their potential to distinguish between Fusarium verticillioides infected and sound whole maize ( Zea mays L.) kernels. Hyperspectral images of infected and sound kernels were acquired using a Spectral Dimensions MatrixNIR camera with a spectral range of 960–1662nm and a sisuChema hyperspectral pushbroom imaging system with a spectral range of 1000–2498 nm. Background, bad pixels and shading were removed using exploratory principal component analysis (PCA) on absorbance images. PCA could be used effectively on the cleaned images to identify classes including infected and non-infected regions on individual kernels. A distinct difference between infected and sound kernels along principal component (PC) one with two distinguishable clusters was found. The loading line plot of the first PC of the sisuChema hypercube showed important absorbance peaks for the two classes, i.e. 1960nm and 2100nm for the infected class and U50 nm, 2300nm and 2350nm for the non-infected class. Partial least squares discriminant analysis (PLS-DA) was applied. The coefficient of determination was 0.73 for the MatrixNIR image and 0.86 for the sisuChema image, both after three PLS components. These PLS-DA models could be used to calculate predictions on a test set image. The predictions could be shown as prediction images and an acceptable root mean square error of prediction was obtained (0.23). NIR hyperspectral imaging has the potential to be used as a rapid, objective means of indentifying fungal infected maize kernels and infected regions.

In contrary to orthodox methods for determination of physicochemical composition and quality characteristic of meat, near infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) systems are more reliable, prompt, simple and concurrent evaluation of abundant meat properties. This present review effort on the use of the NIRS and the HSI system to predict diverse meat properties, based on published literature in different years. The NIRS and the HSI exhibits a noticeable prospective to replace the expensive and laborious chemical analysis of meat composition mainly crude protein (CP), intramuscular fat (IMF), moisture, dry matter (DM), ash, collagen content, technological objective measurement (pH value, color value, L*, a*, b*, water holding capacity, warner-Bratzler shear force) and sensory characteristics (Tenderness, juiciness, chewiness, flavor, texture, odor and firmness). HSI system conglomerates imaging and spectroscopictechnology is promptly gettingfieldas a non-destructive, real-time recognition tool for food quality. The review notice that NIR revealed great potential to evaluate physicochemical properties of meat and toclassify meat into quality classes based on meat quality traits for instances distinctive between feeding systems, discriminating fresh from–frozen-thawed meat and so on. Moreover, NIRS is less precise for evaluating various technological and sensory attributes of meat due to heterogeneity of meat samples and their preparation. Hence, further study is recommended to improve sensory and technological attributes by standardize the sample preparation and accuracy of referencing technique. In conclusion, the NIRS and the HIS are considered to be a very satisfactory system for swift meat evaluation.

The global construction industry is the world’s largest consumer of raw materials and creates an estimated third of the world’s overall waste. A circular economy is one that aims to keep products, components and materials at their highest utility and value at all times. The Opera Square site development project is being utilised as a Lighthouse Demonstrator Project for the Circular Built Environment. The site is a brownfield site located in the heart of Limerick City. The transformational commercial development which commenced in 2022 consists of office, retail, residential and public buildings on a 3.7-acre site. During the demolition and enabling phase of the project, a number of buildings were demolished. Prior to demolition, a pre-demolition audit was undertaken. The purpose was to identify the type and quantities of the materials that would arise from the demolition works and possible opportunities to implement circular economy principles. This research paper will conduct a case study on the Opera Square project located in Limerick, Ireland, evaluating the circular economy interventions implemented during the demolition and enabling phase of the project. The study aims to assess the effectiveness of the interventions in achieving a diversion rate for construction and demolition material from landfill of 98% through on-site and off-site re-use of construction materials, the re-use of material as a piling mat diverted 87% of construction and demolition material from landfill. A life cycle analysis was undertaken and determined a reduction of at least 66% in the embodied carbon global warming potential compared to a business-as-usual construction practice for the piling mat. There are lessons learned from this project that can be applied to future projects, one being the full realisation of opportunities for further re-use of material through the end-of-waste and by-product mechanisms. Achieving the full potential of a circular economy in the built environment requires collaboration among stakeholders, with initiatives that promote community engagement being particularly impactful in creating both social, environmental and economic benefits through a Circular Economy.

Maize kernel hardness classification by near infrared (NIR) hyperspectral imaging and multivariate data analysis

The inhomogeneity of spectral pixel response is an unavoidable phenomenon in hyperspectral imaging, which is mainly manifested by the existence of inhomogeneity banding noise in the acquired hyperspectral data. It must be carried out to get rid of this type of striped noise since it is frequently uneven and densely distributed, which negatively impacts data processing and application. By analyzing the source of the instrument noise, this work first created a novel non-uniform noise removal method for a spatial dimensional push sweep hyperspectral imaging system. Clean and clear medical hyperspectral brain tumor tissue images were generated by combining scene-based and reference-based non-uniformity correction denoising algorithms, providing a strong basis for further diagnosis and classification. The precise procedure entails gathering the reference dark background image for rectification and the actual medical hyperspectral brain tumor image. The original hyperspectral brain tumor image is then smoothed using a weighted least squares algorithm model embedded with bilateral filtering (BLF-WLS), followed by a calculation and separation of the instrument fixed-mode fringe noise component from the acquired reference dark background image. The purpose of eliminating non-uniform fringe noise is achieved. In comparison to other common image denoising methods, the evaluation is based on the subjective effect and unreferenced image denoising evaluation indices. The approach discussed in this paper, according to the experiments, produces the best results in terms of the subjective effect and unreferenced image denoising evaluation indices (MICV and MNR). The image processed by this method has almost no residual non-uniform noise, the image is clear, and the best visual effect is achieved. It can be concluded that different denoising methods designed for different noises have better denoising effects on hyperspectral images. The non-uniformity denoising method designed in this paper based on a spatial dimension push-sweep hyperspectral imaging system can be widely used.

Introduction N ear infrared (NIR) hyperspectral imaging (HSI) has been widely used in the pharmaceutical and food industries for quality monitoring and process control. This spread in applications has been mainly due to the development of instrumentation, computational ability in handling large amounts of data and data processing methods that can extract relevant information from the images. Hyperspectral images are threedimensional images in which a complete spectrum is measured for each spatial pixel. When the spectrum is recorded in the NIR region, an NIR hyperspectral image is obtained. Partial Least Squares-Discriminant Analysis (PLS-DA) is one of the most commonly used data analysis methods for classification of samples on the basis of conventional spectroscopy. When NIR hyperspectral images of different samples are recorded, PLS-DA may be applied to the spectral profiles of the different samples in order to classify them. As usual, a previous calibration step involving known samples is necessary so that PLS-DA is able to classify unknown samples. Plastic classification is an important field in which NIR HSI could be applied; correct identification and classification of plastics would enhance recycling efficiencies. Recently, some attempts at plastic classification by optical methods such as NIR, Raman spectroscopy, Fourier transform infrared (FT-IR) or differential scanning calorimetry (DSC) have been reported, but the existing literature on HSI-based methods is limited. HSI offers the important added benefit of being able to spatially map the location of various different plastic objects in a scene on the basis of their spectral signatures. In this study, we considered the potential of NIR HSI combined with PLS-DA for the classification of different types of polymers. Materials and methods The polymers studied were low-density polyethylene (LDPE), high-density polyethylene (HDPE), polypropylene (PP) and polystyrene PS. Three images have been analysed, denoted sample 1, sample 2 and sample 3. In Figure 1, a false colour image of sample 1 is shown. Samples 2 and 3 can be seen in Figure 2. Each of the images has two sides, the left side consists of a piece of each polymer type (individual polymers) and the right side consists of a mixture of seven pieces of each polymer (polymer mixture). In two of the images (samples 2 and 3), some of the mixed pieces of polymers are overlapped whereas in the other image (sample 1) the pieces are mixed but not overlapped. The initial dimensions of each image were 320 rows × 580 columns × 121 bands, where the first two dimensions (320 × 580) refer to the pixel or spatial dimension of the surface and the last dimension (121) refers to the number of wavelengths of each spectrum measured at each of the pixels. The NIR wavelength interval recorded spanned the range from 880 nm to 1720 nm with a resolution of 7 nm. PLS-DA is widely-used and known for sample classification. In this application, it consisted of a PLS2-based regression in which the response variables were categorical, expressing the class membership of the statistical units. It is a supervised method and it requires an initial calibration step involving some samples belonging to each known class. 2

Several countries have shown interest in the development of methods for recycling photovoltaic (PV) modules because the number of end-of-life modules is expected to increase owing to the increasing use of PV modules. Generally, physical, chemical, and thermal (incineration) methods are used for separating glass from the PV module when the end-of-life modules are recycled. In the physical method, the ethylene vinyl acetate (EVA) is cut using a heated knife or wire, whereas in the chemical method, the EVA is dissolved using chemicals. Among the treatment methods, the thermal method is widely used, wherein EVA is burned at high temperatures. In this article, a structure wherein a sacrificial layer is located between the front glass and EVA is proposed. Herein, a fluorine-doped tin oxide (FTO) thin film was used as a sacrificial layer and was delaminated using transparent conductive oxide corrosion assisted by voltage and moisture in a thin-film solar cell, after which the front glass was easily separated from the EVA. The experiment proceeded by delaminating the FTO thin film deposited on the front glass and separating EVA from the front glass. Finally, after creating a minimodule structure, the front glass was released from the EVA.

Vegetation is crucial for wetland ecosystems. Human activities and climate changes are increasingly threatening wetland ecosystems. Combining satellite images and deep learning for classifying marsh vegetation communities has faced great challenges because of its coarse spatial resolution and limited spectral bands. This study aimed to propose a method to classify marsh vegetation using multi-resolution multispectral and hyperspectral images, combining super-resolution techniques and a novel self-constructing graph attention neural network (SGA-Net) algorithm. The SGA-Net algorithm includes a decoding layer (SCE-Net) to precisely fine marsh vegetation classification in Honghe National Nature Reserve, Northeast China. The results indicated that the hyperspectral reconstruction images based on the super-resolution convolutional neural network (SRCNN) obtained higher accuracy with a peak signal-to-noise ratio (PSNR) of 28.87 and structural similarity (SSIM) of 0.76 in spatial quality and root mean squared error (RMSE) of 0.11 and R2 of 0.63 in spectral quality. The improvement of classification accuracy (MIoU) by enhanced super-resolution generative adversarial network (ESRGAN) (6.19%) was greater than that of SRCNN (4.33%) and super-resolution generative adversarial network (SRGAN) (3.64%). In most classification schemes, the SGA-Net outperformed DeepLabV3 + and SegFormer algorithms for marsh vegetation and achieved the highest F1-score (78.47%). This study demonstrated that collaborative use of super-resolution reconstruction and deep learning is an effective approach for marsh vegetation mapping.

The solar cell is a device to convert light energy into electric, which supplies power to the external load when exposed to the incident light. The photocurrent and voltage occurred in the device are significant factors to decide the output power of solar cells. The crystalline silicon solar cell module has photocurrent loss due to light reflections on the glass and EVA(Ethylene Vinyl Acetate). These photocurrent loss would be a hinderance for high-efficiency solar cell module. In this paper, the quantitative analysis for the photocurrent losses in the 300-1200 wavelength region was performed. The simulation method with MATLAB was used to analyze the reflection on a front glass and EVA layer. To investigate the intensity of light that reached solar cells in PV(Photovoltaic) module, the reflectance and transmittance of PV modules was calculated using the Fresnel equations. The simulated photocurrent in each wavelength was compared with the output of real solar cells and the manufactured PV module to evaluatehe reliability of simulation. As a result of the simulation, We proved that the optical loss largely occurred in wavelengths between 300 and 400 nm

With advances in technology, hyperspectral imaging has become an emerging area of research due to its numerous advantages over conventional imaging techniques. HyperSpectral (HS) cameras generate images of high spectral as well as spatial resolution. Hence, HS images carry much more information from the scene than the conventional red, green and blue (RGB) images. This inspired researchers to use HS technologies for many different applications ranging from crime investigations to crop monitoring. It is important to accurately detect veins during surgical treatments, but this often turns out to be difficult. Wrongly locating veins or anatomical variations could result in accidental injury to blood vessels. This could lead to a longer operation time or even create serious complications. Furthermore, for majority of medical procedures, it is necessary to accurately define the location of veins. Over the past years, various methods including near infrared (NIR) and multi-spectral image processing-based methods have been proposed to help with detecting and accurately locating the veins. However, the performance of these methods is limited and demand for more accurate and convenient methods are increasing. HS images are two-dimensional (2D) representation of the scene at many light spectral. This brings the challenge of processing high dimensional data, which require significant processing power to deal with them. Various methods such as principal component analysis (PCA), Moving Window-PCA and Folded-PCA, which are widely used to reduce the dimensionality of HS image data, are reviewed in this book chapter. Conventional RGB, HS, NIR and multispectral images are studied and then HS imaging systems are introduced. Different applications of HS imaging are reviewed and their potential for vein detection is highlighted. Different techniques for reducing high dimensional data are discussed, and finally, different vein detection methods and some of the existing vein benchmark datasets are also introduced.

Minimally invasive surgery (MIS) has shown vast improvement over open surgery by reducing post-operative stays, intraoperative blood loss, and infection rates. However, in spite of these improvements, there are still prevalent issues surrounding MIS that may be addressed through hyperspectral imaging (HSI). We present a laparoscopic HSI system to further advance the field of MIS. We present an imaging system that integrates high-speed HSI technology with a clinical laparoscopic setup and validate the system's accuracy and functionality. Different configurations that cover the visible (VIS) to near-infrared (NIR) range of electromagnetism are assessed by gauging the spectral fidelity and spatial resolution of each hyperspectral camera. Standard Spectralon reflectance tiles were used to provide ground truth spectral footprints to compare with those acquired by our system using the root mean squared error (RMSE). Demosaicing techniques were investigated and used to measure and improve spatial resolution, which was assessed with a USAF resolution test target. A perception-based image quality evaluator was used to assess the demosaicing techniques we developed. Two configurations of the system were developed for evaluation. The functionality of the system was investigated in a phantom study and by imaging ex vivo tissues. Multiple configurations of our system were tested, each covering different spectral ranges, including VIS (460 to 600nm), red/NIR (RNIR) (610 to 850nm), and NIR (665 to 950nm). Each configuration is capable of achieving real-time imaging speeds of up to 20 frames per second. RMSE values of , , and 3.47% were achieved for the VIS, RNIR, and NIR systems, respectively. We obtained sub-millimeter resolution using our demosaicing techniques. We developed and validated a high-speed hyperspectral laparoscopic imaging system. The HSI system can be used as an intraoperative imaging tool for tissue classification during laparoscopic surgery.