Assessment of the Efficiency of Chemical and Thermochemical Depolymerization Methods for Lignin Valorization: Principal Component Analysis (PCA) Approach

Uncovering Key Factors in Graphene Aerogel-Based Electrocatalysts for Sustainable Hydrogen Production: An Unsupervised Machine Learning Approach

The application of principal component analysis (PCA) as an unsupervised learning method has been used in uncovering correlations among diverse features of aerogel-based electrocatalysts. This analytical approach facilitates a comprehensive exploration of catalytic activity, revealing intricate relationships with various physical and electrochemical properties. The first two principal components (PCs), collectively capturing nearly 70% of the total variance, attested the reliability and efficacy of PCA in unveiling meaningful patterns. This study challenges the conventional understanding that a material's reactivity is solely dictated by the quantity of catalyst loaded. Instead, it unveils a complex perspective, highlighting that reactivity is intricately influenced by the material's overall design and structure. The PCA bi-plot uncovers correlations between pH and Tafel slope, suggesting an interdependence between these variables and providing valuable insights into the complex interactions among physical and electrochemical properties. Tafel slope stands to be positively correlated with PC1 and PC2, showing an evident positive correlation with the pH. These findings showed that the pH can have a positive correlation with the Tafel slope, however, it does not necessarily reflect a direct positive correlation with the overpotential. The impact of pH on current density (j)and Tafel slope underscores the importance of adjusting pH to lower overpotential effectively, enhancing catalytic activity. Surface area (from 30 to 533 m2 g-1) emerges as a key physical property, inclusively inverse correlation with overpotential, indicating its direct role in lowering overpotential and increasing catalytic activity. The introduction of PC3, in conjunction with PC1, enriches the analysis by revealing consistent trends despite a slightly lower variance (60%). This reinforces the robustness of PCA in delineating distinct characteristics of graphene aerogels, affirming their potential implications in diverse electrocatalytic applications. In summary, PCA proves to be a valuable tool for unraveling complex relationships within aerogel-based electrocatalysts, extending insights beyond catalytic sites to emphasize the broader spectrum of material properties. This approach enhances comprehension of dataset intricacies and holds promise for guiding the development of more effective and versatile electrocatalytic materials.

Towards Understanding Aerogels' Effect on Construction Materials: A Principal Component Analysis Approach

This study investigates the applicability of Principal Component Analysis (PCA) for distinguishing construction materials. The approach enhances data presentation, revealing distinct clusters and variable impacts on materials. This perspective provides valuable insights into concrete materials, guiding materials science and engineering practices. Our findings show the capacity of PCA to show a clear distinction between concrete and non-concrete composites. Compressive strength significantly affects certain composites, being influenced by aerogel loading. The peculiar role of aerogel density among the other factors is attributed to their possession of the smallest thermal conductivity. To address moderate total variance of PCA, segregation into concrete (C) and non-concrete (NC) categories is explored, offering a more robust distinction and higher clustering. Concrete materials show higher variance, emphasizing the effectiveness of the segregation approach. PCA highlights aerogel density's influence on thermal conductivity on concrete materials. For non-concrete materials, a moderately higher variance is noted, emphasizing the critical role of aerogel-related properties (size and density). These findings underscore the importance of aerogel characteristics in shaping material behaviour.

Towards Understanding Aerogels' Efficiency for Oil Removal-A Principal Component Analysis Approach

In this study, our aim was to estimate the adsorption potential of three families of aerogels: nanocellulose (NC), chitosan (CS), and graphene (G) oxide-based aerogels. The emphasized efficiency to seek here concerns oil and organic contaminant removal. In order to achieve this goal, principal component analysis (PCA) was used as a data mining tool. PCA showed hidden patterns that were not possible to seek by the bi-dimensional conventional perspective. In fact, higher total variance was scored in this study compared with previous findings (an increase of nearly 15%). Different approaches and data pre-treatments have provided different findings for PCA. When the whole dataset was taken into consideration, PCA was able to reveal the discrepancy between nanocellulose-based aerogel from one part and chitosan-based and graphene-based aerogels from another part. In order to overcome the bias yielded by the outliers and to probably increase the degree of representativeness, a separation of individuals was adopted. This approach allowed an increase in the total variance of the PCA approach from 64.02% (for the whole dataset) to 69.42% (outliers excluded dataset) and 79.82% (outliers only dataset). This reveals the effectiveness of the followed approach and the high bias yielded from the outliers.

Application of Unsupervised Learning for the Evaluation of Burial Behavior of Geomaterials in Peatlands: Case of Lignin Moieties Yielded by Alkaline Oxidative Cleavage

Tropical Peatlands accumulate organic matter (OM) and a significant source of carbon dioxide (CO₂) and methane (CH₄) under anoxic conditions. However, it is still ambiguous where in the peat profile these OM and gases are produced. The composition of organic macromolecules that are present in peatland ecosystems are mainly lignin and polysaccharides. As greater concentrations of lignin are found to be strongly related to the high CO₂ and CH₄ concentrations under anoxic conditions in the surface peat, the need to study the degradation of lignin under anoxic and oxic conditions has emerged. In this study, we found that the "Wet Chemical Degradation" approach is the most preferable and qualified to evaluate the lignin degradation in soils accurately. Then, we applied PCA for the molecular fingerprint consisting of 11 major phenolic sub-units produced by alkaline oxidation using cupric oxide (II) along with alkaline hydrolysis of the lignin sample presented in the investigated peat column called "Sagnes". The development of various characteristic indicators for lignin degradation state on the basis of the relative distribution of lignin phenols was measured by chromatography after CuO-NaOH oxidation. In order to achieve this aim, the so-called Principal Component Analysis (PCA) has been applied for the molecular fingerprint composed of the phenolic sub-units, yielded by CuO-NaOH oxidation. This approach aims to seek the efficiency of the already available proxies and potentially create new ones for the investigation of lignin burial along a peatland. Lignin phenol vegetation index (LPVI) is used for comparison. LPVI showed a higher correlation with PC1 rather than PC2. This confirms the potential of the application of LPVI to decipher vegetation change, even in a dynamic system as the peatland. The population is composed of the depth peat samples, and the variables are the proxies and relative contributions of the 11 yielded phenolic sub-units.

Advances in machine learning for high value-added applications of lignocellulosic biomass

Lignocellulose can be converted into biofuel or functional materials to achieve high value-added utilization. Biomass utilization process is complex and multi-dimensional. This paper focuses on the biomass conversion reaction conditions, the preparation of biomass-based functional materials, the combination of biomass conversion and traditional wet chemistry, molecular simulation and process simulation. This paper analyzes the mechanism, advantages and disadvantages of important machine learning (ML) methods. The application examples of ML in different aspects of high value utilization of lignocellulose are summarized in detail. The challenges and future prospects of ML in this field are analyzed.

Metal Oxide Hydrogel Composites for Remediation of Dye-Contaminated Wastewater: Principal Component Analysis

Water pollution is caused by multiple factors, such as industrial dye wastewater. Dye-contaminated water can be treated using hydrogels as adsorbent materials. Recently, composite hydrogels containing metal oxide nanoparticles (MONPs) have been used extensively in wastewater remediation. In this study, we use a statistical and artificial intelligence method, based on principal component analysis (PCA) with different applied parameters, to evaluate the adsorption efficiency of 27 different MONP composite hydrogels for wastewater dye treatment. PCA showed that the hydrogel composites CTS@Fe3O4, PAAm/TiO2, and PEGDMA-rGO/Fe3O4@cellulose should be used in situations involving high pH, time to reach equilibrium, and adsorption capacity. However, as the composites PAAm-co-AAc/TiO2, PVPA/Fe3O4@SiO2, PMOA/ATP/Fe3O4, and PVPA/Fe3O4@SiO2, are preferred when all physical and chemical properties investigated have low magnitudes. To conclude, PCA is a strong method for highlighting the essential factors affecting hydrogel composite selection for dye-contaminated water treatment.

Post-Consumer Textile Waste Classification through Near-Infrared Spectroscopy, Using an Advanced Deep Learning Approach

The textile industry is generating great environmental concerns due to the exponential growth of textile products’ consumption (fast fashion) and production. The textile value chain today operates as a linear system (textile products are produced, used, and discarded), thus putting pressure on resources and creating negative environmental impacts. A new textile economy based on the principles of circular economy is needed for a more sustainable textile industry. To help meet this challenge, an efficient collection, classification, and recycling system needs to be implemented at the end-of-life stage of textile products, so as to obtain high-quality recycled materials able to be reused in high-value products. This paper contributes to the classification of post-consumer textile waste by proposing an automatic classification method able to be trained to separate higher-quality textile fiber flows. Our proposal is the use of near-infrared (NIR) spectroscopy combined with a mathematical treatment of the spectra by convolutional neural networks (CNNs) to classify and separate 100% pure samples and binary mixtures of the most common textile fibers. CNN is applied for the first time to the classification of textile samples. A total of 370 textile samples were studied—50% used for calibration and 50% for prediction purposes. The results obtained are very promising (100% correct classification for pure fibers and 90–100% for binary mixtures), showing that the proposed methodology is very powerful, able to be trained for the specific separation of flows, and compatible with the automation of the system at an industrial scale.