Implementing machine learning for the identification and classification of compound and mixtures in portable Raman instruments

Modeling predictions of surface tension for binary and ternary liquid mixtures is difficult. In this work, we propose a machine learning model to accurately predict the surface tension of binary mixtures of organic solvents-ionic liquids and ternary mixtures of organic solvents-ionic liquids–water and analytically characterize the proposed model. In total, 1593 binary mixture data points and 216 ternary mixture data points were collected to develop the machine learning model. The model was developed by combining machine learning algorithms, UNIFAC (UNIversal quasi-chemical Functional group Activity Coefficient) and ASP (Abraham solvation parameter). UNIFAC parameters are used to describe ionic liquids, and ASP is used to describe organic solvents. The effect of each parameter on the surface tension is characterized by SHAP (SHapley Additive exPlanation). We considered support vector regression, artificial neural network, K nearest neighbor regression, random forest regression, LightGBM (light gradient boosting machine), and CatBoost (categorical boosting) algorithms. The results show that the CatBoost algorithm works best, MAE = 0.3338, RMSE = 0.7565, and R2 = 0.9946. The SHAP results show that the surface tension of the liquid decreases as the volume and surface area of the anion increase. This work not only accurately predicts the surface tension of binary and ternary mixtures, but also provides illuminating insight into the microscopic interactions between physical empirical models and physical and chemical properties.

This paper is the final in a series of three viscosity and density studies of pure n-alkanes and selected binary and quaternary mixtures. A standard U-tube viscometer was used for viscosity measurements, and a Pyrex flask-type pycnometer was used for density determinations. Results are given here for pure alkane and selected binary mixtures of n-tetradecane + n-octane, for selected quaternary mixtures of n-hexadecane + n-dodecane + n-decane + n-hexane, and for pure and selected quaternary mixtures of n-hexadecane + n-dodecane + n-nonane + n-heptane at 303.16 and 308.16 K. The principle of congruence was tested, as was the Grunberg and Nissan equation, as they have been shown to be useful as prediction techniques for other n-alkane binary mixtures. Comparisons were made between the two groups of quaternary alkane mixtures and the binary n-tetradecane + n-octane mixtures of the same “pseudo” composition to understand better the dependence of mixture viscosities on the composition parameter.

The cybersecurity concerns get increasingly intricate as the digital world progresses. In light of the increasing complexity of cyber threats, it is imperative to develop and implement advanced and flexible security strategies. Machine Learning (ML) has become a potent tool in strengthening cybersecurity, providing the capacity to scrutinise extensive information, recognise trends, and improve threat detection and defence methods. This paper examines the significance of ML in the field of cybersecurity, with a special emphasis on the identification of threats and the implementation of protective measures. By incorporating ML algorithms into cybersecurity frameworks, organisations may automate decision-making processes, facilitating prompt responses to ever-changing threats. The initial segment explores the terrain of cyber threats, highlighting the necessity for dynamic and aggressive security methods. Conventional solutions that rely on signatures are frequently inadequate when it comes to handling sophisticated, shape-shifting attacks. ML algorithms, in contrast, have exceptional proficiency in identifying nuanced patterns and irregularities within extensive datasets, therefore offering a more efficient method of detecting potential threats. The second section delves into several ML methodologies utilised in cybersecurity, including supervised and unsupervised learning, deep learning, and reinforcement learning. Every approach is assessed based on its suitability for threat detection, demonstrating its advantages and constraints. Furthermore, the relevance of feature engineering and data pretreatment in improving machine learning models for cybersecurity applications. The versatility of ML algorithms allows them to grow with emerging threats, making them a useful tool in the ever-changing arena of cyber warfare. The final segment focuses on real-world applications of machine learning in cybersecurity, presenting successful use cases across sectors. From anomaly detection to behavior analysis, ML algorithms contribute to the discovery of dangerous activity, lowering false positives and strengthening the overall security posture. Lastly, the paper covers the obstacles and ethical issues related to the adoption of ML in cybersecurity. Issues like as adversarial assaults, skewed datasets, and the interpretability of ML models are examined, highlighting the necessity for a holistic strategy that integrates modern technology with ethical considerations. The fusion of human expertise and machine intelligence offers a formidable defense against evolving cyber threats, paving the way for a more resilient and secure digital future.

Ebulliometric determination and prediction of (vapor + liquid) equilibria for binary and ternary mixtures containing alcohols (C 1–C 4) and dimethyl carbonate

Quantitative Raman assays for on-site analysis of stockpiled drugs

In this work, surface-enhanced Raman scattering (SERS) spectrum was used to build a rapid analytical method for pesticide residues in fruits. QuEChERS (quick, easy, cheap, effective, rugged and safe) method was modified by multi-walled carbon nanotubes as clean-up sorbents. Overall recoveries of selected pesticide phosmet ranged from 77 to 97% in apples at three spiking levels (0.5, 1 and 2 mg kg−1). The relative standard deviations were between 6.6 and 14%. The limit of detection for phosmet was 0.1 mg kg−1 in standard solution and 0.5 mg kg−1 in apples, which was below the maximum residue limits in fruits of USA, EU and China. The intensity of phosmet characteristic peak existed good linear relationship with the logarithm of concentration between 0.5 and 5 mg kg−1, with the calibration curve coefficients (R2) of 0.9994, which indicated quantitative potential for pesticide residue detection. The method was extended to other pesticides, and the obtained SERS results could be used to establish a spectra database. All the experiments were performed with a portable Raman instrument. Combining pretreatment method with spectra database, a sensitive, rapid and convenient method could be built for pesticide residues detection in fruits.

Well‐resolved Raman spectra of gypsum, anglesite and baryte were detected using a portable Raman instrument (Ahura First Defender XL) in the laboratory and outdoor under atmospheric conditions. Spectra were obtained using a 785‐nm excitation. The portable spectrometers display generally lower spectral resolution compared with the laboratory confocal instrument but permit the fast, unambiguous detection of minerals under field conditions. Portable Raman instruments can be advocated as excellent tools for field geological, environmental as well as exobiological applications. A miniaturized Raman instrument will be included in the Pasteur analytical package of the ESA ExoMars mission and interesting research applications can now be proposed for in situ field planetary studies. Additionally, portable Raman instruments represent an ideal tool for demonstrating possible applications of Raman spectroscopic techniques outdoor. In geosciences this approach represents a new field which could completely change classical field work. Copyright © 2009 John Wiley & Sons, Ltd.

As the size of modern infrastructure increases, novelties related to mass concrete mixtures including supplementary cementitious materials (SCMs) become critical. The effects of binary and ternary cement replacement mixtures including metakaolin, silica fume, ground calcium carbonate, granulated blast furnace slag, and fly ash on the rate and amount of heat generated in concrete mixtures are investigated. Twenty three binary and ternary mixtures with a water-to-cementitious binder ratio of 0.43 are evaluated. Between 15% and 45% cement replacement by weight is considered. Results indicate that binary mixtures containing metakaolin or silica fume offer no advantage in reducing the amount of heat but increase compressive strength by 20%. On contrary, ternary mixtures, including two pozzolanic materials, provide 15% reduction in the amount of heat evolution without compromising strength. This reduction is observed regardless of alumina (Al) or silica (Si) content in pozzolanic materials when 45% cement is replaced with a combination of slag and metakaolin, or slag and silica fume. Furthermore, the effect of increased calcium (Ca) content is investigated. It is concluded that ternary mixtures with decreased Ca/(Al+Si) ratio reduce internal temperature in mass concrete structures and are less likely to be exposed to the threshold temperature for delayed ettringite formation.

Incorporation of high accuracy surface modeling into machine learning to improve soil organic matter mapping

This paper presents the latest results of a series of experiments deigned to identify situations in which linear and nonlinear mixing models are expect to occur. It continues to investigate the possibility that there may be naturally occurring situation in which the typically used linear mixture model may not provide the most accurate spectrum. It has already been shown that for specific situations, in binary mixing cases, the nonlinear mixing model can produce more accurate endmember abundance estimates. These results are extended to include ternary and quaternary mixtures, as well as hyperspectral imagery collected over Cuprite, Nevada. In order to test these hypotheses, laboratory endmember and mixture data are collected in various scenarios for analysis. As shown in experiments, ternary and quaternary mixtures are more complicated than binary mixtures and the nonlinear mixing is more likely to occur in ternary and quaternary mixtures than in binary mixtures.© (2002) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

GeoRaman is an international conference where researchers gather to discuss the application of Raman spectroscopy in the fields of geological, planetary, and archaeological sciences. Historically, the first GeoRaman conference was held in Paris (France) in 1986, and then continued there for some time. After a stint in France, the conference then moved to Valladolid (Spain) in 1999, and then took a wide international journey to Prague (Czech Republic) in 2002, to Hawaii (USA) in 2004, to Almunecar (Spain) in 2006, to Gent (Belgium) in 2008, to Sydney (Australia) in 2010, and then back to Nancy (France) in 2012. For the first time, this conference was held in the continental United States, in St. Louis, Missouri, from 15 to 19 of June 2014. Researchers from over 18 countries attended. GeoRaman XI in St. Louis focused on two major aspects of Raman spectroscopy: (1) the most advanced technologies and instrumentation, from laboratories to a wide variety of field applications, e.g. industrial and security monitoring, geo-fields, deep ocean, and on other planets and (2) the newest applications in studying inorganic, organic, and bio-genetic materials in Earth Sciences, Planetary Sciences, Environmental Science, Forensic Science, Archaeology and Archaeometry, Gemology, and Astrobiology. This special issue of the Journal of Raman spectroscopy dedicated to the 11th International GeoRaman Conference has 31 papers covering areas such as Planetary Science, Astrobiology, Mineralogy and Petrology, Biomineralization, Fluid Inclusions, Archaeology and Archaeometry, and Environmental Science. Several of the papers in this special issue are related to the application of Raman spectroscopy as an instrument for planetary exploration. Wei et al.1 report the first rover test of a Raman spectrometer specifically developed for mission flights, the Mars Micro-beam Raman Spectrometer in the Atacama Desert (Chile). In this work, they discovered γ-anhydrite, which is typically an unstable mineral, in large quantities in the soils of the Atacama Desert. Lui and Wang2 shed light on the dehydration of Na-jarosite, ferricopiapite, and rhomboclase to understand their formation and presence as ferric sulfates on Mars. This paper can be found here http://onlinelibrary.wiley.com/store/10.1002/jrs.4655/asset/jrs4655.pdf. Uriarte et al.3 work on collecting reference spectra of CaCl2.nH2O (n = 0, 2, 4, 6) to enable the geochemical community to identify these key minerals in important fluid geochemical processes here on Earth and Mars. Wang et al.4 provide the first systematic Raman spectroscopic study of phyllosilicates of planetary science importance for the characterization of such materials on the surface of Mars. Bathgate et al.5 identify by Raman spectroscopy primary and secondary minerals of volcanic rock weathering and alteration as a database for upcoming future exploration of Mars. This special issue contains a number of papers detailing the application of Raman spectroscopy to detect chemical traces of life on Mars. Fernandes et al.6 elucidate the pigment chemistry of three lichens of astrobiological relevance. They report the first identification of parietin in these lichens, which this pigment is effective in protecting the organism from free radicals and ultraviolet radiation. The paper can be found here http://onlinelibrary.wiley.com/store/10.1002/jrs.4626/asset/jrs4626.pdf Hooijschuur et al.7 investigate the effects of photodegradation of carotenoids within bacterial cell membranes and calcite. They report that carotenoids residing in the bacterial membranes were less sensitive to photodegradation than the mineral matrix. Harris et al.8 investigated several terrestrial Mars analogue samples to point out a cautionary tale to the astrobiology community potential for confusion in interpreting Raman spectra acquired from these types of samples. Foucher et al.9 demonstrates the potential of Raman mapping of the distribution and change in intensity ratio of the D and G bands arising from carbonaceous material as a biosignature to help identify potential fossilized microbes here in early Earth rocks and Mars. Several of the papers in this special issue are on the application of Raman spectroscopy to problems in mineralogy and petrology. Korsakov et al.10 undertook Confocal two-dimensional and three-dimensional Raman imaging of the Kokchetav metamorphic diamonds from different rock types which these results showed that those various diamonds had different crystal quality with complex internal morphologies associated with defects. The paper by Bartholomew et al.11 investigates the potential of Raman spectroscopy as the number one instrument for mineral identification in the Geosciences. They quantify the range of Raman intensities that can be expected from natural mineral samples and investigate the incorporation of this information into instrument standards and analytical methodology to design data collection strategies across Geoscience laboratories. Carey et al.12 apply machine learning techniques in order to improve mineral identification obtained by Raman spectroscopy. Golovin et al.13 show that the carbonate mineral zemkorite is not likely stable at the Earth's surface but will transform into the more stable polymorph nyerereite at these P-T conditions. Gomez-Nubla et al.14 characterized impact glass formed by meteorite impacts. They show that a substantial degree of post-impact terrestrial weathering can occur in these materials, which needs to be taken under consideration. Frost et al.15 use vibrational spectroscopy to characterize the mineral tangdanite and show that this mineral contains arsenate and sulfate polyhedra. Jehlicka and Vandenabeele16 evaluate portable Raman instruments to investigate the best excitation wavelength in collection of spectra from zeolite and beryllium containing silicate minerals. This work recommends using the portable NIR 785 nm system for the collection of better quality spectra on these materials. Cathelineau et al.17 use Raman spectroscopy to better understand the crystal structure of the economically important Ni-ore talc-like mineral phases, revealing that Raman spectroscopy can quickly evaluate the Ni content in these important economic minerals. Burlet and Vandrabant18 shed light on the structure of economically important manganese oxide minerals lithiophorite and asbolane that are typically difficult to characterize by traditional X-ray diffraction. Lopez and Frost19 shed light on the mineral responsible for the coloration of black marble from a quarry in Chillagoe, North Queensland, Australia. Petriglieri et al.20 use Raman mapping to identify small-scale changes in serpentine mineralogy to enable a greater understanding of the serpentinization process. Moroz et al.21 delineate the best wavelength of laser excitation to collect fluorescence free spectra on thermally immature carbonaceous materials. They clearly demonstrate that the laser excitation wavelength at 325 nm yields the best quality spectra that can be collected from these materials. This was a new session organized at GeoRaman, and while we only have one paper for the special issue, this field is opening up for the application of Raman spectroscopy and should grow enormously in the near future. Bioapatite, a carbonated, hydroxylated calcium phosphate salt, undergoes phase changes during heating. However, these changes are somewhat unclear; Li et al.22 elucidated these thermal transformations using Raman spectroscopy to study various heated material. They observed that the mineral undergoes de-carbonation and recrystallization at relatively low temperatures. This special issue contains a number of papers on fluid inclusions, which have contributed greatly to our understanding of measuring salinity and gaseous phases. Caumon et al.23 shed light on the role of mineral birefringence and on the polarization properties of the O–H stretching band of liquid water for determining the salinity of aqueous fluid inclusions. Tarantola and Caumon24 revealed that salinity measurements in fluid inclusions were overestimated by 1% per 10–15 MPa of negative pressure, thus allowing a way forward to determine the salinity of metastable fluid inclusions by Raman spectroscopy. Li and Chou25 analyze silicate melt inclusions in quartz from granites within pegmatite deposits by Raman spectroscopy revealing for the first time the occurrence of H2 in the vapor phase of the inclusion. Chou26 calibrated the Raman shifts of cyclohexane with the goal of using this calibration to accurately determine the ν1 CH4 band position to calculate CH4 densities in fluid inclusions. Several papers in this special issue are devoted to Archaeology and Archaeometry. Barone et al.27 obtain Raman spectra using portable instruments on an archaeologically significant jewelry museum collection dated to the 17th–18th centuries in order to verify previous identification of the gems in the collection made by conservators. Cianchetta et al.28 used Raman spectroscopy to investigate the process used in the red and black coloring of Athenian pottery. They showed for the first time that these ancient materials were produced using at least two separate firings. Coccato et al.29 investigate carbon black pigments in works of art to elucidate the various sources and origins of different carbons used as artwork color pigments. Rousaki et al.30 analyzed the pigment composition of hunter-gathered archaeological samples from Northern Patagonia. Their work demonstrates these ancient people used clay-like materials rather than the usual hematite as a pigment agent. Belgodere et al.31 determine diffusion coefficients of dissolved carbon dioxide in varying salinities to predict the transport of dissolved gases in sedimentary sequences for mitigation of green house gas emissions. The 31 papers in this special issue dedicated to the 11th International GeoRaman Conference have expanded our understanding in a diverse range of fields. For example, the interaction of geological fluids and their measurement, elucidation of biological activity in recent and ancient environments here on Earth, astrobiological prospecting for life on Mars, thermal transformation of biologically precipitated minerals, mineral stability at the surface of the Earth, structure of economically important minerals, Raman spectroscopy as major tool for mineral identification, and pigment chemistry used in art and cultural artifacts. Given the enthusiasm and quest for knowledge in the GeoRaman community, together with the development of new Raman techniques, the future GeoRaman conferences should continue to generate exciting new research in the Earth Sciences. I would like to thank all the delegates, presenters, and conference assistants (providing great help in the background), the local organizing committee, the international science advisory committee, and Washington University in St. Louis for a wonderful venue. I am extremely grateful to the following companies and institutions that supported this conference: Washington University in St. Louis, Department of Earth and Planetary Sciences, McDonnell Center for Space Sciences, Universities Space Research Association, Lunar and Planetary Institute, Renishaw, WiTec, ThermoFisher Scientific, Andor, Bruker, BWTEK, GemLab Group, Horiba Scientific, Kaiser Optical System, Inc., Ondax, RPMC, SciAps, and R. H. Minerals. Special thanks to the Editor-in-Chief of the Journal of Raman Spectroscopy, Dr Larry Nafie, for making this special issue possible, and of course, to all the authors and reviewers of the manuscripts for their invaluable contribution. It was a pleasure and honor to serve as the guest editor for this diverse collection of papers, and I am looking forward to seeing you at the next GeoRaman conference in Novosibirsk, Russia in 2016!

This paper aims to present an integrated approach for well forecasting that combines advanced Machine Learning (ML) techniques to provide accurate oil, gas and water predictions for existing and new wells in oil reservoirs. Well forecasting is a critical task in the oil and gas industry for optimizing production and maximizing recovery from reservoirs. Traditionally, decline curve analysis has been widely used for well forecasting, but it has limitations in complex reservoirs or wells with uncertain decline trends. The proposed approach overcomes these limitations by utilizing advanced Machine Learning techniques that leverage complex real data for improved production forecasting. By incorporating ML algorithms, the proposed approach can provide more accurate and reliable predictions, particularly in challenging reservoir conditions where traditional methods may fall short. The proposed approach for well forecasting involves several key steps. Firstly, historical data of wells, including production, choke, well head flowing pressure, producing days, injection data, well connection properties, and 3D properties, are collected and preprocessed. Next, 2D properties, such as well location, spatial coordinates, and spatial attributes, are extracted from the 3D properties of the reservoir using geospatial algorithms. Then, for existing wells an ensemble of ML supervised algorithm is trained well by well with enough historical data, and nearby wells are used to train non mature wells. For future new wells, historical data plus geological 2D properties is used to create a model per reservoir. This involves collecting and preprocessing data from nearby wells in the vicinity of the new drilling location to obtain relevant properties. Uncertainty intervals are calculated using quantiles to quantify the uncertainty in the predictions. The integrated well forecasting approach presented in this paper provides a comprehensive solution for predicting well production in oil reservoirs. We used 2 different approaches to predict oil, gas and water production depending on the availability of historical data. Our approach allowed accurate predictions in complex reservoirs where wells have no clear decline trends. The use of uncertainty intervals provides a measure of prediction uncertainty, allowing for informed decision-making.

CTAB-modified carboxymethyl cellulose/bagasse cryogels for the efficient removal of bisphenol A, methylene blue and Cr(VI) ions: Batch and column adsorption studies

On the use of spectra from portable Raman and ATR-IR instruments in synthesis route attribution of a chemical warfare agent by multivariate modeling

Surface-enhancedRaman scattering (SERS) has become a promisingmethod for the detection of contaminants or biomolecules in aqueousmedia. The low interference of water, the unique spectral fingerprint,and the development of portable and handheld equipment for in situmeasurements underpin its predominance among other spectroscopic techniques.Among the SERS nanoparticle substrates, those composed of plasmonicand magnetic components are prominent examples of versatility andefficiency. These substrates harness the ability to capture the targetanalyte, concentrate it, and generate unique hotspots for superiorenhancement. Here, we have evaluated the use of gold-coated magnetitenanorods as a novel multifunctional magnetic–plasmonic SERSsubstrate. The nanostructures were synthesized starting from core-satellitestructures. A series of variants with different degrees of Au coatingswere then prepared by seed-mediated growth of gold, from core-satellitestructures to core–shell with partial and complete shells.All of them were tested, using a portable Raman instrument, with themodel molecule 4-mercaptobenzoic acid in colloidal suspension andafter magnetic separation. Experimental results were compared withthe boundary element method to establish the mechanism of Raman enhancement.The results show a quick magnetic separation of the nanoparticlesand excellent Raman enhancement for all the nanoparticles both indispersion and magnetically concentrated with limits of detectionup to the nM range (∼50 nM) and a quantitative calibrationcurve. The nanostructures were then tested for the sensing of theantibiotic ciprofloxacin, highly relevant in preventing antibioticcontaminants in water reservoirs and drug monitoring, showing thatciprofloxacin can be detected using a portable Raman instrument ata concentration as low as 100 nM in a few minutes, which makes ithighly relevant in practical point-of-care devices and in situ use.