Assessment of artificial neural network to identify compositional differences in ultrahigh-resolution mass spectra acquired from coal mine affected soils

Enhancing ToF-SIMS OLED Data Analysis with Neural Networks and Mathematical Spectral Mixing

This study presents a method employing artificial neural networks (ANN) for automated interpretation and depth profiling of organic multilayers using a limited set of time-of-flight secondary ion mass spectrometry (ToF-SIMS) spectra. To overcome the challenges of acquiring massive data sets for OLEDs, training data was generated by combining existing ToF-SIMS data sets with mathematically generated spectra. The classification model achieved an impressive 99.9% accuracy in identifying the mixed layers of the OLED dyes. The study demonstrates the synergy of ToF-SIMS and ANN analysis for effective classification and depth profiling of the OLED layers, providing valuable insights for the development and optimization of organic electronic devices.

Comparative analysis of organic chemical compositions in airborne particulate matter from Ulaanbaatar, Beijing, and Seoul using UPLC-FT-ICR-MS and artificial neural network

This paper presents comparative study on the composition and sources of PM2.5 in Ulaanbaatar, Beijing, and Seoul. Ultrahigh performance liquid chromatography (UPLC) combined with ultrahigh resolution mass spectrometry (UHR-MS) were employed to analyze 85 samples collected in winter. The obtained 340 spectra were interpreted with artificial neural network (ANN). PM2.5 mass concentrations in Ulaanbaatar were significantly higher than those in Beijing and Seoul. ANN based interpretation of UPLC UHR-MS data showed that aliphatic/lipid derived organo‑sulfur compounds, polycyclic aromatic and organo‑oxygen compounds were characteristic to Ulaanbaatar. Whereas, aliphatic/lipid-derived organo‑oxygen compounds were major components in Beijing and Seoul. Aromatic organo‑nitrogen compounds were the main contributors to differentiating the spectra obtained from Beijing from the other cities. Based on two-dimensional gas chromatography/high resolution mass spectrometric (GCxGC/HRMS) data, it was determined that the concentrations of the polycyclic aromatic hydrocarbon (PAH) and polycyclic aromatic sulfur heterocycle (PASH) containing sulfur were highest in Ulaanbaatar, followed by Beijing and Seoul. Coal/biomass combustion was identified as the primary source of contamination in Ulaanbaatar, while petroleum combustion was the main contributor to PM2.5 in Beijing and Seoul. The conclusion that diesel-powered heavy-duty trucks and buses are the main contributors to NOx emissions in Beijing is consistent with previous reports. This study provides a more comprehensive understanding of the composition and sources of PM2.5 in the three cities, with a focus on the differences in their atmospheric pollution profiles based on the UPLC UHR-MS and ANN analysis. It is notable that this study is the first to utilize this method on a large-scale sample set, providing a more detailed and molecular-level understanding of the compositional differences among PM2.5. Overall, the study contributes to a better understanding of the sources and composition of PM2.5 in Northeast Asia, which is essential for developing effective strategies to reduce air pollution and improve public health.

Research on the Effects of Drying Temperature for the Detection of Soil Nitrogen by Near-Infrared Spectroscopy

Nitrogen nitrates play a significant role in the soil's nutrient cycle, and near-infrared spectroscopy can efficiently and accurately detect the content of nitrate-nitrogen in the soil. Accordingly, it can provide a scientific basis for soil improvement and agricultural productivity by deeply examining the cycle and transformation pattern of nutrients in the soil. To investigate the impact of drying temperature on NIR soil nitrogen detection, soil samples with different N concentrations were dried at temperatures of 50 °C, 65 °C, 80 °C, and 95 °C, respectively. Additionally, soil samples naturally air-dried at room temperature (25 °C) were used as a control group. Different drying times were modified based on the drying temperature to completely eliminate the impact of moisture. Following data collection with an NIR spectrometer, the best preprocessing method was chosen to handle the raw data. Based on the feature bands chosen by the RFFS, CARS, and SPA methods, two linear models, PLSR and SVM, and a nonlinear ANN model were then established for analysis and comparison. It was found that the drying temperature had a great effect on the detection of soil nitrogen by near-infrared spectroscopy. In the meantime, the SPA-ANN model simultaneously yielded the best and most stable accuracy, with Rc2 = 0.998, Rp2 = 0.989, RMSEC = 0.178 g/kg, and RMSEP = 0.257 g/kg. The results showed that NIR spectroscopy had the least effect and the highest accuracy in detecting nitrogen at 80 °C soil drying temperature. This work provides a theoretical foundation for agricultural production in the future.

Identification and quantification of photodegradation products of disposed expanded polystyrene buoy used in aquaculture

This study investigated the chemicals extracted from an EPS buoy used in aquaculture, which were subsequently collected from a recycling center. It was observed that the chemicals generated upon photodegradation make disposed buoys more toxic. Analysis of the extracted chemicals revealed the presence of 37 compounds, with four compounds quantitatively determined. Further analysis showed that the quantity of compounds dissolved in seawater was significantly higher than the amount remaining on the buoy surface. Based on the assumption that the buoy was exposed to sunlight for a year, it was estimated that 14.44 mg of the four compounds dissolved into the ocean. Given that South Korea used over 7 million EPS buoys, photodegraded EPS buoys are expected to represent a significant source of potentially hazardous chemicals.

MnO2-Induced Oxidation of Iodide in Frozen Solution

Metal oxides play a critical role in the abiotic transformation of iodine species in natural environments. In this study, we investigated iodide oxidation by manganese dioxides (β-MnO₂, γ-MnO₂, and δ-MnO₂) in frozen and aqueous solutions. The heterogeneous reaction produced reactive iodine (RI) in the frozen phase, and the subsequent thawing of the frozen sample induced the gradual transformation of in situ-formed RI to iodate or iodide, depending on the types of manganese dioxides. The freezing-enhanced production of RI was observed over the pH range of 5.0-9.0, but it decreased with increasing pH. Fulvic acid (FA) can be iodinated by I^-/MnO₂ in aqueous and frozen solutions. About 0.8-8.4% of iodide was transformed to organoiodine compounds (OICs) at pH 6.0-7.8 in aqueous solution, while higher yields (10.4-17.8%) of OICs were obtained in frozen solution. Most OICs generated in the frozen phase contained one iodine atom and were lignin-like compounds according to Fourier transform ion cyclotron resonance/mass spectrometry analysis. This study uncovers a previously unrecognized production pathway of OICs under neutral conditions in frozen environments.

Advances and key considerations of liquid chromatography–mass spectrometry for porcine authentication in halal analysis

The halal food industries are rapidly expanding to fulfill global halal demands. Non-halal substances such as porcine proteins are often added intentionally or unintentionally to products. The development of highly selective and sensitive analytical tools is necessary, and liquid chromatography–mass spectrometry is a powerful tool that can cope with the challenge. The LC–MS method has great potential for halal authentication, because it has high sensitivity and low detection limit and detects several species markers and different tissue origins at once within one species. This article provides an understanding of recent advances in the application of LC–MS for the improvement of porcine authentication. Sample preparation, marker selection, separation and mass spectrometry conditions, quantitative assessment, and data processing for protein identification were all covered in detail to choose the most suitable method for the analytical needs.

Weight interpretation of artificial neural network model for analysis of rice (Oryza sativa L.) with near-infrared spectroscopy

•

ANN model was build based on NIR spectra and nutrient values of 110 rice samples.

•

Good correlation between ANN predicted and experimental nutrient values observed.

•

Scientific interpretation of weights agreed well with previously reported results.

•

Interpretation of weights was also in good agreement with conventional PLS analysis.

Prediction models for major nutrients of rice were built using near-infrared (NIR) spectral data based on the artificial neural network (ANN). Scientific interpretation of the weight values was proposed and performed to understand the wavenumbers contributing to the prediction of nutrients. NIR spectra were acquired from 110 rice samples. Carbohydrate and moisture contents were predicted with values for the determination coefficient, relative root mean square error, range error ratio, and residual prediction deviation of 0.98, 0.11 %, 44, and 7.3, and 0.97, 0.80 %, 27, and 5.8, respectively. The results agreed well with ones reported in the previous studies and acquired by the conventional partial least squares (PLS)-variable importance in projection method. This study demonstrates that the combination of NIR and ANN is a powerful and accurate tool to monitor nutrients of rice and scientific interpretation of weights can be performed to overcome black box nature of the ANN.