The Fourier Transform Infrared(FTIR)and Fourier transform Raman(FT-Raman)spectra of 1,3-Diphenyl Propenone were recorded in the regions 4000~400 and 4000~100 cm^-1,respectively,in the solid phase.Molecular electronic ...The Fourier Transform Infrared(FTIR)and Fourier transform Raman(FT-Raman)spectra of 1,3-Diphenyl Propenone were recorded in the regions 4000~400 and 4000~100 cm^-1,respectively,in the solid phase.Molecular electronic energy,geometrical structure,harmonic vibrational spectra was computed at the DFT/6-31G(d,p)and three parameter hybrid functional Lee-Yang-Parr/6-31G(d,p)levels of theory.The vibrational studies were interpreted in terms of potential energy distribution(PED).The results were compared with experimental values with the help of scaling procedures.Most of the modes have wave numbers in the expected range and are in good agreement with computed values and also the molecular properties of Mulliken population analysis have been calculated.Besides,thermodynamic properties were performed.展开更多
Five-valued Boolean functions play an important role in the design of symmetric cryptography.While the design and properties of single-output almost optimal five-valued spectra Boolean functions have been extensively ...Five-valued Boolean functions play an important role in the design of symmetric cryptography.While the design and properties of single-output almost optimal five-valued spectra Boolean functions have been extensively studied over the past few decades,there has been limited research on the construction of almost optimal five-valued spectra vectorial Boolean functions.In this paper,we present a construction method for even-variable 2-output almost optimal five-valued spectra balanced Boolean functions,whose Walsh spectra values belong to the set{0,±2^(n/2),±2^(n/2+1)},at the same time,we discuss the existence of sufficient conditions in the construction.Additionally,this paper presents a novel construction method for balanced single-output Boolean functions with even variables featuring a special five-valued spectral structure,whose Walsh spectra values are constrained to the set{0,±2^(n/2),±3·2^(n/2)}.These functions provide new canonical examples for the study of Boolean function spectral theory.展开更多
WITHDRAWAL:Zhang,J.J.,Guo,Y.Q.,Qin,Z.Y.,Wei,C.T.,Hu,Q.H.,Vandeginste,V.,Miao,H.Y.,Yao,P.,and Zhang,P.F.,“Predicting Irreducible Water Saturation of Unconventional Reservoirs by Using NMR T2 Spectra:Methods of Morphol...WITHDRAWAL:Zhang,J.J.,Guo,Y.Q.,Qin,Z.Y.,Wei,C.T.,Hu,Q.H.,Vandeginste,V.,Miao,H.Y.,Yao,P.,and Zhang,P.F.,“Predicting Irreducible Water Saturation of Unconventional Reservoirs by Using NMR T2 Spectra:Methods of Morphological Division and Fractal Models”,Acta Geologica Sinica-English Edition(Accepted Article):https://doi.org/10.1111/1755-6724.15094.展开更多
In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution an...In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution and complex category boundary,mixed pixels containing features from multiple classes are inevitable in HSIs.Additionally,the spectral similarity among different classes challenge for extracting distinctive spectral features essential for HSIC.To address the impact of mixed pixels and spectral similarity for HSIC,we propose a central-pixel guiding sub-pixel and sub-channel convolution network(CP-SPSC)to extract more precise spatial and spectral features.Firstly,we designed spatial attention(CP-SPA)and spectral attention(CP-SPE)informed by the central pixel to effectively reduce spectral interference of irrelevant categories in the same patch.Furthermore,we use CP-SPA to guide 2D sub-pixel convolution(SPConv2d)to capture spatial features finer than the pixel level.Meanwhile,CP-SPE is also utilized to guide 1D sub-channel con-volution(SCConv1d)in selecting more precise spectral channels.For fusing spatial and spectral information at the feature-level,the spectral feature extension transformation module(SFET)adopts mirror-padding and snake permutation to transform 1D spectral information of the center pixel into 2D spectral features.Experiments on three popular datasets demonstrate that ours out-performs several state-of-the-art methods in accuracy.展开更多
Deep learning neural network incorporating surface enhancement Raman scattering technique(SERS)is becoming as a powerful tool for the precise classifications and diagnosis of bacterial infections.However,the large amo...Deep learning neural network incorporating surface enhancement Raman scattering technique(SERS)is becoming as a powerful tool for the precise classifications and diagnosis of bacterial infections.However,the large amount of sample requirement and time-consuming sample collection severely hinder its applications.We herein propose a spectral concatenation strategy for residual neural network using nonspecific and specific SERS spectra for the training data augmentation,which is accessible to acquiring larger training dataset with same number of SERS spectra or same size of training dataset with fewer SERS spectra,compared with pure non-specific SERS spectra.With this strategy,the training loss exhibit rapid convergence,and an average accuracy up to 100%in bacteria classifications was achieved with50 SERS spectra for each kind of bacterium;even reduced to 20 SERS spectra per kind of bacterium,classification accuracy is still>95%,demonstrating marked advantage over the results without spectra concatenation.This method can markedly improve the classification accuracy under fewer samples and reduce the data collection workload,and can evidently enhance the performance when used in different machine learning models with high generalization ability.Therefore,this strategy is beneficial for rapid and accurate bacteria classifications with residual neural network.展开更多
The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrin...The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrino anomaly.In this paper,we report a method that utilizes a feedforward neural network(FNN)model to decompose the prompt energy spectrum observed in a short-baseline reactor neutrino experiment and extract the antineutrino spectra produced by the fission of major isotopes such as^(235)U,^(238)U,^(239)Pu,and^(241)Pu in the nuclear reactor.We present two training strategies for the model and compare them with the traditional X^(2) minimization method by applying them to the same set of pseudo-data corresponding to a total exposure of(2.9×5×1800)GW_(th)·tons·days.The results show that the FNN model not only converges faster and better during the fitting process but also achieves relative errors of less than 1%in the 2−8 MeV range in the extracted spectra,outperforming the X^(2) minimization method.The feasibility and superiority of this method were validated in the study.展开更多
Electrochemical impedance spectroscopy(EIS)offers valuable insights into the dynamic behaviors of lithium-ion batteries,making it a powerful and non-invasive tool for evaluating battery health.However,EIS falls short ...Electrochemical impedance spectroscopy(EIS)offers valuable insights into the dynamic behaviors of lithium-ion batteries,making it a powerful and non-invasive tool for evaluating battery health.However,EIS falls short in quantitatively determining the degree of specific degradation modes,which are essential for improving battery lifespan.This study introduces a novel approach employing deep neural networks enhanced by an attention mechanism to identify the degree of degradation modes.The proposed method can automatically determine the most relevant frequency ranges for each degradation mode,which can link impedance characteristics to battery degradation.To overcome the limitation of scarce labeled experimental data,simulation results derived from mechanistic models are incorporated into the model.Validation results demonstrate that the proposed method could achieve root mean square errors below 3%for estimating loss of lithium inventory and loss of active material of the positive electrode,and below 4%for estimating loss of active material of the negative electrode while requiring only 25%of early-stage experimental degradation data.By integrating simulation results,the proposed method achieves a reduction in maximum estimation error ranging from 42.92%to 66.30%across different temperatures and operating conditions compared to the baseline model trained solely on experimental data.展开更多
The empirical models for wavenumber-frequency spectra of wall pressure are broadly used in the fast prediction of aerodynamic and hydrodynamic noise.However,it needs to fit the parameter using massive data and is only...The empirical models for wavenumber-frequency spectra of wall pressure are broadly used in the fast prediction of aerodynamic and hydrodynamic noise.However,it needs to fit the parameter using massive data and is only used for limited cases.In this letter,we propose Kolmogorov-Arnold networks(KAN)base models for wavenumber-frequency spectra of pressure fluctuations under turbulent boundary layers.The results are compared with DNS results.In turbulent channel flows,it is found that the KAN base model leads to a smooth wavenumber-frequency spectrum with sparse samples.In the turbulent flow over an axisymmetric body of revolution,the KAN base model captures the wavenumber-frequency spectra near the convective peak.展开更多
The anharmonic correction to displaced Franck-Condon(FC)factors introduces a first-order perturbative correction to the Huang-Rhys factors,enabling accurate simulation of vibronic spectra in the gas phase.In contrast,...The anharmonic correction to displaced Franck-Condon(FC)factors introduces a first-order perturbative correction to the Huang-Rhys factors,enabling accurate simulation of vibronic spectra in the gas phase.In contrast,the damped correction to displaced FC factors provides a non-perturbative modification to the Huang-Rhys factors for simulating vibronic spectra in solution,where the damped local-mode motions of the solute molecule effectively represent strong solute-solvent interactions.Practically,the damped FC method is implemented by transforming the mass-weighted unperturbed Hessian matrix(gas phase)into a perturbed Hessian matrix(solution phase)through effective scaling of atomic masses.The anharmonic FC method is applied to simulate the absorption and fluorescence spectra of the pyridine molecule.The results reveal an enhancement in absorption intensity and a corresponding weakening of fluorescence in the first excited state,which are in good agreement with experimental observations.The damped FC method is further employed to reproduce solvent-enhanced absorption and fluorescence spectra for perylene and carbazole molecules in solution.For perylene in benzene,a single-group mass-scaling parameter successfully reproduces the observed spectral enhancement.For carbazole in n-hexane,however,multiple-group mass-scaling parameters are required to capture the extremely enhanced spectral features.Overall,the present anharmonic and damped corrections to displaced Franck-Condon factors provide an analytically tractable and efficient framework for simulating vibronic spectra of large and complex molecular systems.展开更多
Prompt fission neutron spectra(PFNS)have a significant role in nuclear science and technology.In this study,the PFNS for^(239)Pu are evaluated using both differential and integral experimental data.A method that lever...Prompt fission neutron spectra(PFNS)have a significant role in nuclear science and technology.In this study,the PFNS for^(239)Pu are evaluated using both differential and integral experimental data.A method that leverages integral criticality benchmark experiments to constrain the PFNS data is introduced.The measured central values of the PFNS are perturbed by constructing a covariance matrix.The PFNS are sampled using two types of covariance matrices,either generated with an assumed correlation matrix and incorporating experimental uncertainties or derived directly from experimental reports.The joint Monte Carlo transport code is employed to perform transport simulations on five criticality benchmark assemblies by utilizing perturbed PFNS data.Extensive simulations result in an optimized PFNS that shows improved agreement with the integral criticality benchmark experiments.This study introduces a novel approach for optimizing differential experimental data through integral experiments,particularly when a covariance matrix is not provided.展开更多
Recently,information acquired at the canopy top,such as spectral and textural data,has been widely used to estimate plant nitrogen(N)accumulation(PNA).The response of crops to N uptake involves not only changes in hor...Recently,information acquired at the canopy top,such as spectral and textural data,has been widely used to estimate plant nitrogen(N)accumulation(PNA).The response of crops to N uptake involves not only changes in horizontal canopy top information but also an increase in vertical plant height(PH).It remains unclear whether the fusion of spectral indices with PH can improve the estimation performance of PNA models based on spectral remote sensing across different growth stages.展开更多
In this study,we analyzed the characteristics of three-dimensional excitation-emission matrix spectra(EEMs)of 150 samples from five industrial wastewater types and domestic sewage to track water pollution sources effe...In this study,we analyzed the characteristics of three-dimensional excitation-emission matrix spectra(EEMs)of 150 samples from five industrial wastewater types and domestic sewage to track water pollution sources effectively.We then developed a recognition model for wastewater EEMs by establishing a feature dataset containing fluorescence peak values and parameters derived from EEMs,integrated with machine learning techniques.This model enables the rapid and precise identification of pollution sources.Our findings suggest that although the EEMs of the sixwastewater categories are distinct,visual differentiation is challenging.This was confirmed by cosine similarity assessments,showing some samples with low within-group(<0.8)and high between-group(>0.95)similarities.Despite significant variations in EEMs features acrosswastewater categories,identifying specific pollutants remains difficult,especially for pulp mills and leather effluents.Among the tested classification algorithms,Support Vector Machine(SVM)achieved the highest performance with91.7%accuracy,94%precision,91%recall,and 92%F_(1)-score,outperforming K-Nearest Neighbors and Partial Least Squares Discriminant Analysis.The SVM significantly improved identification accuracy for pulpmill and leather processing wastewaters compared to other models.To enhance identification accuracy,further exploration of EEMs features and expanding the training dataset are recommended.Combining EEMs features with machine learning presents a promising method for improvingwater pollution supervision and source tracing in environmental management practices.展开更多
文摘The Fourier Transform Infrared(FTIR)and Fourier transform Raman(FT-Raman)spectra of 1,3-Diphenyl Propenone were recorded in the regions 4000~400 and 4000~100 cm^-1,respectively,in the solid phase.Molecular electronic energy,geometrical structure,harmonic vibrational spectra was computed at the DFT/6-31G(d,p)and three parameter hybrid functional Lee-Yang-Parr/6-31G(d,p)levels of theory.The vibrational studies were interpreted in terms of potential energy distribution(PED).The results were compared with experimental values with the help of scaling procedures.Most of the modes have wave numbers in the expected range and are in good agreement with computed values and also the molecular properties of Mulliken population analysis have been calculated.Besides,thermodynamic properties were performed.
基金National Natural Science Foundation of China(62272360)。
文摘Five-valued Boolean functions play an important role in the design of symmetric cryptography.While the design and properties of single-output almost optimal five-valued spectra Boolean functions have been extensively studied over the past few decades,there has been limited research on the construction of almost optimal five-valued spectra vectorial Boolean functions.In this paper,we present a construction method for even-variable 2-output almost optimal five-valued spectra balanced Boolean functions,whose Walsh spectra values belong to the set{0,±2^(n/2),±2^(n/2+1)},at the same time,we discuss the existence of sufficient conditions in the construction.Additionally,this paper presents a novel construction method for balanced single-output Boolean functions with even variables featuring a special five-valued spectral structure,whose Walsh spectra values are constrained to the set{0,±2^(n/2),±3·2^(n/2)}.These functions provide new canonical examples for the study of Boolean function spectral theory.
文摘WITHDRAWAL:Zhang,J.J.,Guo,Y.Q.,Qin,Z.Y.,Wei,C.T.,Hu,Q.H.,Vandeginste,V.,Miao,H.Y.,Yao,P.,and Zhang,P.F.,“Predicting Irreducible Water Saturation of Unconventional Reservoirs by Using NMR T2 Spectra:Methods of Morphological Division and Fractal Models”,Acta Geologica Sinica-English Edition(Accepted Article):https://doi.org/10.1111/1755-6724.15094.
基金supported by the National Natural Science Foundation of China(No.62071323).
文摘In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution and complex category boundary,mixed pixels containing features from multiple classes are inevitable in HSIs.Additionally,the spectral similarity among different classes challenge for extracting distinctive spectral features essential for HSIC.To address the impact of mixed pixels and spectral similarity for HSIC,we propose a central-pixel guiding sub-pixel and sub-channel convolution network(CP-SPSC)to extract more precise spatial and spectral features.Firstly,we designed spatial attention(CP-SPA)and spectral attention(CP-SPE)informed by the central pixel to effectively reduce spectral interference of irrelevant categories in the same patch.Furthermore,we use CP-SPA to guide 2D sub-pixel convolution(SPConv2d)to capture spatial features finer than the pixel level.Meanwhile,CP-SPE is also utilized to guide 1D sub-channel con-volution(SCConv1d)in selecting more precise spectral channels.For fusing spatial and spectral information at the feature-level,the spectral feature extension transformation module(SFET)adopts mirror-padding and snake permutation to transform 1D spectral information of the center pixel into 2D spectral features.Experiments on three popular datasets demonstrate that ours out-performs several state-of-the-art methods in accuracy.
基金supported by the National Key Research and Development Program of China(No.2023YFC3402900)the National Nature Science of Foundation(No.61875131)+1 种基金Shenzhen Key Laboratory of Photonics and Biophotonics(No.ZDSYS20210623092006020)Shenzhen Science and Technology Innovation Program(No.20231120175730001)。
文摘Deep learning neural network incorporating surface enhancement Raman scattering technique(SERS)is becoming as a powerful tool for the precise classifications and diagnosis of bacterial infections.However,the large amount of sample requirement and time-consuming sample collection severely hinder its applications.We herein propose a spectral concatenation strategy for residual neural network using nonspecific and specific SERS spectra for the training data augmentation,which is accessible to acquiring larger training dataset with same number of SERS spectra or same size of training dataset with fewer SERS spectra,compared with pure non-specific SERS spectra.With this strategy,the training loss exhibit rapid convergence,and an average accuracy up to 100%in bacteria classifications was achieved with50 SERS spectra for each kind of bacterium;even reduced to 20 SERS spectra per kind of bacterium,classification accuracy is still>95%,demonstrating marked advantage over the results without spectra concatenation.This method can markedly improve the classification accuracy under fewer samples and reduce the data collection workload,and can evidently enhance the performance when used in different machine learning models with high generalization ability.Therefore,this strategy is beneficial for rapid and accurate bacteria classifications with residual neural network.
基金supported by the China Postdoctoral Science Foundation(No.2024M753715)Fundamental Research Funds for the Central Universities,Sun Yat-sen University(Nos.24qnpy125 and 22lglj11)Guangdong Basic and Applied Basic Research Foundation(No.2023B1515120030).
文摘The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrino anomaly.In this paper,we report a method that utilizes a feedforward neural network(FNN)model to decompose the prompt energy spectrum observed in a short-baseline reactor neutrino experiment and extract the antineutrino spectra produced by the fission of major isotopes such as^(235)U,^(238)U,^(239)Pu,and^(241)Pu in the nuclear reactor.We present two training strategies for the model and compare them with the traditional X^(2) minimization method by applying them to the same set of pseudo-data corresponding to a total exposure of(2.9×5×1800)GW_(th)·tons·days.The results show that the FNN model not only converges faster and better during the fitting process but also achieves relative errors of less than 1%in the 2−8 MeV range in the extracted spectra,outperforming the X^(2) minimization method.The feasibility and superiority of this method were validated in the study.
基金supported by the National Key R&D Program of China(2024YFB2505003).
文摘Electrochemical impedance spectroscopy(EIS)offers valuable insights into the dynamic behaviors of lithium-ion batteries,making it a powerful and non-invasive tool for evaluating battery health.However,EIS falls short in quantitatively determining the degree of specific degradation modes,which are essential for improving battery lifespan.This study introduces a novel approach employing deep neural networks enhanced by an attention mechanism to identify the degree of degradation modes.The proposed method can automatically determine the most relevant frequency ranges for each degradation mode,which can link impedance characteristics to battery degradation.To overcome the limitation of scarce labeled experimental data,simulation results derived from mechanistic models are incorporated into the model.Validation results demonstrate that the proposed method could achieve root mean square errors below 3%for estimating loss of lithium inventory and loss of active material of the positive electrode,and below 4%for estimating loss of active material of the negative electrode while requiring only 25%of early-stage experimental degradation data.By integrating simulation results,the proposed method achieves a reduction in maximum estimation error ranging from 42.92%to 66.30%across different temperatures and operating conditions compared to the baseline model trained solely on experimental data.
基金supported by the National Natural Science Foundation of China Basic Science Center Program for“Multiscale Problems in Nonlinear Mechanics”(Grant No.11988102)the National Natural Science Foundation of China(Grant Nos.92252203,12102439,and 12425207)+1 种基金the Chinese Academy of Sciences Project for Young Scientists in Basic Research(Grant No.YSBR-087)the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDB0620102).
文摘The empirical models for wavenumber-frequency spectra of wall pressure are broadly used in the fast prediction of aerodynamic and hydrodynamic noise.However,it needs to fit the parameter using massive data and is only used for limited cases.In this letter,we propose Kolmogorov-Arnold networks(KAN)base models for wavenumber-frequency spectra of pressure fluctuations under turbulent boundary layers.The results are compared with DNS results.In turbulent channel flows,it is found that the KAN base model leads to a smooth wavenumber-frequency spectrum with sparse samples.In the turbulent flow over an axisymmetric body of revolution,the KAN base model captures the wavenumber-frequency spectra near the convective peak.
基金supported by Ministry of Science and Technology,Taiwan Province(No.110-2113-M-A49-022).
文摘The anharmonic correction to displaced Franck-Condon(FC)factors introduces a first-order perturbative correction to the Huang-Rhys factors,enabling accurate simulation of vibronic spectra in the gas phase.In contrast,the damped correction to displaced FC factors provides a non-perturbative modification to the Huang-Rhys factors for simulating vibronic spectra in solution,where the damped local-mode motions of the solute molecule effectively represent strong solute-solvent interactions.Practically,the damped FC method is implemented by transforming the mass-weighted unperturbed Hessian matrix(gas phase)into a perturbed Hessian matrix(solution phase)through effective scaling of atomic masses.The anharmonic FC method is applied to simulate the absorption and fluorescence spectra of the pyridine molecule.The results reveal an enhancement in absorption intensity and a corresponding weakening of fluorescence in the first excited state,which are in good agreement with experimental observations.The damped FC method is further employed to reproduce solvent-enhanced absorption and fluorescence spectra for perylene and carbazole molecules in solution.For perylene in benzene,a single-group mass-scaling parameter successfully reproduces the observed spectral enhancement.For carbazole in n-hexane,however,multiple-group mass-scaling parameters are required to capture the extremely enhanced spectral features.Overall,the present anharmonic and damped corrections to displaced Franck-Condon factors provide an analytically tractable and efficient framework for simulating vibronic spectra of large and complex molecular systems.
基金supported by the National Natural Science Foundation of China(No.12347126)。
文摘Prompt fission neutron spectra(PFNS)have a significant role in nuclear science and technology.In this study,the PFNS for^(239)Pu are evaluated using both differential and integral experimental data.A method that leverages integral criticality benchmark experiments to constrain the PFNS data is introduced.The measured central values of the PFNS are perturbed by constructing a covariance matrix.The PFNS are sampled using two types of covariance matrices,either generated with an assumed correlation matrix and incorporating experimental uncertainties or derived directly from experimental reports.The joint Monte Carlo transport code is employed to perform transport simulations on five criticality benchmark assemblies by utilizing perturbed PFNS data.Extensive simulations result in an optimized PFNS that shows improved agreement with the integral criticality benchmark experiments.This study introduces a novel approach for optimizing differential experimental data through integral experiments,particularly when a covariance matrix is not provided.
基金supported by the National Key Research and Development Plan Project Sub-Topic of China(Grant Nos.2022YFD1901500 and 2022YFD1901505-07)the National Natural Science Foundation of China(Grant No.32260531)+1 种基金the Key Laboratory of Molecular Breeding for Grain and Oil Crops in Guizhou Province,China(Grant No.Qiankehezhongyindi[2023]8)the Key Laboratory of Functional Agriculture of Guizhou Provincial Higher Education Institutions,China(Grant No.Qianjiaoji[2023]007).
文摘Recently,information acquired at the canopy top,such as spectral and textural data,has been widely used to estimate plant nitrogen(N)accumulation(PNA).The response of crops to N uptake involves not only changes in horizontal canopy top information but also an increase in vertical plant height(PH).It remains unclear whether the fusion of spectral indices with PH can improve the estimation performance of PNA models based on spectral remote sensing across different growth stages.
基金supported by the Leading Talent of the Science and Technology Nova Program of Zhejiang(No.2020R52039)the Outstanding Innovative Team Supporting Plan of Jiaxing City(No.2022-LHYJ-02-0503-02)+1 种基金the Key Research Project of Yangtze Delta Region Institute of Tsinghua University(No.2023ZQZ005)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.SJCX22-1386).
文摘In this study,we analyzed the characteristics of three-dimensional excitation-emission matrix spectra(EEMs)of 150 samples from five industrial wastewater types and domestic sewage to track water pollution sources effectively.We then developed a recognition model for wastewater EEMs by establishing a feature dataset containing fluorescence peak values and parameters derived from EEMs,integrated with machine learning techniques.This model enables the rapid and precise identification of pollution sources.Our findings suggest that although the EEMs of the sixwastewater categories are distinct,visual differentiation is challenging.This was confirmed by cosine similarity assessments,showing some samples with low within-group(<0.8)and high between-group(>0.95)similarities.Despite significant variations in EEMs features acrosswastewater categories,identifying specific pollutants remains difficult,especially for pulp mills and leather effluents.Among the tested classification algorithms,Support Vector Machine(SVM)achieved the highest performance with91.7%accuracy,94%precision,91%recall,and 92%F_(1)-score,outperforming K-Nearest Neighbors and Partial Least Squares Discriminant Analysis.The SVM significantly improved identification accuracy for pulpmill and leather processing wastewaters compared to other models.To enhance identification accuracy,further exploration of EEMs features and expanding the training dataset are recommended.Combining EEMs features with machine learning presents a promising method for improvingwater pollution supervision and source tracing in environmental management practices.
