Feature Model Research Articles

Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study

ObjectiveTo evaluate the feasibility of utilizing artificial intelligence (AI)-predicted biparametric MRI (bpMRI) image features for predicting the aggressiveness of prostate cancer (PCa).Materials and methodsA total of 878 PCa patients from 4 hospitals were retrospectively collected, all of whom had pathological results after radical prostatectomy (RP). A pre-trained AI algorithm was used to select suspected PCa lesions and extract lesion features for model development. The study evaluated five prediction methods, including (1) A clinical-imaging model of clinical features and image features of suspected PCa lesions selected by AI algorithm, (2) the PIRADS category, (3) a conventional radiomics model, (4) a deep-learning bases radiomics model, and (5) biopsy pathology.ResultsIn the externally validated dataset, the deep learning-based radiomics model showed the highest area under the curve (AUC 0.700 to 0.791). It exceeded the clinical-imaging model (AUC 0.597 to 0.718), conventional radiomic model (AUC 0.566 to 0.632), PIRADS score (AUC 0.554 to 0.613), and biopsy pathology (AUC 0.537 to 0.578). The AUC predicted by the model did not show a statistically significant difference among the three externally verified hospitals (p > 0.05).ConclusionDeep-learning radiomics models utilizing AI-extracted image features from bpMRI images can potentially be used to predict PCa aggressiveness, demonstrating a generalized ability for external validation.Critical relevance statementPredicting the aggressiveness of prostate cancer (PCa) is important for formulating the best treatment plan for patients. The radiomic model based on deep learning is expected to provide an objective and non-invasive method for evaluating the aggressiveness of PCa.Key PointsPredicting the aggressiveness of PCa is important for patients to obtain the best treatment options.The deep learning-based radiomics model can predict the aggressiveness of PCa with high accuracy.The model has good universality when tested on multiple external datasets.Graphical

An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features

Accurate prediction of natural gas purchase volumes is crucial for both the economy and the environment. It not only facilitates the rational allocation of resources for companies but also helps to reduce operational costs. Although existing prediction methods have achieved some success in addressing the nonlinear relationships in natural gas purchases, there remains potential for further improvement. To address this issue, a stacking ensemble learning model was developed to enhance the ability to handle complex nonlinear problems. This model integrates diverse algorithms and incorporates weather factors, while regionalizing characteristics of natural gas usage, thereby achieving accurate forecasts of natural gas purchase volumes. We selected three distinctly different base models—Informer, multiple linear regression (MLR), and support vector regression (SVR)—for our research. By conducting four different feature combination experiments for each base model, including weather, time, regional, and usage features, we constructed 12 foundational models. Subsequently, we integrated these base models using a meta-learner to form the final stacking ensemble model. The experimental results indicate that the stacking ensemble model outperforms individual models across key metrics, including R2, MRE, and RMSE. Notably, the R2 values improved by 4–15% compared to the 12 base models. The model was subsequently applied to predict natural gas purchase volumes in Pi County, Chengdu, China. In November 2024, a side-by-side comparison of the predicted and actual data revealed a maximum error of just 5.39%. This exceptional accuracy effectively meets forecasting requirements, underscoring the model’s predictive strength in the energy sector.

Stylistic Challenges of Translating Legal Texts from Arabic into English among Jadara University Graduates

This research examines the stylistic obstacles encountering Translation master’s students when rendering Arabic legal texts into English. It delineates the influence of attaining the legal stylistic conventions in delivering a desirable legal translation. The study investigates the 20 participants’ renditions of five Arabic legal documents into English from qualitative and quantitative perspectives. Al-Jarf’s model of the salient stylistic features of legal language and Newmark’s model of translation strategies are deployed to comparatively analyse the interpretations of the legal texts translated. The study has identified considerable stylistic challenges in the rendered Arabic legal texts clearly seen in the absence of complex sentences, appropriate tense, lines and use of dots, conditional sentences, passivation, capitalization, nominalization, unique determiners, appropriate negation and restrictive connectors in addition to a number of inconvenient translation methods. The absence of these stylistic features is shown to lead to a serious deterioration in the translation quality of the legal texts translated owing to the loss of the legal themes and meanings signaled by these stylistic devices and conventions. The research has revealed that these stylistic challenges are noticeably arisen from the participants’ deficiency in the knowledge and experience in the stylistic conventions of SL and TL legal systems along with their linguistic incompetence in the SL and TL. This tendency to produce improper legal translation has also noticed to be linked to heavy reliance on machine and through translations on the expense of the contextual rendition of the respective legal text.

EnrichRBP: an automated and interpretable computational platform for predicting and analyzing RNA-binding protein events.

Predicting RNA-binding proteins (RBPs) is central to understanding post-transcriptional regulatory mechanisms. Here, we introduce EnrichRBP, an automated and interpretable computational platform specifically designed for the comprehensive analysis of RBP interactions with RNA. EnrichRBP is a web service that enables researchers to develop original deep learning and machine learning architectures to explore the complex dynamics of RNA-binding proteins. The platform supports 70 deep learning algorithms, covering feature representation, selection, model training, comparison, optimization, and evaluation, all integrated within an automated pipeline. EnrichRBP is adept at providing comprehensive visualizations, enhancing model interpretability, and facilitating the discovery of functionally significant sequence regions crucial for RBP interactions. In addition, EnrichRBP supports base-level functional annotation tasks, offering explanations and graphical visualizations that confirm the reliability of the predicted RNA binding sites. Leveraging high-performance computing, EnrichRBP provides ultra-fast predictions ranging from seconds to hours, applicable to both pre-trained and custom model scenarios, thus proving its utility in real-world applications. Case studies highlight that EnrichRBP provides robust and interpretable predictions, demonstrating the power of deep learning in the functional analysis of RBP interactions. Finally, EnrichRBP aims to enhance the reproducibility of computational method analyses for RNA-binding protein sequences, as well as reduce the programming and hardware requirements for biologists, thereby offering meaningful functional insights. EnrichRBP is available at https://airbp.aibio-lab.com/. The source code is available at https://github.com/wangyb97/EnrichRBP, and detailed online documentation can be found at https://enrichrbp.readthedocs.io/en/latest/. Supplementary data are available at Bioinformatics online.

Empirical modeling of torsional strength in reinforced concrete beams using iterated local search with semantic cluster operator

AbstractThis study conducted a data‐based analysis on the impact of a feature and empirical modeling to increase the accuracy of analytical models related to torsional strength. The torsional strength data of 324 plain and reinforced concrete beams were collected from previous studies, which included data from specimens with various cross‐sectional sizes, material strengths, reinforcement ratios, and cover thicknesses. The data was clustered to analyze the effect of each feature, and the importance of each feature was derived using the Shapley additive explanations technique. An iterated local search using a semantic cluster operator was used to derive simple and highly accurate empirical models to predict the torsional strength. The proposed models predicted the ultimate strength by multiplying the contribution of concrete and transverse reinforcement, contrary to the current codes, and showed better accuracy than the existing models.

Cardiac computer tomography-derived radiomics in assessing myocardial characteristics at the connection between the left atrial appendage and the left atrium in atrial fibrillation patients

ObjectivesTo evaluate the feasibility of utilizing cardiac computer tomography (CT) images for extracting the radiomic features of the myocardium at the junction between the left atrial appendage (LAA) and the left atrium (LA) in patients with atrial fibrillation (AF) and to evaluate its asscociation with the risk of AF.MethodsA retrospective analysis was conducted on 82 cases of AF and 56 cases in the control group who underwent cardiac CT at our hospital from May 2022 to May 2023, with recorded clinical information. The morphological parameters of the LAA were measured. A radiomics model, a clincal feature model and a model combining radiomics and clinical features were constructed. The radiomics model was built by extracting radiomic features of the myocardial tissue using Pyradiomics, and employing Least absolute shrinkage and selection operator (LASSO) method for feature selection, combining random forest with support vector machine (SVM) classifier.ResultsThere were 82 cases in the AF group [44 males, 65.00 (59, 70)], and 56 cases in the control group (21 males, 61.09 ± 7.18). Age, BMI, hypertension, CHA2DS-VASC score, neutrophil to lymphocyte ratio (NLR), LAA volume, LA volume, the myocardial thickness at the junction of LAA and LA, the area, circumference, short diameter, and long diameter of the LAA opening, were significantly different between the AF group and the control group (P < 0.05). After conducting multivariate logistic regression analysis, it was found that BMI, the myocardial thickness at the junction of the LAA and the LA, LA volume, NLR and CHA2DS-VASC score were related to AF. 12 radiomics features of the myocardium at the junction of the LAA and the LA were extracted and identified. ROC curve analysis confirmed that the nomogram based on radiomics scores and clinical factors can effectively predict AF (AUC 0.869).ConclusionRadiomics enables the extraction of the myocardial characteristics at the junction of the LAA and the LA, which are related with AF, facilitating the assessment of its relationship with the risk of AF. The combination of radiomics with clinical characteristics enhances the evaluation capabilities significantly.

An Efficient Retinal Fluid Segmentation Network Based on Large Receptive Field Context Capture for Optical Coherence Tomography Images

Optical Coherence Tomography (OCT) is a crucial imaging modality for diagnosing and monitoring retinal diseases. However, the accurate segmentation of fluid regions and lesions remains challenging due to noise, low contrast, and blurred edges in OCT images. Although feature modeling with wide or global receptive fields offers a feasible solution, it typically leads to significant computational overhead. To address these challenges, we propose LKMU-Lite, a lightweight U-shaped segmentation method tailored for retinal fluid segmentation. LKMU-Lite integrates a Decoupled Large Kernel Attention (DLKA) module that captures both local patterns and long-range dependencies, thereby enhancing feature representation. Additionally, it incorporates a Multi-scale Group Perception (MSGP) module that employs Dilated Convolutions with varying receptive field scales to effectively predict lesions of different shapes and sizes. Furthermore, a novel Aggregating-Shift decoder is proposed, reducing model complexity while preserving feature integrity. With only 1.02 million parameters and a computational complexity of 3.82 G FLOPs, LKMU-Lite achieves state-of-the-art performance across multiple metrics on the ICF and RETOUCH datasets, demonstrating both its efficiency and generalizability compared to existing methods.

Noninvasive identification of HER2 status by integrating multiparametric MRI-based radiomics model with the vesical imaging-reporting and data system (VI-RADS) score in bladder urothelial carcinoma.

HER2 expression is crucial for the application of HER2-targeted antibody-drug conjugates. This study aims to construct a predictive model by integrating multiparametric magnetic resonance imaging (mpMRI) based multimodal radiomics and the Vesical Imaging-Reporting and Data System (VI-RADS) score for noninvasive identification of HER2 status in bladder urothelial carcinoma (BUC). A total of 197 patients were retrospectively enrolled and randomly divided into a training cohort (n = 145) and a testing cohort (n = 52). The multimodal radiomics features were derived from mpMRI, which were also utilized for VI-RADS score evaluation. LASSO algorithm and six machine learning methods were applied for radiomics feature screening and model construction. The optimal radiomics model was selected to integrate with VI-RADS score to predict HER2 status, which was determined by immunohistochemistry. The performance of predictive model was evaluated by receiver operating characteristic curve with area under the curve (AUC). Among the enrolled patients, 110 (55.8%) patients were demonstrated with HER2-positive and 87 (44.2%) patients were HER2-negative. Eight features were selected to establish radiomics signature. The optimal radiomics signature achieved the AUC values of 0.841 (95% CI 0.779-0.904) in the training cohort and 0.794 (95%CI 0.650-0.938) in the testing cohort, respectively. The KNN model was selected to evaluate the significance of radiomics signature and VI-RADS score, which were integrated as a predictive nomogram. The AUC values for the nomogram in the training and testing cohorts were 0.889 (95%CI 0.840-0.938) and 0.826 (95%CI 0.702-0.950), respectively. Our study indicated the predictive model based on the integration of mpMRI-based radiomics and VI-RADS score could accurately predict HER2 status in BUC. The model might aid clinicians in tailoring individualized therapeutic strategies.

Machine Learning-Assisted Prediction of Photothermal Metal-Phenolic Networks.

Photothermal therapy (PTT) demonstrates significant potential in cancer treatment, wound healing, and antibacterial therapy, with its efficacy largely depending on the performance of photothermal agents (PTAs). Metal-phenolic network (MPN) materials are ideal PTA candidates due to their low cost, good biocompatibility and excellent ligand-to-metal charge transfer properties. However, not all MPNs exhibit significant photothermal properties, and the vast chemical space of MPNs (over 700,000 potential combinations) complicates the screening of high-photothermal materials. To address this challenge, this study introduces machine learning (ML) methods for predicting the photothermal performance of MPNs. A database of photothermal properties of 80 modular MPNs was constructed, and the ML process was optimized through feature engineering and model training. The selected extreme gradient boosting model (XGBoost) successfully identified 1,654 high photothermal MPNs from a virtual database of 44,438. Subsequent experimental validation revealed a remarkable success rate of 70% in predicting high photothermal MPNs. Additionally, several previously unreported high photothermal MPNs were discovered, demonstrating advantages in photothermal antibacterial applications. This study offers an innovative ML-driven approach for the efficient screening of MPN materials, providing a solid foundation for PTA design in PTT and other biomedical applications.

Prediction of Structural Vibration Induced by Subway Operations Using Hybrid Method Based on Improved LSTM and Spectral Analysis

With the rapid expansion of urban subway networks, vibrations induced by subway operations have become an increasingly significant concern for nearby structures. To assess the influence of subway-induced vibrations on nearby structures, it is essential to predict the vibration effects accurately prior to the construction of the subway system. By combining an improved Long Short-Term Memory (LSTM) model with a spectral analysis, this paper proposes a hybrid method to enhance the accuracy and efficiency of predicting structural vibrations induced by subway operations. The improved LSTM model is composed of BiLSTM, an attention mechanism, and the DBO algorithm. The symmetry inherent in the vibration propagation paths and the structural layouts of subway systems is leveraged to improve the feature extraction and modeling accuracy. Additionally, the hybrid method utilizes the symmetric properties of vibration signals in the spectral domain to enhance prediction robustness and efficiency. Then, the hybrid method is utilized to rapidly achieve highly accurate vibration responses induced by subway operations. The verification results demonstrate the following: (1) The improved LSTM model enhances the ability to recognize patterns in time-series vibration data, leading to improved model convergence and generalization. The improved LSTM mode has a significant improvement in prediction accuracy compared to the standard LSTM network. For numerical simulation and real-world measured signals, values of R2 increased by 3% and 49.37%. (2) The proposed hybrid method significantly reduces computational time while ensuring results consistent with those obtained from the time-history analysis method. Applying the proposed hybrid method for data augmentation enhances the accuracy of the spectral analysis. The hybrid method achieves an improvement of 7% for the prediction accuracy.

Pore-scale modeling of biofilm formation and biofilm-induced anomalous transport features in heterogenous porous media

Pore-scale modeling of biofilm formation and biofilm-induced anomalous transport features in heterogenous porous media

Enhancing Identification of High-Risk cN0 Lung Adenocarcinoma Patients Using MRI-Based Radiomic Features.

This study aimed to develop a magnetic resonance imaging (MRI)-based radiomics model to predict high-risk pathologic features for lung adenocarcinoma: micropapillary and solid pattern (MPsol), spread through air space, and poorly differentiated patterns. As a prospective study, we screened clinical N0 lung cancer patients who were surgical candidates and had undergone both 18F-fluorodeoxyglucose (FDG) positron emission tomography-computed tomography (PET/CT) and chest CT from August 2018 to January 2020. We recruited patients meeting our proposed imaging criteria indicating high-risk, that is, poorer prognosis of lung adenocarcinoma, using CT and FDG PET/CT. If possible, these patients underwent an MRI examination from which we extracted 77 radiomics features from T1-contrast-enhanced and T2-weighted images. Additionally, patient demographics, maximum standardized uptake value on FDG PET/CT, and the mean apparent diffusion coefficient value on diffusion-weighted image, were considered together to build prediction models for high-risk pathologic features. Among 616 patients, 72 patients met the imaging criteria for high-risk lung cancer and underwent lung MRI. The magnetic resonance (MR)-eligible group showed a higher prevalence of nodal upstaging (29.2% vs. 4.2%, p < 0.001), vascular invasion (6.5% vs. 2.1%, p=0.011), high-grade pathologic features (p < 0.001), worse 4-year disease-free survival (p < 0.001) compared with non-MR-eligible group. The prediction power for MR-based radiomics model predicting high-risk pathologic features was good, with mean area under the receiver operating curve (AUC) value measuring 0.751-0.886 in test sets. Adding clinical variables increased the predictive performance for MPsol and the poorly differentiated pattern using the 2021 grading system (AUC, 0.860 and 0.907, respectively). Our imaging criteria can effectively screen high-risk lung cancer patients and predict high-risk pathologic features by our MR-based prediction model using radiomics.

Development and validation of a radiomic prediction model for TACC3 expression and prognosis in non-small cell lung cancer using contrast-enhanced CT imaging

BackgroundsNon-small cell lung cancer (NSCLC) prognosis remains poor despite treatment advances, and classical prognostic indicators often fall short in precision medicine. Transforming acidic coiled-coil protein-3 (TACC3) has been identified as a critical factor in tumor progression and immune infiltration across cancers, including NSCLC. Predicting TACC3 expression through radiomic features may provide valuable insights into tumor biology and aid clinical decision-making. However, its predictive value in NSCLC remains unexplored. Therefore, we aimed to construct and validate a radiomic model to predict TACC3 levels and prognosis in patients with NSCLC. Materials and methodsGenomic data and contrast-enhanced computed tomography (CT) images were sourced from The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO) database, and The Cancer Imaging Archive (TCIA). A total of 320 cases of lung adenocarcinoma from TCGA and 122 cases of NSCLC from GEO were used for prognostic analysis. Sixty-three cases from TCIA and GEO were included for radiomics feature extraction and model development. The radiomics model was constructed using logistic regression (LR) and support vector machine (SVM) algorithms. We predicted TACC3 expression and evaluated its correlation with NSCLC prognosis using contrast-enhanced CT-based radiomics. ResultsTACC3 expression significantly influenced NSCLC prognosis. High TACC3 levels were associated with reduced overall survival, potentially mediated by immune microenvironment and tumor progression regulation. LR and SVM algorithms achieved AUC of 0.719 and 0.724, respectively, which remained at 0.701 and 0.717 after five-fold cross-validation. ConclusionContrast-enhanced CT-based radiomics can non-invasively predict TACC3 expression and provide valuable prognostic information, contributing to personalized treatment strategies.

Wetland Scene Segmentation of Remote Sensing Images Based on Lie Group Feature and Graph Cut Model

Wetland Scene Segmentation of Remote Sensing Images Based on Lie Group Feature and Graph Cut Model

Feature Modelling for Electricity Load Forecasting Using Hybrid EEMD-BiLSTM with Spatially Correlated Weather Data

Feature Modelling for Electricity Load Forecasting Using Hybrid EEMD-BiLSTM with Spatially Correlated Weather Data

FusionMamba: dynamic feature enhancement for multimodal image fusion with Mamba

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs) struggle to capture global features efficiently, while Transformer-based models are computationally expensive, although they excel at global modeling. Mamba addresses these limitations by leveraging selective structured state space models (S4) to effectively handle long-range dependencies while maintaining linear complexity. In this paper, we propose FusionMamba, a novel dynamic feature enhancement framework that aims to overcome the challenges faced by CNNs and Vision Transformers (ViTs) in computer vision tasks. The framework improves the visual state-space model Mamba by integrating dynamic convolution and channel attention mechanisms, which not only retains its powerful global feature modeling capability, but also greatly reduces redundancy and enhances the expressiveness of local features. In addition, we have developed a new module called the dynamic feature fusion module (DFFM). It combines the dynamic feature enhancement module (DFEM) for texture enhancement and disparity perception with the cross-modal fusion Mamba module (CMFM), which focuses on enhancing the inter-modal correlation while suppressing redundant information. Experiments show that FusionMamba achieves state-of-the-art performance in a variety of multimodal image fusion tasks as well as downstream experiments, demonstrating its broad applicability and superiority.

A lightweight and rapidly converging transformer based on separable linear self-attention for fault diagnosis

Abstract Reaching reliable decisions on equipment maintenance is facilitated by the implementation of intelligent fault diagnosis techniques for rotating machineries. Recently, the Transformer model has demonstrated exceptional capabilities in global feature modeling for fault diagnosis tasks, garnering significant attention from the academic community. However, it lacks sufficient prior knowledge regarding rotation invariance, scale, and shift, necessitating pre-training on extensive datasets. In comparison, contemporary convolutional neural networks exhibit greater ease of optimization. This limitation becomes particularly evident when applying the Transformer model in fault diagnosis scenarios with limited data availability. Moreover, the increasing the number of parameters and FLOPs. Pose a challenge to its suitability for mobile services due to the limited computational resources available on edge devices. To mitigate these issues, this paper introduces a novel lightweight Transformer (SepFormer) based on separable linear self-attention (LSA) for fault diagnosis task. The SepFormer performs a novel sequence-level feature embedding to better leverage the inductive bias inherent in the convolutional layers. Furthermore, it integrate a novel separable LSA mechanism into the Transformer architecture, effectively mitigating the computational burden concerns and significantly enhancing the training convergence speed. Extensive experiments are conducted extensively on a bearing fault dataset and gear fault dataset. The experimental results demonstrate that the SepFormer achieves a top-1 accuracy exceeding state-of-the-art approaches by more than 5%, while utilizing the fewest FLOPs. Moreover, the optimizability of SepFormer surpasses that of CNN, ensuring its superior preservation of inductive bias.

Bidirectional interaction directional variance attention model based on increased-transformer for thyroid nodule classification

Malignant thyroid nodules are closely linked to cancer, making the precise classification of thyroid nodules into benign and malignant categories highly significant. However, the subtle differences in contour between benign and malignant thyroid nodules, combined with the texture features obscured by the inherent noise in ultrasound images, often result in low classification accuracy in most models. To address this, we propose a Bidirectional Interaction Directional Variance Attention Model based on Increased-Transformer, named IFormer-DVNet. This paper proposes the Increased-Transformer, which enables global feature modeling of feature maps extracted by the Convolutional Feature Extraction Module (CFEM). This design maximally alleviates noise interference in ultrasound images. The Bidirectional Interaction Directional Variance Attention module (BIDVA) dynamically calculates attention weights using the variance of input tensors along both vertical and horizontal directions. This allows the model to focus more effectively on regions with rich information in the image. The vertical and horizontal features are interactively combined to enhance the model's representational capability. During the model training process, we designed a Multi-Dimensional Loss function (MD Loss) to stretch the boundary distance between different classes and reduce the distance between samples of the same class. Additionally, the MD Loss function helps mitigate issues related to class imbalance in the dataset. We evaluated our network model using the public TNCD dataset and a private dataset. The results show that our network achieved an accuracy of 76.55% on the TNCD dataset and 93.02% on the private dataset. Compared to other state-of-the-art classification networks, our model outperformed them across all evaluation metrics.

ADVANCED MACHINE LEARNING AND INTERPRETABILITY FOR WINDOWS MALWARE DETECTION

Machine learning (ML) has emerged as a powerful tool for detecting and mitigating malware, addressing the evolving challenges in cybersecurity. This paper presents a comprehensive overview of ML techniques applied to Windows Portable Executable (PE) malware detection, spanning from theoretical foundations to practical implementations. Theoretical underpinnings such as feature engineering, model selection, and evaluation metrics are explored, followed by discussions on practical aspects including data preprocessing, model training, and deployment considerations. The experimental setup using the Dataiku platform is detailed, and seven ML models are evaluated on both binary and multiclass classification tasks before and after applying Principal Component Analysis (PCA). The performance and interpretability of these models are analyzed using SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-agnostic Explanations). By synthesizing insights from theory and practice, this paper aims to provide a comprehensive understanding of ML approaches for Windows PE malware detection and guide future advancements in cybersecurity

Inversion method of organic matter content of different types of soils in black soil area based on hyperspectral indices

Abstract Soil organic matter content (SOMC) is a key factor in improving the soil fertility of arable land. Determining how to quickly and accurately grasp SOMC on a regional scale has become an important task for farmland quality monitoring. Hyperspectral imaging remote sensing technology can enable large-scale SOMC estimation, owing to its large-scale and fine spectral resolution. Enhancing the accuracy and reliability of SOM estimation models based on hyperspectral satellite remote sensing has emerged as a prominent topic of study. In this study, feature spectral indices such as difference indices (DI), ratio indices, and normalized indices were extracted using the correlation coefficient method and used as variables to construct a regression model for SOM, with a split-sample regression method employed to account for the complexity of soil types and map the corresponding spatial distribution of SOM. The results showed that the SOM estimation model, built using these feature spectral indices from hyperspectral satellite imagery, achieved high predictive accuracy, with R² values approaching 0.80 for most soil types. This demonstrates that the model effectively captures variations in SOM content across diverse soil backgrounds, highlighting its robustness and adaptability. The DI499/576 combinations, in particular, contributed significantly to prediction accuracy, demonstrating their importance as key spectral parameters for SOM estimation. Furthermore, among the three sets of feature model variables derived from the split-sample regression strategy, the enhanced vegetation indices and Soil-Adjusted Total Vegetation Index exhibited distinct contributions to different soil sample groups. This variation reveals the specific responsiveness of these indices to soil properties, which further enhances model performance in varied soil contexts. This study provides innovative methods for large-scale SOMC estimation, particularly by utilizing hyperspectral indices to enhance model accuracy across various soil types, demonstrating substantial practical significance.