Gradient Boosting Decision Tree Research Articles

Estimating Maize Crop Height and Aboveground Biomass Using Multi-Source Unmanned Aerial Vehicle Remote Sensing and Optuna-Optimized Ensemble Learning Algorithms

Accurately assessing maize crop height (CH) and aboveground biomass (AGB) is crucial for understanding crop growth and light-use efficiency. Unmanned aerial vehicle (UAV) remote sensing, with its flexibility and high spatiotemporal resolution, has been widely applied in crop phenotyping studies. Traditional canopy height models (CHMs) are significantly influenced by image resolution and meteorological factors. In contrast, the accumulated incremental height (AIH) extracted from point cloud data offers a more accurate estimation of CH. In this study, vegetation indices and structural features were extracted from optical imagery, nadir and oblique photography, and LiDAR point cloud data. Optuna-optimized models, including random forest regression (RFR), light gradient boosting machine (LightGBM), gradient boosting decision tree (GBDT), and support vector regression (SVR), were employed to estimate maize AGB. Results show that AIH99 has higher accuracy in estimating CH. LiDAR demonstrated the highest accuracy, while oblique photography and nadir photography point clouds were slightly less accurate. Fusion of multi-source data achieved higher estimation accuracy than single-sensor data. Embedding structural features can mitigate spectral saturation, with R2 ranging from 0.704 to 0.939 and RMSE ranging from 0.338 to 1.899 t/hm2. During the entire growth cycle, the R2 for LightGBM and RFR were 0.887 and 0.878, with an RMSE of 1.75 and 1.76 t/hm2. LightGBM and RFR also performed well across different growth stages, while SVR showed the poorest performance. As the amount of nitrogen application gradually decreases, the accumulation and accumulation rate of AGB also gradually decrease. This high-throughput crop-phenotyping analysis method offers advantages, such as speed and high accuracy, providing valuable references for precision agriculture management in maize fields.

Predicting the Gas Storage Capacity in Shale Formations Using the Extreme Gradient Boosting Decision Trees Method

Accurate shale gas reserves estimation is essential for development. Existing machine learning (ML) models for predicting gas isothermal adsorption are limited by small datasets and lack verified generalization. We constructed an “original dataset” containing 2112 data points from 11 measurements on samples from 8 formations in 3 countries to develop ML‐based prediction models. Similar to previous ML models, total organic matter, pressure, and temperature are characterized as the three most significant features using the mean impurity method. In contrast to previous ML models, the study reveals that these three features are inadequate to be used to make reasonable predictions for the datasets from the measurements different from those used to train the models. Instead, the extreme gradient boosting decision trees (XGBoost) model with two more features (specific surface area and moisture) exhibits good robustness, generalization, and precision in the prediction of gas isothermal adsorption. Overall, An XGBoost model with optimal input features is developed in this work, which exhibits both good performance in gas adsorption prediction and good potential for the estimation of gas storage in shale gas development.

Spatiotemporal variation in determinants of cropland abandonment across Yangtze River Economic Belt, China

Cropland abandonment is a widespread land-change phenomenon globally, driven by complex social, economic, and political transformations, with significant implications for the environment and society. However, the inconsistent definitions of cropland abandonment and the bias in the selection of study areas hinder the comparison of identified determinants of cropland abandonment. In this study, we defined cropland abandonment from the perspective of vegetation succession. By employing land-cover change detection with Landsat time-series images from 1990 to 2021, we analyzed the spatiotemporal patterns of cropland abandonment across the cities of Yibin, Huangshi, and Chaohu within the Yangtze River Economic Belt. Furthermore, we utilized the Gradient-Boosting Decision Tree model to identify the primary spatial determinants and their relative importance in each city. Our findings showed significant variations in abandonment rates by 2021. Huangshi exhibited the highest rate of cropland abandonment, leading with 53.81±2.1 %, followed by Yibin with 45.36±2.18 %, and Chaohu with the lowest at 36.94±2.21 %. Interestingly, a consistent spatiotemporal trend, areas with higher abandonment rates tended to be abandoned earlier, emerged in abandonment determinants across cities. Areas with lower bulk density, higher soil clay content, and greater organic carbon contents exhibited higher abandonment rates. However, the most influential determinants varied: the distance from water bodies was the most important in Yibin and Huangshi, while the distance from the forest had a greater impact in Chaohu. This study offers a more nuanced perspective on defining cropland abandonment and can be applied to other regions after some adjustment. Our results provide valuable insights for cropland abandonment management by protecting high-value croplands and setting aside some areas for environmental amenities.

Assessing TGF-β Prognostic Model Predictions for Chemotherapy Response and Oncogenic Role of FKBP1A in Liver Cancer.

The Transforming Growth Factor-Beta (TGF-β) signaling pathway plays a crucial role in the pathogenesis of diseases. This study aimed to identify differentially expressed TGF-β-related genes in liver cancer patients and to correlate these findings with clinical features and immune signatures. The TCGA-STAD and LIRI-JP cohorts were utilized for a comprehensive analysis of TGF-β- related genes. Differential gene expression, functional enrichment, survival analysis, and machine learning techniques were employed to develop a prognostic model based on a TGF-β-related gene signature (TGFBRS). We developed a prognostic model for liver cancer based on the expression levels of nine TGF-β- related genes. The model indicates that higher TGFBRS values are associated with poorer prognosis, higher tumor grades, more advanced pathological stages, and resistance to chemotherapy. Additionally, the TGFBRS-High subtype was characterized by elevated levels of immune-suppressive cells and increased expression of immune checkpoint molecules. Using a Gradient Boosting Decision Tree (GBDT) machine learning approach, the FKBP1A gene was identified as playing a significant role in liver cancer. Notably, knocking down FKBP1A significantly inhibited the proliferation and metastatic capabilities of liver cancer cells both in vitro and in vivo. Our study highlights the potential of TGFBRS in predicting chemotherapy responses and in shaping the tumor immune microenvironment in liver cancer. The results identify FKBP1A as a promising molecular target for developing preventive and therapeutic strategies against liver cancer. Our findings could potentially guide personalized treatment strategies to improve the prognosis of liver cancer patients.

Determining the Optimal Window Duration to Enhance Emotion Recognition Based on Galvanic Skin Response and Photoplethysmography Signals

Automatic emotion recognition using portable sensors is gaining attention due to its potential use in real-life scenarios. Existing studies have not explored Galvanic Skin Response and Photoplethysmography sensors exclusively for emotion recognition using nonlinear features with machine learning (ML) classifiers such as Random Forest, Support Vector Machine, Gradient Boosting Machine, K-Nearest Neighbor, and Decision Tree. In this study, we proposed a genuine window sensitivity analysis on a continuous annotation dataset to determine the window duration and percentage of overlap that optimize the classification performance using ML algorithms and nonlinear features, namely, Lyapunov Exponent, Approximate Entropy, and Poincaré indices. We found an optimum window duration of 3 s with 50% overlap and achieved accuracies of 0.75 and 0.74 for both arousal and valence, respectively. In addition, we proposed a Strong Labeling Scheme that kept only the extreme values of the labels, which raised the accuracy score to 0.94 for arousal. Under certain conditions mentioned, traditional ML models offer a good compromise between performance and low computational cost. Our results suggest that well-known ML algorithms can still contribute to the field of emotion recognition, provided that window duration, overlap percentage, and nonlinear features are carefully selected.

Comparison of machine-learning and logistic regression models for prediction of 30-day unplanned readmission in electronic health records: A development and validation study.

It is expected but unknown whether machine-learning models can outperform regression models, such as a logistic regression (LR) model, especially when the number and types of predictor variables increase in electronic health records (EHRs). We aimed to compare the predictive performance of gradient-boosted decision tree (GBDT), random forest (RF), deep neural network (DNN), and LR with the least absolute shrinkage and selection operator (LR-LASSO) for unplanned readmission. We used EHRs of patients discharged alive from 38 hospitals in 2015-2017 for derivation and in 2018 for validation, including basic characteristics, diagnosis, surgery, procedure, and drug codes, and blood-test results. The outcome was 30-day unplanned readmission. We created six patterns of data tables having different numbers of binary variables (that ≥5% or ≥1% of patients or ≥10 patients had) with and without blood-test results. For each pattern of data tables, we used the derivation data to establish the machine-learning and LR models, and used the validation data to evaluate the performance of each model. The incidence of outcome was 6.8% (23,108/339,513 discharges) and 6.4% (7,507/118,074 discharges) in the derivation and validation datasets, respectively. For the first data table with the smallest number of variables (102 variables that ≥5% of patients had, without blood-test results), the c-statistic was highest for GBDT (0.740), followed by RF (0.734), LR-LASSO (0.720), and DNN (0.664). For the last data table with the largest number of variables (1543 variables that ≥10 patients had, including blood-test results), the c-statistic was highest for GBDT (0.764), followed by LR-LASSO (0.755), RF (0.751), and DNN (0.720), suggesting that the difference between GBDT and LR-LASSO was small and their 95% confidence intervals overlapped. In conclusion, GBDT generally outperformed LR-LASSO to predict unplanned readmission, but the difference of c-statistic became smaller as the number of variables was increased and blood-test results were used.

Prediction of 28-Day All-Cause Mortality in Heart Failure Patients with Clostridioides difficile Infection Using Machine Learning Models: Evidence from the MIMIC-IV Database.

Heart failure (HF) may induce bowel hypoperfusion, leading to hypoxia of the villa of the bowel wall and the occurrence of Clostridioides difficile infection (CDI). However, the risk factors for the development of CDI in HF patients have yet to be fully illustrated, especially because of a lack of evidence from real-world data. Clinical data and survival situations of HF patients with CDI admitted to ICU were extracted from the Medical Information Mart for Intensive Care (MIMIC)-IV database. For developing a model that can predict 28-day all-cause mortality in HF patients with CDI, the Recursive Feature Elimination with Cross-Validation (RFE-CV) method was used for feature selection. And nine machine learning (ML) algorithms, including logistic regression (LR), decision tree, Bayesian, adaptive boosting, random forest (RF), gradient boosting decision tree, XGBoost, light gradient boosting machine, and categorical boosting, were applied for model construction. After training and hyperparameter optimization of the models through grid search 5-fold cross-validation, the performance of models was evaluated by the area under curve (AUC), accuracy, sensitivity, specificity, precision, negative predictive value, and F1 score. Furthermore, the SHapley Additive exPlanations (SHAP) method was used to interpret the optimal model. A total of 526 HF patients with CDI were included in the study, of whom 99 cases (18.8%) experienced death within 28 days. Eighteen of the 57 variables were selected for the model construction algorithm for model construction. Among the ML models considered, the RF model emerged as the optimal model achieving the accuracy, F1-score, and AUC values of 0.821, 0.596, and 0.864, respectively. The net benefit of the model surpassed other models at 16%-22% threshold probabilities based on decision curve analysis. According to the importance of features in the RF model, red blood cell distribution width, blood urea nitrogen, Simplified Acute Physiology Score II, Sequential Organ Failure Assessment, and white blood cell count were highlighted as the five most influential variables. We developed ML models to predict 28-day all-cause mortality in HF patients associated with CDI in the ICU, which are more effective than the conventional LR model. The RF model has the best performance among all the ML models employed. It may be useful to help clinicians identify high-risk HF patients with CDI.

Flashlight model: Integrating attention distribution and attention resources for pilots’ visual behaviour analysis and performance prediction

Pilot performance is almost the last line of defense in aircraft safety. Recent years have seen a surge in research aimed at utilizing eye-tracking technology to predict pilot performance, enhancing aviation safety margins. A decline in pilot performance is often attributed to either misdirected attention towards irrelevant tasks or inefficient information processing owing to limited attention resources. Previous research has shown that eye-tracking data can effectively capture these issues and provide accurate performance predictions. Nevertheless, the existing studies either focus on attention distribution or attention resources separately, neglecting the complex interactions between them. To address this gap, our study proposes a synthesized Flashlight model-based eye-tracking analysis for pilot performance prediction, integrating the two perspectives. Accordingly, the combined AOI-gaze metrics are proposed to offer a more nuanced analysis of information processing across specific Areas of Interest (AOIs), thereby enhancing the analysis of gaze metrics. We examined the efficacy of the combined AOI-gaze metrics in the Gradient-boosted decision trees(GBDT) model for pilot performance prediction and compared them with other widely used eye-tracking metrics in a simulated flight experiment case study. Moreover, we employed the SHapley Additive exPlanations (SHAP) method to identify the most influential eye-tracking measurements for pilots’ performance prediction. The result demonstrated that the selected eye-tracking measurements obtained the highest accuracy in performance prediction.

Optimal Mapping of Soil Erodibility in a Plateau Lake Watershed: Empirical Models Empowered by Machine Learning

Soil erodibility (K) refers to the inherent ability of soil to withstand erosion. Accurate estimation and spatial prediction of K values are vital for assessing soil erosion and managing land resources. However, as most K-value estimation models are empirical, they suffer from significant extrapolation uncertainty, and traditional studies on spatial prediction focusing on individual empirical K values have neglected to explore the spatial pattern differences between various empirical models. This work proposed a universal framework for selecting an optimal soil-erodibility map using empirical models enhanced by machine learning. Specifically, three empirical models, namely, the erosion-productivity impact calculator model (K_EPIC), the Shirazi model (K_Shirazi), and the Torri model (K_Torri) were used to estimate K values. Random Forest (RF) and Gradient-Boosting Decision Tree (GBDT) algorithms were employed to develop prediction models, which led to the creation of three K-value maps. The spatial distribution of K values and associated environmental covariates were also investigated across varying empirical models. Results showed that RF achieved the highest accuracy, with R2 of K_EPIC, K_Shirazi, and K_Torri increasing by 46%, 34%, and 22%, respectively, compared to GBDT. And distinctions among environmental variables that shape the spatial patterns of empirical models have been identified. The K_EPIC and K_Shirazi are influenced by soil porosity and soil moisture. The K_Torri is more sensitive to soil moisture conditions and terrain location. More importantly, our study has highlighted disparities in the spatial patterns across the three K-value maps. Considering the data distribution, spatial distribution, and measured K values, the K_Torri model outperformed others in estimating soil erodibility in the plateau lake watershed. This study proposed a framework that aimed to create optimal soil-erodibility maps and offered a scientific and accurate K-value estimation method for the assessment of soil erosion.

Gradient boosting decision trees to study laboratory and field performance in pavement management

Gradient boosting decision trees to study laboratory and field performance in pavement management

Research on non-destructive identification technology of rice varieties based on HSI and GBDT

Accurate identification of rice varieties is of great significance for rice planting, field management and storage, and is also a key link in the process of agricultural breeding. In this study, a gradient boosting decision tree (GBDT) model was established based on hyperspectral imaging (HSI) to realize high-speed and non-destructive variety identification of six rice varieties. In this study, the near-infrared hyperspectral images of 600 rice samples of 6 varieties were taken as the research object, and the characteristic spectra of sensitive regions of the sample spectral images were processed by multiplicative scatter correction (MSC), and after the characteristic wavelengths were determined by the importance scores, the GBDT model to realize the identification of rice sample varieties, and the grid search algorithm was used to optimize the four internal parameters of GBDT. The results showed that the established GBDT model for the accuracy of rice variety identification of vitro test set samples reached 95%, indicating that HSI can be used to quickly and non-destructively identify rice varieties, and provide a new idea for batch online non-destructive testing of rice seeds.

Estimation of Greenhouse Gas Emissions of Taxis and the Nonlinear Influence of Built Environment Considering Spatiotemporal Heterogeneity

The fuel consumption and greenhouse gas (GHG) emission patterns of taxis are in accordance with the urban structure and daily travel footprints of residents. With taxi trajectory data from the intelligent transportation system in Xi’an, China, this study excludes trajectories from electric taxis to accurately estimate GHG emissions of taxis. A gradient boosting decision tree (GBDT) model is employed to examine the nonlinear influence of the built environment (BE) on the GHG emissions of taxis on weekdays and weekends in various urban areas. The research findings indicate that the GHG emissions of taxis within the research area exhibit peak levels during the time intervals of 7:00–9:00, 12:00–14:00, and 23:00–0:00, with notably higher emission factors on weekends than on weekdays. Moreover, a clear nonlinear association exists between BE elements and GHG emissions, with a distinct impact threshold. In the different urban areas, the factors that influence emissions exhibit spatial and temporal heterogeneity. Metro/bus/taxi stops density, residential density, and road network density are the most influential BE elements impacting GHG emissions. Road network density has both positive and negative influences on the GHG emissions in various urban areas. Increasing the road network density in subcentral urban areas and increasing the mixed degree of urban functions in newly developed urban centers to 1.85 or higher can help reduce GHG emissions. These findings provide valuable insights for reducing emissions in urban transportation and promoting sustainable urban development by adjusting urban functional areas.

Hybrid forecasting model of building cooling load based on EMD-LSTM-Markov algorithm

Precise forecasting of the cooling load (CL) of buildings is crucial for the efficient functioning of central air conditioning systems. The study proposed a new hybrid model based on empirical modal decomposition (EMD) and Markov chain improved LSTM neural network, denoted as EMD-LSTM-Markov. First, Pearson’s correlation coefficient (PCC) and Gradient Boosting Decision Tree (GBDT) are used to extract features with a high degree as the input data. Then, the LSTM is employed to establish a prediction model. Finally, to verify the validity and prediction accuracy of the proposed model, this paper selects the CL data of an office building in Guangzhou as the research sample. The results show that the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) of the EMD-LSTM-Markov model are 4.53 and 0.84%. Compared with the other three predicting models, the RMSE and MAPE values of EMD-LSTM-Markov are decreased by 40% − 94% and 70% − 96%, which has better performance in accuracy and stability. It testifies that the proposed strategy is reliable and effective. This work successfully resolves the issue of delayed cold response. The hybrid model proposed demonstrates significant energy-saving potential for accurately predicting building CLs and enhancing the optimal control of cooling systems. Future research should explore the hybrid model’s robustness across different building types and climatic regions.

Manufacturing time estimation for offer pricing: A machine learning application in a French metallurgy industry

- In today's market where many companies are competing for the same opportunities, a quick, accurate, and reliable estimation of the offers' prices is essential for the suppliers. This allows them to answer to more solicitations and to remain competitive. Many suppliers use the manufacturing time as key parameter to define their offers' prices. However, in Make-To-Order (MTO) and Engineer-To-Order (ETO) contexts, with the increasing number of demands, the huge diversity of the products and the manufacturing process complexity, estimating the manufacturing time is challenging. To face this issue, this article proposes a new approach for the manufacturing time estimation using machine learning. Its originality relies on the exploitation of structured tabular data, unstructured textual data and domain knowledge. It also proposes two strategies that allow to choose the best estimation model for each product family, while minimizing the number of estimation models and considering product families with fewer available data. All the proposals have been applied to a real industrial case in a French small metallurgy industry, and the results have shown their applicability and effectiveness. Among the plethora of machine learning techniques implemented, CatBoost, which is a member of the family of Gradient Boosted Decision Trees (GBDT) ensemble techniques, provided the best results.

Use of machine learning algorithms to determine the relationship between air pollution and cognitive impairment in Taiwan

Air pollution has become a major global threat to human health. Urbanization and industrialization over the past few decades have increased the air pollution. Plausible connections have been made between air pollutants and dementia. This study used machine learning algorithms (k-nearest neighbors, random forest, gradient-boosted decision trees, eXtreme gradient boosting, and CatBoost) to investigate the association between cognitive impairment and air pollution. Data from the Taiwan Biobank and 75 air-pollution-monitoring stations in Taiwan were analyzed to determine individual levels of exposure to air pollutants. The pollutants examined were particulate matter with a diameter of ≤ 2.5 μm (PM2.5), nitrogen dioxide, nitric oxide, carbon monoxide, and ozone. The results revealed that the most strongly correlated with cognitive impairment were ozone, PM2.5, and carbon monoxide levels with adjustment of educational level, age, and household income. The model based on these factors achieved accuracy as high as 0.97 for detecting cognitive impairment, indicating a positive association between air pollutions and cognitive impairment.

AN EFFICIENT MACHINE LEARNING-BASED DETECTION AND PREDICTION MECHANISM FOR CYBER THREATS USING INTELLIGENT FRAMEWORK IN IOTS

The dangers that Internet of Things (IoT) devices pose to large corporate corporations and smart districts have been dissected by several academics. Given the ubiquitous use of IoT and its unique characteristics, such as mobility and normalization restrictions, intelligent frameworks that can independently detect suspicious activity in privately linked IoT devices are crucial. The IoTs have led an explosion in traffic through the network, bringing information processing techniques for attack detection. The increase in traffic poses challenges in detecting attacks and differentiating traffic that is harmful. In this work, we have proposed a mechanism that uses the standard algorithms in a system that is designed to detect, track, measure and identify online traffic from organizations with malignant transmission: Random Forest (RF), gradient-boosted decision trees (GBDT), and support vector machines (SVM) gives an optimal accuracy of 80.34%,87.5%, and 88.6% while the random forest-based supervised approach is 5.5% better than the previous techniques. To facilitate comparisons between training time, prediction time, specificity, and accuracy, the proposed approach leverages the NSL KDD dataset accuracy.

AN EFFICIENT MACHINE LEARNING-BASED DETECTION AND PREDICTION MECHANISM FOR CYBER THREATS USING INTELLIGENT FRAMEWORK IN IOTS

The dangers that Internet of Things (IoT) devices pose to large corporate corporations and smart districts have been dissected by several academics. Given the ubiquitous use of IoT and its unique characteristics, such as mobility and normalization restrictions, intelligent frameworks that can independently detect suspicious activity in privately linked IoT devices are crucial. The IoTs have led an explosion in traffic through the network, bringing information processing techniques for attack detection. The increase in traffic poses challenges in detecting attacks and differentiating traffic that is harmful. In this work, we have proposed a mechanism that uses the standard algorithms in a system that is designed to detect, track, measure and identify online traffic from organizations with malignant transmission: Random Forest (RF), gradient-boosted decision trees (GBDT), and support vector machines (SVM) gives an optimal accuracy of 80.34%,87.5%, and 88.6% while the random forest-based supervised approach is 5.5% better than the previous techniques. To facilitate comparisons between training time, prediction time, specificity, and accuracy, the proposed approach leverages the NSL KDD dataset accuracy.

Predicting non-chemotherapy drug-induced agranulocytosis toxicity through ensemble machine learning approaches.

Agranulocytosis, induced by non-chemotherapy drugs, is a serious medical condition that presents a formidable challenge in predictive toxicology due to its idiosyncratic nature and complex mechanisms. In this study, we assembled a dataset of 759 compounds and applied a rigorous feature selection process prior to employing ensemble machine learning classifiers to forecast non-chemotherapy drug-induced agranulocytosis (NCDIA) toxicity. The balanced bagging classifier combined with a gradient boosting decision tree (BBC + GBDT), utilizing the combined descriptor set of DS and RDKit comprising 237 features, emerged as the top-performing model, with an external validation AUC of 0.9164, ACC of 83.55%, and MCC of 0.6095. The model's predictive reliability was further substantiated by an applicability domain analysis. Feature importance, assessed through permutation importance within the BBC + GBDT model, highlighted key molecular properties that significantly influence NCDIA toxicity. Additionally, 16 structural alerts identified by SARpy software further revealed potential molecular signatures associated with toxicity, enriching our understanding of the underlying mechanisms. We also applied the constructed models to assess the NCDIA toxicity of novel drugs approved by FDA. This study advances predictive toxicology by providing a framework to assess and mitigate agranulocytosis risks, ensuring the safety of pharmaceutical development and facilitating post-market surveillance of new drugs.

Identifying neuroimaging biomarkers in major depressive disorder using machine learning algorithms and functional near-infrared spectroscopy (fNIRS) during verbal fluency task

One of the most prevalent psychiatric disorders is major depressive disorder (MDD), which increases the probability of suicidal ideation or untimely demise. Abnormal frontal hemodynamic changes detected by functional near-infrared spectroscopy (fNIRS) during verbal fluency task (VFT) have the potential to be used as an objective indicator for assessing clinical symptoms. However, comprehensive quantitative and objective assessment instruments for individuals who exhibit symptoms suggestive of depression remain undeveloped. Drawing from a total of 467 samples in a large-scale dataset comprising 289 MDD patients and 178 healthy controls, fNIRS measurements were obtained throughout the VFT. To identify unique MDD biomarkers, this research introduced a data representation approach for extracting spatiotemporal features from fNIRS signals, which were subsequently utilized as potential predictors. Machine learning classifiers (e.g., Gradient Boosted Decision Trees (GBDT) and Multilayer Perceptron) were implemented to assess the ability to predict selected features. The mean and standard deviation of the cross-validation indicated that the GBDT model, when combined with the 180-feature pattern, distinguishes patients with MDD from healthy controls in the most effective manner. The accuracy of correct classification for the test set was 0.829 ± 0.053, with an AUC of 0.895 (95 % CI: 0.864–0.925) and a sensitivity of 0.914 ± 0.051. Channels that made the most important contribution to the identification of MDD were identified using Shapley Additive Explanations method, located in the frontopolar area and the dorsolateral prefrontal cortex, as well as pars triangularis Broca's area. Assessment of abnormal prefrontal activity during the VFT in MDD serves as an objectively measurable biomarker that could be utilized to evaluate cognitive deficits and facilitate early screening for MDD. The model suggested in this research could be applied to large-scale case-control fNIRS datasets to detect unique characteristics of MDD and offer clinicians an objective biomarker-based analytical instrument to assist in the evaluation of suspicious cases.

Development of a Predictive Model for Carbon Dioxide Corrosion Rate and Severity Based on Machine Learning Algorithms.

Carbon dioxide corrosion is a pervasive issue in pipelines and the petroleum industry, posing substantial risks to equipment safety and longevity. Accurate prediction of corrosion rates and severity is essential for effective material selection and equipment maintenance. This paper begins by addressing the limitations of traditional corrosion prediction methods and explores the application of machine learning algorithms in CO2 corrosion prediction. Conventional models often fail to capture the complex interactions among multiple factors, resulting in suboptimal prediction accuracy, limited adaptability, and poor generalization. To overcome these limitations, this study systematically organized and analyzed the data, performed a correlation analysis of the data features, and examined the factors influencing corrosion. Subsequently, prediction models were developed using six algorithms: Random Forest (RF), K-Nearest Neighbors (KNN), Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), XGBoost, and LightGBM. The results revealed that SVM exhibited the lowest performance on both training and test sets, while RF achieved the best results with R2 values of 0.92 for the training set and 0.88 for the test set. In the classification of corrosion severity, RF, LightGBM, SVM, and KNN were utilized, with RF demonstrating superior performance, achieving an accuracy of 99% and an F1-score of 0.99. This study highlights that machine learning algorithms, particularly Random Forest, offer substantial potential for predicting and classifying CO2 corrosion. These algorithms provide innovative approaches and valuable insights for practical applications, enhancing predictive accuracy and operational efficiency in corrosion management.