Gradient Boosting Decision Tree Research Articles

Observation-Based Ozone Formation Rules by Gradient Boosting Decision Trees Model in Typical Chemical Industrial Parks

Observation-Based Ozone Formation Rules by Gradient Boosting Decision Trees Model in Typical Chemical Industrial Parks

Evaluating Realistic Adversarial Attacks against Machine Learning Models for Windows PE Malware Detection

During the last decade, the cybersecurity literature has conferred a high-level role to machine learning as a powerful security paradigm to recognise malicious software in modern anti-malware systems. However, a non-negligible limitation of machine learning methods used to train decision models is that adversarial attacks can easily fool them. Adversarial attacks are attack samples produced by carefully manipulating the samples at the test time to violate the model integrity by causing detection mistakes. In this paper, we analyse the performance of five realistic target-based adversarial attacks, namely Extend, Full DOS, Shift, FGSM padding + slack and GAMMA, against two machine learning models, namely MalConv and LGBM, learned to recognise Windows Portable Executable (PE) malware files. Specifically, MalConv is a Convolutional Neural Network (CNN) model learned from the raw bytes of Windows PE files. LGBM is a Gradient-Boosted Decision Tree model that is learned from features extracted through the static analysis of Windows PE files. Notably, the attack methods and machine learning models considered in this study are state-of-the-art methods broadly used in the machine learning literature for Windows PE malware detection tasks. In addition, we explore the effect of accounting for adversarial attacks on securing machine learning models through the adversarial training strategy. Therefore, the main contributions of this article are as follows: (1) We extend existing machine learning studies that commonly consider small datasets to explore the evasion ability of state-of-the-art Windows PE attack methods by increasing the size of the evaluation dataset. (2) To the best of our knowledge, we are the first to carry out an exploratory study to explain how the considered adversarial attack methods change Windows PE malware to fool an effective decision model. (3) We explore the performance of the adversarial training strategy as a means to secure effective decision models against adversarial Windows PE malware files generated with the considered attack methods. Hence, the study explains how GAMMA can actually be considered the most effective evasion method for the performed comparative analysis. On the other hand, the study shows that the adversarial training strategy can actually help in recognising adversarial PE malware generated with GAMMA by also explaining how it changes model decisions.

Rapid accomplishment of cost-effective and macro-defect-free LPBF-processed Ti parts based on deep data augmentation

Machine learning methods can accurately predict the density of as-built parts by laser power bed fusion (LPBF), providing a reference for optimizing process parameters. However, obtaining massive training data via experiments is time-consuming and high-cost. Herein, a novel data augmentation method based on the Wasserstein generative adversarial network and regularization strategy (LC-WGAN) was developed to generate new training data for density prediction modelling. Four machine learning (ML) algorithms, support vector regression (SVR), multilayer perceptron (MLP), random forest (RF) and gradient boosting decision tree (GBDT), were adopted to construct the density prediction models. Results show that the proposed LC-WGAN effectively enhanced the prediction performance of all four models. R2 of MLP dramatically increased by 73.06 %, while that of RF and GBDT was marginally improved by 10.07 % and 7.48 %, respectively. RF trained by augmented dataset has the highest prediction performance on test set with MAE, RMSE and R2 of 0.7589, 0.9584 and 0.9822, respectively, which is suitable for density prediction. Additionally, SHAP analysis reveals that energy density is the most important parameter with an overall positive impact on density. The proposed method can provide valuable insights for the limited sample modelling in other fields.

Probing the interactions of axion-like particles with electroweak bosons and the Higgs boson in the high energy regime at LHC

We study the interactions of axion-like particles (ALPs) with the Standard Model particles, aiming to probe their phenomenology via non-resonant searches at the LHC. These interactions are mediated by higher dimensional effective operators within two possible frameworks of linearly and non-linearly realised electroweak symmetry breaking. We consider the ALPs to be light enough to be produced on-shell and exploit their derivative couplings with the SM Higgs boson and the gauge bosons. We will use the high momentum transfer processes, namely hZ, Zγ, WW and WWγ production from pp collisions. We derive upper limits on the gauge-invariant interactions of ALPs with the electroweak bosons and/or Higgs boson that contribute to these processes, from the re-interpretation of the latest Run 2 available LHC data. The constraints we obtain are strong for ALP masses below 100 GeV. These allowed effective interactions in the ALP parameter space yield better significance at HL-LHC and thus, offer promising avenues for subsequent studies. Furthermore, we augment our cut-based analysis with gradient-boosted decision trees, which improve the statistical significance distinctly across these interaction channels. We briefly compare the results with the complementary probe of these couplings via direct production of ALPs in association with the Higgs boson or a vector boson.

Identification of Dominant Species and Their Distributions on an Uninhabited Island Based on Unmanned Aerial Vehicles (UAVs) and Machine Learning Models

Comprehensive vegetation surveys are crucial for species selection and layout during the restoration of degraded island ecosystems. However, due to the poor accessibility of uninhabited islands, traditional quadrat surveys are time-consuming and labor-intensive, and it is challenging to fully identify the specific species and their spatial distributions. With miniaturized sensors and strong accessibility, high spatial and temporal resolution, Unmanned Aerial Vehicles (UAVs) have been extensively implemented for vegetation surveys. By collecting UAVs multispectral images and conducting field quadrat surveys on Anyu Island, we employ four machine learning models, namely Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Random Forest (RF) and Multiple Classifier Systems (MCS). We aim to identify the dominant species and analyze their spatial distributions according to spectral characteristics, vegetation index, topographic factors, texture features, and canopy heights. The results indicate that SVM model achieves the highest (88.55%) overall accuracy (OA) (kappa coefficient = 0.87), while MCS model does not significantly improve it as expected. Acacia confusa has the highest OA among 7 dominant species, reaching 97.67%. Besides the spectral characteristics, the inclusion of topographic factors and texture features in the SVM model can significantly improve the OA of dominant species. By contrast, the vegetation index, particularly the canopy height even reduces it. The dominant species exhibit significant zonal distributions with distance from the coastline on the Anyu Island (p < 0.001). Our study provides an effective and universal path to identify and map the dominant species and is helpful to manage and restore the degraded vegetation on uninhabited islands.

Exploring non-linear effects of environmental factors on the volume of pedestrians of different ages using street view images and computer vision technology

Creating pedestrian-friendly neighborhoods and encouraging walking activities not only improves urban liveliness but also delivers health and environmental benefits. Previous research has largely focused on individual walking behavior, which often exhibits stronger associations with personal traits than with built environment characteristics. Pedestrian volume, a significant indicator of urban vitality and collective walking behavior, may have a stronger relationship with environmental characteristics. Moreover, prior studies often hypothesize a linear relationship between built environmental determinants and walking behavior. The exploration of potential non-linear influences may help policy makers and urban planners by identifying minimum, maximum, and optimal values of built environmental variables conducive for walking. Furthermore, studies focusing on the collective walking of older pedestrians remain scarce in the context of aging societies.In this study, we utilize street view imagery and advanced computer vision algorithms to estimate citywide pedestrian volumes and their corresponding age classifications (older adults vs. all). Additionally, we assessed both micro and macro built environmental factors. The possible non-linear impact is examined using Gradient Boosting Decision Tree (GBDT). Our findings reveal disparities in the influence of environmental determinants on the volume of older pedestrians versus that of all pedestrians. Also, the significance of environmental elements exhibits variations across different spatial resolutions. Further, both eye-level vegetation and building level show an inverted U-shaped influence on the pedestrian count.

Application of machine learning in predicting the thermal conductivity of single-filler polymer composites

Polymer composites with superior thermal conductivity and low electrical conductivity are pivotal in the cooling of electronic devices. Despite their prevalence, the accurate prediction of the thermal conductivity of these composites remains a challenge. The emergence of machine learning (ML) provides a groundbreaking approach to solving this issue. In this study, we constructed a comprehensive dataset collected from previous experimental papers and successfully predicted the thermal conductivity of single-filler polymer composites using four ML regression algorithms: random forest regression (RFR), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and Gaussian process regression (GPR). By employing feature engineering to select pertinent features from the original datasets, the accuracy of the four models on the test set was improved, among which GBDT exhibited the highest accuracy with the Pearson correlation coefficient value of 0.981. Factors such as filler volume fraction and matrix thermal conductivity significantly influence the thermal conductivity of composite materials, while the thermal conductivity of the fillers has a relatively minor impact. Additionally, we identified the topological polar surface area (TPSA) as a crucial descriptor for surface modifications, quantifying diverse surface-modifying agents. Due to the incorporation of more descriptors, ML models exhibit higher precision and broader applicability compared to empirical formulas. Our study provides an effective tool for predicting the thermal conductivity of polymer composites with single fillers and underscores the potential of machine learning in accelerating materials design.

Machine Learning Reveals Serum Glycopatterns as Potential Biomarkers for the Diagnosis of Nonalcoholic Fatty Liver Disease (NAFLD).

Nonalcoholic fatty liver disease (NAFLD) has emerged as the predominant chronic liver condition globally, and underdiagnosis is common, particularly in mild cases, attributed to the asymptomatic nature and traditional ultrasonography's limited sensitivity to detect early-stage steatosis. Consequently, patients may experience progressive liver pathology. The objective of this research is to ascertain the efficacy of serum glycan glycopatterns as a potential diagnostic biomarker, with a particular focus on the disease's early stages. We collected a total of 170 serum samples from volunteers with mild-NAFLD (Mild), severe-NAFLD (Severe), and non-NAFLD (None). Examination via lectin microarrays has uncovered pronounced disparities in serum glycopatterns identified by 19 distinct lectins. Following this, we employed four distinct machine learning algorithms to categorize the None, Mild, and Severe groups, drawing on the alterations observed in serum glycopatterns. The gradient boosting decision tree (GBDT) algorithm outperformed other models in diagnostic accuracy within the validation set, achieving an accuracy rate of 95% in differentiating the None group from the Mild group. Our research indicates that employing lectin microarrays to identify alterations in serum glycopatterns, when integrated with advanced machine learning algorithms, could constitute a promising approach for the diagnosis of NAFLD, with a special emphasis on its early detection.

Community screening for dementia among older adults in China: a machine learning-based strategy

BackgroundDementia is a leading cause of disability in people older than 65 years worldwide. However, diagnosing dementia in its earliest symptomatic stages remains challenging. This study combined specific questions from the AD8 scale with comprehensive health-related characteristics, and used machine learning (ML) to construct diagnostic models of cognitive impairment (CI).MethodsThe study was based on the Shenzhen Healthy Ageing Research (SHARE) project, and we recruited 823 participants aged 65 years and older, who completed a comprehensive health assessment and cognitive function assessments. Permutation importance was used to select features. Five ML models using BalanceCascade were applied to predict CI: a support vector machine (SVM), multilayer perceptron (MLP), AdaBoost, gradient boosting decision tree (GBDT), and logistic regression (LR). An AD8 score ≥ 2 was used to define CI as a baseline. SHapley Additive exPlanations (SHAP) values were used to interpret the results of ML models.ResultsThe first and sixth items of AD8, platelets, waist circumference, body mass index, carcinoembryonic antigens, age, serum uric acid, white blood cells, abnormal electrocardiogram, heart rate, and sex were selected as predictive features. Compared to the baseline (AUC = 0.65), the MLP showed the highest performance (AUC: 0.83 ± 0.04), followed by AdaBoost (AUC: 0.80 ± 0.04), SVM (AUC: 0.78 ± 0.04), GBDT (0.76 ± 0.04). Furthermore, the accuracy, sensitivity and specificity of four ML models were higher than the baseline. SHAP summary plots based on MLP showed the most influential feature on model decision for positive CI prediction was female sex, followed by older age and lower waist circumference.ConclusionsThe diagnostic models of CI applying ML, especially the MLP, were substantially more effective than the traditional AD8 scale with a score of ≥ 2 points. Our findings may provide new ideas for community dementia screening and to promote such screening while minimizing medical and health resources.

A structural depth network embedding stacking model based on Moran’s index and seasonal trend for short-term solar irradiance prediction

Solar irradiance prediction of multi-station is influenced by complex spatial characteristics and temporal fluctuations, so how to obtain accurate short-term irradiance prediction by using photovoltaic cluster data becomes a challenge. In order to address the challenge, a structural depth network embedding stacking model based on Moran’s I and seasonal trend for short-term solar irradiance prediction is proposed. Firstly, the deep spatial characteristics of photovoltaic clusters are analyzed by using bivariate Moran index to capture strong correlations between stations. Secondly, seasonal trend decomposition is used to smooth the seasonal factors in time series, and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise is used to decompose the residual components to reduce the fluctuation of signals and the complexity of data feature mapping. Finally, based on the Stacking framework, Long Short-term Memory Network, Least Absolute Selection and Shrinkage Operator, Gradient Boosted Decision Tree, and Artificial Neural Network are superimposed. And the aggregated sub-modal components are introduced into the robust integration model to predict the solar irradiance in multiple steps. Through the case study of the National Renewable Energy Laboratory open-source dataset in the United States, the conclusions are as follows: (1) The spatio-temporal method in this paper can effectively extract the deep spatial characteristics of photovoltaic stations. (2) The fusion strategy of embedded structured deep network effectively improves the stacking effect. (3) Comparing with many classical forecasting models, it shows that this method can effectively improve the forecasting effect.

Life cycle assessment of urban road networks: Quantifying carbon footprints and forecasting future material stocks

This study introduces a comprehensive framework designed to assess the carbon footprint of urban road networks, covering all stages from production to maintenance. Complementing this framework, a dedicated prediction model is also developed. Utilizing a machine learning methodology, specifically the Gradient Boosting Decision Tree (GBDT) algorithm, this model aims to accurately predict the material stock of urban road networks, thereby enhancing the overall understanding of their environmental impact. A case study focusing on Nanjing's infrastructure revealed that material production constitutes 78 % of the total emissions. Additionally, it was observed that the growth in the carbon footprint of Nanjing's urban road network has slowed down in recent years. The machine learning-based model, analyzing data from 2014 to 2020, accurately predicted the total material stock for 2021 and the stocks of different road construction materials, with a relative error under 2 %. This approach aids in the design of carbon-neutral urban transport systems and represents a stride in combating climate change.

The Florida Scoring System for stratifying children with suspected Sjögren's disease: a cross-sectional machine learning study.

Childhood Sjögren's disease is a rare, underdiagnosed, and poorly-understood condition. By integrating machine learning models on a paediatric cohort in the USA, we aimed to develop a novel system (the Florida Scoring System) for stratifying symptomatic paediatric patients with suspected Sjögren's disease. This cross-sectional study was done in symptomatic patients who visited the Department of Pediatric Rheumatology at the University of Florida, FL, USA. Eligible patients were younger than 18 years or had symptom onset before 18 years of age. Patients with confirmed diagnosis of another autoimmune condition or infection with a clear aetiological microorganism were excluded. Eligible patients underwent comprehensive examinations to rule out or diagnose childhood Sjögren's disease. We used latent class analysis with clinical and laboratory variables to detect heterogeneous patient classes. Machine learning models, including random forest, gradient-boosted decision tree, partial least square discriminatory analysis, least absolute shrinkage and selection operator-penalised ordinal regression, artificial neural network, and super learner were used to predict patient classes and rank the importance of variables. Causal graph learning selected key features to build the final Florida Scoring System. The predictors for all models were the clinical and laboratory variables and the outcome was the definition of patient classes. Between Jan 16, 2018, and April 28, 2022, we screened 448 patients for inclusion. After excluding 205 patients due to symptom onset later than 18 years of age, we recruited 243 patients into our cohort. 26 patients were excluded because of confirmed diagnosis of a disorder other than Sjögren's disease, and 217 patients were included in the final analysis. Median age at diagnosis was 15 years (IQR 11-17). 155 (72%) of 216 patients were female and 61 (28%) were male, 167 (79%) of 212 were White, and 20 (9%) of 213 were Hispanic, Latino, or Spanish. The latent class analysis identified three distinct patient classes: class I (dryness dominant with positive tests, n=27), class II (high symptoms with negative tests, n=98), and class III (low symptoms with negative tests, n=92). Machine learning models accurately predicted patient class and ranked variable importance consistently. The causal graphical model discovered key features for constructing the Florida Scoring System. The Florida Scoring System is a paediatrician-friendly tool that can be used to assist classification and long-term monitoring of suspected childhood Sjögren's disease. The resulting stratification has important implications for clinical management, trial design, and pathobiological research. We found a highly symptomatic patient group with negative serology and diagnostic profiles, which warrants clinical attention. We further revealed that salivary gland ultrasonography can be a non-invasive alternative to minor salivary gland biopsy in children. The Florida Scoring System requires validation in larger prospective paediatric cohorts. National Institute of Dental and Craniofacial Research, National Institute of Arthritis, Musculoskeletal and Skin Diseases, National Heart, Lung, and Blood Institute, and Sjögren's Foundation.

Accurate fall risk classification in elderly using one gait cycle data and machine learning

BackgroundFalls among the elderly are a major societal problem. While observations of medium-distance walking using inertial sensors identified potential fall predictors, classifying individuals at risk based on single gait cycles remains elusive. This challenge stems from individual variability and step-to-step fluctuations, making accurate classification difficult. MethodsWe recruited 44 participants, equally divided into high and low fall-risk groups. A smartphone secured on their second sacral spinous process recorded data during indoor walking. Features were extracted at each gait cycle from a 6-dimensional time series (tri-axial angular velocity and tri-axial acceleration) and classified using the gradient boosting decision tree algorithm. FindingsMean accuracy across five-fold cross-validation was 0.936. “Age” was the most influential individual feature, while features related to acceleration in the gait direction held the highest total relative importance when aggregated by axis (0.5365). InterpretationCombining acceleration, angular velocity data, and the gradient boosting decision tree algorithm enabled accurate fall risk classification in the elderly, previously challenging due to lack of discernible features. We reveal the first-ever identification of three-dimensional pelvic motion characteristics during single gait cycles in the high-risk group. This novel method, requiring only one gait cycle, is valuable for individuals with physical limitations hindering repetitive or long-distance walking or for use in spaces with limited walking areas. Additionally, utilizing readily available smartphones instead of dedicated equipment has potential to improve gait analysis accessibility.

Ensemble learning-based structural health monitoring of a bridge using an interferometric radar system

Ensemble learning-based structural health monitoring of a bridge using an interferometric radar system

Research on Evaluation and Optimization Algorithm of Athletes' Sports Skills Based on Trajectory Analysis and Machine Learning

Evaluating athletes' sports skills is significant for optimizing their training strategies and improving competitive outcomes. Although various studies are done to assess athletes' skills, they face challenges because of their limitations in capturing the complex, intricate patterns in athletes' movements. Hence, we proposed an innovative approach utilizing trajectory analysis and machine learning algorithms to evaluate and optimize athletes' sports skills. Initially, the trajectory data is collected using advanced motion tracking technology during either training or competitive sessions of the athletes. The collected data was pre-processed, and then feature extraction was performed to extract the most important and relevant features within the data. Further, the Gradient Boosting Decision Tree (GBDT) was trained using the extracted features to predict the athletes' performances. The GBDT is a powerful machine learning algorithm that can handle complex, non-linear interconnections among variables, enabling it to accurately predict the athletes' performances. Finally, we applied the Whale Optimization Algorithm (WOA) to refine the training process of the GBDT, enabling precise training and accurate predictions. The proposed methodology was implemented in the MATLAB software, and it is validated using the real-world athlete data collected during training sessions. The experimental results are validated in terms of parameters such as accuracy, precision, recall, and f-measure. Furthermore, we made a comparative study with the existing methods to validate the effectiveness and robustness of the proposed technique.

A Novel Ensemble Approach with HGBDTRF for Enhanced Detection and Prediction of Heart Disease

Heart disease is responsible for around one-third of all deaths that occur throughout the globe, as shown by the statistics. The employ of machine learning headed for anticipate cardiac illness have emerged as an important technique for both treating and preventing the ailment as more research is carried out in this area. A unique method that we are working on is called Hybrid Gradient Boosting Decision Tree with Random Forest (HGBDTRF), and it is being developed via the use of ensemble learning in the research paper that we are now working on. Machine learning will be able to make more accurate predictions about heart disease as a result of this. It has been shown by the actual findings that the HGBDTRF algorithm is capable of achieving a prediction accuracy of 95% in the Cleveland cardiac disease dataset, which has 1322 samples.

Hardness-guided machine learning for tungsten alloy strength prediction

Yield strength determines the material's resistance to permanent deformation. However, the traditional estimation method based on the triple relationship of Vickers hardness exhibits limited accuracy when applied to tungsten heavy alloys (WHA) with two-phase structure. This study presents a novel approach using machine learning and hardness data to predict the yield strength of tungsten heavy alloy efficiently and accurately. Among the eight machine learning models used, Gradient boosting decision tree model (GBDT) was the most effective model. The results demonstrate a strong agreement between the GBDT-based predictions and experimental results, with an average error of 6.7 %. We also gave the hardness versus yield strength relationship for the 90WNiFe alloy system. This finding highlights the potential of the GBDT regression model in conjunction with hardness measurements for predicting yield strength with high precision.

Prediction Model for Severe Thrombocytopenia Induced by Gemcitabine Plus Cisplatin Combination Therapy in Patients with Urothelial Cancer.

Chemotherapy-induced thrombocytopenia is often a use-limiting adverse reaction to gemcitabine and cisplatin (GC) combination chemotherapy, reducing therapeutic intensity, and, in some cases, requiring platelet transfusion. A retrospective cohort study was conducted on patients with urothelial cancer at the initiation of GC combination therapy and the objective was to develop a prediction model for the incidence of severe thrombocytopenia using machine learning. We performed receiver operating characteristic analysis to determine the cut-off values of the associated factors. Multivariate analyses were conducted to identify risk factors associated with the occurrence of severe thrombocytopenia. The prediction model was constructed from an ensemble model and gradient-boosted decision trees to estimate the risk of an outcome using the risk factors associated with the occurrence of severe thrombocytopenia. Of 186 patients included in this study, 46 (25%) experienced severe thrombocytopenia induced by GC therapy. Multivariate analyses revealed that platelet count ≤ 21.4 (×104/µL) [odds ratio 7.19, p<0.01], hemoglobin ≤ 12.1 (g/dL) [odds ratio 2.41, p=0.03], lymphocyte count ≤ 1.458 (×103/µL) [odds ratio 2.47, p=0.02], and dose of gemcitabine ≥ 775.245 (mg/m2) [odds ratio 4.00, p<0.01] were risk factors of severe thrombocytopenia. The performance of the prediction model using these associated factors was high (area under the curve 0.76, accuracy 0.82, precision 0.68, recall 0.50, and F-measure 0.58). Platelet count, hemoglobin level, lymphocyte count, and gemcitabine dose contributed to the development of a novel prediction model to identify the incidence of GC-induced severe thrombocytopenia.

A stacked deep multi-kernel learning framework for blast induced flyrock prediction

Blasting operations are widely and frequently used for rock excavation in Civil and Mining constructions. Flyrock is one of the most important issues induced by blasting operations in open pit mines, and therefore needs to be well predicted in order to identify the safety zone to prevent the potential injuries. For this purpose, 234 sets of blasting data were collected from Sungun Copper Mine site, and a stacked deep multi-kernel learning (SD-MKL) framework was proposed to estimate the blast induced flyrock with confidence accuracy. The proposed model uses the stacking-based representation learning framework (S-RL) to achieve deep learning on small-scale training sets. A multi-kernel learning model (MKL) is used as the base module of S-RL framework, which uses a multi-feature fusion strategy to generate multiple kernels with different kernel length in order to reduce the effort in tuning hyperparameters. In addition, this study further enhanced the predictive capability of SD-MKL by introducing the boosting method into the S-RL framework and hence proposed a boosted SD-MKL model. For comparison purpose, several existing machine learning models were implemented, i.e., kernel ridge regression (KRR), support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), ensemble deep random vector functional link (edRVFL), SD-KRR and SD-SVM. Our experimental results showed that the proposed boosted SD-MKL achieved the best overall performance, with the lowest RMSE of 0.21/1.73, MAE of 0.08/0.78, and the highest VAF of 99.98/99.24.

Intelligent prediction model of a polymer fracture grouting effect based on a genetic algorithm-optimized back propagation neural network

Polymer grouting can effectively improve the stability of surrounding rock fractures. However, in practical construction, it is difficult to judge the degree of coupling between the slurry and the rock, and the effective grouting range after grouting. Therefore, early prediction of the effect of grouting on the surrounding rock is crucial. In this paper, a new artificial intelligence method is proposed to predict the polymer fracture grouting effect. The genetic algorithm optimized back propagation neural network (GA-BP) is employed to construct an intelligent prediction model. To acquire a substantial dataset for constructing the model, an easily assembled/disassembled test apparatus for polymer fracture grouting is designed. The maximum coupling degree of the fractures and slurry diffusion distance are chosen as the evaluation metrics for the grouting effectiveness. The influences of the fracture characteristic parameters and grouting volume on the grouting effect are investigated. Furthermore, a comprehensive analysis is conducted on the spatiotemporal diffusion characteristics and slurry-rock coupling mechanism of polymer grouting. Compared to traditional BP neural networks, and three other machine learning algorithms (decision trees, random forests and gradient boosting decision trees), the GA-BP model outperforms them in terms of R2 (coefficient of determination), MSE (mean squared error), MBE (mean bias error), MAE (mean absolute error) and RMSE (root mean squared error) in both the test and training sets. The GA algorithm significantly improves the accuracy and robustness of the prediction model. The optimized model demonstrates significant accuracy in predicting grouting results and assessing efficiency, providing a practical reference for grouting construction.