Learning Modeling Research Articles

PWAS Hub for exploring gene-based associations of common complex diseases.

PWAS (proteome-wide association study) is an innovative genetic association approach that complements widely used methods like GWAS (genome-wide association study). The PWAS approach involves consecutive phases. Initially, machine learning modeling and probabilistic considerations quantify the impact of genetic variants on protein-coding genes' biochemical functions. Secondly, for each individual, aggregating the variants per gene determines a gene-damaging score. Finally, standard statistical tests are activated in the case-control setting to yield statistically significant genes per phenotype. The PWAS Hub offers a user-friendly interface for an in-depth exploration of gene-disease associations from the UK Biobank (UKB). Results from PWAS cover 99 common diseases and conditions, each with over 10,000 diagnosed individuals per phenotype. Users can explore genes associated with these diseases, with separate analyses conducted for males and females. For each phenotype, the analyses account for sex-based genetic effects, inheritance modes (dominant and recessive), and the pleiotropic nature of associated genes. The PWAS Hub showcases its usefulness for asthma by navigating through proteomic-genetic analyses. Inspecting PWAS asthma-listed genes (a total of 27) provide insights into the underlying cellular and molecular mechanisms. Comparison of PWAS-statistically significant genes for common diseases to the Open Targets benchmark shows partial but significant overlap in gene associations for most phenotypes. Graphical tools facilitate comparing genetic effects between PWAS and coding GWAS results, aiding in understanding the sex-specific genetic impact on common diseases. This adaptable platform is attractive to clinicians, researchers, and individuals interested in delving into gene-disease associations and sex-specific genetic effects.

Prediction of urban surface water quality scenarios using hybrid stacking ensembles machine learning model in Howrah Municipal Corporation, West Bengal

In the pursuit of understanding surface water quality for sustainable urban management, we created a machine learning modeling framework that utilized Random Forest (RF), Cubist, Extreme Gradient Boosting (XGB), Multivariate Adaptive Regression Splines (MARS), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), and their hybrid stacking ensemble RF (SE-RF), as well as stacking Cubist (SE-Cubist), to predict the distribution of water quality in the Howrah Municipal Corporation (HMC) area in West Bengal, India. Additionally, we employed the ReliefF and Shapley Additive exPlanations (SHAP) methods to elucidate the underlying factors driving water quality. We first estimated the water quality index (WQI) to model seven water quality parameters: total hardness (TH), pH, total dissolved solids (TDS), dissolved oxygen (DO), biochemical oxygen demand (BOD), calcium (Ca), magnesium (Mg). Then six independent factors were utilized (i.e. Precipitation (Pr), Maximum Temperature (Tmax), Minimum Temperature (Tmin), Normalized Difference Turbidity Index (NDTI), Normalized Difference Chlorophyll Index (NDCI), and Total Dissolved Solids (TDS)) for predicting the WQI mapping through the different ML models. This study demonstrated that the SE-Cubist model outperforms other ML models. During the testing phase, it achieved the best modeling results with an R2 = 0.975, RMSE = 0.351, and MAE = 0.197. The ReliefF and SHAP analyses identified Pr and Tmax as the most significant factors influencing WQI within the study area.

Detection of Floating Algae Blooms on Water Bodies Using PlanetScope Images and Shifted Windows Transformer Model

The increasing water temperature due to climate change has led to more frequent algae blooms and deteriorating water quality in coastal areas and rivers worldwide. To address this, we developed a deep learning-based model for identifying floating algae blooms using PlanetScope optical images and the Shifted Windows (Swin) Transformer architecture. We created 1,998 datasets from 105 scenes of PlanetScope imagery collected between 2018 and 2023, covering 14 water bodies known for frequent algae blooms. The methodology included data pre-processing, dataset generation, deep learning modeling, and inference result generation. The input images contained six bands, including vegetation indices such as the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), enhancing the model’s responsiveness to algae blooms. Evaluations were conducted using both single-period and multi-period datasets. The single-period model achieved a mean Intersection over Union (mIoU) between 72.18% and 76.47%, while the multi-period model significantly improved performance, with an mIoU of 91.72%. This demonstrates the potential of our model and highlights the importance of change detection in multi-temporal images for algae bloom monitoring. Additionally, the padding technique proposed in this study resolved the border issue that arises when mosaicking inference results from individual patches, providing a seamless view of the satellite scene.

Integrating Machine Learning, Land Cover, and Hydrological Modeling to Contribute Parameters for Climate Impacts on Water Resource Management

The purpose of this study is to establish basic policies for managing the impacts of climate change on water resources using the integration of machine learning and land cover modeling. We predicted future changes in land cover within the water management and assessed its vulnerability to climate change. After confirming this vulnerability, we considered measures to improve climate resilience and presented future water resource parameters. We reviewed the finances available to promote climate projects, noting the major river management funds. The future project will serve as a stepping stone to promote climate resilience projects addressing water resource challenges exacerbated by future climate change. The study examined the results of analyzing changes in land cover maps due to climate change and assessed vulnerability in water management areas until 2050. According to the analysis results, the regulations for our study areas were set lower than those for other water management zones, resulting in a high rate of urbanization. Therefore, the climate resilience project in the water management area should be implemented first, despite the need for a long-term view in adapting to climate change.

Can Data Empower Indigenous People? Unveiling an Innovative Dataset for Quantitative Analysis, Replication Modeling, and Economic Development

Abstract Indigenous peoples are among the most vulnerable, ignored, and marginalized groups in society. Poverty is the oldest social problem and difficult to counter. The Indigenous people with which the authors live and work, the Agta Tabangnon, suffer from poverty and multidimensional socioeconomic deprivations. Indigenous peoples’ studies are qualitative, while poverty studies are typically generic, exposed to large sampling errors, and intended for nationwide decisions. Therefore, measuring poverty for specific tribes through complete enumeration with multifaceted disaggregation is critical for economic development. There is no comprehensive census specifically designed for Indigenous peoples to encompass the multidimensional aspects of their way of life. Nonetheless, the authors are resourceful in generating useful datasets from their partners. The locale is situated in the poorest district of the poorest province in the poorest region of Luzon, Philippines. The datasets contain multidimensional poverty indicators that are readily usable, along with complementary analytics to visualize the data. They may serve to measure poverty in Indigenous communities across different regions and countries. By utilizing this data, further empirical analysis, regressions, machine learning, and econometric modeling can be conducted. It can be freely utilized to target policies that address the multifaceted poverty and promote economic development within tribal communities.

Anti-machine-learning-attack strong PUF design based on multi-path delay selection strategy

Physical unclonable functions (PUF) have significant potential for application in information security. However, strong PUFs are vulnerable to machine learning (ML) modeling attacks, which severely limit their application in device authentication. Despite a variety of resistance techniques, strong PUFs suffer from hardware cost and stability deficiencies. This study proposes an anti-machine-learning-attack strong PUF based on a multi-path delay selection strategy through research on the entropy source of a strong PUF and the delay signal selection mechanism. First, we constructed a deviation source circuit based on multiplexers to increase the diversity of the delay signal transmission paths. Second, we constructed a delay selection circuit based on the logic gates. This circuit dynamically selects the delay signals with the same transmission path in the deviation source using AND and OR gates. Subsequently, the deviation source and delay selection circuits were utilized to construct the delay module, and the interconnection module was inserted between the delay modules to achieve alternating appearances of different types of logic gates along the delay path. Finally, RS flip-flops were employed to make decisions on the bias signals with the same delay path, and the final response was output through an XOR operation. The proposed PUF was implemented on a Xilinx Artix-7 FPGA, and the prediction accuracy of the four typical ML models was below 59 % (with 500,000 challenge-response pairs as the training set). Moreover, the proposed PUF structure is scalable and exhibits better performance in terms of hardware cost and stability than existing classic structures.

Artificial intelligence methods used in various aquaculture applications: A systematic literature review

AbstractThis research article presents a systematic literature review on the current state‐of‐the‐art artificial intelligence (AI) methodologies used in aquaculture applications. As the demand for seafood continues to grow, the aquaculture industry faces numerous challenges, including disease management, feeding optimization, water quality monitoring, and extraction of aquaculture area. To address these challenges effectively and sustainably, AI techniques have been increasingly applied in aquaculture systems over recent years. This review aims to analyze various AI methodologies utilized within different aspects of aquacultural practices. By examining existing studies and identifying trends and gaps in research areas related to AI integration into aquaculture practices, this paper provides valuable insights for further advancements. The purpose was to synthesize current knowledge on application and its challenges in implementing AI technologies within the commercial aquaculture industry. Specifically, the review is to identify and analyze peer‐reviewed studies reporting on applications of AI technologies in aquaculture industry, to classify and summarize the key findings from the selected studies in aquaculture operations through AI, and to evaluate and discuss any challenges reported regarding the implementation and adoption of AI solutions in commercial aquaculture. The overall goal was to comprehensively assess these via a systematic literature review process. Challenges of AI technologies and methods were identified in the research literature for applying AI to optimize commercial aquaculture practices and production. An exhaustive search of a scholarly database from Scopus, was performed and papers published in English between 2020 and 2024 were considered for inclusion. After a rigorous screening process involving over 116 studies, 57 highly relevant works were identified and analyzed according to key themes involving demonstrated AI applications, employed methodologies and challenges that are expected when applying such methods. The findings revealed that AI‐driven tools such as computer vision, machine learning, and predictive modeling hold much potential for enhancing sustainability, efficiency, and productivity within aquaculture operations through applications like disease monitoring, environmental management, and production optimization. However, the review also uncovered substantial challenges that will continue limiting widespread adoption, including restricted access to representative data, prohibitive expenses, technical complexities, lack of social acceptance, and data privacy and security concerns. This comprehensive synthesis of the current evidence available provides an empirical foundation upon which further progress can be built by identifying priority areas requiring additional research efforts to fully address challenges on the responsible integration of suitable solutions for the commercial aquaculture industry globally.

Spatial variation of soil carbon, nitrogen, and phosphorus in the Caatinga dry forest

Soil nutrients are crucial for understanding the impact of global changes on terrestrial ecosystems. Carbon (C), nitrogen (N), and phosphorus (P) are required in specific quantities by plants and are related to soil fertility. In the Caatinga, one of the world’s largest and most diverse tropical dry forests, there have been limited studies investigating the factors that contribute to the spatial distribution of organic carbon (OC), N, and P in the soil and, even fewer, those that explored the use of Machine learning (ML) modeling. In this research, we aim to predict the spatial distribution of these properties at depths ranging from 0 to 20 cm in the Caatinga biome and assess the predictive capability of environmental and geographic variables. We used the Random Forest model in Google Earth Engine to forecast maps with a spatial resolution of 30 m. The best result was obtained for predicting P [Lin's concordance correlation coefficient (LCCC) of 0.32 and R2 of 0.25], followed by OC (LCCC of 0.25 and R2 of 0.17), N (LCCC of 0.21 and R2 of 0.12) and C/N ratio (LCCC of 0.14 and R2 of 0.10). The final maps exhibited a consistent spatial pattern, with OC, N, and C/N ratio showing correlation with climatic covariates (air and soil temperature in the first 15 cm deep), topographic data (altitude), and geographic regions (longitude and latitude). The variation in P content was primarily influenced by parent material. We highlight the relevance of ecotones, which recorded the highest average levels of C and N and C/N, demonstrating the importance of these areas for the maintenance and dynamics of these ecosystems.

Investigation of Tandem Queuing Systems Using Machine Learning Methods

This paper considers tandem queuing systems with limited buffer sizes in each phase. The system handles an incoming correlated MAP flow and the service time obeys a PH-distribution. Models of such systems and methods for their investigation are briefly reviewed from the historical perspective. According to the review, the problem statement presented below, the methods proposed for solving this problem, and the corresponding results are novel. An accurate algorithm for calculating the performance characteristics of low-dimensional tandem queuing systems is described, including an estimate of the algorithm’s complexity. An approach using both machine learning and simulation modeling is suggested for the investigation of high-dimensional tandem queuing systems. Numerical analysis results are provided to show the effectiveness of machine learning methods for estimating the performance of tandem queuing systems.

Discussing discarded models: an integrative teaching resource

This study proposes a kind of teaching resource adaptable to different levels of teaching and training objectives that allows the introduction of contextual issues and concepts of history and the nature of science while providing tools for learning modeling and integrating different kinds of knowledge. A controversial case from science history was sought to develop an integrating teaching activity. The case to find must be one that confront at least two different models to solve a scientific problem or a technological one. Torricelli’s theory vs. horror vacui theory as it was modified by Galileo result a useful case to take as content for the teaching activity. Groups of students must argument in favor and against each of theories or models. The proposed activity introduces future teachers in the student’s role, considering that they will play the teacher’s role when they use similar activities with their future students. Moreover, it trains future physics teachers to integrate modeling, history and nature of science.

Digital Engineering in Photonics: Optimizing Laser Processing

This article explores the transformative impact of digital engineering on photonic technologies, emphasizing advancements in laser processing through digital models, artificial intelligence (AI), and freeform optics. It presents a comprehensive review of how these technologies enhance efficiency, precision, and control in manufacturing processes. Digital models are pivotal for predicting and optimizing thermal effects in laser processing, thereby reducing material deformation and defects. The integration of AI further refines these models, improving productivity and quality in applications such as micromachining and cladding. Additionally, the combination of AI with freeform optics advances laser technology by enabling real-time adjustments and customizable beam profiles, which enhance processing versatility and reduce material damage. The use of digital twins is also examined as a key development in laser-based manufacturing, offering significant improvements in process optimization, defect reduction, and system efficiency. By incorporating real-time monitoring, machine learning, and physics-based modeling, digital twins facilitate precise simulations and predictions, leading to more effective and reliable manufacturing practices. Overall, the integration of digital twins, AI, and freeform optics into laser processing marks a significant progression in manufacturing technology. These advancements collectively enhance precision, efficiency, and adaptability, resulting in improved product quality and reduced operational costs. The continued evolution of these technologies is expected to drive further advancements in manufacturing practices, offering more robust solutions for complex production environments.

The challenges of mapping quiet urban areas from mobile sound surveys

Detailed spatial data on noise levels are needed to identify quiet areas. Yet noise maps derived from sound propagation models based on traffic flows or sensor networks are often incomplete. Surveys using mobile sound recording coupled with machine learning modelling have offered a possible solution, but so far have focused on averaged noise levels. We argue that quiet areas should ideally be consistently quiet, rather than simply quiet on average, yet mobile survey data usually lack the full temporal profile needed to quantify consistency in noise levels. Using data from our Southampton study area, we show that modification of the loss function used in machine learning modelling of mobile survey data can yield information on the likely range of noise levels at any location across an entire city. We use this approach not only to identify locations that are consistently quiet, but also to help understand which urban features may be associated with quiet, average and noisy events at any given location.

DSA Quantitative Analysis and Predictive Modeling of Obliteration in Cerebral AVM following Stereotactic Radiosurgery.

Stereotactic radiosurgery is a key treatment modality for cerebral AVMs, particularly for small lesions and those located in eloquent brain regions. Predicting obliteration remains challenging due to evolving treatment paradigms and complex AVM presentations. With digital subtraction angiography (DSA) being the gold standard for outcome evaluation, radiomic approaches offer potential for more objective and detailed analysis. We aimed to develop machine learning modeling using DSA quantitative features for post-SRS obliteration prediction. A prospective registry of patients with cerebral AVMs was screened to include patients with digital prestereotactic radiosurgery DSA. Anterior-posterior and lateral views were retrieved and manually segmented. Quantitative features were computed from the lesion ROI. Following feature selection, machine learning models were developed to predict unsuccessful 2-year total obliteration using processed radiomics features in comparison with clinical and radiosurgical features. When we evaluated through area under the receiver operating characteristic curve (AUROC), accuracy, area under the precision-recall curve F1, recall, and precision, the best performing model predictions on the test set were interpreted using the Shapley additive explanations approach. DSA images of 100 included patients were retrieved and analyzed. The best-performing clinical radiosurgical model was a gradient boosting classifier with an AUROC of 68% and a recall of 67%. When we used radiomics variables as input, the AdaBoost classifier had the best evaluation metrics with an AUROC of 79% and a recall of 75%. The most important clinico-radiosurgical features, ranked by model contribution, were lesion volume, patient age, treatment dose rate, the presence of seizure at presentation, and prior resection. The most important ranked radiomics features were the following: gray-level size zone matrix, gray-level nonuniformity, kurtosis, sphericity, skewness, and gray-level dependence matrix dependence nonuniformity. The combination of radiomics with machine learning is a promising approach for predicting cerebral AVM obliteration status following stereotactic radiosurgery. DSA could enhance prognostication of stereotactic radiosurgery-treated AVMs due to its high spatial resolution. Model interpretation is essential for building transparent models and establishing clinically valid radiomic signatures.

LLMs4OL 2024 Overview: The 1st Large Language Models for Ontology Learning Challenge

This paper outlines the LLMs4OL 2024, the first edition of the Large Language Models for Ontology Learning Challenge. LLMs4OL is a community development initiative collocated with the 23rd International Semantic Web Conference (ISWC) to explore the potential of Large Language Models (LLMs) in Ontology Learning (OL), a vital process for enhancing the web with structured knowledge to improve interoperability. By leveraging LLMs, the challenge aims to advance understanding and innovation in OL, aligning with the goals of the Semantic Web to create a more intelligent and user-friendly web. In this paper, we give an overview of the 2024 edition of the LLMs4OL challenge and summarize the contributions.

Recent Advances in Ocular Drug Delivery: Insights into Lyotropic Liquid Crystals.

Background/Objectives: This review examines the evolution of lyotropic liquid crystals (LLCs) in ocular drug delivery, focusing on their ability to address the challenges associated with traditional ophthalmic formulations. This study aims to underscore the enhanced bioavailability, prolonged retention, and controlled release properties of LLCs that significantly improve therapeutic outcomes. Methods: This review synthesizes data from various studies on both bulk-forming LLCs and liquid crystal nanoparticles (LCNPs). It also considers advanced analytical techniques, including the use of machine learning and AI-driven predictive modeling, to forecast the phase behavior and molecular structuring of LLC systems. Emerging technologies in biosensing and real-time diagnostics are discussed to illustrate the broader applicability of LLCs in ocular health. Results: LLCs are identified as pivotal in promoting targeted drug delivery across different regions of the eye, with specific emphasis on the tailored optimization of LCNPs. This review highlights principal categories of LLCs used in ocular applications, each facilitating unique interactions with physiological systems to enhance drug efficacy and safety. Additionally, novel applications in biosensing demonstrate LLCs' capacity to improve diagnostic processes. Conclusions: Lyotropic liquid crystals offer transformative potential in ocular drug delivery by overcoming significant limitations of conventional delivery methods. The integration of predictive technologies and biosensing applications further enriches the utility of LLCs, indicating a promising future for their use in clinical settings. This review points to continued advancements and encourages further research in LLC technology to maximize its therapeutic benefits.

Deep deoxidation of water in a miniaturized annular rotating device: Experimental investigation and machine learning modeling

Conventional gas–liquid devices exhibit limitations, including inadequate dispersion efficiency and significant backmixing, leading to low conversion and large equipment volume. Thus, a miniaturized annular rotating device (m-ARD) was proposed based on microscale effects and rotating flow field to achieve efficient gas–liquid mass transfer and high conversion. Nitrogen-oxygenated water was selected as the experimental system to evaluate the performance of the m-ARD. The gas–liquid flow characteristics were investigated. The analysis focused on examining the impact of different factors on deoxygenation efficiency. The deoxygenation performance was optimized and compared with different devices. The study found that the m-ARD enables a continuous counter-current gas–liquid flow mode, with superior mixing performance and a narrow residence time distribution. The deoxygenated water with an oxygen concentration as low as 0.14 ppm can be produced, with a volumetric mass transfer coefficient (kLa) of 0.26 s−1, a theoretical stage value of 4.22, and a handling capacity of 30 mL/min under optimized experimental conditions. In addition, kLa was predicted using an artificial neural network model and showed good agreement with the simulated values. This work provides a promising reactor for chemical reactions that require high conversions.

Intelligence analysis of membrane distillation via machine learning models for pharmaceutical separation

This study investigates simulation of pharmaceutical separation via membrane distillation process by computational simulation and machine learning modeling strategy. The efficacy of three regression models, i.e., Multi-layer Perceptron (MLP), Gamma Regression, and Support Vector Regression (SVR) in predicting the solute concentration, C(mol/m³), was evaluated. The hyper-parameters were optimized by fine-tuning the models using the Red Deer Algorithm (RDA). Computational analyses were carried out for removal of pharmaceuticals from solution by membrane distillation in continuous mode. Mass transfer and machine learning models were implemented focusing on concentration of solute in the feed section of membrane. Results indicate that the Multi-layer Perceptron model achieved great accuracy with an R2 of 0.9955, an MAE of 0.0084, and an RMSE of 0.0148, effectively capturing complex nonlinear relationships in the data. Gamma Regression also performed acceptably, with fitting R2 of 0.9214, showing its suitability for positively skewed data. The Support Vector Regression model, while capturing the general trend, showed the lowest performance with an R2 of 0.8710. These findings suggest that the Multi-layer Perceptron is the most accurate model for this dataset, followed by Gamma Regression and Support Vector Regression. This underscores the importance of careful model selection and optimization in regression analysis in combination with computational simulation of membrane processes.

Impact and Effectiveness of COVID-19 Vaccines Based on Machine Learning Analysis of a Time Series: A Population-Based Study.

Background: Although confirmed cases of infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have been declining since late 2020 due to general vaccination, little research has been performed regarding the impact of vaccines against SARS-CoV-2 in Spain in terms of hospitalizations and deaths. Objective: Our aim was to identify the reduction in severity and mortality of coronavirus disease 2019 (COVID-19) at a nationwide level due to vaccination. Methods: We designed a retrospective, population-based study to define waves of infection and to describe the characteristics of the hospitalized population. We also studied the rollout of vaccination and its relationship with the decline in hospitalizations and deaths. Finally, we developed two mathematical models to estimate non-vaccination scenarios using machine learning modeling (with the ElasticNet and RandomForest algorithms). The vaccination and non-vaccination scenarios were eventually compared to estimate the number of averted hospitalizations and deaths. Results: In total, 498,789 patients were included, with a global mortality of 14.3%. We identified six waves or epidemic outbreaks during the observed period. We established a strong relationship between the beginning of vaccination and the decline in both hospitalizations and deaths due to COVID-19 in all age groups. We also estimated that vaccination prevented 170,959 hospitalizations (CI 95% 77,844-264,075) and 24,546 deaths (CI 95% 2548-46,543) in Spain between March 2021 and December 2021. We estimated a global reduction of 9.19% in total deaths during the first year of COVID-19 vaccination. Conclusions: Demographic and clinical profiles changed over the first months of the pandemic. In Spain, patients over 80 years old and other age groups obtained clinical benefit from early vaccination. The severity of COVID-19, in terms of hospitalizations and deaths, decreased due to vaccination. Our use of machine learning models provided a detailed estimation of the averted burden of the pandemic, demonstrating the effectiveness of vaccination at a population-wide level.

Hydrothermal bio-oil yield and higher heating value of high moisture and lipid biomass: Machine Learning modeling and feature response behavior analysis

The yield and higher heating value (HHV) of bio-oil products are significant performance parameters for the hydrothermal conversion of high-water and high-lipid biomass. Machine learning (ML) modeling prediction is a fast and convenient means of obtaining performance parameters. An informative dataset with 243 samples was prepared, and two highly adapted ML algorithms were used: Random Forest (RF) and Extreme Gradient Boosting Tree (XGBoost). It is interesting to note that the developed ML models demonstrated great prediction ability; for example, the regression coefficient () of the XGBoost model for yield and HHV prediction was as high as 0.942 and 0.940, respectively. Furthermore, partial dependence plots and SHAP (SHapley Additive exPlanations) interpretability methodologies were adopted to address the main contributions of the feature identification and response behavior analysis of the features. The results demonstrated that the biomass composition had the greatest effect on bio-oil yield, with fat contributing up to 40%. In contrast, the elemental composition had the most significant effect on the HHV of bio-oil. Notably, hydrogen content affected the HHV of up to 4.5 units. The interaction response behavior showed that the interaction of the process parameters with feedstock properties was most common and significant. The information obtained from the response mechanism can be used to enhance the subsequent hydrothermal fuel preparation process for bio-oils.

High-Strength Self-Compacting Concrete Production Incorporating Supplementary Cementitious Materials: Experimental Evaluations and Machine Learning Modelling

AbstractThis study investigates mechanical properties, durability performance, non-destructive testing (NDT) characteristics, environmental impact evaluation, and advanced machine learning (ML) modelling techniques employed in the analysis of high-strength self-compacting concrete (HSSCC) incorporating varying supplementary cementitious materials (SCMs) to develop sustainable building construction. The findings from the fresh characteristics test indicate that mixes’ optimal flowability and passing qualities can be achieved using different concentrations of marble powder (MP) alongside a consistent amount of silica fume (SF) and fly ash (FA). Moreover, the incorporation of 10% MP along with 10% FA and 20% SF in HSSCC significantly improved the compressive strength by 14.68%, while the splitting tensile strength increased by 15.59% compared to the reference mix at 56 days. While random forest (RF), gradient boosting (GB), and their ensemble models exhibit strong coefficient correlation (R2) values, the GB model demonstrates more precision, indicating reliable predicted outcomes of the mechanical properties. Following subsequent testing, it has been demonstrated that incorporating SCMs improves the NDT properties of HSSCC and enhances its durability. The finer MP, SF, and FA particles enhanced microstructural performance by minimizing voids and cracks while improving the C–H–S bond. As noticed by its lower CO2-eq per MPa for SCMs, the HSSCC mix with up to 15% MP inclusion increased mechanical strength while reducing the environmental footprint, making it an eco-friendly concrete alternative.