SEARCH · Engineering Papers

Results for “k mean”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Entropy-Assisted Quality Pattern Identification in Finance

Short-term patterns in financial time series form the cornerstone of many algorithmic trading strategies, yet extracting these patterns reliably from noisy market data remains a formidable challenge. In this paper, we propose an entropy-assisted framework for identifying high-quality, non-overlapping patterns that exhibit consistent behavior over time. We ground our approach in the premise that historical patterns, when accurately clustered and pruned, can yield substantial predictive power for short-term price movements. To achieve this, we incorporate an entropy-based measure as a proxy for information gain: patterns that lead to high one-sided movements in historical data yet retain low local entropy are more “informative” in signaling future market direction. Compared to conventional clustering techniques such as K-means and Gaussian Mixture Models (GMMs), which often yield biased or unbalanced groupings, our approach emphasizes balance over a forced visual boundary, ensuring that quality patterns are not lost due to over-segmentation. By emphasizing both predictive purity (low local entropy) and historical profitability, our method achieves a balanced representation of Buy and Sell patterns, making it better suited for short-term algorithmic trading strategies. This paper offers an in-depth illustration of our entropy-assisted framework through two case studies on Gold vs. USD and GBPUSD. While these examples demonstrate the method’s potential for extracting high-quality patterns, they do not constitute an exhaustive survey of all possible asset classes.

Physics↗

DOE OSTI2024

Uncertainty Quantification in CO2 Trapping Mechanisms: A Case Study of PUNQ-S3 Reservoir Model Using Representative Geological Realizations and Unsupervised Machine Learning

Evaluating uncertainty in CO2 injection projections often requires numerous high-resolution geological realizations (GRs) which, although effective, are computationally demanding. This study proposes the use of representative geological realizations (RGRs) as an efficient approach to capture the uncertainty range of the full set while reducing computational costs. A predetermined number of RGRs is selected using an integrated unsupervised machine learning (UML) framework, which includes Euclidean distance measurement, multidimensional scaling (MDS), and a deterministic K-means (DK-means) clustering algorithm. In the context of the intricate 3D aquifer CO2 storage model, PUNQ-S3, these algorithms are utilized. The UML methodology selects five RGRs from a pool of 25 possibilities (20% of the total), taking into account the reservoir quality index (RQI) as a static parameter of the reservoir. To determine the credibility of these RGRs, their simulation results are scrutinized through the application of the Kolmogorov–Smirnov (KS) test, which analyzes the distribution of the output. In this assessment, 40 CO2 injection wells cover the entire reservoir alongside the full set. The end-point simulation results indicate that the CO2 structural, residual, and solubility trapping within the RGRs and full set follow the same distribution. Simulating five RGRs alongside the full set of 25 GRs over 200 years, involving 10 years of CO2 injection, reveals consistently similar trapping distribution patterns, with an average value of Dmax of 0.21 remaining lower than Dcritical (0.66). Using this methodology, computational expenses related to scenario testing and development planning for CO2 storage reservoirs in the presence of geological uncertainties can be substantially reduced.

Mahjour, Seyed Kourosh↗

DOE OSTI2021

Optical Classification of Lower Amazon Waters Based on In Situ Data and Sentinel-3 Ocean and Land Color Instrument Imagery

Optical water types (OWTs) were identified from an in situ dataset of concomitant biogeochemical and optical parameters acquired in the Amazon River and its tributaries, in the Lower Amazon region, at different hydrological conditions from 2014 to 2017. A seasonal bio-optical characterization was performed. The k-means classification was applied to the in situ normalized reflectance spectra (rn(λ)), allowing the identification of four OWTs. An optical index method was also applied to the rn(λ) defining the thresholds of the OWTs. Next, level-3 Sentinel-3 Ocean and Land Color Instrument images representative of the seasonal discharge conditions were classified using the identified in situ OWTs as reference. The differences between Amazon River and clearwater tributary OWTs were dependent on the hydrological dynamics of the Amazon River, also showing a strong seasonal variability. Each OWT was associated with a specific bio-optical and biogeochemical environment assessed from the corresponding absorption coefficient values of colored dissolved organic matter (aCDOM) and particulate matter (ap), chlorophyll-a and suspended particulate matter (SPM) concentrations, and aCDOM/ap ratio. The rising water season presented a unique OWT with high SPM concentration and high relative contribution of ap to total absorption compared to the other OWTs. This bio-optical characterization of Lower Amazon River waters represents a first step for developing remote sensing inversion models adjusted to the optical complexity of this region.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Improving Medication Regimen Recommendation for Parkinson’s Disease Using Sensor Technology

Parkinson’s disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson’s patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician’s initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson’s medication changes—clinically assessed by the MDS-Unified Parkinson’s Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients’ cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose—with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Integrated Land Suitability Assessment for Depots Siting in a Sustainable Biomass Supply Chain

A sustainable biomass supply chain would require not only an effective and fluid transportation system with a reduced carbon footprint and costs, but also good soil characteristics ensuring durable biomass feedstock presence. Unlike existing approaches that fail to account for ecological factors, this work integrates ecological as well as economic factors for developing sustainable supply chain development. For feedstock to be sustainably supplied, it necessitates adequate environmental conditions, which need to be captured in supply chain analysis. Using geospatial data and heuristics, we present an integrated framework that models biomass production suitability, capturing the economic aspect via transportation network analysis and the environmental aspect via ecological indicators. Production suitability is estimated using scores, considering both ecological factors and road transportation networks. These factors include land cover/crop rotation, slope, soil properties (productivity, soil texture, and erodibility factor) and water availability. This scoring determines the spatial distribution of depots with priority to fields scoring the highest. Two methods for depot selection are presented using graph theory and a clustering algorithm to benefit from contextualized insights from both and potentially gain a more comprehensive understanding of biomass supply chain designs. Graph theory, via the clustering coefficient, helps determine dense areas in the network and indicate the most appropriate location for a depot. Clustering algorithm, via K-means, helps form clusters and determine the depot location at the center of these clusters. An application of this innovative concept is performed on a case study in the US South Atlantic, in the Piedmont region, determining distance traveled and depot locations, with implications on supply chain design. The findings from this study show that a more decentralized depot-based supply chain design with 3depots, obtained using the graph theory method, can be more economical and environmentally friendly compared to a design obtained from the clustering algorithm method with 2 depots. In the former, the distance from fields to depots totals 801,031,476 miles, while in the latter, it adds up to 1,037,606,072 miles, which represents about 30% more distance covered for feedstock transportation.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2021

Physical Drivers of Emission-line Diversity of SDSS Seyfert 2s and LINERs after Removal of Contributions from Star Formation

Ionization sources other than H ιι regions give rise to the right-hand branch in the standard ([N ιι]) BPT diagram, populated by Seyfert 2s and LINERs. However, because the majority of Seyfert/LINER hosts are star-forming (SF), H ιι regions contaminate the observed lines to some extent, making it unclear if the position along the branch is merely due to various degrees of mixing between pure Seyferts/LINERs and SF, or whether it reflects the intrinsic diversity of Seyfert/LINER ionizing sources. In this study, we empirically remove SF contributions in ~100,000 Seyferts/LINERs from SDSS using the doppelganger method. Here, we find that mixing is not the principal cause of the extended morphology of the observed branch. Rather, Seyferts/LINERs intrinsically have a wide range of line ratios. Variations in ionization parameter and metallicity can account for much of the diversity of Seyfert/LINER line ratios, but the hardness of the ionization field also varies significantly. Furthermore, our k -means classification on seven decontaminated emission lines reveals that LINERs are made up of two populations, which we call soft and hard LINERs. The Seyfert 2s differ from both types of LINERs primarily by higher ionization parameter, whereas the two LINER types mainly differ from each other (and from star-forming regions) in the hardness of the radiation field. We confirm that the [N ιι] BPT diagram more efficiently identifies LINERs than [S ιι] and [O ι] diagnostics, because in the latter many LINERs, especially soft ones, occupy the same location as pure starformers, even after the SF has been removed from LINER emission.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

Unsupervised Machine Learning for Exploratory Data Analysis of Exoplanet Transmission Spectra

Abstract Transit spectroscopy is a powerful tool for decoding the chemical compositions of the atmospheres of extrasolar planets. In this paper, we focus on unsupervised techniques for analyzing spectral data from transiting exoplanets. After cleaning and validating the data, we demonstrate methods for: (i) initial exploratory data analysis, based on summary statistics (estimates of location and variability); (ii) exploring and quantifying the existing correlations in the data; (iii) preprocessing and linearly transforming the data to its principal components; (iv) dimensionality reduction and manifold learning; (v) clustering and anomaly detection; and (vi) visualization and interpretation of the data. To illustrate the proposed unsupervised methodology, we use a well-known public benchmark data set of synthetic transit spectra. We show that there is a high degree of correlation in the spectral data, which calls for appropriate low-dimensional representations. We explore a number of different techniques for such dimensionality reduction and identify several suitable options in terms of summary statistics, principal components, etc. We uncover interesting structures in the principal component basis, namely well-defined branches corresponding to different chemical regimes of the underlying atmospheres. We demonstrate that those branches can be successfully recovered with a K-means clustering algorithm in a fully unsupervised fashion. We advocate for lower-dimensional representations of the spectroscopic data in terms of the main principal components, in order to reveal the existing structure in the data and quickly characterize the chemical class of a planet.

Matchev, Konstantin T. (ORCID:0000000341829096)↗

DOE OSTI2020

Cloud regimes over the Amazon Basin: perspectives from the GoAmazon2014/5 campaign

Abstract. Radiosonde observations collected during the GoAmazon2014/5 campaign are analyzed to identify the primary thermodynamic regimes accompanying different modes of convection over the Amazon. This analysis identifies five thermodynamic regimes that are consistent with traditional Amazon calendar definitions of seasonal shifts, which include one wet, one transitional, and three dry season regimes based on a k-means cluster analysis. A multisensor ground-based approach is used to project associated bulk cloud and precipitation properties onto these regimes. This is done to assess the propensity for each regime to be associated with different characteristic cloud frequency, cloud types, and precipitation properties. Additional emphasis is given to those regimes that promote deep convective precipitation and organized convective systems. Overall, we find reduced cloud cover and precipitation rates to be associated with the three dry regimes and those with the highest convective inhibition. While approximately 15 % of the dataset is designated as organized convection, these events are predominantly contained within the transitional regime.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

A full year of aerosol size distribution data from the central Arctic under an extreme positive Arctic Oscillation: insights from the Multidisciplinary drifting Observatory for the Study of Arctic Climate (MOSAiC) expedition

Abstract. The Arctic environment is rapidly changing due to accelerated warming in the region. The warming trend is driving a decline in sea ice extent, which thereby enhances feedback loops in the surface energy budget in the Arctic. Arctic aerosols play an important role in the radiative balance and hence the climate response in the region, yet direct observations of aerosols over the Arctic Ocean are limited. In this study, we investigate the annual cycle in the aerosol particle number size distribution (PNSD), particle number concentration (PNC), and black carbon (BC) mass concentration in the central Arctic during the Multidisciplinary drifting Observatory for the Study of Arctic Climate (MOSAiC) expedition. This is the first continuous, year-long data set of aerosol PNSD ever collected over the sea ice in the central Arctic Ocean. We use a k-means cluster analysis, FLEXPART simulations, and inverse modeling to evaluate seasonal patterns and the influence of different source regions on the Arctic aerosol population. Furthermore, we compare the aerosol observations to land-based sites across the Arctic, using both long-term measurements and observations during the year of the MOSAiC expedition (2019–2020), to investigate interannual variability and to give context to the aerosol characteristics from within the central Arctic. Our analysis identifies that, overall, the central Arctic exhibits typical seasonal patterns of aerosols, including anthropogenic influence from Arctic haze in winter and secondary aerosol processes in summer. The seasonal pattern corresponds to the global radiation, surface air temperature, and timing of sea ice melting/freezing, which drive changes in transport patterns and secondary aerosol processes. In winter, the Norilsk region in Russia/Siberia was the dominant source of Arctic haze signals in the PNSD and BC observations, which contributed to higher accumulation-mode PNC and BC mass concentrations in the central Arctic than at land-based observatories. We also show that the wintertime Arctic Oscillation (AO) phenomenon, which was reported to achieve a record-breaking positive phase during January–March 2020, explains the unusual timing and magnitude of Arctic haze across the Arctic region compared to longer-term observations. In summer, the aerosol PNCs of the nucleation and Aitken modes are enhanced; however, concentrations were notably lower in the central Arctic over the ice pack than at land-based sites further south. The analysis presented herein provides a current snapshot of Arctic aerosol processes in an environment that is characterized by rapid changes, which will be crucial for improving climate model predictions, understanding linkages between different environmental processes, and investigating the impacts of climate change in future Arctic aerosol studies.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

A bi-level spatiotemporal clustering approach and its application to drought extraction

We present a novel flexible bi-level spatiotemporal clustering algorithm to extract events based on their intensity and spatiotemporal structures. Our algorithm consists of using (i) a novel space-time k-means clustering to obtain spatiotemporally coherent intensity clusters, and (ii) a density-based spatial clustering of applications with noise (DBSCAN) to spatiotemporally section the intensity clusters into individual events. We discuss the development of the algorithm, the selection, tuning and meaning of the parameters within each step, as well as its validation. Finally, we apply the algorithm to a spatiotemporal drought index, standardized vapor pressure deficit drought index (SVDI), over the continental United States (US) from 1980–2021 and show that it captures historical drought events over the continental United States and their spatiotemporal extents.

17 WIND ENERGY↗

DOE OSTI2023

Evaluating precipitation distributions at regional scales: a benchmarking framework and application to CMIP5 and 6 models

Abstract. As the resolution of global Earth system models increases, regional-scale evaluations are becoming ever more important. This study presents a framework for quantifying precipitation distributions at regional scales and applies it to evaluate Coupled Model Intercomparison Project (CMIP) 5 and 6 models. We employ the Intergovernmental Panel on Climate Change (IPCC) sixth assessment report (AR6) climate reference regions over land and propose refinements to the oceanic regions based on the homogeneity of precipitation distribution characteristics. The homogeneous regions are identified as heavy-, moderate-, and light-precipitating areas by K-means clustering of Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (GPM) version 6 final run product (IMERG) precipitation frequency and amount distributions. With the global domain partitioned into 62 regions, including 46 land and 16 ocean regions, we apply 10 established precipitation distribution metrics. The collection includes metrics focused on the maximum peak, lower 10th percentile, and upper 90th percentile in precipitation amount and frequency distributions; the similarity between observed and modeled frequency distributions; an unevenness measure based on cumulative amount; average total intensity on all days with precipitation; and number of precipitating days each year. We apply our framework to 25 CMIP5 and 41 CMIP6 models, as well as six observation-based products of daily precipitation. Our results indicate that many CMIP5 and 6 models substantially overestimate the observed light-precipitation amount and frequency, as well as the number of precipitating days, especially over midlatitude regions outside of some land regions in the Americas and Eurasia. Improvement from CMIP5 to 6 is shown in some regions, especially in midlatitude regions, but it is not evident globally, and over the tropics most metrics point toward degradation.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

The pantropical response of soil moisture to El Niño

Abstract. The 2015–2016 El Niño event ranks as one of the most severe on record in terms of the magnitude and extent of sea surface temperature (SST) anomalies generated in the tropical Pacific Ocean. Corresponding global impacts on the climate were expected to rival, or even surpass, those of the 1997–1998 severe El Niño event, which had SST anomalies that were similar in size. However, the 2015–2016 event failed to meet expectations for hydrologic change in many areas, including those expected to receive well above normal precipitation. To better understand how climate anomalies during an El Niño event impact soil moisture, we investigate changes in soil moisture in the humid tropics (between ±25∘) during the three most recent super El Niño events of 1982–1983, 1997–1998 and 2015–2016, using data from the Global Land Data Assimilation System (GLDAS). First, we use in situ soil moisture observations obtained from 16 sites across five continents to validate and bias-correct estimates from GLDAS (r2=0.54). Next, we apply a k-means cluster analysis to the soil moisture estimates during the El Niño mature phase, resulting in four groups of clustered data. The strongest and most consistent decreases in soil moisture occur in the Amazon basin and maritime southeastern Asia, while the most consistent increases occur over eastern Africa. In addition, we compare changes in soil moisture to both precipitation and evapotranspiration, which showed a lack of agreement in the direction of change between these variables and soil moisture most prominently in the southern Amazon basin, the Sahel and mainland southeastern Asia. Our results can be used to improve estimates of spatiotemporal differences in El Niño impacts on soil moisture in tropical hydrology and ecosystem models at multiple scales.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Watershed zonation through hillslope clustering for tractably quantifying above- and below-ground watershed heterogeneity and functions

Abstract. In this study, we develop a watershed zonation approach for characterizing watershed organization and functions in a tractable manner by integrating multiple spatial data layers. We hypothesize that (1) a hillslope is an appropriate unit for capturing the watershed-scale heterogeneity of key bedrock-through-canopy properties and for quantifying the co-variability of these properties representing coupled ecohydrological and biogeochemical interactions, (2) remote sensing data layers and clustering methods can be used to identify watershed hillslope zones having the unique distributions of these properties relative to neighboring parcels, and (3) property suites associated with the identified zones can be used to understand zone-based functions, such as response to early snowmelt or drought and solute exports to the river. We demonstrate this concept using unsupervised clustering methods that synthesize airborne remote sensing data (lidar, hyperspectral, and electromagnetic surveys) along with satellite and streamflow data collected in the East River Watershed, Crested Butte, Colorado, USA. Results show that (1) we can define the scale of hillslopes at which the hillslope-averaged metrics can capture the majority of the overall variability in key properties (such as elevation, net potential annual radiation, and peak snow-water equivalent – SWE), (2) elevation and aspect are independent controls on plant and snow signatures, (3) near-surface bedrock electrical resistivity (top 20 m) and geological structures are significantly correlated with surface topography and plan species distribution, and (4) K-means, hierarchical clustering, and Gaussian mixture clustering methods generate similar zonation patterns across the watershed. Using independently collected data, we show that the identified zones provide information about zone-based watershed functions, including foresummer drought sensitivity and river nitrogen exports. The approach is expected to be applicable to other sites and generally useful for guiding the selection of hillslope-experiment locations and informing model parameterization.

58 GEOSCIENCES↗

DOE OSTI2021

Unsupervised Power System Event Detection and Classification Using Unlabeled PMU Data

This paper proposes a novel data-driven power system event detection and classification method based on 5TB of actual PMU measurements collected from the US western interconnect. Firstly, a set of comprehensive power quality rules are proposed to pre-filter the raw data and extract the regions of interest (ROI). Six distinct event categories are defined and corresponding patterns are chosen as references. Meanwhile, detailed characteristics of patterns are summarized to enhance our understanding of the actual events. Then, the time-independent feature vectors are generated by extracting the statistical, temporal, and spectral features from the raw time-series data. Furthermore, an ensemble model is proposed to cluster the events by combining multiple K-means clustering models using a voting strategy. Besides, both system-level and PMU-level clustering models are developed. The accuracy and robustness of the event detection method are further improved through interactive evaluation of the two-level clustering results. This paper summarizes the actual characteristics of each event category and provides a reliable basis for accurate label generation. The experiments demonstrate the effectiveness of the proposed event detection and classification method.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

Unsupervised Power System Event Detection and Classification Using Unlabeled PMU Data

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

Exploring Geothermal Potential of Great Basin Sub-Regions: Preprint

The INnovative Geothermal Exploration through Novel Investigations Of Undiscovered Systems (INGENIOUS) project aims to discover new, economically viable hidden geothermal systems in the Great Basin region by building on previous work in play fairway analysis and machine learning. A key objective of this project is to develop an exploration workflow to reduce geothermal exploration risks for hidden geothermal systems. A single preliminary play fairway workflow was developed from the assessment of the regional INGENIOUS geological, geophysical, and geochemical datasets. This workflow provided new preliminary predictive geothermal fairway maps for the INGENIOUS study area, which encompasses most of Nevada, western Utah, southern Idaho, southeastern Oregon, and easternmost California. However, a recent study (incorporating machine learning techniques) of a portion of Nevada identified four geologic domains and determined that the relative importance of individual datasets or features as indicators of geothermal potential may differ across these domains. The INGENIOUS study area includes a much larger and more geologically diverse region; therefore, additional geologic domains or sub-regions are expected. To assess the sub-regions in the INGENIOUS study area, principal component analysis and k-means clustering were applied. Preliminary results indicate that the INGENIOUS regional data cluster into groups that relate to different geologic domains in the Great Basin region. These include domains such as the Walker Lane, extensional western Great Basin region, broad lower strain region in the eastern Great Basin of western Utah and eastern Nevada, Quaternary volcanic fields, and the area adjacent to the Snake River Plain. These clusters are assessed to determine the key geologic drivers of the identified clusters. Understanding this variability can provide key insights for the exploration and characterization of hidden geothermal systems in the Great Basin region and could indicate the need to develop multiple geothermal conceptual models and play fairway workflows for the INGENIOUS study area.

GEOTHERMAL ENERGY↗

DOE OSTI2025

Electron-Proton Scattering Event Generation using Structured Tokenization

Recent work such as Omnijet-$\alpha$ has demonstrated that effective tokenization combined with transformer-based architectures can produce effective foundation models for jet physics. While tokenization may help models capture generalizable event characteristics, it also introduces discretization errors that may compromise the precision required for downstream physics analyses. As the number and complexity of the particle features grow, these errors are likely to grow proportionally. In this study, we investigate new tokenization strategies to improve the application of generative transformer models to \textsc{Pythia8} simulations of electron-proton scattering at the Electron-Ion Collider. Specifically, we propose a feature-based structured tokenization approach that utilizes multiple tokens per particle, improving expressivity, while reducing the total number of unique tokens needed. We evaluate this method against grid-based binning, K-means clustering, and vector-quantized variational auto-encoders on the event simulations. Our results show that feature-based structured tokenization reduces discretization error, leading to more accurate generative modeling of particle-level events.

Goldenberg, Steven [Thomas Jefferson National Acce↗

DOE OSTI2025

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Atom Probe Tomography (APT) is a powerful technique for visualizing the atomic-scale distribution of solutes in materials, but quantitative cluster analysis of APT datasets remains a challenge due to the need for subjective parameter selection in clustering algorithms. While distance-based and density-based methods such as HDBSCAN are widely used, their performance is highly sensitive to user-defined parameters, which undermines reproducibility and accuracy. This study proposes an image-based, deep learning-aided workflow for automating parameter selection and cluster detection in APT data analysis. By projecting 3D APT point clouds onto 2D planes, we leverage pretrained convolutional neural networks (ConvNeXt-Tiny and ResNet-50) through transfer learning to predict the number of clusters present in synthetic datasets. The output is used to guide K-means clustering and estimate HDBSCAN parameters, specifically minimum cluster size and minimum sample points. This approach reduces reliance on manual parameter tuning, improving consistency and scalability. The methodology demonstrates the feasibility of using image-based deep learning for interpreting complex spatial patterns in APT data, enabling faster and more objective analysis. The complete workflow and code are made publicly available to support reproducibility and future research.

Density-based clustering↗