Search Results (255)

Federated, semi-supervised novelty detection is well suited for intrusion detection on resource-constrained Internet of Things (IoT) nodes: each device learns a model of benign traffic, shares only summary statistics, and does not transmit raw traffic samples. A previously published cross-layer federated detector, Baseline K-Means, showed that periodically merging worker statistics through a coordinator raises the detection rate, but it also exhibited a systematic side effect: after every merge, the precision decays, and the false-positive rate (FPR) climbs because the coordinator recomputes its threshold from streaming distances filtered by the closest observed anomaly, so tightens after every merge, flagging progressively more benign traffic; the threshold was also hand-tuned. We present AF-BKM, an Adaptive Federated Baseline K-Means that repairs the federated mechanism with two label-free, statistics-only enhancements, denoted as E1 and E2: (i) an adaptive decision threshold read from the benign Mahalanobis-distance distribution, requiring no manual percentile search and no attack labels (E1), and (ii) a robust, benignly anchored aggregation that blends worker means under quality weighting and outlier-worker filtering and recalibrates the threshold on a trusted benign anchor to a stable, anchor-referenced false-positive level, which a target-FPR rule can make operator-selectable instead of tightening it toward the nearest anomaly (E2). With MinMax scaling fit only on benign baseline data and non-IID federated streams on NSL-KDD, UNSW-NB15 and the N-BaIoT corpus of real traffic from commercial IoT devices, AF-BKM removes the merge-induced precision decay (the first-to-last-epoch precision change improves from $-0.134$ to $-0.002$ on NSL-KDD, from $-0.121$ to $-0.014$ on UNSW-NB15, and from $-0.170$ to $-0.009$ on N-BaIoT) and reduces the mean FPR by 30–$64\%$, depending on the dataset; all central improvements are significant across 10 seeds (Wilcoxon $p=0.002$, large effect sizes). AF-BKM preserves recall on NSL-KDD and N-BaIoT and, on the harder UNSW-NB15, exposes an explicit precision–recall trade-off through a benign target-FPR knob. In fp32, the deployed model serializes to $5.5$–52 KB, a packet is classified in 11–27 µs on a desktop CPU, and each merge round uploads a $d+3$-value summary (160–472 B) $94.6$–$98.3\%$ smaller than the same summary extended with the covariance upper triangle. A robustness study covering selected faulty-worker updates, contamination of the commissioning anchor, and detector-level white-box evasion reports the measured degradation patterns: fabricated threshold candidates have no direct path to the threshold, although a fabricated mean still reaches it indirectly through the blended centroid, and the anchor-referenced false-positive level remains stable under percent-level anchor contamination, while recall sensitivity is dataset-dependent and the evasion budget tracks the benign–attack margin of each dataset. We frame the contribution with a focused taxonomy that identifies merge-induced precision decay under non-IID workers as an open gap. Code is released for reproducibility. Full article

This study investigated how detection distance affects spectral models for soluble solids content (SSC) and firmness evaluation in Korla fragrant pears and provides a reference for calibrating standardized indoor non-destructive detection equipment. Two hundred visually intact fruit samples at the early-ripening stage were collected from the Korla production area in Xinjiang. An FS-640 multispectral camera system equipped with a VS-SWR fixed-focus industrial lens (16 mm focal length, F1.8 maximum aperture, 1/2-inch sensor format) was used to acquire fruit reflectance spectra at seven vertical lens-to-fruit-surface distances of 90, 100, 110, 120, 130, 140, and 150 cm. A 625-pixel region of interest (ROI) was selected using ENVI at an undamaged equatorial or near-equatorial position of each fruit, and the regional mean spectrum was used as the spectral feature of one fruit sample. The sample-set partitioning based on joint X–Y distances (SPXY) algorithm was used to divide the calibration and prediction sets at a 3:1 ratio after outlier removal via a residual-threshold method. Four preprocessing methods, namely LOESS smoothing, standardization, vector normalization, and Savitzky–Golay (SG) smoothing, were compared. Competitive adaptive reweighted sampling (CARS) was performed with 50 Monte-Carlo sampling runs, a maximum of 30 principal components, and 10-fold cross-validation, yielding 99 characteristic wavelengths. Partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and artificial neural network (ANN) models were then established using identical input variables and sample partitions. Model performance was evaluated using the coefficient of determination for calibration ($R_c^2$), coefficient of determination for prediction ($R_P^2$), root-mean-square error of calibration (RMSEC), root-mean-square error of prediction (RMSEP), relative prediction deviation (RPD), and ratio of performance to interquartile distance (RPIQ). Under the static laboratory acquisition conditions in this work, the SSC model achieved the best prediction performance at 110 cm with SG smoothing ($R_P^2$) = 0.8949, RPD = 3.0633, RPIQ = 5.8661), whereas the firmness model obtained optimal prediction performance at 140 cm with standardization ($R_P^2$) = 0.7460, RPD = 1.9425, RPIQ = 3.2867). Changes in detection distance altered illumination uniformity, effective reflected signal, photon-scattering paths, and background-noise proportion. These effects may partially explain why the chemical-absorption-dominated SSC index and the tissue-scattering-dominated firmness index responded differently to detection distance. The results provide a reference for setting spectral detection parameters for Korla fragrant pears; however, samples were obtained from only a single producing region, harvest season, and maturity stage, and no independent external validation dataset was used. Therefore, the generalization ability of the developed models needs to be further verified using cross-season and cross-orchard sample sets. Full article

LiDAR (Light Detection and Ranging) and RGB-D camera imaging have emerged as essential tools in agricultural applications, particularly for plant size and distance measurements, enabling non-destructive, cost-effective, and precise estimation. The objective of this study was to measure the plant canopy dimensions and distance between apples using commercial LiDAR, and an RGB-D camera with a speed sprayer platform was used to determine whether LiDAR provides a higher measurement accuracy under field conditions. Data were collected in an apple orchard in Muju, Republic of Korea. Commercial 3D LiDAR, a terminal box, an RGB-D camera, a microcontroller, a power supply, and individual display monitors were integrated into a customized data acquisition (DAQ) box for LiDAR point cloud (PCD), RGB, and depth imagery data collection. Commercial software was used for data acquisition, data conversion (pcap to PCD), segmentation of regions of interest (ROI), and pre-processing of data. PCD processing and measurement consisted of data frame selection, data conversion, outlier removal, downsampling, denoising, ground point removal by filtering, voxelization, and density map generation using an open access programming language script. Depth image processing included importing raw data, shaping metadata using intrinsic camera parameters, visualizing depth images, extracting depth points, and measuring the plant canopy at the pixel level. RGB image analysis involved grayscale conversion, thresholding, segmentation of ROI, contour preparation, noise removal, and binary masking for eliminating the background. Estimated results were compared to measured results. LiDAR measurements showed the closest agreement with the measured results for plant height, canopy volume, plant spacing, and row distance, outperforming both RGB and depth imaging. Under field conditions, plant spacing and row distance were estimated with accuracies of 97.5% and 94.7%, respectively, exhibiting higher measurement accuracies than RGB and depth imagery data results. Despite some discrepancies due to complex plant geometry and dynamic data collection, the results support data collection strategies critical for precision horticulture. Full article

This study evaluates groundwater quality in the Bismil Plain (Diyarbakır, Southeast Türkiye) using a total of 208 samples collected from 26 wells during eight seasonal sampling periods conducted between 2022 and 2024. In each sample, pH, electrical conductivity (EC), and the major ions Ca²⁺, Mg²⁺, Na⁺, K⁺, Cl⁻, SO₄²⁻, HCO₃⁻ and NO₃⁻ were analyzed, and a WHO-based Water Quality Index (WQI) was calculated for every observation. The study combines classical hydrochemical interpretation methods, including descriptive statistics, hierarchical correlation analysis, variance inflation factor, and Piper and Gibbs diagrams, with an explainable machine learning framework integrating SHAP-based feature selection into Random Forest, XGBoost, support vector regression, and stacking ensemble models. In addition, spatial residuals were evaluated using Moran’s I and ordinary kriging, anomalies were identified using Isolation Forest and Local Outlier Factor algorithms, and predictive uncertainty was quantified through bootstrap resampling. WQI values ranged from 79.37 to 125.48 (mean: 99.67), with all samples classified only within the “Good” (49.5%) and “Poor” (50.5%) quality categories, indicating that the aquifer is close to a critical water-quality threshold. Spatially, the highest (poorest-quality) WQI values form a coherent zone in the south-western and central parts of the plain, whereas the central-eastern wells return the lowest values; the same pattern is reproduced by all four models. XGBoost and the stacking ensemble models showed comparable predictive performance (R² = 0.911 and 0.910; RMSE = 3.29 and 3.27, respectively), while SHAP analysis identified EC as the dominant controlling factor, followed by NO₃⁻, SO₄²⁻, Ca²⁺, Mg²⁺ and Cl⁻ (mean |SHAP| = 6.86, 1.57, 1.10, 1.09, 0.85 and 0.72 WQI units, respectively). Moran’s I computed on the residual fields was −0.067 (p = 0.275) for XGBoost and −0.068 (p = 0.273) for the stacking ensemble, so ordinary kriging of these residuals produced an essentially null correction, whereas the SVR residuals remained spatially autocorrelated (I = 0.242; p = 0.001) and were meaningfully corrected by the geostatistical step. The originality of the study lies in integrating explainable machine learning, geostatistical residual analysis, anomaly detection, and bootstrap-based uncertainty assessment within a unified framework for a multi-season groundwater dataset, while also evaluating the effectiveness of spatial correction using a Moran’s I-based approach. Full article

Extreme atmospheric events are rare phenomena characterized by unusual intensity or chemical composition compared to the atmospheric background state. Many such events, in the context of global warming, pose threats to human health, thereby making their early detection and monitoring essential. The Infrared Atmospheric Sounding Interferometer (IASI), able to measure more than 30 atmospheric chemical species on a global scale, offers strong potential in this context. However, the large volume of current and upcoming satellite observations makes intelligent data screening more and more challenging. This work aims to overcome this limitation by developing a dedicated algorithm based on Principal Component Analysis (PCA) of Level 1C IASI spectra. Named IASI-PCA, it is designed for the systematic detection of fires, volcanic eruptions, dust storms, pollution plumes, and other extreme atmospheric events that remain unclassified. The detected events are defined as spectral outliers relative to the representative global variability of IASI observations under normal or unperturbed conditions. The detection of an individual spectrum is driven by its anomalous behavior in selected spectral domains, where a set of optimized indicators corresponding to more than 10 species has been defined to discriminate events according to their chemical signatures. This methodology has been implemented in a near-real-time operational system providing detection and classification products within one hour and one day, respectively. The IASI-PCA approach has been applied to multiple case studies demonstrating that it is a powerful tool for: (1) efficiently detecting and monitoring fires, whether isolated sources or extended plumes; (2) handling both clear and cloudy conditions; (3) detecting dust plumes predominantly associated with calcite; (4) identifying pollution sources; and (5) detecting volcanic events. The consistency of our results with those obtained with the EUMETSAT Principal Component Compression (PCC) is also illustrated through the processing of a representative study period. Full article

Epilepsy is a challenging brain disease that requires significant clinical findings. (1) Background: The aim of this study is to improve the success rate of epilepsy detection using a newly developed method by optimizing the high-dimensional dataset obtained from brain MRI images. Standard machine learning models fall short of achieving the desired success in high-dimensional datasets. To achieve this, we aimed to develop an optimized hybrid model by combining the local classification power of the k-Nearest Neighbor classifier and the anomaly detection success of the negative selection algorithm. (2) Methods: Cortical and subcortical brain regions were analyzed to examine volumetric differences. A dataset was created by identifying regions statistically significant for epilepsy. This dataset was then optimized using the Scatter Search Snake Optimization algorithm. The performances of six different machine learning models trained on this optimized dataset were compared. (3) Results: The standard and popular models, SVM (82.70%), kNN (78.70%), RF (69.30%), MLP (73.30%), and NSA (95.89%), demonstrated a detection success rate. In contrast, the proposed hybrid model, kNN-NSA (98.65%), demonstrated a detection success rate. (4) Conclusions: The optimized hybrid kNN-NSA approach, which considers local density in such high-dimensional datasets and tolerates outliers within the self-data, appears to outperform traditional methods. Furthermore, this study has demonstrated that volumetric differences in regions not previously reported in the literature, such as WM-hypointensities, ventral DC, and choroid plexus, may be effective in the decision-making process for diagnosing epilepsy, as they are also found to be significant. Full article

Significant radiometric discrepancies commonly exist among multisource optical satellite images due to differences in sensor characteristics, acquisition geometry, atmospheric conditions, and imaging time, which severely limit their application accuracy in land-cover classification, change detection, and geophysical parameter retrieval. Therefore, relative radiometric normalization (RRN) has become an essential preprocessing step for the integrated application of multisource optical satellite imagery. However, existing RRN methods often suffer from low automation in radiometric reference sample selection and are highly sensitive to anomalous samples, resulting in limited normalization accuracy and robustness. To address these issues, this study proposes an automated cross-sensor RRN framework based on automatic construction and intelligent refinement of radiometric reference sample set (RRSS). An unsupervised deep-learning-based change detection approach is employed to automatically identify radiometrically stable samples and construct an initial RRSS. Subsequently, a dual-stage sample refinement strategy integrating statistical outlier detection and topographic prior knowledge is developed to progressively remove anomalous samples and improve sample reliability. Linear regression is then performed using the refined samples to establish the radiometric normalization model. Experiments conducted on multisource optical satellite imagery acquired under different terrain conditions demonstrate that the proposed framework consistently outperforms five mainstream RRN methods, achieving lower Root Mean Square Error (RMSE) and higher Spectral Angle Cosine (SAC) and Structural Similarity Index Measure (SSIM) values. The results indicate that automatic construction and intelligent refinement of RRSS effectively improve inter-image radiometric consistency, particularly in topographically complex regions. Root Mean Square Error (RMSE), Spectral Angle Cosine (SAC), and Structural Similarity Index Measure (SSIM). Full article

This study proposes a Variational AutoEncoder (VAE)-based Quality Controlled (QC) generative augmentation framework for North Atlantic right whale (NARW) upcall detection. Existing generative augmentation methods can generate synthetic samples; however, they do not provide a sample-level criterion for determining whether each generated sample is a positive sample that contributes to improved detector performance or a synthetic outlier that should be removed. This study learns manually extracted upcall frequency contours using a 1D-VAE and evaluates generated contour candidates in a 10-dimensional acoustic morphology feature space. The QC score is computed with respect to the reference distribution of manually extracted real upcall contours, and stochastic acceptance probabilities for borderline samples around the hard threshold are calibrated using same-call manual re-extraction variability. QC-passed contours are converted into detector training spectrograms using smooth amplitude modulation and Gaussian noise injection based on SNR statistics. Using 30,000 acoustic segments from the Kaggle NARW dataset, Original, Denoising Diffusion Probabilistic Models (DDPM), Contour-VAE without QC, and VAE-QC conditions were compared under the same detector and augmentation budget. VAE-QC with α = 0.97 achieved the highest mean AUC of 0.901, outperforming Original training (0.802), DDPM (0.845), and Contour-VAE without QC (0.810). Feature distribution and QC-score analyses further showed that VAE-QC suppresses morphology outlier tails observed in unfiltered generation. These results indicate that the key factor in generative augmentation is the QC process that defines feature boundaries useful for detector learning and selects synthetic positive samples accordingly. Full article

The global adoption of electric vehicles (EVs) highlights the critical role of lithium-ion battery packs in ensuring safety and performance, while voltage outliers as precursors to thermal runaway pose significant risks. Existing fault detection methods suffer from limited adaptability, poor uncertainty quantification, and inadequate handling of long-term temporal dynamics. To address these gaps, this study proposes a Probabilistic Hierarchical Adaptive Framework (PHAF) for early, uncertainty-aware detection of impending voltage outliers. PHAF integrates three core innovations: (1) the Weighted Outlier Depth (WOD) metric, which fuses Boltzmann-weighted voltage deviations and gradient-based thermal penalties to sensitively capture electro-thermal anomalies, especially under thermal stress (>45 °C); (2) the Learnable Spectral Convolution Network (LSCN), a novel architecture that combines adaptive spectral modulation and dual-path convolutions to model long-range frequency patterns and local temporal dependencies in voltage sequences; and (3) a hierarchical multi-model system that dynamically selects specialized models (LSCN, GRU, and LSTM) across four prediction horizons (160–40 min), leveraging quantile regression for uncertainty quantification and an early-termination mechanism to optimize computational efficiency. Evaluated on real-world data from 60 AITO EVs, PHAF achieves 95.4% classification accuracy for Level 1 (early-stage) faults at the 160 min horizon, >90% accuracy for critical Level 3 faults within 80 min, and a maximum AUC of 0.943 for long-term anomaly detection. This framework enables a transition from passive remediation to active prevention of battery thermal runaway, providing reliable, confidence-aware monitoring for safety-critical EV applications. Full article

As calibration errors have a direct impact on epipolar consistency, rectification accuracy, and metric 3D reconstruction performance, stereo camera calibration is a fundamental requirement for high-accuracy 3D modeling and reliable digital twin data acquisition. Because current calibration workflows (based on pairwise calibration methods) lack systematic data-quality checks mechanisms, there is a clear need for more robust data selection strategies. The novelty of the approach consists in the development of a new outlier-aware stereo calibration algorithm (OutAw) that introduces a unified multi-stage approach that integrates hard geometric selection, candidate subset generation, multi-criterion ranking, bootstrap stability analysis, and triangulation assessment into a comprehensive and systematic calibration framework. Unlike conventional approaches, OutAw (through its mechanism of detecting and rejecting inconsistent pairs) redefines the calibration strategy from arbitrary to criterion-based data selection. Also, the proposed algorithm is compared with BSC (a baseline OpenCV all-pairs calibration algorithm) and InterFil (an intermediate filtered variant) using 49 stereo pairs (at 1280 × 720 resolution) captured using a planar checkerboard. OutAw algorithm achieved (using only nine image pairs) superior results (epipolar error 0.5119 px, stereo RMS 0.7666 px) to the BSC ones (epipolar error 1.3687 px, stereo RMS 1.9385 px), representing statistically significant improvements (60.5%, respectively 62.3%). OutAw geometric consistency was validated by triangulation-based metrics (square-length standard deviation 0.1140 mm and square absolute error 0.1097 mm). Contamination analysis revealed that as the outlier rate increases, the calibration process degrades progressively. Also, the results obtained highlight that geometric quality-driven image selection is critical for achieving a reliable stereo calibration for DT applications. Full article

This work presents a robust preprocessing pipeline for photovoltaic (PV) time series forecasting aimed at improving the quality, consistency, and physical coherence of the input data used in predictive models. The proposed methodology integrates temporal lag correction, Fourier-based temporal enrichment, supervised and unsupervised outlier detection, and feature selection to adapt the preprocessing workflow to different operational conditions and data characteristics. The pipeline is validated using real-world data from two PV plants with different temporal resolutions and operating regimes. The results show that the proposed approach improves dataset coherence and strengthens the relationship between meteorological predictors and PV output, providing a reliable basis for subsequent forecasting tasks. In addition, an online forecasting validation over January 2025 shows that a Random Forest model using preprocessed inputs substantially reduces prediction errors compared with the same model using raw inputs, with MAE reductions of 54.2% for the Test Plant and 25.6% for the Production Plant, and corresponding RMSE reductions of 32.1% and 12.6%. Full article

Interest in light detection and ranging (LiDAR) for the precise monitoring of vegetative growth of grain crops has increased. The study was conducted to estimate wheat size and plant distance using LiDAR and the convex hull method (CHM) compared to the voxel grid method (VGM). A commercial LiDAR system was used for data collection in the middle and late growth stages using static and dynamic scanning. A small number (ten) of data frames, consisting of a region of interest (ROI) of 1 m × 0.9 m for each frame, were selected as data samples. The data processing workflow consisted of data conversion, targeted data frame selection, visualization, region of interest (ROI) segmentation, outlier and untargeted point removal, downsampling, denoising, voxelization, preparation of the convex hull, and 3D PCD density map. To estimate the plant size and distance of wheat, the results obtained using CHM and VGM were compared with measured data results, and both methods were applied for the middle and late growth stages of wheat. The relative accuracy of LiDAR-estimated plant height, canopy volume, plant spacing, and row distances with respect to the measured results were 94%, 87%, 94%, and 87%, respectively, using CHM, and 76%, 72%, 62%, and 71% by VGM for static data scanning; for dynamic scanning, the estimated relative accuracy percentages were 87%, 91%, 94%, and 93%, respectively, using CHM, and 77%, 74%, 75%, and 74%, respectively, using VGM. The same methods were applied to the late growth stage data sets. Between the two methods, CHM provided higher accuracy for static and dynamic data-scanning approaches in the middle and late growth stages because the complex geometry of plants, thin and sparse leaf area, and structure complicated voxelization. Despite several challenges in PCD collection and processing, this study supports size and distance estimation for wheat and similar grains as non-destructive methods. Full article

Wind power forecasting is essential for improving renewable energy exploitation and maintaining power system stability. However, influenced by factors such as the velocity and orientation of the wind and atmospheric pressure, wind power exhibits strong variability and uncertainty. Moreover, raw data often contains missing values, shutdown periods, and anomalies, which can degrade forecasting performance. Aiming at solving these challenges, this study develops a wind power forecasting approach integrating data cleaning with a hybrid prediction model. In the preprocessing stage, correlation analysis is employed to select meteorological variables strongly associated with power output as input features, thereby reducing redundancy and improving model effectiveness. Subsequently, missing values and shutdown records are removed, and an improved DBSCAN method is applied to detect anomalous samples. These outliers are then corrected using least squares regression, enhancing data quality while preserving continuity. In the forecasting stage, a hybrid model integrating TCN, BiLSTM, and the Plant Root Growth Optimization (PRGO) algorithm is developed. Specifically, TCN serves to capture local temporal features, while BiLSTM extracts bidirectional temporal dependencies. The PRGO serves to globally optimize model architecture parameters and key hyperparameters, improving convergence efficiency and generalization performance. Experiments on real wind farm data demonstrate that the proposed TCN-BiLSTM-PRGO model consistently outperforms all baselines (TCN, LSTM, TCN-BiLSTM, TCN-Transformer, and TCN-BiLSTM-WOA) across 12 h, 24 h, and 48 h horizons. At 12 h, it achieves a mean R² of 0.942, NMAE of 6.014%, and NRMSE of 7.539% over five runs, improving R² by 0.008–0.123 and reducing NMAE by 0.37–4.57 percentage points compared to other models. It also attains the highest R² at 24 h (0.791) and 48 h (0.833). Statistical significance (p < 0.05) and chronological split tests (R² = 0.940) further confirm their robustness and generalization. The proposed method offers a reliable solution for high-precision wind power forecasting. Full article

Bioethanol production from lignocellulosic biomass remains energy-intensive, and its energy performance can be affected by equipment degradation, utility disturbances, and operating variability. This study developed a degradation-aware mechanistic–AI framework for energy forecasting, anomaly detection, maintenance-oriented interpretation, and multi-objective optimization in bioethanol production under limited-data conditions. Reduced-order energy models were formulated for pretreatment, hydrolysis–fermentation, and ethanol purification. Equipment deterioration was represented through heat-transfer fouling, column-efficiency decline, and pump-efficiency decay. Condition-dependent modifiers were introduced to account for load-related degradation and intervention-related partial recovery. Benchmark-constrained synthetic time-series datasets were generated under baseline, accelerated-degradation, condition-dependent, stress, and data-quality perturbation scenarios. Empirical baselines and machine-learning models were compared for specific energy consumption prediction, with uncertainty reported using confidence intervals. The long short-term memory model achieved the lowest prediction errors under both baseline and stress conditions. Robustness testing showed that sensor drift, missing values, and outliers increased forecasting and anomaly-detection uncertainty. Sensitivity analysis identified degradation coefficients, seasonal disturbance, and anomaly-threshold selection as influential factors. Multi-objective optimization revealed trade-offs among specific energy consumption, ethanol purity, and equipment-health penalty. The proposed framework should be interpreted as a benchmarked methodological platform rather than a plant-validated maintenance or control system. Plant-specific deployment requires calibration with operating records, maintenance logs, cleaning records, and sensor-quality assessment. Full article

Background/Objectives: Metastatic Prostate Cancer (mPCa) is generally treated with systemic therapy. Many of these treatments, particularly androgen ablation, are not curative and cause substantial morbidity. Oligometastasis is defined as a limited number of metastatic deposits, whose disease does not seem to progress to a widespread distribution of cancer. There have been some reports of trials of localized treatment of PCa oligometastatic disease with curative intent. We herein report a case of oligometastatic prostate cancer treated primarily with surgical removal of metastases, which has no evidence of active disease twenty years post-operatively. Methods: Extensive retrospective chart review, immunohistochemical staining, growth rate calculations, and imaging studies were performed to trace the progression of this patient’s disease course. Results: A detailed investigation of biochemical markers of recurrence revealed normal-low prostate specific antigen (PSA) despite advanced disease, early rather than metachronous dissemination of metastases to distant sites, and hypoxia-conditioned phenotypic plasticity and memory in disseminated tumor cells (DTCs). Conclusions: This rare outlier case of oligometastatic prostate adenocarcinoma challenges traditional linear models of metastatic progression and clinical reliance on PSA as a marker for PCa detection and treatment in advanced cases. By investigating key questions regarding the identity, timing, and trajectory of DTCs, we propose a biologically informed narrative of this patient’s disease progression and a reconsideration of metastases directed therapy (MDT) of oligometastases as primary therapy in select patients. Full article