Jorge Alexander Celades-Martínez

Mr. Jorge Alexander Celades-Martínez

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 August 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
JCJorge Alexander Celades-Martínez
Jorge Alexander Celades-Martínez
JRJorge Rojas
Jorge Rojas
MDMelissa Diago-Mosquera
Melissa Diago-Mosquera
AFAlvaro Peña Fritz
Alvaro Peña Fritz
JGJose Garcia
Jose Garcia
Accurate path-loss characterization in the upper mid-band is critical for 5G/6G outdoor planning, yet classical deterministic expressions lose fidelity at 18 GHz, and purely data-driven regressors offer limited physical insight. We present a physics-guided residual learner that couples a calibrated two-ray model with an XGBoost regressor trained on the deterministic residuals. To enlarge the feature space without promoting overfitting, synthetic samples obtained by perturbing antenna height and ground permittivity within realistic bounds are introduced with a weight of w=0.3. The methodology is validated with narrowband measurements collected along two straight 25 m corridors. Under cross-corridor transfer, the hybrid predictor attains 0.59–0.62 dB RMSE and R2≥0.996, reducing the error of a pure-ML baseline by half and surpassing deterministic formulas by a factor of four. Small-scale analysis yields decorrelation lengths of 0.23 m and 0.41 m; a cross-correlation peak of unity at Δ=0.10 m confirms the physical coherence of both corridors. We achieve <1 dB error using a small set of field measurements plus simple synthetic data. The method keeps a clear mathematical core and can be extended to other priors, NLOS cases, and semi-open hotspots.

21 January 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JCJorge Alexander Celades-Martínez
Jorge Alexander Celades-Martínez
MDMelissa E. Diago-Mosquera
Melissa E. Diago-Mosquera
APAlvaro Peña
Alvaro Peña
JGJosé García
José García
Reliable wireless connectivity in precision agriculture requires accurate propagation models that remain robust across varying orchard corridor geometries within a given vegetation canopy type. This study characterizes radio propagation at 18 GHz (FR3 band) through an extensive measurement campaign (N = 17,269 samples) in a custard apple orchard, systematically varying corridor width \(W \in [1.3,\,3.8]\) m and transmitter height \(h_{tx} \in [1.0,\,2.03]\) m across nine geometric configurations. The standard Close-In (CI) model captures the distance-dependent path loss (global fit \(n = 2.51\)) but leaves substantial geometry-dependent variability unexplained (RMSE = 3.91 dB). When the CI model is fitted per configuration, the parameters vary markedly (\(n \in [1.93,\,2.68]\) and \(\sigma \in [2.25,\,5.88]\) dB), indicating that a single averaged exponent should not be interpreted as geometry-invariant. To address this limitation, we propose a Hybrid Linear+XGBoost framework that combines physically interpretable geometric corrections with nonlinear residual learning. Under leave-one-scenario-out cross-validation, the hybrid model achieves RMSE = 2.97 dB, a 24.0% improvement over the CI baseline. Crucially, while pure ensemble methods (Random Forest, Gradient Boosting, XGBoost) exhibit performance degradation up to 1.05 dB when extrapolating to unseen geometric configurations, the hybrid architecture demonstrates a 0.35 dB improvement, achieving better accuracy on novel corridor configurations than on interpolated data. Corridor width emerged as the dominant factor influencing shadow fading (SF) within the studied custard apple canopy. These findings establish that geometric parameters must be explicitly incorporated into channel models and that hybrid physics-ML architectures offer robust methodological generalization across corridor geometries, whereas the fitted numerical coefficients are expected to depend on vegetation descriptors such as leaf area index, leaf orientation, and moisture content.

1 October 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JCJorge Alexander Celades-Martínez
Jorge Alexander Celades-Martínez
JCJose Manuel Gornall Cacciuttolo
Jose Manuel Gornall Cacciuttolo
JHJuan Herrera
Juan Herrera
AFAlvaro Pena Fritz
Alvaro Pena Fritz
MGMiguel Gutiérrez Gaitán
Miguel Gutiérrez Gaitán
JGJose Garcia
Jose Garcia

20 October 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
FRFelipe Rifo
Felipe Rifo
ECErick S. Chávez-Caipe
Erick S. Chávez-Caipe
JCJorge Alexander Celades-Martínez
Jorge Alexander Celades-Martínez
JGJose Garcia
Jose Garcia
MDMelissa Diago-Mosquera
Melissa Diago-Mosquera
Accurate propagation modeling is essential for network planning and performance evaluation. This paper presents a measurement-based analysis of large-scale path loss (PL) and shadow fading (SF) at 18 GHz in a line-of-sight (LoS) street-canyon scenario, using three receiver heights. Several PL models are evaluated, and a height-dependent close-in model (CI-H) is identified as a suitable baseline, achieving a global root-mean-square error (RMSE) of 2.48 dB while preserving physical interpretability. Based on CI-H, SF is extracted and statistically characterized, exhibiting near-zero mean and a global standard deviation of 2.47 dB, with increasing variability at larger distances. Using the spatial structure of SF, spatial interpolation and machine-learning (ML) models are tested under both dense-route interpolation and spatially blocked validation. Under random grouped interpolation, Ordinary Kriging (OK) and Gaussian Process Regression (GPR) reduce the PL RMSE to 1.35 dB and 1.21 dB, respectively. When continuous 5–20 m route segments are excluded, GPR yields 2.21–2.38 dB, improving upon the corresponding 2.51–2.53 dB CI-H values by 0.15–0.32 dB. Under nested spatial cross-validation, GPR yields 2.32 dB, 0.21 dB below the 2.53 dB CI-H baseline. Thus, the large gains obtained with nearby measurements decrease substantially as spatial separation increases, although GPR retains a modest and consistent advantage on unseen route segments.