Guillermo Martínez-Flores

Dr. Guillermo Martínez-Flores

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 April 2021 in Journal for Nature Conservation
Verified
Journal Article
Closed access
FUFrancisco J. Urcádiz-Cázares
Francisco J. Urcádiz-Cázares
VCVíctor Hugo Cruz-Escalona
Víctor Hugo Cruz-Escalona
Mark PetersonMark Peterson
Mark Peterson
EMEmigdio Marín-Enriquez
Emigdio Marín-Enriquez
AGAdrián F. González-Acosta
Adrián F. González-Acosta
AOAlfredo Ortega-Rubio
Alfredo Ortega-Rubio

1 November 2025 in Data
Verified
Journal Article
Open access
PDF file
JEJosé Manuel Echevarría-Rubio
José Manuel Echevarría-Rubio
GMGuillermo Martínez-Flores
Guillermo Martínez-Flores
RMRubén Morales-Pérez
Rubén Morales-Pérez
Over the past decade, recurring influxes of pelagic Sargassum have posed significant environmental and economic challenges in the Caribbean Sea. Effective monitoring is crucial for understanding bloom dynamics and mitigating their impacts. This study presents a comprehensive machine learning (ML) and deep learning (DL) framework for detecting Sargassum and estimating its fractional cover using imagery from key satellite sensors: the Operational Land Imager (OLI) on Landsat-8 and the Multispectral Instrument (MSI) on Sentinel-2. A spectral library was constructed from five core spectral bands (Blue, Green, Red, Near-Infrared, and Short-Wave Infrared). It was used to train an ensemble of five diverse classifiers: Random Forest (RF), K-Nearest Neighbors (KNN), XGBoost (XGB), a Multi-Layer Perceptron (MLP), and a 1D Convolutional Neural Network (1D-CNN). All models achieved high classification performance on a held-out test set, with weighted F1-scores exceeding 0.976. The probabilistic outputs from these classifiers were then leveraged as a direct proxy for the sub-pixel fractional cover of Sargassum. Critically, an inter-algorithm agreement analysis revealed that detections on real-world imagery are typically either of very high (unanimous) or very low (contentious) confidence, highlighting the diagnostic power of the ensemble approach. The resulting framework provides a robust and quantitative pathway for generating confidence-aware estimates of Sargassum distribution. This work supports efforts to manage these harmful algal blooms by providing vital information on detection certainty, while underscoring the critical need to empirically validate fractional cover proxies against in situ or UAV measurements.


3 September 2022 in Land
Verified
Journal Article
Open access
PDF file
ZPZenia Pérez-Falls
Zenia Pérez-Falls
GMGuillermo Martínez-Flores
Guillermo Martínez-Flores
OSOlga Sarychikhina
Olga Sarychikhina
Land subsidence (LS) increases flood vulnerability in coastal areas, coastal plains, and river deltas. The coastal plain of Tabasco (TCP) has been the scene of recurring floods, which caused economic and social damage. Hydrocarbon extraction is the main economic activity in the TCP and could be one of the causes of LS in this region. This study aimed to investigate the potential of differential SAR interferometric techniques for LS detection in the TCP. For this purpose, Sentinel-1 SLC descending and ascending images from the 2018–2019 period were used. Conventional DInSAR, together with the differential interferograms stacking (DIS) approach, was applied. The causes of interferometric coherence degradation were analyzed. In addition, Sentinel-1 GRD images were used for delimitation of areas recurrently affected by floods. Based on the results of the interferometric processing, several subsiding zones were detected. The results indicate subsidence rates of up to −6 cm/yr in the urban centers of Villahermosa, Paraíso, Comalcalco, and other localities. The results indicate the possibility of an influence of LS on the flood vulnerability of the area south of Villahermosa city. They also suggest a possible relationship between hydrocarbon extraction and surface deformation.

28 October 2024 in Water
Verified
Journal Article
Open access
PDF file
NRNicole Reguera-Rouzaud
Nicole Reguera-Rouzaud
GMGuillermo Martínez-Flores
Guillermo Martínez-Flores
NDNoé Díaz-Viloria
Noé Díaz-Viloria
AMAdrian Munguia-Vega
Adrian Munguia-Vega
Understanding how ocean currents influence larval dispersal and measuring its magnitude is critical for conservation and sustainable exploitation, especially in the Tropical Eastern Pacific (TEP), where the larval transport of rocky reef fish remains untested. For this reason, a lagrangian simulation model was implemented to estimate larval transport pathways in Northwestern Mexico and TEP. Particle trajectories were simulated with data from the Hybrid Ocean Coordinate Model, focusing on three simulation scenarios: (1) using the occurrence records of Lutjanus peru and L. argentiventris as release sites; (2) considering a continuous distribution along the study area, and (3) taking the reproduction seasonality into account in both species. It was found that the continuous distribution scenario largely explained the genetic structure previously found in both species (genetic brakes between central and southern Mexico and Central America), confirming that the ocean currents play a significant role as predictors of genetic differentiation and gene flow in Northwestern Mexico and the TEP. Due to the oceanography of the area, the southern localities supply larvae from the northern localities; therefore, disturbances in any southern localities could affect the surrounding areas and have impacts that spread beyond their political boundaries.