Marina Vicens-Miquel

Ms. Marina Vicens-Miquel

Computer Science Department, Texas A&M University – Corpus Christi, Corpus Christi, Texas, USA
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 July 2018
Verified
Conference Paper
Closed access
MRMaryam Rahnemoonfar
Maryam Rahnemoonfar
RMRobin Murphy
Robin Murphy
MVMarina Vicens-Miquel
Marina Vicens-Miquel
DDDugan Dobbs
Dugan Dobbs
AAAshton Adams
Ashton Adams
The emergence of small unmanned aerial vehicles (UAV) along with inexpensive sensors presents the opportunity to collect thousands of images after each natural disaster with high flexibility and easy maneuverability for rapid response and recovery. Despite the ease of data collection, data analysis of the big datasets remains a significant barrier for scientists and analysts. Here we propose an integration of densely connected CNN and RNN networks, which is able to accurately segment out semantically meaningful object boundaries with end-to-end learning. The proposed network is applied on UAV aerial images of flooded areas in Houston, TX. We achieved 96% accuracy in detecting flooded areas on a large UAV dataset.

26 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MVMarina Vicens-Miquel
Marina Vicens-Miquel
FMF. Antonio Medrano
F. Antonio Medrano
PTPhilippe Tissot
Philippe Tissot
HKHamid Kamangir
Hamid Kamangir
Michael StarekMichael Starek
Michael Starek
KCKatherine Faith Adelle Colburn
Katherine Faith Adelle Colburn
Automatically detecting the wet/dry shoreline from remote sensing imagery has many benefits for beach management in coastal areas by enabling managers to take measures to protect wildlife during high water events. This paper proposes the use of a modified HED (Holistically-Nested Edge Detection) architecture to create a model for automatic feature identification of the wet/dry shoreline and to compute its elevation from the associated DSM (Digital Surface Model). The model is generalizable to several beaches in Texas and Florida. The data from the multiple beaches was collected using UAS (Uncrewed Aircraft Systems). UAS allow for the collection of high-resolution imagery and the creation of the DSMs that are essential for computing the elevations of the wet/dry shorelines. Another advantage of using UAS is the flexibility to choose locations and metocean conditions, allowing to collect a varied dataset necessary to calibrate a general model. To evaluate the performance and the generalization of the AI model, we trained the model on data from eight flights over four locations, tested it on the data from a ninth flight, and repeated it for all possible combinations. The AP and F1-Scores obtained show the success of the model’s prediction for the majority of cases, but the limitations of a pure computer vision assessment are discussed in the context of this coastal application. The method was also assessed more directly, where the average elevations of the labeled and AI predicted wet/dry shorelines were compared. The absolute differences between the two elevations were, on average, 2.1 cm, while the absolute difference of the elevations’ standard deviations for each wet/dry shoreline was 2.2 cm. The proposed method results in a generalizable model able to delineate the wet/dry shoreline in beach imagery for multiple flights at several locations in Texas and Florida and for a range of metocean conditions.

11 October 2024 in Water
Verified
Journal Article
Open access
PDF file
MVMarina Vicens-Miquel
Marina Vicens-Miquel
PTPhilippe Tissot
Philippe Tissot
FMF. Antonio Medrano
F. Antonio Medrano
Accurate and timely water level predictions are essential for effective shoreline and coastal ecosystem management. As sea levels rise, the frequency and severity of coastal inundation events are increasing, causing significant societal and economic impacts. Predicting these events with sufficient lead time is essential for decision-makers to mitigate economic losses and protect coastal communities. While machine learning methods have been developed to predict water levels at specific sites, there remains a need for more generalized models that perform well across diverse locations. This study presents a robust deep learning model for predicting water levels at multiple tide gauge locations along the Gulf of Mexico, including the open coast, embayments, and ship channels, all near major ports. The selected architecture, Seq2Seq, achieves significant improvements over the existing literature. It meets the National Oceanic and Atmospheric Administration’s (NOAA) operational criterion, with the percentage of predictions within 15 cm for lead times up to 108 h at the tide gauges of Port Isabel (92.2%) and Rockport (90.4%). These results represent a significant advancement over current models typically failing to meet NOAA’s standard beyond 48 h. This highlights the potential of deep learning models to improve water level predictions, offering crucial support for coastal management and flood mitigation.

22 August 2024 in Climate
Verified
Journal Article
Open access
PDF file
CRCristina Radin
Cristina Radin
VNVeronica Nieves
Veronica Nieves
MVMarina Vicens-Miquel
Marina Vicens-Miquel
JAJose Luis Alvarez-Morales
Jose Luis Alvarez-Morales
Climate change and rising sea levels pose significant threats to coastal regions, necessitating accurate and timely forecasts. Current methods face limitations due to their inability to fully capture nonlinear complexities, high computational costs, gaps in historical data, and bridging the gap between short-term and long-term forecasting intervals. Our study addresses these challenges by combining advanced machine learning techniques to provide region-specific sea level predictions in the Mediterranean Sea. By integrating high-resolution sea surface temperature data spanning 40 years, we employed a tailored k-means clustering technique to identify regions of high variance. Using these clusters, we developed RNN-GRU models that integrate historical tide gauge data and sea surface height data, offering regional sea level predictions on timescales ranging from one month to three years. Our approach achieved the highest predictive accuracy, with correlation values ranging from 0.65 to 0.84 in regions with comprehensive datasets, demonstrating the model’s robustness. In areas with fewer tide gauge stations or shorter time series, our models still performed moderately well, with correlations between 0.51 and 0.70. However, prediction accuracy decreases in regions with complex geomorphology. Yet, all regional models effectively captured sea level variability and trends. This highlights the model’s versatility and capacity to adapt to different regional characteristics, making it invaluable for regional planning and adaptation strategies. Our methodology offers a powerful tool for identifying regions with similar variability and providing sub-regional scale predictions up to three years in advance, ensuring more reliable and actionable sea level forecasts for Mediterranean coastal communities.

17 July 2022
Verified
Conference Paper
Closed access
MVMarina Vicens-Miquel
Marina Vicens-Miquel
FMF. Antonio Medrano
F. Antonio Medrano
PTPhilippe Tissot
Philippe Tissot
HKHamid Kamangir
Hamid Kamangir
MSMichael Starek
Michael Starek
Automatically detection the wet/dry shoreline would facilitates several applications in geological, and societal tasks such as biodiversity or beach management in coastal areas. High resolution remote imagery from UAVs simplifies detecting tiny wet/dry lines. Recently, deep learning models have shown much success compared to conventional image processing techniques for line/edge detection in terms of accuracy and automation. In this paper, an end-to-end deep learning model originated from Holistically-Nested Edge Detection (HED) model has been proposed to automatically detect the wet/dry shoreline in Fish Pass area, Texas, USA. The results shown 81% ODS (Optimal Dataset Scale), 100% OIS (per-Image best threshold), and 78.1% AP (Average Precision) score.

1 October 2026 in Artificial Intelligence for the Earth Systems
Verified
Journal Article
Closed access
MVMarina Vicens-Miquel
Marina Vicens-Miquel
AMAmy McGovern
Amy McGovern
AHAaron J. Hill
Aaron J. Hill
EFEfi Foufoula-Georgiou
Efi Foufoula-Georgiou
CGClement Guilloteau
Clement Guilloteau
SSSamuel S. P. Shen
Samuel S. P. Shen
Accurate precipitation forecasting is essential for hydrometeorological risk management, especially for anticipating high-intensity rainfall that can lead to flash flooding and infrastructure damage. This study introduces a diffusion-based deep learning (DL) framework that systematically compares three residual prediction strategies differing only in their input sources: 1) a fully data-driven model using only past observations from the Multi-Radar Multi-Sensor (MRMS) system, 2) a corrective model using only forecasts from the High-Resolution Rapid Refresh (HRRR) numerical weather prediction system, and 3) a hybrid model integrating both MRMS and selected HRRR forecast variables. By evaluating these approaches under a unified setup, we provide a clearer understanding of how each data source contributes to predictive skill over the contiguous United States (CONUS). Forecasts are produced at 1-km spatial resolution, beginning with direct 1-h predictions and extending to 12 h using autoregressive rollouts. Performance is evaluated using both CONUS-wide and region-specific metrics that assess overall performance and skill at high-intensity rainfall thresholds. Across all lead times, our DL framework consistently outperforms the HRRR baseline in pixelwise and spatiostatistical metrics. The hybrid model performs best at the shortest lead time, while the HRRR-corrective model outperforms others at longer lead times, maintaining high skill through 12 h. To assess reliability, we incorporate physically informed uncertainty quantification tailored to the residual learning setup. These gains, particularly at longer lead times, are critical for emergency preparedness, where modest increases in forecast horizon can improve decision-making. This work advances DL-based precipitation forecasting by enhancing predictive skill, reliability, and applicability across regions. Significance Statement: Forecasting high-resolution precipitation over large areas like the contiguous United States (CONUS) is essential yet challenging due to complex spatial and temporal variability. We introduce a deep learning–based framework that produces 1-km hourly forecasts up to 12 h in advance, improving upon the High-Resolution Rapid Refresh (HRRR) numerical weather prediction model. Our work evaluates three strategies within a unified and operationally motivated setup. The proposed framework outperforms the HRRR in predictive skill at both low and high rainfall intensities, sustaining improved performance through 12-h lead times. By incorporating interpretable uncertainty quantification, we enhance forecast transparency and trust. This approach enables more reliable, actionable predictions for emergency response, agriculture, and infrastructure planning across diverse U.S. regions.