BUSCADOR RECOLECTA

This study presents a novel and highly sensitive torsion sensor based on a multicore fiber (MCF) inside a Sagnac interferometer, which acts both as a mirror and a sensor head of a fiber ring laser. This laser sensor configuration also incorporates a distributed reflector consisting of an optical fiber segment doped with ZnGa2O4 nanocrystals, enhancing the overall performance. The sensor demonstrates high sensitivity to torsion across a range of 0° to 150°. The phase analysis in the 0°-50° range achieves a sensitivity of 0.08 rad/º. A Machine Learning Integration, with a function-fitting neural network, shows a detection limit of 0.06°., This work was supported in part by projects PID2022-137269OB, funded by MCIN/AEI/10.13039/501100011033 and FEDER “A way to make Europe”, and TED2021-130378B funded by MCIN/AEI/10.13039/501100011033 and European Union “Next generation EU”/PRTR.

This article presents a novel high-birefringence
fiber-based torsion sensor based on a microstructured optical fiber with nine holes and seven cores microstructured
holes and cores optical fiber (MHCF) embedded into a
Sagnac interferometer (SI). A segment of this fiber is inserted
into a symmetric SMF-MMF-MHCF-MMF-SMF arrangement,
which provides efficient coupling to the multiple cores of
the birefringent fiber and, consequently, multimode interference (MMI). Fast Fourier transform (FFT) spectral data
analysis is employed to enhance measurement stability and reduce dependence on optical source variations. The
sensor demonstrates a linear response to torsion angles between −50◦ and +50◦
, with a 16-mrad/◦ sensitivity. The high
sensitivity and good linearity of the sensor are enhanced through the application of machine learning (ML) techniques., This work was supported in part by CIN/AEI/10.13039/501100011033 and Fondo Europeo de Desarrollo Regional (FEDER) \u201CA way to make Europe,\u201D under Project PID2022-137269OB; and in part by MCIN/AEI/10.13039/501100011033 and European Union (EU) \u201CNext generation EU\u201D/Plan de Recuperaci\u00F3n, Transformaci\u00F3n y Resiliencia (PRTR) under Project TED2021-130378B. Open access funding provided by Universidad P\u00FAblica de Navarra.

In this work, optical fiber Bragg grating sensors were used to measure water velocity and examine how it was distributed in open channels. Several types of coatings were incorporated into the design of the sensors to examine their effects on the strain that the fibers experienced as a result of the water flow. Due to their low elastic coefficient, which reduced the hysteresis, the results indicated that the aluminum- and acrylate-coated fibers had the best performance. ANSYS-CFX V2020 R2 software was used to model the strain encountered by the fibers under various flow rates to assess the performance of the FBG sensors. The calculations and actual data exhibited good convergence, demonstrating the accuracy of the FBG sensors in determining water velocity. The study illustrated the usability of the proposal in both scenarios by contrasting its application in rivers and channels., This work was supported in part by projects PID2022-137269OB-C21, funded by MCIN/AEI/https://doi.org/10.13039/501100011033 and FEDER 'A way to make Europe', and TED2021-130378B-C22 funded by MCIN/AEI/https://doi.org/10.13039/501100011033 and European Union 'Next generation EU'/PTR

We demonstrate a new optical fiber liquid level sensor based on two sections of capillary optical fibers spliced between single-mode fibers. Last section without coating is in contact with the liquid. A measurement range of 60 mm is obtained when the structure is monitored in reflection by using a FBGs interrogator., This work was supported in part by projects PID2019-107270RB-C02 and PID2022-137269OB-C21 funded by MCIN/AEI/10.13039/501100011033 and FEDER 'A way to make Europe', and TED2021-130378B-C22 funded by MCIN/AEI/10.13039/501100011033 and European Union 'Next generation EU'/PTR.

This paper presents a novel capillary structure for liquid level measurement. The multifiber interferometric structure, which employs two capillary sections, is well-suited to the measurement of liquid levels in both short distances and with high resolution. The measurement range extends up to 60 mm with a resolution of 0.70 mm., This work was supported in part by the MCIN/AEI/10.13039/501100011033 and FEDER "A way to make Europe" under Grant PID2022-137269OB-C21 and in part by the MCIN/AEI/10.13039/501100011033 and European Union "Next generation EU"/PRTR under Grant TED2021-130378B-C22. Open access funding provided by Universidad Pública de Navarra.

Esta tesis presenta el desarrollo y análisis de distintas tecnologías fotónicas basadas en fibra óptica para la monitorización de magnitudes físicas, con énfasis en configuraciones tanto puntuales como cuasidistribuidas. El trabajo se organiza en torno a tres bloques principales que abordan, de forma progresiva, desde el diseño de fuentes láser hasta técnicas avanzadas de interrogación y monitorización estructural.
El primer bloque se centra en el estudio de láseres aleatorios de fibra óptica coherentes, fabricados a partir de reflectores pseudoaleatorios inscritos mediante láser de femtosegundo. Se desarrollan diferentes configuraciones orientadas a mejorar la estabilidad espectral, lograr operación en modo longitudinal único y extender la emisión a bandas C y L. Asimismo, se analiza su funcionalidad como sensores multiparamétricos, destacando su capacidad para la discriminación simultánea de temperatura y deformación mediante fuentes multilínea.
El segundo bloque examina sensores ópticos interferométricos construidos con fibras de núcleo hueco, en los que se propone una estrategia alternativa de interrogación basada en la transformación espectral al dominio temporal. Este enfoque permite descomponer interferogramas complejos, mejorar la resolución de medida y facilitar la identificación precisa de los mecanismos físicos subyacentes. La técnica se valida experimentalmente en la medición de deformación transversal, demostrando su viabilidad para aplicaciones de caracterización multiparamétrica.
El tercer bloque introduce una estrategia cuasidistribuida de monitorización mediante reflectometría óptica en el dominio de la frecuencia. A través de una catenaria de reflectores interferométricos y un modelo analítico detallado, se logra la detección simultánea de vibraciones espectralmente complejas y deformaciones longitudinales, con mejoras en resolución y tiempos de respuesta frente a otras tipologías de esquemas distribuidos basados en retrodispersión Rayleigh. Esta arquitectura se plantea como una solución escalable para aplicaciones de diagnóstico estructural de precisión.
En conjunto, la tesis proporciona una base técnica y metodológica para el desarrollo de sistemas fotónicos de monitorización física, abordando tanto aspectos estructurales de los dispositivos como estrategias de interrogación y procesamiento de señal. Los resultados permiten identificar nuevas vías de avance en el diseño de láseres y sensores compactos, estables y adaptables a diferentes entornos operativos., This thesis presents the development and analysis of various photonic technologies based on optical fiber for the monitoring of physical parameters, with an emphasis on both point and quasi-distributed configurations. The work is organized into three main sections that progressively address topics ranging from the design of laser sources to advanced interrogation techniques and structural monitoring.
The first section focuses on the study of coherent random fiber lasers, fabricated using pseudo-random reflectors inscribed by femtosecond laser.
Several configurations are developed with the aim of improving spectral stability, achieving single longitudinal mode operation, and extending emission to the C and L bands. Additionally, their functionality as multiparametric sensors is analyzed, highlighting their ability to simultaneously discriminate between temperature and strain through multi-line sources.
The second section examines interferometric optical sensors constructed with hollow-core fibers, proposing an alternative interrogation strategy based on spectral-to-temporal domain transformation. This approach enables the decomposition of complex interferograms, enhances measurement resolution, and facilitates the precise identification of underlying physical mechanisms. The technique is experimentally validated in the measurement of transverse strain, demonstrating its feasibility for multiparametric characterization applications.
The third section introduces a quasi-distributed monitoring strategy using frequency-domain optical reflectometry. Through a catenary of interferometric reflectors and a detailed analytical model, simultaneous detection of spectrally complex vibrations and longitudinal strains is enabled, with improved resolution and response times compared to other distributed schemes based on Rayleigh backscattering. This architecture is proposed as a scalable solution for precision structural diagnostics.
Overall, the thesis provides a technical and methodological foundation for the development of photonic systems for physical monitoring, addressing both structural aspects of the devices and strategies for interrogation and signal processing. The results make it possible to identify new avenues for advancement in the design of compact, stable, and adaptable lasers and sensors for various operational environments., Financiado por Universidad Pública de Navarra mediante los «Contratos predoctorales UPNA 2020/2021»(Resolución 989/2020), Ministerio de Ciencia e Innovación, Agencia Estatal de Investigación (AEI) mediante el proyecto «Dispositivos y Sistemas Fotónicos Sensores para estructuras inteligentes y evaluación no destructiva II»(PID2019-107270RB-C22), Ministerio de Ciencia e Innovación, Agencia Estatal de Investigación (AEI), Unión Europea NextGenerationEU/PRTR mediante el proyecto «Sistema integrado para la monitorización de tráfico y mantenimiento de carreteras usando sensores de fibra óptica I»(PDC2021-121172-C21) y Fondo Europeo de Desarrollo Regional, Agencia Estatal de Investigación (AEI) mediante el proyecto «Sensores fotónicos para ciudades inteligentes y sostenibles I»(PID2022-137269OB-C21)., Programa de Doctorado en Tecnologías de las Comunicaciones, Bioingeniería y de las Energías Renovables (RD 99/2011), Bioingeniaritzako eta Komunikazioen eta Energia Berriztagarrien Teknologietako Doktoretza Programa Ofiziala (ED 99/2011)

In this article, the design and implementation of a bidirectional curvature sensor based on a fiber-optic interferometer are presented. The sensor structure was fabricated by fusing a capillary fiber fragment between single-mode fibers (SMFs), with the addition of a long end capillary to promote a long interferometric section, forming a Fabry-Perot (FP) cavity. Detailed analysis of the curvature data was carried out using machine learning techniques, allowing accurate classification of curvature in both directions of rotation. The experimental results showed excellent agreement (R2: 0.9998) with the predicted values. The sensor exhibits a maximum error of 1.9485°. This approach presents significant potential for applications requiring accurate real-time curvature measurements., This work was supported in part by CIN/AEI/10.13039/501100011033 and FEDER "AWay to Make Europe" under Project PID2022-137269OB and in part by MCIN/AEI/10.13039/501100011033 and European Union "Next Generation EU"/PRTR under Project TED2021-130378B. Open access funding provided by Universidad Publica de Navarra.

This research introduces a new method for creating synthetic Distributed Acoustic Sensing (DAS) datasets from transport microsimulation models. The process involves modeling detailed vehicle interactions, trajectories, and characteristics from the PTV VISSIM transport microsimulation tool. It then applies the Flamant-Boussinesq approximation to simulate the resulting ground deformation detected by virtual fiber-optic cables. These synthetic DAS signals serve as large-scale, scenario-controlled, labeled datasets on training machine learning models for various transport applications. We demonstrate this by training several U-Net convolutional neural networks to enhance spatial resolution (reducing it to half the original gauge length), filtering traffic signals by vehicle direction, and simulating the effects of alternative cable layouts. The methodology is tested using simulations of real road scenarios, featuring a fiber-optic cable buried along the westbound shoulder with sections deviating from the roadside. The U-Net models, trained solely on synthetic data, showed promising performance (e.g., validation MSE down to 0.0015 for directional filtering) and improved the detectability of faint signals, like bicycles among heavy vehicles, when applied to real DAS measurements from the test site. This framework uniquely integrates detailed traffic modeling with DAS physics, providing a novel tool to develop and evaluate DAS signal processing techniques, optimize cable layout deployments, and advance DAS applications in complex transportation monitoring scenarios. Creating such a procedure offers significant potential for advancing the application of DAS in transportation monitoring and smart city initiatives., This research was funded by the Spanish Goverment 'Subprograma Ayudas Predoctorales 2020 Investigadores' program under Grant PRE2020-096336, assigned to the National Plan project PID2019-107270RB-C21, 'Photonic Devices and Systems Sensors for Intelligent Structures and Non Destructive Evaluation I'; the National 'Knowledge Generation Projects' project 'Photonic Sensors for Smart and Sustainable Cities (Performance)' under grant ID6448137269-137269-4-22; the project 'Integrated System for Traffic and Road Condition Monitoring Using Fiber-Optic Sensors (Ingestion)', under grant PDC2021-121172-C22 funded by MICIU/AEI/10.13039/501100011033 and by the European Union Next GenerationEU/PRTR). This work was supported in part by grant PID2022-137269OB-C21 by MICIU/AEI/10.13039/501100011033 and by ERDF 'A way of making Europe'; and grant PID2022-137269OB-C22 by MICIU/AEI/10.13039/501100011033 and by the European Union.

We present an interferometric vibration sensor that uses three-core fibers. The transducer is constructed by splicing a segment 20 mm long of a multicore optical fiber (MCF) to a single-mode optical fiber (SMF). The end of the MCF segment is cut off and painted using silver metallic paint. The sensor head is operated in reflection mode. The structure is placed on a polyvinyl chloride (PVC) plate, which is excited with a wide range of frequency signals. The vibrations induce cyclic bending in the MCF segment, resulting in periodic oscillations of the reflected interference spectrum. This device is demonstrated to be suitable to measure vibrations in a frequency range of the order of 300 kHz detecting deformations as small as 0.40μm ., This work was
supported in part by projects PID2019-107270RB-C02 and PID2022-
137269OB-C21, funded by MCIN/AEI/10.13039/501100011033 and
FEDER “A way to make Europe,” and TED2021-130378B-C22 funded
by MCIN/AEI/10.13039/501100011033 and European Union “Next generation EU”/PRTR.

This research explores the impact of cyclic uniaxial transverse deformation on an in-line hollow-core fiber etalon. The structure consists of a 6 mm long section of capillary fiber spliced between two standard single-mode fibers. The optical response of the structure is theoretically analyzed in spectral and transformed domains, evidencing Fabry-Perot and antiresonant interferometric mechanisms. A validation of the theoretical behavior is carried out both through simulation and experimentation. The performance of the structure for uniaxial transverse deformation is subsequently evaluated by tracking the phase of the main component in the transformed domain. The relevance of measuring in the time domain is discussed, demonstrating improved accuracy over wavelength shift and inverse spatial domain methods. Several sensors with different internal diameters underwent cycles of transverse deformation, revealing robust linear trends in every case. On average, the structure demonstrated elastic behavior under deformations up to 42 μm, with a mean sensitivity of 0.174 rad/μm, and mechanical breakage taking place at 58 μm. The results confirmed the suitability of the sensor to withstand uniaxial micro-displacements or pressures, with smaller inner diameter capillary fibers showing the best performance., This work was supported in part by
MCIN/AEI/10.13039/501100011033 and FEDER "A way to make Europe"
under Project PID2019-107270RB-C22 and Project PID2022-137269OB-C21,
in part by MCIN/AEI/10.13039/501100011033 and European Union "Next generation
EU"/PRTR under Project PDC2021-121172-C21 and Project TED2021-
130378B-C22, and in part by the Public University of Navarre under Project
PJUPNA06-2022. Open access funding provided by Public University of
Navarre.

This work presents a power-efficient solution based on Power over Fiber technology that combines and enables the use of electronic devices in fiber optic networks. The optical carrier is modulated via a microelectromechanical variable optical attenuator, using the processed sensor data, which is encoded in a frequency shift keying technique. To illustrate the concept, a 50-km remote environmental station is powered by energy harvesting techniques to provide the requisite power, and a low-power microcontroller encodes the data from electronic sensors. The data was successfully retrieved, achieving data rates of up to 1.5 kbps., This work was supported in part by projects PID2022-137269OB-C21, funded by MCIN/AEI/10.13039/501100011033 and FEDER “A way to make Europe”, and TED2021-130378B-C22 funded by MCIN/AEI/10.13039/501100011033 and European Union “Next generation EU”/PRTR.

This paper presents a Power-over-Fiber based remote electronic and optical fiber sensors multiplexing scheme. The system architecture consists of a 50-km linear cavity Raman-fiber laser that is used for interrogation of FBG optical fiber sensors. Simultaneously, electronic sensors information is modulated in amplitude while the optical sensors' data are encoded in the spectral information. In order to bias the electronic sensors, the residual power of the Raman pump laser is collected in an energy harvesting unit. This electric power is used for biasing an ATTiny85 control unit and two electro-optical modulators. A proof-of-concept is presented where a couple of optical fiber-Bragg-gratings sensors collect strain information that is self-compensated in temperature according to the digital data achieved from the electronic sensors. A 9.6 kbit/s data rate was achieved using Mach-Zehnder amplitude modulators and a maximum 35 ksample/s was retrieved using a high-speed C-band spectrometer and performing spectral analysis via a software developed in Python. Authors, This work was supported in part by MCIN/AEI/10.13039/501100011033 and FEDER "A way to make Europe", under Project PID2022-137269OB-C21, in part by
MCIN/AEI/10.13039/501100011033 and European Union "Next generation EU"/PRTR under Project TED2021-130378B-C22, and in part by MICINN
under the Beatriz Galindo BEAGAL18/00116 Grant. Open access funding provided by Universidad Publica de Navarra.

We introduce a method to measure the Rayleigh
signature of an optical fiber, which is defined as the frequency
dependence of the backscattering from each position along its
length. The method uses the Short-Frequency Fourier transform
to extract frequency-dependent time-resolved information from the
spectrum of the detected pulse response in an optical time-domain
reflectometry (OTDR) setup. The Rayleigh signature obtained can
be used to implement broadband high-sensitivity high-linearity
distributed acoustic sensors (DAS) that are immune to signal
fading problems commonly affecting other OTDR-based systems.
Rayleigh signature interrogation has been widely applied in optical frequency-domain reflectometry sensors and some specialized
OTDR configurations. However, to our knowledge, this is the first
technique that enables its general use in conventional single-pulse
coherent OTDR setups, as well as in other time-domain systems that
measure the impulse response of a fiber, such as those that utilize
pulse compression. We experimentally demonstrate the method
in a conventional heterodyne-detection OTDR DAS and also in a
enhanced-performance pulse compression setup employing phasecoded waveforms. Measurements in a 50 km fiber with spatial
resolution 2 m and a sensitivity of 113 p/√Hz demonstrate the
capabilities of the technique., publication 15 July 2025; date of current version 16 September 2025. This work was supported in part by Grant PID2022-137269OBC21 funded by MCIN/AEI/10.13039/501100011033 and by ERDF “A way
to make Europe”, in part by Grant TED2021-130378B-C22 funded by
MCIN/AEI/10.13039/501100011033 and European Union “Next generationEU”/PRTR. Open access funding provided by Universidad Pública de
Navarra.

Fecha de publicación: 2024-06-21, This study presents a new quasi-distributed vibration sensing approach with a 3-cm spatial resolution, capable of performing multiparameter measurements. In-line interferometers are employed simultaneously as strain point sensors and reflectors for vibration monitoring due to the Doppler effect. The interferometers consist of capillary fiber segments spliced between single-mode fibers, forming a sensing etalon. A study of the characteristics required for the fiber array fabrication is carried out. A 60 cm array comprising 20 sensing sections is used for the proof-of-concept of the technique for strain and vibration sensing. An analysis of the behavior for static strain and vibrations is performed, both individually and simultaneously, using a free-end cantilever experiment., This work was supported in part by MCIN/AEI/10.13039/501100011033 and FEDER "A way to make Europe", under Project PID2022-137269OB-C21, in part by MCIN/AEI/10.13039/501100011033 and European Union "Next generation EU"/PRTR, under Project TED2021-130378B-C22, and in part by the Science and Technology Commission of Shanghai Municipality, China under Grant 23002400300. Open access funding provided by Public University of Navarre.

In this work, a fabrication technique for microchannel-based reflectors used as an optical fiber sensor is demonstrated by using a processed optical fiber by an ultrafast laser-assisted etching method. This microdisplacement sensor was experimentally demonstrated to have an outstanding resolution of 5.9 rad/μm in the measurement range from 0 to 80 microns, by using the fast Fourier transform (FFT) measuring method., This work was supported in part by projects PID2022-137269OB, funded by MCIN/AEI/10.13039/501100011033 and FEDER "A way to make Europe", and TED2021-130378B funded by MCIN/AEI/10.13039/501100011033 and European Union "Next generation EU"/PRTR, and by the R+D project INNVAL23/10 financed by IDIVAL.

La tecnología de fibra óptica ha avanzado significativamente en las últimas décadas debido a su rendimiento superior en aplicaciones de comunicación. Basándose en estas innovaciones científicas y tecnológicas, los sensores de fibra óptica (FOS) han surgido como soluciones versátiles a muchas limitaciones de las tecnologías de detección tradicionales. Por ejemplo, los sensores de fibra óptica son químicamente inertes y resistentes a la interferencia electromagnética, lo que los hace ideales para su uso en entornos peligrosos. Además de estos beneficios, los sensores de fibra óptica tienen otras características deseables, como bajo ruido de señal, diseño ligero y compacidad. Estas cualidades únicas han hecho posible su implementación en varias aplicaciones, siendo las que han mostrado mayor éxito, las tecnologías basadas en mecanismos interferométricos, de retrodispersión y de redes de difracción de Bragg (FBGs).
Las estrategias de detección por fibra óptica utilizan diversos mecanismos de transductores y métodos de multiplexación. Sin embargo, se necesitan mejoras, principalmente debido al alto coste de los sensores de fibra en comparación con las tecnologías establecidas. Por lo tanto, las técnicas de multiplexación son esenciales para reducir los costes por sensor. Elegir un enfoque de multiplexación depende del tipo específico de sensor y de los requisitos de la aplicación. Por ejemplo, las redes de difracción de Bragg funcionan bien con la multiplexación por división de longitud de onda, mientras que los sensores interferométricos requieren métodos más complejos.
Aunque el coste es una preocupación principal, el rendimiento y la versatilidad también deben ser considerados para una solución óptima.
El progreso de las Ciudades Inteligentes requiere tecnologías de sensores innovadoras que puedan abordar las complejidades de los sistemas urbanos modernos con precisión, eficiencia y escalabilidad. En este sentido, esta tesis pretende contribuir con nuevas soluciones de sensores de fibra óptica puntuales. Incluye la incorporación de redes de difracción de Bragg y fibras ópticas microestructuradas, desplegando métodos de multiplexación híbridos para redes de sensores escalables, e implementando la tecnología Power over Fiber para facilitar el suministro remoto de energía y la interrogación eficiente de redes de sensores heterogéneas. Estas estructuras pueden adaptarse para aplicaciones tales como la medición de parámetros ambientales y el monitoreo de la calidad del agua y la salud estructural.
El trabajo desarrollado durante esta tesis ha sido realizado en el grupo de investigación de Comunicaciones Ópticas y Aplicaciones Electrónicas de la Universidad Pública de Navarra (UPNA) bajo el Programa de Doctorado en “Tecnologías de la Comunicación, Bioingeniería y Energías Renovables” para el Grado de Doctor en Ingeniería de Telecomunicación. Además, este trabajo se ha desarrollado en parte durante una estancia de investigación en la Universidade de Aveiro (Portugal) bajo la supervisión del Prof. Dr. Carlos Marques., Fiber optic technology has advanced significantly in recent decades due to its superior performance in communication applications. Building on these scientific and technological innovations, fiber optic sensors (FOS) have emerged as versatile solutions to many limitations of traditional sensing technologies. For instance, fiber optic sensors are chemically inert and resistant to electromagnetic interference, making them ideal for use in hazardous environments. In addition to these benefits, fiber optic sensors have other desirable features, including low signal noise, a lightweight design, and compactness. These unique qualities have enabled their deployment in several applications, with technologies based on interferometric mechanisms, backscattering, and Fiber Bragg Gratings (FBGs) showing the most success.
Several fiber optic sensing strategies use various transducer mechanisms and multiplexing methods. However, improvements are needed, primarily due to the high cost of fiber sensors compared to established technologies. Thus, multiplexing techniques are essential for reducing the cost per sensor. Choosing a multiplexing approach depends on the specific sensor type and application requirements. For example, fiber Bragg gratings work well with wavelength division multiplexing, while interferometric sensors require more complex methods. Although cost is a primary concern, performance and versatility must also be considered for an optimal solution.
The progress of Smart Cities requires innovative sensing technologies that can address the complexities of modern urban systems with precision, efficiency, and scalability. In this regard, this thesis aims to contribute to the development of new point optical fiber sensing solutions. It includes the incorporation of fiber Bragg gratings and microstructured optical fibers, deploying hybrid multiplexing methods for scalable sensor networks, and implementing Power over Fiber technology to facilitate remote power provision and efficient interrogation of heterogeneous sensor networks. These structures can be adapted for various applications, including measuring environmental parameters and monitoring water quality and structural integrity.
The work developed during this thesis was conducted in the Optical Communication and Electronic Applications research group at Universidad Pública de Navarra (UPNA) under the Doctorate Program in “Communications Technologies, Bioengineering, and Renewable Energies” for the degree of Doctor of Philosophy (Ph.D.) in Telecommunication Engineering. Additionally, this work was developed in part during a research stay at the Department of Physics and I3N, Universidade de Aveiro, Aveiro, Portugal, under the supervision of Prof. Dr. Carlos Marques., Financial support received: Universidad Pública de Navarra (UPNA) through the pre-doctoral research grants, mobility grants, and complementary grants for doctoral theses; Research project PID2019-107270RB-C02 funded by the Spanish Government Ministerio de Ciencia e Innovación (MCIN)/Agencia Estatal de Investigación (AEI) and FEDER “A way to make Europe”; Research project PDC2021-121172-C01 funded by the Spanish Government MCIN/AEI and the European Union “Next generation EU” / Plan de Recuperación, Transformación y Resilencia (PRTR); Research project TED2021-130378B-C22 funded by the Spanish Government MCIN/AEI and the European Union “Next Generation EU” / PRTR and Research project PID2022-137269OB funded by the Spanish Government CIN/AEI and FEDER “A way to make Europe”., Programa de Doctorado en Tecnologías de las Comunicaciones, Bioingeniería y de las Energías Renovables (RD 99/2011), Bioingeniaritzako eta Komunikazioen eta Energia Berriztagarrien Teknologietako Doktoretza Programa Ofiziala (ED 99/2011)

This work introduces an innovative capillary or hollow core-based sensor designed to measure turbidity by using the reflection of light in its cladding. The structure consists of two different capillary sections and has been optimized to maximise the interaction of light with the external liquid. Experimentation includes data collection from different turbidity levels using the reflected spectrum. To improve the measuring results, machine learning is implemented, exploring the effectiveness of various algorithms and neural network architectures to achieve a good root mean square error., This work was supported in part by projects PID2022-137269OB, funded by MCIN/AEI/10.13039/501100011033 and FEDER “A way to make Europe”, and TED2021-130378B funded by MCIN/AEI/10.13039/501100011033 and European Union “Next generation EU”/PRTR.