In the railway sector, rolling stock and infrastructure must be maintained in perfect condition to ensure reliable and safe operation for passengers. Climate change is affecting the urban and regional infrastructure through sea level rise, water accumulations, river flooding, and other increased-frequency extreme natural situations (heavy rains or snows) which pose a challenge to maintenance. In this paper, the use of artificial intelligence based on predictive maintenance implementation is proposed for the early detection of degraded conditions of a bridge due to extreme climatic conditions. For this prediction, continuous monitoring is proposed, with the aim of establishing alarm thresholds to detect dangerous situations, so restrictions could be determined to mitigate the risk. However, one of the main challenges for railway infrastructure managers nowadays is the high cost of monitoring large infrastructures. In this work, a methodology for monitoring railway infrastructures to define the optimal number of transductors that are economically viable and the thresholds according to which infrastructure managers can make decisions concerning traffic safety is proposed. The methodology consists of three phases that use the application of machine learning (Random Forest) and artificial cognitive systems (LSTM recurrent neural networks).

Recently, passenger comfort and user experience are becoming increasingly relevant for the railway operators and, therefore, for railway manufacturers as well. The main reason for this to happen is that comfort is a clear differential value considered by passengers as final customers. Passengers’ comfort is directly related to the accelerations received through the car-body of the train. For this reason, suspension and damping components must be maintained in perfect condition, assuring high levels of comfort quality. An early detection of any potential failure in these systems derives in a better maintenance inspections’ planification and in a more sustainable approach to the whole train maintenance strategy. In this paper, an optimized model based on neural networks is trained in order to predict lateral car-body accelerations. Comparing these predictions to the values measured on the train, a normal characterisation of the lateral dynamic behaviour can be determined. Any deviation from this normal characterisation will imply a comfort loss or a potential degradation of the suspension and damping components. This model has been trained with a dataset from a specific train unit, containing variables recorded every second during the year 2017, including lateral and vertical car-body accelerations, among others. A minimum average error of 0.034 m/s² is obtained in the prediction of lateral car-body accelerations. This means that the average error is approximately 2.27% of the typical maximum estimated values for accelerations in vehicle body reflected in the EN14363 for the passenger coaches (1.5 m/s²). Thus, a successful model is achieved. In addition, the model is evaluated based on a real situation in which a passenger noticed a lack of comfort, achieving excellent results in the detection of atypical accelerations. Therefore, as it is possible to measure acceleration deviations from the standard behaviour causing lack of comfort in passengers, an alert can be sent to the operator or the maintainer for a non-programmed intervention at depot (predictive maintenance) or on board (prescriptive maintenance). As a result, a condition-based maintenance (CBM) methodology is proposed to avoid comfort degradation that could end in passenger complaints or speed limitation due to safety reasons for excessive acceleration. This methodology highlights a sustainable maintenance concept and an energy efficiency strategy.

Bearing overheating and anomalous accelerations are two principal failure modes for this safety component. The supervision of bearing’s behaviour is essential to ensure a safe and reliable operation. A safety component’s failure may cause a speed limitation or even a non-available train for operating, so a predictive maintenance for bearings and other critical components is mandatory for the manufacturers, operators and maintainers in the railway sector. Bearing temperature, exterior temperature, train speed and other variables are measured every second in real time. From all the data collected and stored in the last years some algorithms and models are designed and trained in this paper to detect bearing anomalies 2 days before a real failure is detected and the safety alarm is enabled. The methodology for obtaining the optimal algorithm is exposed. Different artificial neural networks based on different optimization models such as the Mini-batch Gradient Descent (MGD) or Adam optimizer are compared. A final neural network with 10 hidden layers to detect bearing failure is proposed reaching 99% of accuracy, 95% of precision and 90% of sensitivity. The objective of predicting a bearing anomaly with some days in advanced is reached with high precision level, which will lead also to cost savings and a contribution for the sustainability because many inspections could be reduced and the energy cost associated to them.

Reliable prediction of population displacement flows is essential for transport planning, demand-responsive service design, and evidence-based urban policy. This paper presents a novel, explainable machine learning framework for short- and medium-term displacement prediction applied to official Spanish geolocation data (MITMA dataset, January 2022–March 2024, ~750 GB/year). The framework addresses three nested spatial scales simultaneously—interprovincial, intermunicipal, and interdistrict—and introduces two original contributions beyond state-of-the-art benchmarking: (i) a scale-adaptive model selection criterion grounded in the Coefficient of Variation (CV) of demand and spatial entropy, providing a theoretically justified and operationally replicable decision rule; and (ii) a SHAP-based feature importance analysis that reveals how the dominant drivers of mobility shift qualitatively across spatial scales, yielding insights of direct value to transport planners.Four supervised learning models are rigorously evaluated: Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Sequential Deep Neural Network (SDNN), and Linear Time-Series Regression (LTSR). XGBoost consistently achieves the best predictive accuracy across all three scales: %EMAE = 15.6% (interprovincial, R² = 0.881), 13.1% (intermunicipal, R² = 0.914), and 10.3% (interdistrict, R² = 0.933), outperforming the linear baseline by 8–14 percentage points. Statistical superiority over all competing models is confirmed via Diebold–Mariano tests (p < 0.05). SHAP analysis reveals a systematic scale-dependency of feature importance: public holiday indicators dominate at the interprovincial scale (φ = 0.31), weekday encoding dominates at the intermunicipal scale (φ = 0.28), and same-week lag features dominate at the interdistrict scale (φ = 0.34). A complete model is validated.

Until the last century, transport was understood as the movement of a person or goods from an initial point, called origin, to an end point, called destination. However, this transport service has not been analyzed from a global perspective, since energy efficiency, accident rate, energy consumption, sustainability, adaptation of supply and demand, ancillary services to the traveler as part of the user experience, combination of transport services, etc., have not been discussed. All this leads to the evolution of the traditional concept of transport to the concept of mobility. A study of the state of the art has been carried out based on 72 research articles related to the application of new technologies and artificial intelligence in the three main interest groups of rail mobility. Only 9% of the articles deal with issues incorporating all the stakeholders, being more than 50% of the cases in which only one of the participants is involved in the treatment and resolution of the exposed problem. This shows that the existing problems and challenges related to rail mobility are not being addressed in a transversal way, generating partial solutions that are far from reaching the optimum for all parties involved. In the development of this doctoral thesis, three well differentiated parts are presented. In the first part, a mobility study is developed based on the data provided by the government, in order to know how the population moves between the different provinces of Spain. This part responds to how the population needs to move between provinces in Spain, that is, the real demand for transport that exists in Spain today. In the second part, the mobility options currently available for each province and route are presented, comparing the different modes of transport in terms of time and cost. This section deals with how the population can move between provinces in Spain, i.e. the actual range of transport services available. The mobility objective of a country like Spain should be to guarantee accessibility to a transport service in which, for any citizen, the cost of traveling 100 km and the time to travel 100 km is within a reasonable and equitable range depending on the origin and destination of the trip. From this analysis, the most neglected trips that need urgent investment in infrastructure and public transport services will come to light. In the third part, 5 success stories are presented in which artificial intelligence has helped to optimize mobility in the railway sector in a concrete way: Case 1. Prediction of passenger mobility in Spain using neural networks. Case 2. Prediction of anomalous dynamic behavior of a railway bridge with the passage of trains due to extreme weather conditions. Case 3. Prediction of railway bearing failures due to over temperature. Case 4. Prediction of degradation of passenger comfort due to deterioration of train damping. Case 5. Prediction of passenger comfort degradation due to train damping deterioration using LSTM (long short term memory) networks. By grouping the three previous parts, a methodology ("Trainsportation") consisting of two distinct phases is finally proposed. In the first phase, the aim is to know the real mobility needs and the existing supply, in order to align supply and demand in the most efficient way possible. The second phase involves optimizing the operation and maintenance of mobility services in order to achieve intelligent, efficient and sustainable mobility. RESUMEN Hasta el siglo pasado, se entendía el transporte como el desplazamiento de una persona o una mercancía desde un punto inicial, denominado origen, hasta un punto final, denominado destino. Sin embargo, no se ha estado analizando este servicio de transporte desde una perspectiva global, dado que no se hablaba de eficiencia energética, tasa de accidentalidad, consumo energético, sostenibilidad, adaptación de oferta y demanda, servicios auxiliares al viajero como parte de la experiencia de usuario, combinación de servicios de transporte, Todo ello conlleva a evolucionar el tradicional concepto de transporte al concepto de movilidad. Se ha realizado un estudio del estado del arte en base a 72 artículos de investigación relacionados con la aplicación de las nuevas tecnologías y la inteligencia artificial en los tres principales grupos de interés de la movilidad ferroviaria. Tan solo el 9% de los artículos tratan temáticas incorporando a todos los grupos de interés, siendo más del 50% de los casos en los que únicamente uno de los participantes interviene en el tratamiento y resolución de la problemática expuesta. Esto demuestra que no se están tratando de forma transversal los problemas y retos existentes relacionados con la movilidad ferroviaria, generando soluciones parciales que se alejan de alcanzar el óptimo para todas las partes involucradas. En el desarrollo de esta tesis doctoral, se presentan tres partes bien diferenciadas. En una primera parte, se desarrolla un estudio de movilidad realizado a partir de los datos aportados por el gobierno, con objeto de conocer cómo se mueve la población entre las distintas provincias de España. Esta parte responde a cómo necesita moverse la población entre provincias en España, esto es, la demanda real de transporte que existe en España hoy en día. En una segunda parte, se exponen para cada provincia y trayecto las opciones de movilidad existentes en la actualidad, comparando los distintos modos de transporte en términos de tiempos y costes. Este apartado responde a cómo puede moverse la población entre provincias de España, esto es, la oferta real de los servicios de transporte que existe. El objetivo en materia de movilidad de un país como España debe ser garantizar la accesibilidad a un servicio de transporte en el que, a cualquier ciudadano, el...