AI on the rails: efficiency in metro transport

Column

Innovation

December 15, 2025

AI on the rails: efficiency in metro transport

Automated control, predictive maintenance, and personalized passenger experience consolidate technology as an engine of innovation in the sector

The railway transport is one of the fundamental pillars of modern urban mobility. In large cities, the subway represents an efficient, fast, and sustainable means of transport, responsible for connecting millions of people daily. According to guidelines from the Union Internationale des Transports Publics (UITP) and the World Bank, high-capacity systems like the subway are essential for reducing congestion and the emission of pollutants into the urban atmosphere.

However, growing demand, operational challenges, and user expectations for quality and reliability require systems to continuously modernize. In this context, artificial intelligence (AI) emerges as a strategic tool, aligned with the recommendations of ISO/IEC 42001:2023 (international AI management standard), capable of optimizing operations, reducing costs, improving passenger experience, and increasing safety, through technologies that help computational systems perform tasks that would traditionally require human intelligence, such as pattern recognition, decision-making, prediction, and learning from data.

Applications

One of the main applications of AI in subways is the automation of train operations. Many cutting-edge systems — such as those in Paris, London, Singapore, and Hong Kong — follow the technical standards of IEC 62290, which defines the GoA (Grade of Automation) levels. GoA4, in which the train operates without a driver, uses AI systems that continuously process information from sensors, cameras, and signaling to adjust speed, braking, and stopping, ensuring maximum energy efficiency and safety.

Another relevant application is predictive traffic control. This type of solution is aligned with the best practices recommended by the Institute of Electrical and Electronics Engineers (IEEE), especially in the standards for intelligent transportation systems (ITS).

Using machine learning algorithms, systems can predict the flow of passengers at different times and stations, automatically adjusting the interval between trains. This allows the subway to operate with greater regularity and avoid overcrowding during peak hours. Furthermore, AI can integrate external data — such as sporting events, weather conditions, or traffic incidents — to anticipate variations in demand and plan rapid responses.

Predictive maintenance and reliability

Traditionally, metro systems perform preventive maintenance based on fixed schedules. However, this model is not always efficient, as it can lead to the unnecessary replacement of components still in good condition or the unexpected failure of parts before their scheduled review.

AI-based predictive maintenance is revolutionizing this practice. Through the collection and analysis of data from sensors installed on trains and track equipment — such as engines, brakes, rails, and electrical systems —, artificial intelligence algorithms identify wear patterns and anomalies before they cause failures. This allows for more precise planning of interventions, reducing unscheduled downtime and unnecessary maintenance costs. Furthermore, it increases service reliability, as problems are proactively solved.

A practical example of this application is the use of machine learning models to predict the degradation of train axles, brake wear, and track condition. The system “learns” from historical data and continuously adjusts its predictions, indicating the ideal time for each repair. Cities like London and Tokyo already widely use this type of technology in their subways.

Security and surveillance

Artificial intelligence is also a powerful tool in passenger security, especially with the use of computer vision and intelligent video analysis. Cameras equipped with AI algorithms can detect suspicious behaviors, accidental falls on platforms, presence of abandoned objects, and even signs of medical emergencies, such as fainting.

These systems can automatically trigger control centers, allowing for immediate responses from security or relief teams. Furthermore, AI helps optimize human monitoring, reducing the need for operators to watch dozens of screens simultaneously. Thus, surveillance becomes more efficient and less susceptible to human error.

Another important advance is the use of AI for prevention of operational accidents. Sensors and cameras in tunnels and stations can identify obstacles, undue intrusions on the tracks, and abnormal variations in environmental conditions (such as smoke or excessive heat). The system then automatically alerts central control, avoiding risks before they become critical.

User experience

Beyond operational improvements, AI also plays a growing role in the passenger experience. Chatbot systems and virtual assistants can provide real-time information on schedules, routes, delays, and transportation alternatives, both in applications and on totems installed at stations. These assistants are capable of interacting in natural language, making communication simpler and more accessible.

AI is also used for the analysis of user behavior, based on electronic ticketing data and presence sensors. This information helps operators understand displacement patterns and optimize information campaigns, works, and improvement actions. In some cities, visual information systems adapt the content displayed on station panels according to the profile of users present at the location and the real-time operational situation.

Energy efficiency and sustainability

Energy consumption is one of the main operating costs of a subway. Artificial intelligence can significantly reduce this expense through optimized automatic driving algorithms, which adjust acceleration and braking according to the terrain, the weight of the train, and the interval between trains. This technique, called automated eco-driving, allows for significant savings in electrical energy and reduced wear on mechanical components.

Furthermore, AI systems can also optimize the use of lighting, ventilation, and air conditioning in stations, adapting their operation according to the flow of people and weather conditions. This intelligent management contributes to a more sustainable operation, with less environmental impact.

Challenges and perspectives

Despite the advances, the adoption of artificial intelligence in rail transport still faces challenges. The integration of legacy systems, high initial implementation costs, the need for qualified professionals in data analysis, and cybersecurity are critical factors. Furthermore, it is essential to ensure that the use of passenger data follows ethical and privacy principles.

However, metros are expected to become increasingly autonomous, integrated, and intelligent systems. The concept of a “digital metro” — in which all operational decisions are based on real-time data — is already beginning to materialize in cities like Dubai and Beijing.

In this way, artificial intelligence is profoundly transforming rail transport, making it safer, more efficient, and user-centered. From automated train control to predictive maintenance and personalized passenger experience, AI is consolidating itself as the engine of innovation in the sector. As cities grow and mobility demands intensify, investing in intelligent solutions is no longer an option but a necessity.

Subway transport in Brazil

The Brazilian subway network, added to light rail and monorail systems, is concentrated in a few metropolitan regions and represents a reduced percentage of the national public transport demand. Expansion occurs slowly, marked by funding discontinuities, changes in government, limitations of federal investments, and dependence on complex models of PPPs and concessions.

Despite this, some systems stand out for their efficient operation and technological advancement, especially that of the São Paulo Metro, a continental benchmark in reliability, fare integration, and advanced traffic control. The main challenges faced by the sector in Brazil are:

  • Institutional fragmentation: the division of responsibilities among States, Municipalities, and the Union hinders the full integration between subways, metropolitan trains, and buses, in addition to generating decision-making slowness;
  • Dependence on complex financing models: PPPs and concessions are important, but often face legal insecurity, regulatory risks, and economic instability;
  • Low operational digitalization: some systems still operate with legacy signaling, traffic control, and ticketing technologies, which limits the adoption of advanced AI solutions;
  • Socio-spatial and urban challenges: expansion into peripheral areas — where demand is high, but income is lower — requires public policies that reconcile financial viability and social inclusion;
  • Operational security and cybersecurity: technological modernization increases vulnerability to cyberattacks and requires continuous protocols and training.

Strategies for the Future

The creation of a National Rail Program is the first essential step, because, just as occurred in the Brazilian energy and telecommunications sectors, rail mobility needs a federal framework for permanent financing, with expansion goals for 10, 20, and 30 years. Subsequently, strengthening metropolitan integration becomes equally important, which involves adopting a single ticketing system and integrated line planning, ensuring greater efficiency in the system.

Furthermore, the incentive for sustainable PPP models requires special attention to regulatory stability, revenue predictability, the Union’s participation as guarantor, and contract standardization, ensuring governance and legal certainty.

None of this, however, eliminates the need to maintain focus on social equity and inclusion, so that metropolitan projects prioritize connections with dense peripheries, promote a more balanced distribution of supply, ensure affordable fares, and articulate policies that integrate urban development and transportation.

Finally, AI-based technological modernization plays a decisive role in this set of guidelines, involving the adoption of CBTC systems and automation at GoA2, GoA3, and GoA4 levels, the use of energy optimization algorithms and the implementation of integrated predictive maintenance, in addition to intelligent video analysis systems and integration with smart cities and urban data.

Perspectives

Brazil has the potential to transform its metro-rail networks into modern, efficient, and intelligent systems. The convergence of structural investments, integrated metropolitan policies, and emerging technologies — especially artificial intelligence — can generate a new era of urban mobility, aligned with the social, environmental, and economic needs of Brazil’s major cities.

With continuous planning, stable governance, and technological innovation, the country is in a position to expand its rail network, improve the quality of public transport, and build a more sustainable and accessible future. The metro of the future will inevitably be a metro powered by intelligence — not only by its machines, but by the harmonious integration of technology, management, and quality public service.

Who wrote this column

Pedro Henrique Fabri Zanini

É gestor público com mais de 15 anos de experiência na administração pública, com atuação em Gestão de Contratos e Licitações, Administração Financeira e Orçamentária, ESG, cidades inteligentes e governo digital. Possui mestrado em Administração Pública, MBA em Gestão Pública, pós-graduação em Direito Público e graduação em Administração de Empresas. É professor orientador na USP/Esalq, autor de questões de concursos públicos para bancas examinadoras, escritor e membro do CRA/SP.

You may also like

November 17, 2026

Detection and Diagnosis of Diseases in Corn and Rice in Mozambique with Deep Learning

Mozambican agriculture depends on corn and rice, fundamental crops for food security, but their productivity is strongly affected by phytosanitary diseases, whose early and accurate identification remains a challenge in resource-limited contexts. The study aimed to develop and compare Deep Learning-based models for the automatic detection and diagnosis of diseases in corn and rice leaves in Mozambique. Three approaches were used: a classic Convolutional Neural Network (CNN) developed from scratch, and two transfer learning models, ResNet50 and MobileNetV2. The dataset consisted of images from public databases and collected in the field, which underwent cleaning, balancing, and artificial augmentation steps. The models were trained and evaluated with standard performance metrics, including accuracy, precision, recall, F1-score, Log Loss, and Cohen’s Kappa. The classic CNN presented the best overall performance, with 94% precision, recall, and F1-score, and 93% accuracy and Cohen’s Kappa. MobileNetV2 achieved 91% F1-score and 90% accuracy, standing out for its lower Log Loss (0.30) and training time (6h32min59s). ResNet50 reached 80% F1-score and 79% accuracy. It was concluded that Deep Learning techniques have high potential to support phytopathological diagnosis in real agricultural contexts, contributing to faster and more accurate decisions in the management of corn and rice diseases.

Keywords: Deep learning; Rice; Plant diseases; Corn; Computer vision.

November 17, 2026

Artificial intelligence in accounting operational routines and financial efficiency

The incorporation of Artificial Intelligence (AI) and automation tools has reconfigured the routines of Brazilian accounting offices, impacting productivity, error mitigation, and financial efficiency. These impacts were analyzed in a small accounting firm, specialized in serving service providers in the medical field in São Caetano do Sul, São Paulo. The research adopted a qualitative approach, with a single case study design and incorporated units of analysis. Data were collected through a structured questionnaire, applied via Google Forms between January and February 2026, to five professionals in the operational structure of the firm in a census survey. The treatment followed content analysis with a priori and emergent categories. All respondents declared the use of automated tools or tools with AI resources. The perception of reduced execution time, decreased operational errors, rework, and better use of the team’s time converged in 80% of affirmative responses and 20% partial responses. The most benefited activities were bank reconciliation, import of fiscal documents, and tax assessment, with visible gains on typing errors, duplicate entries, and incorrect classification. Human intervention remained indispensable in tax planning, scenario analysis, and verification of ancillary obligations. The overall evaluation of AI’s contribution was predominantly favorable, with moderation linked to the complexity of fiscal regulations.

Keywords: Content analysis; Process automation; Accounting 4.0; Small business; Digital transformation.

November 17, 2026

Factors influencing schedule management in sewage treatment plant “retrofit” projects

Projects involving “retrofit” in Sewage Treatment Plants (STP) are characterized by high complexity, operational restrictions, and multiple technical interfaces. The study analyzed the perception of the professionals involved regarding the management and adherence to deadlines in “retrofit” projects for sewage treatment plants, considering technical, operational, and organizational factors. The research was characterized as an applied study, with a quali-quantitative approach, designed as a field survey. Data analysis was performed using descriptive statistics and qualitative categorization, employing SWOT, risk matrix (Probability x Impact), and 5W2H action plan tools. The results indicated a high perception of clarity (77.8%) and realism of deadlines (100% agreement), evidencing consistent initial planning. However, 77.7% of respondents pointed out that rework and scope changes directly impacted deadline adherence. The integration between engineering, manufacturing, and Production Planning and Control (PPC) showed an intermediate evaluation (77.7% partial/total agreement), indicating fragility in interfunctional coordination. The risk matrix highlighted as critical: scope changes, operational limitations of the STP, and technical complexity, all with a high level. As a central improvement, the standardization of scope change control, analysis, and approval was proposed, aiming to reduce rework and increase schedule predictability.

Keywords: Performance; Integration; Planning; Rework; Risk.

November 17, 2026

B2C Acquisition in diagnostic medicine: strategic partnerships with specialized medical offices

The diagnostic medicine sector in Brazil operates with high dependence on health plan providers, which limits the financial autonomy of service providers. This study proposed and analyzed a direct patient acquisition model (B2C) for a highly complex diagnostic medicine institution, structured through partnerships with Oncology and Cardiology practices and operationalized by a personalized customer service called concierge. The investigation adopted a mixed-methods approach in three phases: a field survey with a structured questionnaire applied to 87 patients, mapping of the operational flow using “Service Blueprint”, and analysis of the conversion rate from 312 medical referrals registered in the pilot project. The results indicated that trust in medical referral achieved 92.0% agreement, establishing itself as the main factor for adherence. The convenience of performing the exam on the same day reached 78.2%, and the willingness to pay directly was 55.2%, with polarization associated with the predominance of health plan users. The “Service Blueprint” identified three critical points in the transitions between stages of the patient journey. The overall conversion rate was 51.0%, with superior performance in Oncology (58.2%) compared to Cardiology (45.0%), and the greatest loss was concentrated in the acceptance and scheduling stage (28.3%). It was concluded that the model demonstrated possible operational viability and indications of patient acceptance, conditioned by price transparency and a reduction in the interval between consultation and approach by the concierge.

Keywords: Direct payment; Patient journey; Supplementary health; Concierge service; Conversion rate.

November 17, 2026

The role of the school manager in promoting an inclusive culture: leadership and educational policies

The research analyzed the school manager’s performance in promoting an inclusive culture, considering the need to transform legal guidelines and pedagogical foundations into effective institutional practices. It was assumed that school inclusion requires planning, organization, and strategic leadership in the school’s daily operations. A qualitative approach of an applied nature was adopted, developed in three complementary stages: documentary analysis of Brazilian legislation on inclusive education, bibliographic review on school leadership and management, and data systematization using management tools such as SWOT analysis and the PDCA cycle. The results indicated that the school management’s performance directly influenced the consolidation of inclusive environments, especially in the organization of processes, continuous team training, and strengthening of a collaborative institutional culture respectful of diversity. Structural, pedagogical, and relational challenges that demanded planned interventions were also identified. Finally, a Practical Guide for School Managers was developed, with guidelines, protocols, and operational orientations for decision-making and the organization of inclusive processes. It was concluded that the construction of an inclusive culture depended on the management’s ability to articulate public policies, pedagogical practices, and institutional processes, consolidating inclusion as a permanent commitment in the school context.

Keywords: educational accessibility; educational equity; participatory management; strategic planning; institutional processes.

November 17, 2026

An AI artifact based on Design Thinking to support the elicitation of software requirements from user needs

The development of software oriented to user needs frequently faces challenges in requirements elicitation, stemming from ambiguities in natural language and communication failures. Given this, an intelligent artifact integrating Design Thinking and Artificial Intelligence was proposed and validated, focusing on the Empathy and Definition stages, to support the collection, interpretation, and structuring of user needs. The research, of an applied, qualitative, and exploratory nature, conducted a Proof of Concept in a controlled environment, employing hypothetical scenarios. The artifact operated through guided natural language interviews, organizing information into elements such as pain points, context, and impact, and generating traceable problem syntheses. The results indicated that the system organized unstructured reports, reduced ambiguities, and preserved the meaning of the original information in most cases. The ability to reorganize logically in complex scenarios was also observed, although with limitations in separating multiple problems and dependence on instructions. It was concluded that the artifact has potential as a support for requirements elicitation, improving the clarity and structuring of information, but requires supervision and contextual control.

Keywords: Design Thinking; Requirements Elicitation; Requirements Engineering; Artificial Intelligence; Natural Language Processing.

November 17, 2026

The Extinction of the Monophasic Tax System in the Pharmaceutical Industry in Light of the Tax Reform

The consumption Tax Reform, established by Constitutional Amendment No. 132/2023, introduced structural changes to the Brazilian tax system, with the replacement of the Social Integration Program (PIS) and the Social Security Financing Contribution (COFINS) by the Contribution on Goods and Services (CBS), in a dual Value Added Tax (VAT) model. The objective was to analyze the impacts of the extinction of the single-stage system on the pharmaceutical industry, in light of the new regulatory design and its economic and legal effects. A qualitative, exploratory research was conducted through a case study and documentary analysis of legislation and specialized doctrine. It was examined whether the end of the single-stage system would imply a relevant increase in the tax burden for the sector. The results indicated that, although the formal overcoming of the single-stage system has occurred, the material exemption of medicines has been preserved, mainly due to the application of reduced rates of 60% and, in certain cases, a zero rate of the Tax on Goods and Services (IBS) and CBS. The change in model may cause occasional variations in revenue collection, without characterizing a structural increase in the tax burden, tending towards neutrality over time. It was preliminarily concluded that the Tax Reform reorganized the taxation technique in the pharmaceutical industry, replacing a concentrated regime with more transparent exemption mechanisms. This approach proved compatible with the principles of neutrality, full non-cumulativeness, and fiscality, maintaining tax protection for essential medicines and aligning fiscal policy with the fundamental right to health.

Keywords: CBS; COFINS; IBS; Dual VAT; PIS.