Parth Yogeshbhai Purohit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Parth Yogeshbhai Purohit has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Peter Hecker
Institut für Flugführung, Technische Universität Braunschweig
2 shared publicationsThomas Feuerle
Institut für Flugführung, Technische Universität Braunschweig
2 shared publications- Jonas Ernst Bernhard Langner
Institute of Flight Guidance, Technische Universität Braunschweig, 38108 Braunschweig, Germany
1 shared publication - Peter Hecker
Institute of Flight Guidance, Technische Universität Braunschweig, 38108 Braunschweig, Germany
1 shared publication - Thomas Feuerle
Institute of Flight Guidance, Technische Universität Braunschweig, 38108 Braunschweig, Germany
1 shared publication
Latest Publications
- Open Access
- 3 November 2026
- Published by Elsevier in Journal of Air Transport Management
- Vol. 140
Availability before precision: how the quality of inbound information governs the aircraft turnaround departure-delay decision
- 3 November 2026
- Published by Elsevier in Journal of Air Transport Management
- Vol. 140
Open AccessAvailability before precision: how the quality of inbound information governs the aircraft turnaround departure-delay decision
- Open Access
- 19 October 2026
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 9, 1977034
Pre-arrival OCC decision support for aircraft turnaround coordination: a human-in-the-loop architecture and scenario-based evaluation
Aircraft turnaround coordination depends on maintenance, catering, passenger-assistance, gate, and bottleneck information that may become available before arrival but is often handled through fragmented workflows. This paper presents a human-in-the-loop Operations Control Center (OCC) decision-support architecture for pre-arrival aircraft turnaround coordination. The architecture integrates component-aware maintenance risk indicators, service-area inventory readiness, process-class bottleneck forecasting, passenger-assistance readiness logic, and a transparent rule-based fusion layer that converts heterogeneous signals into readiness scores, alert levels, and operator-facing action queues. The evaluation is deliberately framed as controlled synthetic scenario analysis rather than airline deployment validation. Existing module-level holdout results are combined with a deterministic scenario sweep of 1,000 synthetic inbound cases across six operational regimes, monotonicity and sanity checks, and ablation and baseline comparisons. The scenario sweep produced mean readiness 47.4, median readiness 50.6, 370 Critical cases, 284 Priority cases, and 188 Routine cases. Ablations show that removing maintenance influence increased mean readiness by 13.7 points, while removing bottleneck influence increased mean readiness by 10.0 points, indicating that the fusion layer materially changes prioritization under controlled stress conditions. Two maintenance-related monotonicity checks did not strictly pass because small local readiness increases occurred at low malfunction levels before urgency thresholds changed; these failures are treated as limitations of the current model-fusion interaction rather than hidden. The work contributes a reproducible OCC decision-support architecture and scenario-evaluation package, while explicitly preserving the limitations that no airline operational data, OCC user study, deployment, certification, or measured operational savings are claimed.
- 19 October 2026
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 9, 1977034
Open AccessPre-arrival OCC decision support for aircraft turnaround coordination: a human-in-the-loop architecture and scenario-based evaluation
Aircraft turnaround coordination depends on maintenance, catering, passenger-assistance, gate, and bottleneck information that may become available before arrival but is often handled through fragmented workflows. This paper presents a human-in-the-loop Operations Control Center (OCC) decision-support architecture for pre-arrival aircraft turnaround coordination. The architecture integrates component-aware maintenance risk indicators, service-area inventory readiness, process-class bottleneck forecasting, passenger-assistance readiness logic, and a transparent rule-based fusion layer that converts heterogeneous signals into readiness scores, alert levels, and operator-facing action queues. The evaluation is deliberately framed as controlled synthetic scenario analysis rather than airline deployment validation. Existing module-level holdout results are combined with a deterministic scenario sweep of 1,000 synthetic inbound cases across six operational regimes, monotonicity and sanity checks, and ablation and baseline comparisons. The scenario sweep produced mean readiness 47.4, median readiness 50.6, 370 Critical cases, 284 Priority cases, and 188 Routine cases. Ablations show that removing maintenance influence increased mean readiness by 13.7 points, while removing bottleneck influence increased mean readiness by 10.0 points, indicating that the fusion layer materially changes prioritization under controlled stress conditions. Two maintenance-related monotonicity checks did not strictly pass because small local readiness increases occurred at low malfunction levels before urgency thresholds changed; these failures are treated as limitations of the current model-fusion interaction rather than hidden. The work contributes a reproducible OCC decision-support architecture and scenario-evaluation package, while explicitly preserving the limitations that no airline operational data, OCC user study, deployment, certification, or measured operational savings are claimed.
- Open Access
Optimizing Aircraft Turnaround Operations Through Intelligent Technology Integration: A Comprehensive Analysis of the INTACT System’s Impact on Flight Efficiency and Economic Performance
Delays during turnaround operations are a significant source of operational inefficiency for airlines. They reduce airline profit margins by resulting in rescheduled flights and missed connections for passengers. This research paper presents the findings of an approach developed within the INTACT research project (subsequently called “the INTACT system”). The INTACT system aims to achieve reduced delays during turnaround operations and therefore increase their operational efficiency by introducing new technologies. A simulation study, including 350 simulated days, was conducted to assess the impact of three of INTACT’s abilities: (1) the localization of wheelchairs for passengers, (2) the assessment of what trolleys are onboard and how many trolley items are needed, and (3) visual observations of cabin failures and communication back to the destination airport. Results show that the implementation of these technologies leads to a statistically significant average delay reduction of 3 min per turnaround. Under the modeled schedule constraints in the discrete-event simulation, this reduction shifts the distribution of feasible daily flight counts, resulting in an average increase of 0.11 flights/day (38 additional completed flights over 350 simulated days) relative to the full-delay scenario. In addition, the cost–benefit analysis shows that the INTACT system saves an average of $966.95 in turnaround costs and gains $2714.29 in additional revenue per day and per aircraft. With estimated initial investment costs of around 2 million dollars, the payback period is only 1.5 years. During this study, gross additional revenue was reported as an upper-bound estimate; net operational benefit depends on airline-specific variable operating costs. The INTACT system can help to improve turnaround operation issues while providing positive economic performance for stakeholders in the industry.
Open AccessOptimizing Aircraft Turnaround Operations Through Intelligent Technology Integration: A Comprehensive Analysis of the INTACT System’s Impact on Flight Efficiency and Economic Performance
Delays during turnaround operations are a significant source of operational inefficiency for airlines. They reduce airline profit margins by resulting in rescheduled flights and missed connections for passengers. This research paper presents the findings of an approach developed within the INTACT research project (subsequently called “the INTACT system”). The INTACT system aims to achieve reduced delays during turnaround operations and therefore increase their operational efficiency by introducing new technologies. A simulation study, including 350 simulated days, was conducted to assess the impact of three of INTACT’s abilities: (1) the localization of wheelchairs for passengers, (2) the assessment of what trolleys are onboard and how many trolley items are needed, and (3) visual observations of cabin failures and communication back to the destination airport. Results show that the implementation of these technologies leads to a statistically significant average delay reduction of 3 min per turnaround. Under the modeled schedule constraints in the discrete-event simulation, this reduction shifts the distribution of feasible daily flight counts, resulting in an average increase of 0.11 flights/day (38 additional completed flights over 350 simulated days) relative to the full-delay scenario. In addition, the cost–benefit analysis shows that the INTACT system saves an average of $966.95 in turnaround costs and gains $2714.29 in additional revenue per day and per aircraft. With estimated initial investment costs of around 2 million dollars, the payback period is only 1.5 years. During this study, gross additional revenue was reported as an upper-bound estimate; net operational benefit depends on airline-specific variable operating costs. The INTACT system can help to improve turnaround operation issues while providing positive economic performance for stakeholders in the industry.
- 2 October 2025
- Published by Centre for Continental Network in Eco-Innovation and Research in Journal of Airline Operations and Aviation Management
- Vol. 4 (2) , 15-40
Advanced Machine Learning Approaches for Predictive Inventory Management in Aviation: A Comprehensive Synthetic Data-Driven Analysis
The airline industry confronts increasingly sophisticated challenges in inventory management on board their aircraft fleet, demanding advanced predictive models capable of navigating the complex interdependencies of resource allocation across heterogeneous operational environments. This comprehensive research introduces a groundbreaking methodological framework for inventory efficiency prediction, integrating cutting-edge machine learning techniques with innovative synthetic data generation strategies. This study's primary contributions are threefold: (1) the creation of a high-fidelity synthetic dataset capturing the intricate nuances of aviation operational dynamics, (2) the implementation of advanced machine learning algorithms for unprecedented predictive accuracy, and (3) the development of a holistic analytical approach that provides actionable strategic insights for industry stakeholders. The synthetic dataset generated in this research represents a significant methodological innovation, meticulously constructed to simulate realistic aviation operational conditions. By incorporating a comprehensive array of multidimensional features—including flight duration, route complexity, aircraft specifications, passenger demographic profiles, maintenance histories, seasonal fluctuations, and geospatial variations—we establish an unparalleled foundation for predictive modeling. Employing a sophisticated ensemble of machine learning methodologies, including advanced regression techniques, probabilistic classification algorithms, and hybrid predictive models, we achieved exceptional computational performance. Our regression models demonstrated extraordinary explanatory power, while classification models exhibited near-perfect risk assessment capabilities. The research presents several critical methodological innovations: (1) a novel synthetic data generation protocol that preserves statistical distributions and complex interdependencies, (2) advanced feature engineering and preprocessing techniques that enhance model interpretability and generalizability, and (3) a hybrid machine learning approach that integrates probabilistic reasoning with empirical predictive modeling. Our findings provide transformative, data-driven strategies for aviation inventory management, offering unprecedented insights into resource optimization, operational risk mitigation, and efficiency enhancement. The proposed framework not only advances academic understanding of complex inventory systems but also presents practical, implementable solutions for airline industry stakeholders seeking to leverage advanced analytical methodologies.
- 2 October 2025
- Published by Centre for Continental Network in Eco-Innovation and Research in Journal of Airline Operations and Aviation Management
- Vol. 4 (2) , 15-40
Advanced Machine Learning Approaches for Predictive Inventory Management in Aviation: A Comprehensive Synthetic Data-Driven Analysis
The airline industry confronts increasingly sophisticated challenges in inventory management on board their aircraft fleet, demanding advanced predictive models capable of navigating the complex interdependencies of resource allocation across heterogeneous operational environments. This comprehensive research introduces a groundbreaking methodological framework for inventory efficiency prediction, integrating cutting-edge machine learning techniques with innovative synthetic data generation strategies. This study's primary contributions are threefold: (1) the creation of a high-fidelity synthetic dataset capturing the intricate nuances of aviation operational dynamics, (2) the implementation of advanced machine learning algorithms for unprecedented predictive accuracy, and (3) the development of a holistic analytical approach that provides actionable strategic insights for industry stakeholders. The synthetic dataset generated in this research represents a significant methodological innovation, meticulously constructed to simulate realistic aviation operational conditions. By incorporating a comprehensive array of multidimensional features—including flight duration, route complexity, aircraft specifications, passenger demographic profiles, maintenance histories, seasonal fluctuations, and geospatial variations—we establish an unparalleled foundation for predictive modeling. Employing a sophisticated ensemble of machine learning methodologies, including advanced regression techniques, probabilistic classification algorithms, and hybrid predictive models, we achieved exceptional computational performance. Our regression models demonstrated extraordinary explanatory power, while classification models exhibited near-perfect risk assessment capabilities. The research presents several critical methodological innovations: (1) a novel synthetic data generation protocol that preserves statistical distributions and complex interdependencies, (2) advanced feature engineering and preprocessing techniques that enhance model interpretability and generalizability, and (3) a hybrid machine learning approach that integrates probabilistic reasoning with empirical predictive modeling. Our findings provide transformative, data-driven strategies for aviation inventory management, offering unprecedented insights into resource optimization, operational risk mitigation, and efficiency enhancement. The proposed framework not only advances academic understanding of complex inventory systems but also presents practical, implementable solutions for airline industry stakeholders seeking to leverage advanced analytical methodologies.