2025
Fekete, Tamas; Mengistu, Girum; Wicaksono, Hendro
Leveraging causal AI to uncover the dynamics in sustainable urban transport: A bike sharing time-series study Journal Article
In: Sustainable Cities and Society, vol. 122, pp. 106240, 2025.
Abstract | Links | BibTeX | Tags: artificial intelligence, causal AI, machine learning, sustainability, transportation
@article{nokey,
title = {Leveraging causal AI to uncover the dynamics in sustainable urban transport: A bike sharing time-series study},
author = {Tamas Fekete and Girum Mengistu and Hendro Wicaksono },
doi = {https://doi.org/10.1016/j.scs.2025.106240},
year = {2025},
date = {2025-03-15},
journal = {Sustainable Cities and Society},
volume = {122},
pages = {106240},
abstract = {The importance of developing sustainable urban transportation systems to protect the environment is increasingly recognized worldwide, particularly within the European Union. In the era of digitalization, data-driven approaches are crucial for informed decision-making. This study introduces a methodology leveraging causal artificial intelligence (causal AI) to uncover cause-and-effect relationships in urban transport data. Unlike traditional methods relying on correlations, causal AI identifies the true drivers of transport dynamics. A case study using MOL Bubi bike-sharing data from Budapest demonstrates how the PCMCI (Peter and Clark Momentary Conditional Independence) algorithm revealed complex temporal dependencies within the data, with temperature emerging as the strongest causal factor positively influencing bike usage. Additionally, the reopening of the Chain Bridge led to a 10.7% increase in bike trips, as quantified by Causal Impact analysis. This case study can be extended to more complex scenarios with unpredictable outcomes. The insights gained provide policymakers with a deeper understanding, enabling them to design policies fostering sustainable urban mobility. These results showcase the potential of causal AI to guide policies that enhance sustainable urban mobility.},
keywords = {artificial intelligence, causal AI, machine learning, sustainability, transportation},
pubstate = {published},
tppubtype = {article}
}
The importance of developing sustainable urban transportation systems to protect the environment is increasingly recognized worldwide, particularly within the European Union. In the era of digitalization, data-driven approaches are crucial for informed decision-making. This study introduces a methodology leveraging causal artificial intelligence (causal AI) to uncover cause-and-effect relationships in urban transport data. Unlike traditional methods relying on correlations, causal AI identifies the true drivers of transport dynamics. A case study using MOL Bubi bike-sharing data from Budapest demonstrates how the PCMCI (Peter and Clark Momentary Conditional Independence) algorithm revealed complex temporal dependencies within the data, with temperature emerging as the strongest causal factor positively influencing bike usage. Additionally, the reopening of the Chain Bridge led to a 10.7% increase in bike trips, as quantified by Causal Impact analysis. This case study can be extended to more complex scenarios with unpredictable outcomes. The insights gained provide policymakers with a deeper understanding, enabling them to design policies fostering sustainable urban mobility. These results showcase the potential of causal AI to guide policies that enhance sustainable urban mobility.
Jeong, Heonyoung; Fekete, Tamas; Bashyal, Atit; Wicaksono, Hendro
From Theory to Practice: Implementing Causal AI in Manufacturing for Sustainability Journal Article
In: Procedia Computer Science, vol. 253, pp. 1495-1504, 2025.
Abstract | Links | BibTeX | Tags: artificial intelligence, causal AI, causal inference, energy management, manufacturing, sustainability
@article{nokey,
title = {From Theory to Practice: Implementing Causal AI in Manufacturing for Sustainability},
author = {Heonyoung Jeong and Tamas Fekete and Atit Bashyal and Hendro Wicaksono },
url = {https://www.sciencedirect.com/science/article/pii/S1877050925002194},
doi = {https://doi.org/10.1016/j.procs.2025.01.211},
year = {2025},
date = {2025-02-25},
journal = {Procedia Computer Science},
volume = {253},
pages = {1495-1504},
abstract = {The use of AI in industry is increasingly popular, but its black-box nature poses decision-making challenges due to the lack of understanding of how variables influence each other. Causal AI addresses this by studying cause-and-effect relationships in the data. This paper explores applying causal AI in industry through a case study of CNC machines, which are significant in manufacturing and consume large amounts of energy. Industry 4.0 is transforming manufacturing, with CNC machines generating vast data analyzed by often opaque machine learning methods. Causal AI can uncover and quantify causal relationships between variables, aiding decision-making. Our case study uses CNC power consumption data to demonstrate causal AI in manufacturing, with existing models verifying our methodology. Future studies should extend our research to include variables without existing models, such as human habits. This case study serves as a starting point for other researchers, facilitating similar studies on complex data.},
keywords = {artificial intelligence, causal AI, causal inference, energy management, manufacturing, sustainability},
pubstate = {published},
tppubtype = {article}
}
The use of AI in industry is increasingly popular, but its black-box nature poses decision-making challenges due to the lack of understanding of how variables influence each other. Causal AI addresses this by studying cause-and-effect relationships in the data. This paper explores applying causal AI in industry through a case study of CNC machines, which are significant in manufacturing and consume large amounts of energy. Industry 4.0 is transforming manufacturing, with CNC machines generating vast data analyzed by often opaque machine learning methods. Causal AI can uncover and quantify causal relationships between variables, aiding decision-making. Our case study uses CNC power consumption data to demonstrate causal AI in manufacturing, with existing models verifying our methodology. Future studies should extend our research to include variables without existing models, such as human habits. This case study serves as a starting point for other researchers, facilitating similar studies on complex data.
2024
Nesro, Vahid Menu; Fekete, Tamas; Wicaksono, Hendro
Leveraging Causal Machine Learning for Sustainable Automotive Industry: Analyzing Factors Influencing CO2 Emissions Journal Article
In: Procedia CIRP, vol. 130, pp. 161-166, 2024.
Abstract | Links | BibTeX | Tags: causal AI, causal inference, sustainability
@article{nokey,
title = {Leveraging Causal Machine Learning for Sustainable Automotive Industry: Analyzing Factors Influencing CO2 Emissions},
author = {Vahid Menu Nesro and Tamas Fekete and Hendro Wicaksono},
url = {https://www.sciencedirect.com/science/article/pii/S2212827124012241},
doi = {https://doi.org/10.1016/j.procir.2024.10.071},
year = {2024},
date = {2024-11-27},
urldate = {2024-11-27},
journal = {Procedia CIRP},
volume = {130},
pages = {161-166},
abstract = {Integrating artificial intelligence (AI) and machine learning (ML) in the industry has become increasingly essential with the rise of Industry 4.0. These technologies can revolutionize product development, decision-making, and operational optimization in industrial processes. However, most modern ML tools focus on identifying associations between data points rather than causal relationships, a crucial limitation for industries. This paper explores the potential for causal machine learning to overcome this limitation. The investigation involves selecting a focus area within the automotive sector, analyzing a dataset, and modeling, identifying, and estimating causal associations. The chosen case study investigates the potential causes of CO2 emissions from vehicles, which is a critical area in terms of sustainability. Furthermore, the applied dataset is suitable for demonstrating the proposed approach as an alternative to engineering techniques that explain factors influencing CO2 emissions. In the future, a more detailed model based on the case study can help learn more about the potential causes of environmental harm caused by vehicles. This paper provides valuable insights into how this technology can be leveraged to optimize industrial processes and improve outcomes in reducing CO2 emissions in product creation processes to achieve environmental sustainability goals.
},
keywords = {causal AI, causal inference, sustainability},
pubstate = {published},
tppubtype = {article}
}
Integrating artificial intelligence (AI) and machine learning (ML) in the industry has become increasingly essential with the rise of Industry 4.0. These technologies can revolutionize product development, decision-making, and operational optimization in industrial processes. However, most modern ML tools focus on identifying associations between data points rather than causal relationships, a crucial limitation for industries. This paper explores the potential for causal machine learning to overcome this limitation. The investigation involves selecting a focus area within the automotive sector, analyzing a dataset, and modeling, identifying, and estimating causal associations. The chosen case study investigates the potential causes of CO2 emissions from vehicles, which is a critical area in terms of sustainability. Furthermore, the applied dataset is suitable for demonstrating the proposed approach as an alternative to engineering techniques that explain factors influencing CO2 emissions. In the future, a more detailed model based on the case study can help learn more about the potential causes of environmental harm caused by vehicles. This paper provides valuable insights into how this technology can be leveraged to optimize industrial processes and improve outcomes in reducing CO2 emissions in product creation processes to achieve environmental sustainability goals.
Prayitno, Kutut Aji; Wicaksono, Hendro
Leveraging Causal Machine Learning for Sustainable Automotive Industry: Analyzing Factors Influencing CO2 Emissions Journal Article
In: Procedia CIRP, vol. 130, pp. 1070-1076, 2024.
Abstract | Links | BibTeX | Tags: causal AI, logistics, ontologies, reinforcement learning, sustainability
@article{nokey,
title = {Leveraging Causal Machine Learning for Sustainable Automotive Industry: Analyzing Factors Influencing CO2 Emissions},
author = {Kutut Aji Prayitno and Hendro Wicaksono},
url = {https://www.sciencedirect.com/science/article/pii/S2212827124013659},
doi = {https://doi.org/10.1016/j.procir.2024.10.208},
year = {2024},
date = {2024-11-27},
urldate = {2024-11-27},
journal = {Procedia CIRP},
volume = {130},
pages = {1070-1076},
abstract = {Efficiently managing logistics operations is crucial in elevating sustainability and tackling the challenges urbanization brings in today’s urban environment. Collaborations among the public and private sectors in urban logistics are essential to minimize environmental impacts. This study aims to create a novel conceptual framework for collaborative logistics designed explicitly for sustainable metropolitan areas. The framework aims to enable collaborative data-driven sustainability optimization in urban logistics. It comprises ontologies to facilitate interoperability among stakeholders by providing a shared understanding of the exchanged data. The framework utilizes causal artificial intelligence to enable traceability and transparency of data-driven decisions compared to conventional machine learning working based on correlations. Furthermore, the framework also employs causal reinforcement learning that enables agents to learn what actions lead to targeted outcomes and why those actions are effective. The developed framework optimizes vehicle routes and conveyance selection while considering several operational constraints such as time windows, split-load scenarios, and commodity-specific requirements. Moreover, the system integrates the distinctive features of public transport networks. The suggested strategy minimizes fuel use and overall delivery costs, promoting a more sustainable logistics environment in metropolitan areas measured using Environmental, Social, and Governance (ESG) indicators. This study contributes to the theoretical understanding of collaborative logistics. It underscores the importance of environmental stewardship and societal well-being in logistics planning and implementation by utilizing a data-driven approach.
},
keywords = {causal AI, logistics, ontologies, reinforcement learning, sustainability},
pubstate = {published},
tppubtype = {article}
}
Efficiently managing logistics operations is crucial in elevating sustainability and tackling the challenges urbanization brings in today’s urban environment. Collaborations among the public and private sectors in urban logistics are essential to minimize environmental impacts. This study aims to create a novel conceptual framework for collaborative logistics designed explicitly for sustainable metropolitan areas. The framework aims to enable collaborative data-driven sustainability optimization in urban logistics. It comprises ontologies to facilitate interoperability among stakeholders by providing a shared understanding of the exchanged data. The framework utilizes causal artificial intelligence to enable traceability and transparency of data-driven decisions compared to conventional machine learning working based on correlations. Furthermore, the framework also employs causal reinforcement learning that enables agents to learn what actions lead to targeted outcomes and why those actions are effective. The developed framework optimizes vehicle routes and conveyance selection while considering several operational constraints such as time windows, split-load scenarios, and commodity-specific requirements. Moreover, the system integrates the distinctive features of public transport networks. The suggested strategy minimizes fuel use and overall delivery costs, promoting a more sustainable logistics environment in metropolitan areas measured using Environmental, Social, and Governance (ESG) indicators. This study contributes to the theoretical understanding of collaborative logistics. It underscores the importance of environmental stewardship and societal well-being in logistics planning and implementation by utilizing a data-driven approach.
Mechai, Nadhir; Wicaksono, Hendro
Causal Inference in Supply Chain Management: How Does Ever Given Accident at the Suez Canal Affect the Prices of Shipping Containers? Journal Article
In: Procedia Computer Science, vol. 232, pp. 3173–3182, 2024.
Abstract | Links | BibTeX | Tags: causal AI, causal inference, supply chain management
@article{mechai2024causal,
title = {Causal Inference in Supply Chain Management: How Does Ever Given Accident at the Suez Canal Affect the Prices of Shipping Containers?},
author = {Nadhir Mechai and Hendro Wicaksono},
url = {https://www.sciencedirect.com/science/article/pii/S1877050924003119},
doi = {https://doi.org/10.1016/j.procs.2024.02.133},
year = {2024},
date = {2024-09-20},
urldate = {2024-01-01},
journal = {Procedia Computer Science},
volume = {232},
pages = {3173–3182},
publisher = {Elsevier},
abstract = {In March 2021, the Ever Given, a colossal 4000-meter-long container ship with a capacity of 20,000 TEUs (Twenty-foot equivalent units), became lodged in the Suez Canal for six days, causing a significant disruption. This accident blocked approximately 400 ships, impacting not only the vessel itself and the canal but also global trade and the already strained global supply chain post-pandemic. Our research leverages causal inference techniques to rigorously assess and quantify the causal effects of the Ever Given accident on the World Container Index (WCI). We conducted experiments using time series data from eight major global shipping routes, achieving statistically significant results with a confidence level of 99.89%. This research conclusively demonstrates that the Ever Given incident at the Suez Canal had a substantial impact on shipping container prices, quantifying the effect as a remarkable 40% price increase post-exposure. By offering companies the ability to apply causal inference in understanding cause-and-effect dynamics within their supply chain networks, this study equips them with the knowledge needed to make well-informed decisions, especially in times of disruption, thus facilitating the optimization of their supply chain configuration and operations.
},
keywords = {causal AI, causal inference, supply chain management},
pubstate = {published},
tppubtype = {article}
}
In March 2021, the Ever Given, a colossal 4000-meter-long container ship with a capacity of 20,000 TEUs (Twenty-foot equivalent units), became lodged in the Suez Canal for six days, causing a significant disruption. This accident blocked approximately 400 ships, impacting not only the vessel itself and the canal but also global trade and the already strained global supply chain post-pandemic. Our research leverages causal inference techniques to rigorously assess and quantify the causal effects of the Ever Given accident on the World Container Index (WCI). We conducted experiments using time series data from eight major global shipping routes, achieving statistically significant results with a confidence level of 99.89%. This research conclusively demonstrates that the Ever Given incident at the Suez Canal had a substantial impact on shipping container prices, quantifying the effect as a remarkable 40% price increase post-exposure. By offering companies the ability to apply causal inference in understanding cause-and-effect dynamics within their supply chain networks, this study equips them with the knowledge needed to make well-informed decisions, especially in times of disruption, thus facilitating the optimization of their supply chain configuration and operations.
Ompusunggu, Agusmian P; Tjahjowidodo, Tegoeh; Wicaksono, Hendro
Causal AI-powered Digital Product Passports for enabling a circular and sustainable manufacturing ecosystem Proceedings Article
In: Cranfield University, 2024.
Abstract | Links | BibTeX | Tags: causal AI, causal inference, circular economy, digital product passport
@inproceedings{ompusunggua2024causal,
title = {Causal AI-powered Digital Product Passports for enabling a circular and sustainable manufacturing ecosystem},
author = {Agusmian P Ompusunggu and Tegoeh Tjahjowidodo and Hendro Wicaksono},
doi = {10.57996/cran.ceres-2579},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
publisher = {Cranfield University},
abstract = {Digital product passport (DPP) has been recently introduced by policymakers (e.g., the European Commission) to advance sustainable business practices towards a circular economy (CE). As a newly introduced concept, DPP is still relatively high-level and vague. Therefore, its definition, information flow architecture, what relevant information needs to be stored, and how to use such information in the context of a circular and sustainable manufacturing ecosystem, etc., are still open research questions. This paper addresses these research questions by proposing a novel conceptual framework for DPP, facilitating seamless information exchanges among CE stakeholders, and providing a transparent and trustworthy basis for decision-making. Causal AI utilisation is proposed to extract causal relationships among sustainability/circularity KPIs comprehensively, encompassing raw material supply chain, circularity-compliant product design, manufacturing optimisation on the shop floor, and after-sale product usage optimisation. Seamless information exchange will be achieved through semantic interoperability and a comprehensive model of the whole supply chain by employing an ontology model. The causal AI approach is proposed to identify causalities among KPIs and other factors to predict environmental impacts. This way, a causal model integrating domain expert knowledge and causality discovered from measured data will increase the transparency/explainability of prediction/decision made by machine learning algorithms.},
keywords = {causal AI, causal inference, circular economy, digital product passport},
pubstate = {published},
tppubtype = {inproceedings}
}
Digital product passport (DPP) has been recently introduced by policymakers (e.g., the European Commission) to advance sustainable business practices towards a circular economy (CE). As a newly introduced concept, DPP is still relatively high-level and vague. Therefore, its definition, information flow architecture, what relevant information needs to be stored, and how to use such information in the context of a circular and sustainable manufacturing ecosystem, etc., are still open research questions. This paper addresses these research questions by proposing a novel conceptual framework for DPP, facilitating seamless information exchanges among CE stakeholders, and providing a transparent and trustworthy basis for decision-making. Causal AI utilisation is proposed to extract causal relationships among sustainability/circularity KPIs comprehensively, encompassing raw material supply chain, circularity-compliant product design, manufacturing optimisation on the shop floor, and after-sale product usage optimisation. Seamless information exchange will be achieved through semantic interoperability and a comprehensive model of the whole supply chain by employing an ontology model. The causal AI approach is proposed to identify causalities among KPIs and other factors to predict environmental impacts. This way, a causal model integrating domain expert knowledge and causality discovered from measured data will increase the transparency/explainability of prediction/decision made by machine learning algorithms.