Yuanwei Qu

• Kamburjan, Eduard; Klungre, Vidar Norstein; Qu, Yuanwei; Schlatte, Rudolf; Kostylev, Egor V. & Giese, Martin [Show all 7 contributors for this article] (2026). Semantically Reflected Programs. Transactions on Graph Data and Knowledge (TGDK). 4(1), p. 3:1–3:52. doi: 10.4230/TGDK.4.1.3. Full text in Research Archive Show summary

  This paper addresses the dichotomy between the formalization of structural and the formalization of executable behavioral knowledge by means of semantically lifted programs, which explore an intuitive connection between imperative programs and knowledge graphs. While knowledge graphs and ontologies are eminently useful to represent formal knowledge about a system’s individuals and universals, programming languages are designed to describe the system’s evolution. To address this dichotomy, we introduce a semantic lifting of the program states of an executing progam into a knowledge graph, for an object-oriented programming language. The resulting graph is exposed as a semantic reflection layer within the programming language, allowing programmers to leverage knowledge of the application domain in their programs during execution. In this paper, we formalize semantic lifting and semantic reflection for a small imperative programming language, SMOL, explain the operational aspects of the language, and consider type correctness and virtualization for runtime program queries through the semantic reflection layer. We illustrate semantic lifting and semantic reflection through a case study of geological modeling and discuss different applications of the technique. The language implementation is open source and available online.

• Qu, Yuanwei; Waaler, Arild Torolv Søetorp; Torabi, Anita & Zhou, Baifan (2025). Challenges and Approach: AI for Digitalised Carbon Storage Analysis. CEUR Workshop Proceedings. 3975. Full text in Research Archive Show summary

  Carbon Capture and Storage (CCS) plays an essential role in mitigating climate change. A comprehensive CO2 storage analysis is key to CCS success, however, its advancement is hindered by interdisciplinary complexities, data fragmentation, and the need for enhanced transparency. This paper presents ongoing work in an integrated digitalisation framework for CO2 storage analysis that addresses three major challenges: knowledge complexity across geosciences, reservoir engineering, and computer science; the heterogeneous, multi-scale nature of geological data; and the requirement for explainable decision-making in high-risk subsurface storage scenarios. Our approach leverages both symbolic AI and generative AI. On the symbolic AI side, it includes ontologydriven knowledge engineering to harmonise domain-specific terminologies, and employs a layered information modelling and data integration system to standardise diverse datasets. Additionally, a generative AI-powered query and explanation system provides context-aware, transparent analyses. This framework aims to streamline multidisciplinary collaboration and enhance the accountability and reliability of long-term CO2 storage, thereby supporting the transition to a carbon-neutral future

• Zhou, Yan; Zhou, Baifan; Li, Huajian; Lyu, Qianhang; Qu, Yuanwei & Waaler, Arild Torolv Søetorp [Show all 7 contributors for this article] (2025). Dataset for Industrial Question Answering with Explanation and Scalable Ensemble Generation. In Long, Guodong; Blumestein, Michale & Chang, Yi (Ed.), WWW '25: Companion Proceedings of the ACM on Web Conference 2025. Association for Computing Machinery (ACM). ISSN 9798400713316. p. 825–828. doi: 10.1145/3701716.3715310. Full text in Research Archive Show summary

  The digital and green transition under Industry 4.0 has accelerated the adoption of AI in industries such as manufacturing, energy, and mining. Question Answering with Explanation (QAE), as a way of human interaction with AI, is crucial for enhancing transparency and trust in high-stakes industrial applications. However, industrial QAE remains underexplored due to the lack of publicly available, high-quality datasets, hindered by the need for expert effort and corporate restrictions. To this end, we introduce PANDAX ( https://doi.org/10.5281/zenodo.14510798 ), the first open-source industrial QAE dataset, and SEG, a scalable method for generating high-quality QAE datasets using LLMs. PANDAX focuses on three key topics of industrial system information: partonomy, functionality, and parameters, across critical domains such as green technology and cooling systems. SEG ensures scalability and quality through ensemble generation, majority voting, expert ranking, etc. The human evaluation validates PANDAX's high quality, positioning it as a valuable resource for advancing QAE techniques, benchmarking language technologies, and supporting research in explainable AI for industrial systems.

• Qu, Yuanwei; Kamburjan, Eduard; Torabi, Anita & Giese, Martin (2024). Semantically triggered qualitative simulation of a geological process. Applied Computing and Geosciences. 21. doi: 10.1016/j.acags.2023.100152. Full text in Research Archive
• Qu, Yuanwei; Perrin, Michel; Torabi, Anita; Abel, Mara & Giese, Martin (2023). GeoFault: A well-founded fault ontology for interoperability in geological modeling. Computers & Geosciences. ISSN 0098-3004. 182. doi: 10.1016/j.cageo.2023.105478. Full text in Research Archive Show summary

  Geological modeling currently uses various computer-based applications. Data harmonization at the semantic level using ontologies is essential to make these applications interoperable. Since geo-modeling is part of several multidisciplinary projects, interoperability requires semantic harmonization to exchange information between geological applications and integrate other domain knowledge at a general level. Therefore, domain ontologies that describe geological knowledge must be based on a sound ontological background to ensure this knowledge is integrable. Faults are essential for understanding and solving structural problems but are complex to model because the concept of fault includes a group of geological entities with a distinct ontological nature. A fault can correspond to thin, deformed rock volumes or spatial arrangements resulting from the displacement of geological blocks, but at a broader scale, geologists describe faults as surfaces or components of complex fault arrays. Our work intends to harmonize these views by presenting a domain ontology, GeoFault, resting on the Basic Formal Ontology (BFO) and the GeoCore ontology. GeoCore and GeoFault support the parametric description of geological sites as a preliminary step for quantitative and qualitative analysis. We have proposed GeoFault after systematically revising the literature and several knowledge-acquisition sessions with expert structural geologists. The ontology formalizes a vocabulary for fault “sensu stricto,” excluding ductile shear deformations. It covers the regional to outcrop scales, excluding structures at the microscopic, orogenic, and tectonics scales, and it avoids interpretive language associated with geological processes as far as possible. Extending the BFO and GeoCore ontologies allows the fault concept to be related to formal ontological classes in a consistent semantic-rich framework. The ontology artifact is implemented in OWL 2, validated by competency questions with two use cases, and tested using an in-house ontology-driven data entry application. The GeoFault ontology is publicly available and provides a solid framework for clarifying fault knowledge and a foundation for many applications.

• Qu, Yuanwei; Zhou, Baifan; Waaler, Arild Torolv Søetorp & Cameron, David B. (2023). Real-Time Event Detection with Random Forests and Temporal Convolutional Networks for More Sustainable Petroleum Industry. In Liu, Fenrong; Sadanandan, Arun Anand; Pham, Duc Nghia; Mursanto, Petrus & Lukose, Dickson (Ed.), 20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023 (PRICAI 2023): Trends in Artificial Intelligence. Springer. ISSN 9789819970247. p. 466–473. doi: 10.1007/978-981-99-7025-4_41. Full text in Research Archive Show summary

  The petroleum industry is crucial for modern society, but the production process is complex and risky. During the production, accidents or failures, resulting from undesired production events, can cause severe environmental and economic damage. Previous studies have investigated machine learning (ML) methods for undesired event detection. However, the prediction of event probability in real-time was insufficiently addressed, which is essential since it is important to undertake early intervention when an event is expected to happen. This paper proposes two ML approaches, random forests and temporal convolutional networks, to detect undesired events in real-time. Results show that our approaches can effectively classify event types and predict the probability of their appearance, addressing the challenges uncovered in previous studies and providing a more effective solution for failure event management during the production.

• Qu, Yuanwei; Kamburjan, Eduard & Giese, Martin (2023). A Geological Case Study on Semantically Triggered Processes. In Pesquita, Catia; Jimenez-Ruiz, Ernesto; McCusker, Jamie; Faria, Daniel; Dragoni, Mauro; Dimou, Anastasia; Troncy, Raphaël & Hertling, Sven (Ed.), The Semantic Web: 20th International Conference, ESWC 2023, Hersonissos, Crete, Greece, May 28–June 1, 2023, Proceedings. Springer. ISSN 9783031334559. Full text in Research Archive

View all works in NVA

• Rainaud, Jean-François; Perrin, Michel; Qu, Yuanwei & Abel, Mara (2024). Converting the Geology Knowledge Model Embedded in RESQML into a Well-Conformed Domain Ontology. Full text in Research Archive
• Qu, Yuanwei & Cordeiro, Fábio Corrêa (2023). Term Frequency Analysis for Semantic Modeling of Geological Fault Knowledge in the Energy Industry. Full text in Research Archive
• Qu, Yuanwei; Zheng, Zhuoxun; Zhou, Baifan; Zhou, Yan; Santos, Nicolau & Savkovic, Ognjen [Show all 8 contributors for this article] (2023). Towards Data Integrity Verification for More Sustainable Petroleum Industry. Full text in Research Archive
• Qu, Yuanwei (2022). Geological Information Capture with Sketches and Ontologies. Full text in Research Archive
• Qu, Yuanwei; Zhou, Baifan; Kharlamov, Evgeny & Giese, Martin (2022). Industrial Geological Information Capture with GeoStructure Ontology. Full text in Research Archive Show summary

  Understanding geological structures plays an essential role in a wide range of industries. Various tools and software have been developed to support the observation and characterisation of the geological structures and they produce a large volume of heterogeneous data. Thanks to the development of semantic technologies, plenty of works have investigated industrial geological data. In contrast, geological sketches, figure interpretations, and illustrations as the initial data collection and analysis steps have received little attention. Most structure information is still reported as PDF files with forms, tables, and raster images with interpretations. We attempt to fill this gap by providing an ontology- based industrial geological information capture method to allow users to input and store structure information formally. Following users’ sketches, the corresponding knowledge graphs will be generated. This work aims to make the first-hand geological structure information findable, accessible, interoperable, reusable (FAIR), and to support qualitative information reasoning, from a user-driven perspective, and to meet the needs of digitised industry.

View all works in NVA