Tag: artificial-intelligence

Call for Publication: 3D Documentation of Natural and Cultural Heritage

https://www.mdpi.com/topics/554674P4Q3

Dear Colleagues,

The definition of tangible cultural heritage is wide and includes, but is not limited to, landscapes, built heritage, cities, territories, archaeological sites, minor historical centres, urban environments, cities, suburbs, villages, and hamlets (Article 1 of the UNESCO World Heritage Convention). It is widely accepted that the accurate spatial documentation (from 3D integrated metric surveys or from harmonised geospatial datasets) of these assets is crucial for preservation, restoration, historical analysis, revitalisation, and various other applications. Moreover, such 3D documentation could help, with its high accuracy, highly detailed datasets, or multiscale geodatabases, in planning processing involving different stakeholders, citizens, and local communities.

The proposed Topic will deal with advanced spatial documentation techniques, both 2D and 3D, leveraging contemporary geomatics technologies, GeoAI, 3D city models, and Digital Twins. Several specific documentation techniques can be used to achieve accurate and complete documentation of CH including, but not limited to, the following:

  • Unmanned Aerial Systems (UASs) for high-resolution aerial data acquisition using different sensors (e.g., RGB, thermal, multispectral data) and techniques (e.g., aerial imagery and photogrammetry with the aim to create detailed 2D products and 3D models);
  • Terrestrial Laser Scanning (TLS) and MMS (Mobile Mapping System) generating 3D point clouds with different degrees of accuracy and levels of detail;
  • Creation and publication of geodatabase from cartographic dataset of national geoportals (standards compliant with geographic information standards);
  • GeoAI approaches that use artificial intelligence to analyse, classify, and interpret geospatial data for cultural heritage applications;
  •  Novel technology for the metric documentation of CH.

For the application of these geomatics techniques to CH documentation, the following specific aims are considered in this Topic:

  • Provide precise and detailed 2D and 3D metric documentation (by means of geomatics techniques acquisitions and approaches) of cultural heritage assets;
  • Enable various analyses through the application of modern geomatics techniques and GeoAI;
  • Facilitate the creation and use of Digital Twins for cultural heritage sites;
  • Support diverse applications, including risk assessment, restoration planning, and heritage management;
  • Use the documentation to deal with possible scenarios like risk management, urban planning, sustainable plans, regulatory plans, restoration actions, etc.

We are targeting contributions that achieve the following:

  • Present case studies demonstrating the successful application of 2D and 3D metric documentation techniques in cultural heritage;
  • Explore innovative methods and technologies for spatial documentation;
  • Discuss the integration of documentation data into various analytical and application frameworks;
  • Analyse the impact of advanced spatial documentation on risk assessment, restoration planning, and heritage management.

This Topic highlights the importance of advanced spatial documentation in cultural heritage, with the aim of supporting independent researchers, professionals, and national public and private entities in its management, conservation, study, and promotion. By integrating cutting-edge geomatics techniques, GeoAI, and Digital Twins, this research will provide new insights and methodologies for comprehensive documentation, facilitating the various applications crucial for preserving and managing cultural heritage.

Furthermore, the proposed Topic seeks to advance the understanding and application of the available documentation approaches for Cultural Heritage. By fostering interdisciplinary research and collaboration, this Topic also aims to contribute to the development of innovative solutions for the preservation and management of cultural heritage sites, ensuring their protection and appreciation for future generations.

Dr. Lorenzo Teppati Losè
Dr. Elisabetta Colucci
Dr. Arnadi Dhestaratri Murtiyoso
Topic Editors

PhD Studentship: Al and Behavioral Modelling – Using Artificial Intelligence and Machine Learning for Underwater Archaeology

University of Bradford

https://www.jobs.ac.uk/job/DPR640/phd-studentship-al-and-behavioral-modelling-using-artificial-intelligence-and-machine-learning-for-underwater-archaeology

Application Deadline: 28 January 2026

Project Supervisors:

Prof Vincent Gaffney
Dr Andrew Fraser

Project Description:

The University of Bradford is inviting applications for a PhD studentship in Archaeological Sciences, funded through the ERC Synergy Subnordica project. The student would be based at the Submerged Landscapes Centre, in the School of Archaeological and Forensic Sciences, at the University of Bradford.

This PhD studentship is integrated into work package 5 of the ERC Synergy Subnordica Project, which will combine data from across the entire project into a set of predictive models for comparative analysis across case study regions. The successful candidate will work on the development and application of AI/Machine learning and behavioural modelling within the North and Baltic seas, utilising legacy and new data collected as part of the wider project. The candidate will work closely with the wider Subnordica team, and our partners, in order to integrate data across a number of case study areas.

The successful candidate will start this project in June 2026.

The candidate should hold a masters, (or due for completion before the intended start), in a related discipline. Furthermore a background in machine learning/AI, geoarchaeology, environmental science, or computer science would be beneficial, but is not required, depending on equivalent experience.

Funding notes:

This project is funded by the European Research Council (ERC). The successful applicant will be awarded a studentship, which will cover Home tuition fees, plus an annual tax-free stipend of at least £20,780 per year.

Funding for:

UK Students

Enquiries email name and address:  

For informal enquiries, please contact research@bradford.ac.uk

How to apply:

Formal applications can be submitted via the University of Bradford web site. Applicants should register an account, and include the project title on the Research Proposal section.

PhD Student Position in Geospatial Machine Learning: Texas A&M University

Dr. Leila Character is seeking a creative problem solver PhD student to join her lab at Texas A&M University, Department of Geography, starting in Fall 2026.

The successful candidate will work on projects closely aligned with Dr. Character’s expertise, focusing on collection, manipulation, and preprocessing of remotely sensed and training data to enable production of new information; development and application of deep learning models for object detection and segmentation using high-resolution remotely sensed data; and geospatial and spatial statistical analyses.

Potential research areas include:

• Environmental Monitoring: Advancing methods for the detection, characterization, and modeling of natural and ecological phenomena with applications in the identification of environmental features, assessment of ecological health, and spatial characterization of terrestrial and marine environments.

• Geospatial Intelligence: Developing approaches for a diverse set of problems related to automatic target recognition (ATR), including remote sensing data collection, preprocessing, and fusion; machine learning model development and implementation; and human-in-the-loop decision-making systems.

• Archaeological Machine Learning: Developing deep learning and remote sensing approaches for the detection, mapping, and analysis of archaeological and cultural heritage features in terrestrial and underwater environments; integrating data from lidar, sonar, and other sensing modalities to advance heritage preservation, landscape analysis, and repatriation efforts.

The student’s research will leverage diverse datasets and state-of-the-art machine learning frameworks contributing to both theoretical advancements and real-world problem-solving. There may also be a significant fieldwork component for data collection and ground-truthing.

Required Qualifications:

• Bachelor’s degree in Geography, Environmental Science, Computer Science, or related field.

• Ability to work on projects funded by the Department of Defense (DOD)

• Strong skills in Geographic Information Systems (GIS) software (e.g., ArcGIS Pro, QGIS) and remote sensing data processing and analysis.

• Interest in exploring and developing machine learning and deep learning models using Python, and willingness to work hard to develop these skills.

• Excellent analytical, problem-solving, and communication skills (written and oral).

• A strong interest in interdisciplinary research and the application of advanced geospatial techniques to complex real-world problems.

Preferred Qualifications:

• Demonstrated proficiency in Python programming for machine learning (e.g., TensorFlow, Keras, PyTorch, Scikit-Learn).

• Experience with and understanding of deep learning and other machine learning algorithms for feature detection.

• Master’s degree in Geography, Environmental Science, Computer Science, or related field.

Application Instructions:

Interested candidates are strongly encouraged to review Professor Character’s CV and recent publications to understand the scope and nature of the lab’s research.

To express interest, please send an email to leilacharacter@tamu.edu with the subject line “PhD Application – Geospatial Machine Learning” including:

1. Your Curriculum Vitae (CV).

2. A short statement of interest (a couple of paragraphs in the email) outlining your research experience, your specific interests that align with Professor Character’s work, and

  • your long-term academic and career goals.