We welcome PhD candidate Alessia Brucato, from the University Bari Aldo Moro – Department of Ricerca e Innovazione Umanistica and the Instituto di Scienze del Patrimonio Culturale (ISPC) of the Consiglio Nazionale delle Richerche (CNR), who will be staying with us for 6 months to train on the application of the computational methods developed in GIAP (ICAC) (see references at the end of this post).
During her stay, she will be supervised and trained by Prof. Hèctor A. Orengo (ICREA Research Professor) and Arnau Garcia-Molsosa (Ramón y Cajal Researcher), with the support of the rest of the computational team and the collaboration of Felipe Lumbreras from the Computer Vision Centre (CVC-UAB)
We hope she has a productive and enjoyable stay with us!
About Alessia and her research:
“Since my M.A. studies at the Alma Mater Studiorum University of Bologna (UNIBO), my research interests have turned to the field of Prehistory and Protohistory and to the semi-arid and extremely arid environments of the Near East and North Africa, participating in international archaeological research missions in Egypt with the Aswan Kom Ombo Archaeological Project (AKAP – UNIBO) and with Yale University (YALE), and in Ethiopia with the University of California Los Angeles (UCLA). In those missions, in addition to the standard fieldwork activities, I was able to develop and experiment with digital survey techniques and computational analyses of the results through photogrammetry systems, 3D modeling, and GIS.
The desire to look at archaeological contexts from a broader perspective, intertwined with the paleoenvironment and the mobility/sedentarization phenomena of prehistoric and protohistoric groups in North Africa, led me to study many remote sensing and computational approaches to various kinds of archaeological data. Among these, satellite imagery has proved extremely promising but also vast, dense, and complex to manually collect, filter and classify to investigate specific archaeological features. Consequently, I also decided to delve into the study of automatic and semi-automatic image analysis and classification via machine and deep learning approaches.
In 2021, driven by these interests, I formulated a Ph.D. research project, with which I won a scholarship in the Doctoral Program of Mediterranean Archaeological, Historical, Architectural and Landscape Heritage (PASAP_Med), held at the University of Bari Aldo Moro (UNIBA), in collaboration with the Institute of Cultural Heritage Sciences of the National Research Council of Italy (CNR ISPC) and directed by Prof. Giuliano Volpe.
The project title is “The eye of the machine in the time of travel: application of machine learning algorithms to satellite datasets for the detection of potential new archaeological sites related to the mobility of prehistoric and protohistoric groups. Case studies between Southern Italy and the Sahara” and it is supervised by Dr. Giulio Lucarini, CNR ISPC Researcher; Dr. Nicola Masini, CNR ISPC Research Executive and Head of the Potenza office; Dr. Giuseppe Scardozzi, CNR ISPC Research Executive and Head of the Lecce office. This research also benefits from the collaboration and supervision of Dr. Hector A. Orengo, Ramón y Cajal Researcher (R3) and Co-Director of the Landscape Archaeology Research Group of the Catalan Institute of Classical Archaeology (GIAP ICAC); Dr. Arnau Garcia-Molsosa, Beatriu de Pinós – Marie Curie co-fund Postdoctoral Researcher (R2) of the GIAP ICAC; Dr. Nicolò Taggio of the Italian company Planetek Italia s.r.l.
The archaeological features studied in this project are:
- a specific kind of hut foundation (Slab Structure) present in the Holocene proto-settlements (7th-6th mill. B.C.) of the Egyptian Western Desert oases (Farafra, Dakhlah, Kharga); they were built by the hunters-gatherers/early-herders inhabiting the regions during major environmental and climate changes;
- the Key-Hole (Key-Hole) and Antenna “Tumuli” of the Central and Western Sahara, built by Pre-Garamantian pastoral communities of the Middle Holocene (4th-2nd mill. BCE), which crossed on various trajectories all the North African region during its desertification process;
- some Early Neolithic settlements (V-IV mill. B.C.) of the central Mediterranean islands, built by local communities as consequences to multiple cultural and paleo-environmental conditions; they are sporadic sites compared with the rock shelters and other forms of encampment.
The research materials consist of the following:
- Digitized archaeological records and study materials;
- Geolocation of sites of interest;
- Panchromatic, RGB, SAR, Multi-Spectral, DEM satellite images.
The methodology used is based on automatic and semi-automatic detection approaches of these structures on satellite imagery and then the analysis of their spatial distribution:
- application of statistical filters and image enhancers;
- identification of proxy indicators in the archaeological record and satellite images;
- automatic and semi-automatic classification of satellite images;
- spatial analyses.
In the future, the results of this study will be submitted to other archaeological approaches for a broader understanding of the mobility patterns of these prehistoric groups.”
Translated and adapted from: https://www.ispc.cnr.it/en/2022/12/17/the-eye-of-the-machine-in-the-time-of-travel/
Funded by: PON R&I 2014-2020 (CCI2014IT16M2OP005) on additional ESF REACT-EU (Action 4 Innovation) resources.
- Berganzo-Besga, I.; Orengo, H.A.; Canela, J.; Belarte, M.C. Potential of Multitemporal Lidar for the Detection of Subtle Archaeological Features under Perennial Dense Forest. Land 2022, 11, 1964. https://doi.org/10.3390/land11111964
- Berganzo-Besga, I., Orengo, H.A., Lumbreras, F., Aliende, P., N. Ramsey, M. 2022. Automated detection and classification of multi-cell Phytoliths using Deep Learning-Based Algorithms. Journal of Archaeological Science https://doi.org/10.1016/j.jas.2022.105654
- Garcia-Molsosa, A., Orengo, H.A., Lawrence, D., Philip, G., Hopper, K., Petrie, C.A. 2021. Potential of deep learning segmentation for the extraction of archaeological features from historical map series. Archaeological Prospection, vol 28-2. https://doi.org/10.1002/arp.1807
- Orengo, H.A. and Petrie, C.A. 2017. Large-scale, multi-temporal remote sensing of palaeo-river networks: a case study from northwest India and its implications for the Indus Civilisation. Remote Sensing, 9(7): 735. https://doi.org/10.3390/rs9070735
- Orengo, H.A. and Petrie, C.A. 2018. Multi-Scale Relief Model (MSRM): a new algorithm for the visualisation of subtle topographic change of variable size in digital elevation models. Earth Surface Processes and Landforms, 43(6): 1361-9. https://doi.org/10.1002/esp.4317
- Conesa, F.C., Orengo, H.A., Lobo, A., Petrie, C.A. 2023. An Algorithm to Detect Endangered Cultural Heritage by Agricultural Expansion in Drylands at a Global Scale. Remote Sens. 2023, 15, 53. https://doi.org/10.3390/rs15010053
- Orengo, H.A. and Garcia-Molsosa, A. 2019. A brave new world for archaeological survey: automated machine learning-based potsherd detection using high-resolution drone imagery. Journal of Archaeological Science, 112: 105013. https://doi.org/10.1016/j.jas.2019.105013
- Orengo, H.A.; Garcia-Molsosa, A.; Berganzo-Besga, I.; Landauer, J.; Aliende, P. and Tres-Martínez, S. 2021. New developments in drone-based automated surface survey: towards a functional and effective survey system. Archaeological Prospection. https://doi.org/10.1002/arp.1822
Links of interest: