Lorenzo Cardarelli | Università degli Studi "La Sapienza" di Roma (original) (raw)

Uploads

Thesis Chapters by Lorenzo Cardarelli

Research paper thumbnail of Produzione vascolare dal contesto cultuale del Monte Cimino (Soriano nel Cimino - Vt) e il Bronzo finale in Etruria meridionale

Papers by Lorenzo Cardarelli

Research paper thumbnail of From fragments to digital wholeness: An AI generative approach to reconstructing archaeological vessels

Journal of Cultural Heritage, 2024

Reconstructing archaeological vessels from their fragments is a complex task that requires a long... more Reconstructing archaeological vessels from their fragments is a complex task that requires a long investment of time as well as in-depth knowledge of specific archaeological material. This paper proposes a framework based on generative artificial intelligence to reconstruct the entire vessel from a fragment. The proposed framework is based on a fragment simulation mechanism and the combination of three different deep learning models that position, reconstruct, and post-process the fragment to obtain a readyto-use reconstruction. The method is applied as a case-study to a dataset of six Italian Bronze and Early Iron Age burial contexts, including about 40 0 0 complete vessels and over 400 actual fragments. The results are evaluated using statistical metrics and expert human evaluation, showing promising results. The proposed method is a positive application of generative artificial intelligence in archaeology and provides a solution to the use of fragments in the digital and computational analysis of ceramics. The dataset, as well as the code used and the analytical pipeline, are fully available in the supplementary materials.

Research paper thumbnail of CQARCHAEO: A PYTHON PACKAGE FOR COSINE QUANTOGRAM ANALYSIS AND MONTE CARLO SIMULATIONS

Archeologia e Calcolatori, 2024

Cosine Quantogram Analysis (CQA) is a statistical analysis employed in archaeology for the study ... more Cosine Quantogram Analysis (CQA) is a statistical analysis employed in archaeology for the study of numerical datasets with hypothesized quantal distribution. To verify thesignificance of the results, the analysis is often combined with the execution of Monte Carlo simulations. In this article, we present a freely downloadable Python package (CQArchaeo) that integrates CQA and Monte Carlo simulations in the same environment, making the analysis customizable in the main parameters. We provide a guide that enables the use of this tool even for researchers with limited experience in Python programming and demonstrate the applicability, functioning, and main limitations of the analysis on some archaeological datasets.

Research paper thumbnail of The Late Bronze Age hilltop site of Monte Croce Guardia in the context of Bronze Age and Early Iron Age settlement organization in Peninsular Italy

Origini, 2023

The site of Monte Croce Guardia offers a unique opportunity to investigate the spatial organizati... more The site of Monte Croce Guardia offers a unique opportunity to investigate the spatial organization of a Final Bronze Age settlement in peninsular Italy. Data from new excavations and geophysical surveys are presented, focusing on the distribution of identified dwellings. This distribution is explored and compared with that of coeval sites such as Sorgenti della Nova and Sovana. An organizational pattern based on groups of huts, likely related to family groups, emerges from the analysis. The described model is further compared with several settlements and buildings dating from the Bronze Age to the Early Iron Age, across continental Italy, particularly focusing on the area south of the Po river.

Research paper thumbnail of Traditional and digital typologies compared: the example of Italian protohistory

Origini, 2023

The study of material culture, particularly ceramics, is an important aspect of archaeology. The ... more The study of material culture, particularly ceramics, is an important aspect of archaeology. The classification and typology of ceramics is often a key focus, with traditional methods based on the observation of specific morphological characteristics and the creation of taxonomies based on these types. However, recent advances in digital technologies and the use of Machine Learning have led to the development of new, digital approaches to ceramic classification. These approaches rely on statistical methods and computer science techniques to quantify vessel morphology and create multivariate datasets. The aim of this study is to compare a traditional approach elaborated by Renato Peroni and applied by many of his students, especially in the field of Italian protohistory, with a proposed digital method of ceramic classification. The comparison will be conducted using a database of approximately 1400 records from several Italian Bronze and Iron Age funerary contexts, including Casinalbo and other contexts in the Po Valley and northern Italy, as well as Pianello di Genga and Torre Galli. The proposed digital approach involves a combination of a non-linear dimensionality reduction algorithm and density-based clustering for the automated classification of ceramics. The study will consider the similarities and differences between the two methods and the potential for combining them in a complementary manner. The results of the study will provide a deeper understanding of traditional typologies and explore the potential for digital methods to enhance, improve, and complement them.

Research paper thumbnail of Defining Southern Etruria Final Bronze Age settlement models using an integrated GIS and Machine Learning approach

Archeologia e Calcolatori, 2023

This research aims to use quantitative and repeatable GIS techniques, as well as Machine Learning... more This research aims to use quantitative and repeatable GIS techniques, as well as Machine Learning algorithms, to study the settlement patterns in Southern Etruria during the final phase of the Bronze Age (1150-950/925 BC). The region of Southern Etruria is located in present-day Latium, Tuscany, and Umbria. The study, which includes 166 settlements, focuses on identifying the morphological characteristics of these settlements by means of raster analysis. Using a Machine Learning approach, the research will compare real settlements with random points within the region to understand the specific characteristics of the settlement pattern in the landscape. The study will also examine the use of feature selection and features importance methods to select the most significant features of a multivariate dataset.

Research paper thumbnail of Money or ingots? Metrological research on pre-contact Ecuadorian “axe-monies”

Journal of Archaeological Science: Reports, 2023

The so-called “axe-monies”, trapezoidal sheet metal objects made of arsenical copper alloy, are a... more The so-called “axe-monies”, trapezoidal sheet metal objects made of arsenical copper alloy, are associated with graves and hoards of the Mante ̃no-Huancavilca (AD 600–1532) and Milagro-Quevedo (AD 400–1532) cultures, both located on the southern coast of Ecuador. Historically, scholars identified these artifacts as money, relating
them to a currency system. This paper aims to test this hypothesis by investigating the degree of standardization (if any) through analyzing an important sample of these objects. Metrological analysis of their dimensions (length, width) and weight show that the currency hypothesis is flawed because neither clustering of dimensions nor a tendency towards a single (range of) weight value(s) is found. We suggest that the axe-monies may have been used as ingots, for arsenical copper alloys were a key commodity in the framework of exchange involving different cultures across America’s Pacific coast.

Research paper thumbnail of Dimensionality reduction for data visualization and exploratory analysis of ceramic assemblages

Archeologia e Calcolatori, 2022

Dimensionality reduction algorithms are essential in the study of multivariate datasets. Many var... more Dimensionality reduction algorithms are essential in the study of multivariate datasets. Many variables make it difficult to visualize data. In Archaeology, this problem often concerns the study of some variables, which can be quantitative or qualitative. In this article, several methods for dimension reduction are applied to a pottery dataset from the protohistoric necropolis Osteria dell’Osa, located 20 km East of Rome. These methods offer the possibility of visualising and analysing large amount of data in a very short time. Our results show that non-linear and non-parametric algorithms such as t-SNE and UMAP are the best choice for visualising and exploring this type of data.

Research paper thumbnail of Money or ingots? Metrological research on pre-contact Ecuadorian ‘axe-monies’

The Axe-monies, trapezoidal sheet objects made of arsenical copper, are associated with graves an... more The Axe-monies, trapezoidal sheet objects made of arsenical copper, are associated with graves and hoards of the Manteño-Huancavilca (600–1532 A.D) and Milagro-Quevedo (400–1532 A.D.) cultures, both located in the coast of Ecuador. Historically, scholars identified these artifacts as monies, relating them to a currency system. This paper aims to test this hypothesis by searching for standardization analyzing an important sample of these objects. Metrological analyses on dimensions (length, width) and weight show that the currency hypothesis is flawed because neither apparent clustering of dimensions nor a tendency to a single (range of) weight value(s) is found. We suggest ‘axe-monies’ were used as ‘ingot-objects’ and copper was a commodity in the framework of exchanges involving different cultures throughout America's Pacific coast.

Research paper thumbnail of A deep variational convolutional Autoencoder for unsupervised features extraction of ceramic profiles. A case study from central Italy

Journal of Archaeological Science, 2022

The need for a quantitative approach to the morphologic study of ceramics is becoming increasingl... more The need for a quantitative approach to the morphologic study of ceramics is becoming increasingly evident. Ceramics are the most common material in many archaeological sites and a huge amount of data has accumulated over time. This data can be handled by Machine Learning algorithms which are rapidly gaining popularity in archaeology. Although most approaches can be referred to classification tasks, in this contribution a particular type of Neural Network is proposed for feature extraction from archaeological ceramics. Through this proposed method it is possible to gain a numerical weighted representation of the pottery profile that can be used for multivariate analyses. The case study will focus on regionalisation processes in pottery production between the end of the 2nd millennium BC and the first half of the 1st millennium BC in central Tyrrhenian Italy, a period that saw major transformations in the cultural and socio-political structure of Ancient Italy. The results seem to confirm the regionalisation hypothesis and offer interesting insights into the quantitative study of archaeological ceramics.

Research paper thumbnail of Capienza delle forme vascolari, da un metodo open source all’uso di modelli regressivi: il caso dell’insediamento protostorico del Monte Cimino

Archeologia e Calcolatori, 2020

The volume of ceramic vessels provides several information about their use. However, due to the f... more The volume of ceramic vessels provides several information about their use. However, due to the fragmentation of pottery coming from settlement sites, data concerning the volume are rarely published. The first goal of this paper is presenting a new method to calculate the volume starting from the archaeological drawings. The dataset could be extended with a predictive regression analysis. The sample analyzed involves cups and bowls found on the top of Monte Cimino (Viterbo-Italy), a settlement and cult site dated to the Final Bronze Age (ca. 1150-950/925 BC).

Books by Lorenzo Cardarelli

Research paper thumbnail of Morphological variability and standardisation of vessel shapes in the 2nd and first half of the first millennium BC in continental Italy A data science and machine learning project for the quantitative study of archaeological ceramic profiles

Viola = titolo in c.po 18 + due a capo vuoti e poi cominciare con il testo Nero = testo in c.po 1... more Viola = titolo in c.po 18 + due a capo vuoti e poi cominciare con il testo Nero = testo in c.po 11 con interlinea singola (ma nel layout del Paragrafo è tutto già impostato). Ogni capoverso ha già rientro impostato. Verde = brevi testi in epigrafi/citazioni allinenati a destra in corsivo, in c.po 10, se riportati di lunghi testi vanno, con rientro impostato, in c.po 10 Rosso = richiami alle figure Arancione = indica che prima di inserire una immagine si richiede un a capo vuoto e così dopo la didascalia Azzurro = didascalia come indicato (in c.po 11) possibilmente centrata sotto l'immagine Se un capitolo finisce a pagina dispari aggiungere sempre la pagina pari bianca successiva. Ogni capitolo deve ricominciare con una pagina dispari 18 8 Volume pubblicato nell'ambito e con il contributo del progetto CHANGES-Cultural Heritage Active Innovation for Sustainable Society Project code: PE0000020-CUP: H53C22000860006 Fondazione CHANGES, presso Sapienza Università di Roma: presidente prof. Marco Mancini Spoke 1. Historical landscapes, traditions and cultural identities Spoke leader Università di Bari 'Aldo Moro', coordinatore scientifico: prof. Giuliano Volpe

Research paper thumbnail of Produzione vascolare dal contesto cultuale del Monte Cimino (Soriano nel Cimino - Vt) e il Bronzo finale in Etruria meridionale

Research paper thumbnail of From fragments to digital wholeness: An AI generative approach to reconstructing archaeological vessels

Journal of Cultural Heritage, 2024

Reconstructing archaeological vessels from their fragments is a complex task that requires a long... more Reconstructing archaeological vessels from their fragments is a complex task that requires a long investment of time as well as in-depth knowledge of specific archaeological material. This paper proposes a framework based on generative artificial intelligence to reconstruct the entire vessel from a fragment. The proposed framework is based on a fragment simulation mechanism and the combination of three different deep learning models that position, reconstruct, and post-process the fragment to obtain a readyto-use reconstruction. The method is applied as a case-study to a dataset of six Italian Bronze and Early Iron Age burial contexts, including about 40 0 0 complete vessels and over 400 actual fragments. The results are evaluated using statistical metrics and expert human evaluation, showing promising results. The proposed method is a positive application of generative artificial intelligence in archaeology and provides a solution to the use of fragments in the digital and computational analysis of ceramics. The dataset, as well as the code used and the analytical pipeline, are fully available in the supplementary materials.

Research paper thumbnail of CQARCHAEO: A PYTHON PACKAGE FOR COSINE QUANTOGRAM ANALYSIS AND MONTE CARLO SIMULATIONS

Archeologia e Calcolatori, 2024

Cosine Quantogram Analysis (CQA) is a statistical analysis employed in archaeology for the study ... more Cosine Quantogram Analysis (CQA) is a statistical analysis employed in archaeology for the study of numerical datasets with hypothesized quantal distribution. To verify thesignificance of the results, the analysis is often combined with the execution of Monte Carlo simulations. In this article, we present a freely downloadable Python package (CQArchaeo) that integrates CQA and Monte Carlo simulations in the same environment, making the analysis customizable in the main parameters. We provide a guide that enables the use of this tool even for researchers with limited experience in Python programming and demonstrate the applicability, functioning, and main limitations of the analysis on some archaeological datasets.

Research paper thumbnail of The Late Bronze Age hilltop site of Monte Croce Guardia in the context of Bronze Age and Early Iron Age settlement organization in Peninsular Italy

Origini, 2023

The site of Monte Croce Guardia offers a unique opportunity to investigate the spatial organizati... more The site of Monte Croce Guardia offers a unique opportunity to investigate the spatial organization of a Final Bronze Age settlement in peninsular Italy. Data from new excavations and geophysical surveys are presented, focusing on the distribution of identified dwellings. This distribution is explored and compared with that of coeval sites such as Sorgenti della Nova and Sovana. An organizational pattern based on groups of huts, likely related to family groups, emerges from the analysis. The described model is further compared with several settlements and buildings dating from the Bronze Age to the Early Iron Age, across continental Italy, particularly focusing on the area south of the Po river.

Research paper thumbnail of Traditional and digital typologies compared: the example of Italian protohistory

Origini, 2023

The study of material culture, particularly ceramics, is an important aspect of archaeology. The ... more The study of material culture, particularly ceramics, is an important aspect of archaeology. The classification and typology of ceramics is often a key focus, with traditional methods based on the observation of specific morphological characteristics and the creation of taxonomies based on these types. However, recent advances in digital technologies and the use of Machine Learning have led to the development of new, digital approaches to ceramic classification. These approaches rely on statistical methods and computer science techniques to quantify vessel morphology and create multivariate datasets. The aim of this study is to compare a traditional approach elaborated by Renato Peroni and applied by many of his students, especially in the field of Italian protohistory, with a proposed digital method of ceramic classification. The comparison will be conducted using a database of approximately 1400 records from several Italian Bronze and Iron Age funerary contexts, including Casinalbo and other contexts in the Po Valley and northern Italy, as well as Pianello di Genga and Torre Galli. The proposed digital approach involves a combination of a non-linear dimensionality reduction algorithm and density-based clustering for the automated classification of ceramics. The study will consider the similarities and differences between the two methods and the potential for combining them in a complementary manner. The results of the study will provide a deeper understanding of traditional typologies and explore the potential for digital methods to enhance, improve, and complement them.

Research paper thumbnail of Defining Southern Etruria Final Bronze Age settlement models using an integrated GIS and Machine Learning approach

Archeologia e Calcolatori, 2023

This research aims to use quantitative and repeatable GIS techniques, as well as Machine Learning... more This research aims to use quantitative and repeatable GIS techniques, as well as Machine Learning algorithms, to study the settlement patterns in Southern Etruria during the final phase of the Bronze Age (1150-950/925 BC). The region of Southern Etruria is located in present-day Latium, Tuscany, and Umbria. The study, which includes 166 settlements, focuses on identifying the morphological characteristics of these settlements by means of raster analysis. Using a Machine Learning approach, the research will compare real settlements with random points within the region to understand the specific characteristics of the settlement pattern in the landscape. The study will also examine the use of feature selection and features importance methods to select the most significant features of a multivariate dataset.

Research paper thumbnail of Money or ingots? Metrological research on pre-contact Ecuadorian “axe-monies”

Journal of Archaeological Science: Reports, 2023

The so-called “axe-monies”, trapezoidal sheet metal objects made of arsenical copper alloy, are a... more The so-called “axe-monies”, trapezoidal sheet metal objects made of arsenical copper alloy, are associated with graves and hoards of the Mante ̃no-Huancavilca (AD 600–1532) and Milagro-Quevedo (AD 400–1532) cultures, both located on the southern coast of Ecuador. Historically, scholars identified these artifacts as money, relating
them to a currency system. This paper aims to test this hypothesis by investigating the degree of standardization (if any) through analyzing an important sample of these objects. Metrological analysis of their dimensions (length, width) and weight show that the currency hypothesis is flawed because neither clustering of dimensions nor a tendency towards a single (range of) weight value(s) is found. We suggest that the axe-monies may have been used as ingots, for arsenical copper alloys were a key commodity in the framework of exchange involving different cultures across America’s Pacific coast.

Research paper thumbnail of Dimensionality reduction for data visualization and exploratory analysis of ceramic assemblages

Archeologia e Calcolatori, 2022

Dimensionality reduction algorithms are essential in the study of multivariate datasets. Many var... more Dimensionality reduction algorithms are essential in the study of multivariate datasets. Many variables make it difficult to visualize data. In Archaeology, this problem often concerns the study of some variables, which can be quantitative or qualitative. In this article, several methods for dimension reduction are applied to a pottery dataset from the protohistoric necropolis Osteria dell’Osa, located 20 km East of Rome. These methods offer the possibility of visualising and analysing large amount of data in a very short time. Our results show that non-linear and non-parametric algorithms such as t-SNE and UMAP are the best choice for visualising and exploring this type of data.

Research paper thumbnail of Money or ingots? Metrological research on pre-contact Ecuadorian ‘axe-monies’

The Axe-monies, trapezoidal sheet objects made of arsenical copper, are associated with graves an... more The Axe-monies, trapezoidal sheet objects made of arsenical copper, are associated with graves and hoards of the Manteño-Huancavilca (600–1532 A.D) and Milagro-Quevedo (400–1532 A.D.) cultures, both located in the coast of Ecuador. Historically, scholars identified these artifacts as monies, relating them to a currency system. This paper aims to test this hypothesis by searching for standardization analyzing an important sample of these objects. Metrological analyses on dimensions (length, width) and weight show that the currency hypothesis is flawed because neither apparent clustering of dimensions nor a tendency to a single (range of) weight value(s) is found. We suggest ‘axe-monies’ were used as ‘ingot-objects’ and copper was a commodity in the framework of exchanges involving different cultures throughout America's Pacific coast.

Research paper thumbnail of A deep variational convolutional Autoencoder for unsupervised features extraction of ceramic profiles. A case study from central Italy

Journal of Archaeological Science, 2022

The need for a quantitative approach to the morphologic study of ceramics is becoming increasingl... more The need for a quantitative approach to the morphologic study of ceramics is becoming increasingly evident. Ceramics are the most common material in many archaeological sites and a huge amount of data has accumulated over time. This data can be handled by Machine Learning algorithms which are rapidly gaining popularity in archaeology. Although most approaches can be referred to classification tasks, in this contribution a particular type of Neural Network is proposed for feature extraction from archaeological ceramics. Through this proposed method it is possible to gain a numerical weighted representation of the pottery profile that can be used for multivariate analyses. The case study will focus on regionalisation processes in pottery production between the end of the 2nd millennium BC and the first half of the 1st millennium BC in central Tyrrhenian Italy, a period that saw major transformations in the cultural and socio-political structure of Ancient Italy. The results seem to confirm the regionalisation hypothesis and offer interesting insights into the quantitative study of archaeological ceramics.

Research paper thumbnail of Capienza delle forme vascolari, da un metodo open source all’uso di modelli regressivi: il caso dell’insediamento protostorico del Monte Cimino

Archeologia e Calcolatori, 2020

The volume of ceramic vessels provides several information about their use. However, due to the f... more The volume of ceramic vessels provides several information about their use. However, due to the fragmentation of pottery coming from settlement sites, data concerning the volume are rarely published. The first goal of this paper is presenting a new method to calculate the volume starting from the archaeological drawings. The dataset could be extended with a predictive regression analysis. The sample analyzed involves cups and bowls found on the top of Monte Cimino (Viterbo-Italy), a settlement and cult site dated to the Final Bronze Age (ca. 1150-950/925 BC).

Research paper thumbnail of Morphological variability and standardisation of vessel shapes in the 2nd and first half of the first millennium BC in continental Italy A data science and machine learning project for the quantitative study of archaeological ceramic profiles

Viola = titolo in c.po 18 + due a capo vuoti e poi cominciare con il testo Nero = testo in c.po 1... more Viola = titolo in c.po 18 + due a capo vuoti e poi cominciare con il testo Nero = testo in c.po 11 con interlinea singola (ma nel layout del Paragrafo è tutto già impostato). Ogni capoverso ha già rientro impostato. Verde = brevi testi in epigrafi/citazioni allinenati a destra in corsivo, in c.po 10, se riportati di lunghi testi vanno, con rientro impostato, in c.po 10 Rosso = richiami alle figure Arancione = indica che prima di inserire una immagine si richiede un a capo vuoto e così dopo la didascalia Azzurro = didascalia come indicato (in c.po 11) possibilmente centrata sotto l'immagine Se un capitolo finisce a pagina dispari aggiungere sempre la pagina pari bianca successiva. Ogni capitolo deve ricominciare con una pagina dispari 18 8 Volume pubblicato nell'ambito e con il contributo del progetto CHANGES-Cultural Heritage Active Innovation for Sustainable Society Project code: PE0000020-CUP: H53C22000860006 Fondazione CHANGES, presso Sapienza Università di Roma: presidente prof. Marco Mancini Spoke 1. Historical landscapes, traditions and cultural identities Spoke leader Università di Bari 'Aldo Moro', coordinatore scientifico: prof. Giuliano Volpe