Claudio Angelini
Research Subjects
Research Interests
Claudio Angelini has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
B. A. Reinke
Department of Biology Northeastern Illinois University Chicago IL USA
1 shared publicationC. Costa
Consiglio per la ricerca in agricoltura e l'analisi dell'economia agraria (CREA) – Centro di ricerca Ingegneria e Trasformazioni agroalimentari Monterotondo Italy
1 shared publication- Christoph Leeb
Central Research Laboratories, Natural History Museum Vienna, Vienna, Austria
1 shared publication - Corrado Costa
Consiglio per la Ricerca in Agricoltura e l’Analisi dell’Economia Agraria (CREA), Centro di Ricerca Ingegneria e Trasformazioni Agroalimentari, Via della Pascolare 16, 00015 Monterotondo, Italy
1 shared publication Daniela Mastrodomenico
Rete faunistica dei Monti Lepini
1 shared publicationGiovanni Mastrobuoni
Rete faunistica dei Monti Lepini
1 shared publication
Latest Publications
- 21 December 2025
- Published by Wiley in Journal of Zoology
- Vol. 328 (3) , 290-297
Using deep learning to distinguish cryptic traits in animal colour patterns
Colouration is often useful for distinguishing between closely related species, or between sexes of a given species. Nevertheless, sometimes colouration is so complex or non‐descript to a human viewer that it cannot be used for delimitation. In this article, we propose the use of a Deep Learning (DL) algorithm to discriminate colour patterns of individuals belonging to different species, populations or sexes that are not discriminable by humans. Namely, we test the effectiveness of DL at distinguishing (i) between two species of the amphibian urodele Salamandrina, S. perspicillata and S. terdigitata , (ii) between two populations of S. perspicillata based on ventral colour pattern, and between (iii) two populations and (iv) sexes of the painted turtle Chrysemys picta based on plastron colouration. The classification algorithm performs well at distinguishing Salamandrina species (96.8% of the test set), and C. picta sexes (83.9%) and populations (76.7%), but has a lower performance on distinguishing populations of S. perspicillata (66.7%). Thus, DL is able to detect colour pattern differences between biological groups when humans cannot reliably distinguish them, representing a new way to examine animal colouration when it is highly variable or has only subtle differences among individuals, although DL does not output how patterns are similar or different. However, finding that colour differences occur can represent the first step of a longer analytical workflow based on possible explanatory hypotheses, or can allow researchers to save time in the opposite case.
- 21 December 2025
- Published by Wiley in Journal of Zoology
- Vol. 328 (3) , 290-297
Using deep learning to distinguish cryptic traits in animal colour patterns
Colouration is often useful for distinguishing between closely related species, or between sexes of a given species. Nevertheless, sometimes colouration is so complex or non‐descript to a human viewer that it cannot be used for delimitation. In this article, we propose the use of a Deep Learning (DL) algorithm to discriminate colour patterns of individuals belonging to different species, populations or sexes that are not discriminable by humans. Namely, we test the effectiveness of DL at distinguishing (i) between two species of the amphibian urodele Salamandrina, S. perspicillata and S. terdigitata , (ii) between two populations of S. perspicillata based on ventral colour pattern, and between (iii) two populations and (iv) sexes of the painted turtle Chrysemys picta based on plastron colouration. The classification algorithm performs well at distinguishing Salamandrina species (96.8% of the test set), and C. picta sexes (83.9%) and populations (76.7%), but has a lower performance on distinguishing populations of S. perspicillata (66.7%). Thus, DL is able to detect colour pattern differences between biological groups when humans cannot reliably distinguish them, representing a new way to examine animal colouration when it is highly variable or has only subtle differences among individuals, although DL does not output how patterns are similar or different. However, finding that colour differences occur can represent the first step of a longer analytical workflow based on possible explanatory hypotheses, or can allow researchers to save time in the opposite case.
- 12 November 2025
- Published by Walter de Gruyter GmbH in Amphibia-Reptilia
- Vol. 47 (1) , 13-24
The yellow and black of Salamandra salamandra across Italy: colour polymorphism analyses
The colour pattern of the fire salamander Salamandra salamandra is highly variable across the species’ range. In Italy, the nominal subspecies ( S. s. salamandra ), occurs in the north, and S. s. gigliolii is found in the peninsular Italy. Herein, we analyse the individual colour pattern of six populations of S. salamandra (five in Italy – representative of the entire Italian range and including both subspecies – plus one location in Austria) by taking pictures of the dorsal sides of 289 individuals. We employed topographical image analysis with both unsupervised and supervised clustering methods, based on information on the colour and position of each pixel from individual pictures. Furthermore, we studied the amount and the intensity of each individual’s colour using linear mixed models. In addition, we explored the genetic structure of these five Italian populations, plus an additional four Italian populations (for which we have insufficient number of individuals for colour analysis) using both mitochondrial (cytochrome b and D-loop; 402 and 780 bp sequences, respectively) and nuclear (12 microsatellite loci) DNA. In general, we find that the colouration is highly related to population identity, with both the relative colour abundance and pattern showing a geographic structure. Intriguingly, females were a darker black than males across all investigated populations. This geographic structure was, however, not reflected in the genetic data, which indicated both mitonuclear discordance and a counterintuitive structuring pattern, with the most geographically distant populations being the most genetically similar.
- 12 November 2025
- Published by Walter de Gruyter GmbH in Amphibia-Reptilia
- Vol. 47 (1) , 13-24
The yellow and black of Salamandra salamandra across Italy: colour polymorphism analyses
The colour pattern of the fire salamander Salamandra salamandra is highly variable across the species’ range. In Italy, the nominal subspecies ( S. s. salamandra ), occurs in the north, and S. s. gigliolii is found in the peninsular Italy. Herein, we analyse the individual colour pattern of six populations of S. salamandra (five in Italy – representative of the entire Italian range and including both subspecies – plus one location in Austria) by taking pictures of the dorsal sides of 289 individuals. We employed topographical image analysis with both unsupervised and supervised clustering methods, based on information on the colour and position of each pixel from individual pictures. Furthermore, we studied the amount and the intensity of each individual’s colour using linear mixed models. In addition, we explored the genetic structure of these five Italian populations, plus an additional four Italian populations (for which we have insufficient number of individuals for colour analysis) using both mitochondrial (cytochrome b and D-loop; 402 and 780 bp sequences, respectively) and nuclear (12 microsatellite loci) DNA. In general, we find that the colouration is highly related to population identity, with both the relative colour abundance and pattern showing a geographic structure. Intriguingly, females were a darker black than males across all investigated populations. This geographic structure was, however, not reflected in the genetic data, which indicated both mitonuclear discordance and a counterintuitive structuring pattern, with the most geographically distant populations being the most genetically similar.
- Open Access
- 30 June 2023
- Published by Sociedad Colombiana de Mastozoologia in Mammalogy Notes
- Vol. 9 (1) , 354
New records of Capreolus capreolus Linnaeus, 1758 in the Monti Lepini (Lazio, Central Italy)
The Roe Deer was present in the Monti Lepini (Southern Lazio) up to the first half of the nineteenth century, then it went locally extinct. In this note we report four new records of this species that testify for the current existence of a (likely very small) local population, which would represent the only other wild ungulate in the area, in addition to the very common Wild Boar.
- 30 June 2023
- Published by Sociedad Colombiana de Mastozoologia in Mammalogy Notes
- Vol. 9 (1) , 354
Open AccessNew records of Capreolus capreolus Linnaeus, 1758 in the Monti Lepini (Lazio, Central Italy)
The Roe Deer was present in the Monti Lepini (Southern Lazio) up to the first half of the nineteenth century, then it went locally extinct. In this note we report four new records of this species that testify for the current existence of a (likely very small) local population, which would represent the only other wild ungulate in the area, in addition to the very common Wild Boar.
- Open Access
- 20 April 2023
- Published by PAGEPress Publications in Natural History Sciences
- Vol. 10 (1)
A preliminary camera trapping study of mammals of Monti Lepini (Central Italy)
We used 52 camera traps to survey mammal species in the Lepini Mountains (Lazio, Central Italy) during three trapping sessions. Thirteen mammal species have been recorded. Compared to data based on previous opportunistic observations (2000-2018), camera trapping has quickly increased knowledge about the distribution of species, especially for elusive ones. We modelled species and average community occupancy also considering habitat covariates in a hierarchical modelling framework. Occupancy at community level was positively impacted by woods and negatively impacted by open habitats, indicating that the ongoing reforestation of the area may favour mammal diversity. Open surfaces have a negative effect on the presence of Sciurus vulgaris, a species for which our study confirms extensive recolonization of the area. We have also shown that woods increase the probability of occupation by Canis lupus and Felis silvestris, confirming that these species could be negatively impacted by increased deforestation.
- 20 April 2023
- Published by PAGEPress Publications in Natural History Sciences
- Vol. 10 (1)
Open AccessA preliminary camera trapping study of mammals of Monti Lepini (Central Italy)
We used 52 camera traps to survey mammal species in the Lepini Mountains (Lazio, Central Italy) during three trapping sessions. Thirteen mammal species have been recorded. Compared to data based on previous opportunistic observations (2000-2018), camera trapping has quickly increased knowledge about the distribution of species, especially for elusive ones. We modelled species and average community occupancy also considering habitat covariates in a hierarchical modelling framework. Occupancy at community level was positively impacted by woods and negatively impacted by open habitats, indicating that the ongoing reforestation of the area may favour mammal diversity. Open surfaces have a negative effect on the presence of Sciurus vulgaris, a species for which our study confirms extensive recolonization of the area. We have also shown that woods increase the probability of occupation by Canis lupus and Felis silvestris, confirming that these species could be negatively impacted by increased deforestation.