Born in Naples, 28.05.1985
I am a PhD student in the Astroinformatics group at the HITS – Heidelberg Institute for Theoretical Studies
Brief Curriculum Vitae
2004: High School Diploma at “Liceo Scientifico Statale E. Majorana”, Pozzuoli (NA), with 100/100
2009: Bachelor Degree in Physics at “University of Naples Federico II”, with 104/110
2014: Master Degree in Astrophysics and Space Science at “University of Naples Federico II” with 110/110 cum laude
2015: PhD student at University of Heidelberg with HITS scholarship.
Extension to intermediate redshift of a method for galaxies photometric redshifts determination in multiband surveys, Supervisors Prof. G. Longo, Dr. Raffaele D’Abrusco
Abstract: The main purpose of this thesis work was the determination of photometric redshifts of galaxies using data obtained with synoptic surveys, using neural networks and Virtual Observatory tools.
Classification of astronomical transients with machine learning methods, Supervisors Prof. G. Longo, Dr. M. Brescia, Dr. S. Cavuoti
Abstract: The huge data burst which took place over the last years and the new generation of instruments have increased the request for new techniques and methods of data analysis and classification, that, if possible, must be fully automatized and efficient. In this light, a new method for classification of transients has been tested: MLPQNA, a neural network algorithm available in the DAMEWARE platform. The main purposes were to increase the efficiency of classification and to implement the first step of a more general workflow, based on the construction of a decision tree constituted by different classifiers.
D’Isanto, A., Cavuoti, S., Brescia, M., Donalek, C., Longo, G., Riccio, G., Djorgovski, S.G., 2016. An analysis of feature relevance in the classification of astronomical transients with machine learning methods. MNRAS, 457, 3, 3119-3132
Polsterer, K.L., D’Isanto, A., Gieseke, F., 2016, Uncertain Photometric Redshifts. (only arXiv, provisional)
D’Isanto, A., 2016. Uncertain Photometric Redshifts with Deep Learning Methods. Proceedings IAU Symposium No. 325, 2016
D’Isanto, A., Polsterer, K.L., 2017. Uncertain Photometric Redshifts via Combining Deep Convolutional and Mixture Density Networks. ESANN 2017 Proceedings
A. D’Isanto and K. L. Polsterer, 2018, A&A, 609, A111. Photometric redshift estimation via deep learning – Generalized and pre-classification-less, image based, fully probabilistic redshifts
My research interests
I am mainly interested in the application of machine learning, deep learning and data mining techniques to Astrophysical problems, in particular in the regime of Big Data.
Currently I am working on the cosmological field, being interested in the problem of photometric redshifts determination in the form of density distributions.
- Probabilistic photometric redshifts via deep learning
- Efficient feature selection for photometric redshift estimation (provisional)
Conferences & Summer Schools
- Astroinformatics 2016 (Sorrento): poster presentation
- Astrostatistics and Data Mining Summer School 2016 (Heidelberg)
- European Symposium on Artificial Neural Networks 2017 (Bruges): poster presentation
- DeepLearn Summer School 2017 (Bilbao)
- AG 2017 – Meeting of the German Astronomical Society (Goettingen): talk
- Astroinformatics 2017 (Cape Town) – talk
I always loved sport and in particular martial arts. For about 15 years I used to practice Taekwondo, in which I am 2nd dan black belt. Since one year I am studying also Kung Fu Wing Chun. Furthermore, I have a passion for reading, mainly fantasy and science fiction, cinema and role-playing games. Obviously Astronomy (and astronomical outreach) is not just my job but also one of my hobbies.
Another big passion that occupied an important period of my life was politics. I have been leader of the city section of a party for a year and actively participate to the political life of my home town for about three years.