About me:

Born in Naples, 28.05.1985

I am a PostDoc in the Astroinformatics group at the HITS – Heidelberg Institute for Theoretical Studies


Mobile: +49(0)17635788930

Office: +49(0)6221533315

Email: antonio.disanto@h-its.org

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.

2019: PhD thesis defended successfully cum laude.

2019: Postdoctoral researcher at HITS.



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.  


Probabilistic photometric redshift estimation in massive digital sky surveys via machine learning. Supervisors Prof. Dr. Joachim Wambsganß, Dr. Coryn Bailer-Jones

Abstract: The problem of photometric redshift estimation is a major subject in astronomy, since the need of estimating distances for a huge number of sources, as required by the data deluge of the recent years. The ability to estimate redshifts through spectroscopy does not scale with this avalanche of data. Photometric redshifts provide the required redshift estimates at the cost of some precision. The success of several forthcoming missions is highly dependent on the availability of photometric redshifts. The purpose of this thesis is to provide innovative methods for photometric redshift estimation. Two models are proposed. The first is fully-automatized, based on the combination of a convolutional neural network with a mixture density network, to predict probabilistic multimodal redshifts directly from images. The second model is features-based, performing a massive combination of photometric parameters to apply a forward selection in a huge feature space. The proposed models perform very efficiently compared to some of the most common models used in the literature. An important part of the work is dedicated to the correct estimation of the errors and prediction quality. The proposed models are very general and can be applied to different topics in astronomy and beyond.


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

A. D’Isanto, S. Cavuoti, F. Gieseke and K. L. Polsterer, 2018, A&A, 616, A97, Return of the features – Efficient feature selection and interpretation for photometric 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.

Current projects

Conferences & Summer Schools

Invited talks

Public Outreach

I collaborated for several years with Tom’s Hardware Italy for the production of scientific contents in the Science section of the website. Actually I have published more than 50 articles. The full list of them (only in Italian) is available HERE.

Other interests

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 three years 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.

Switch to the German homepage or stay on this page