On Thursday May 6, Elena Donini succesfully defended her PhD Theses on “Advanced methods for simulation-based performance assessment and analysis of radar sounder data”.
The committee awarded her the PhD in Information and Communication Technology cum laude.
The defense was done in virtual mode due to the restriction related to Coronavirus.
Congratulations to Elena!
Sudipan Saha recieved the “FBK Best PhD Student Award 2020”. The FBK Best Student Award is a prestigious recognition awarded each year to the student with the most outstanding achievements. The price was awarded during the FBK PhD day by Bernando Magnini, Director of the FBK International PhD Program, with the citation “For the excellent scientific contribution in the field of remote sensing. Specifically for the innovative use of deep learning applied to the analysis of multitemporal images, which has significantly contributed to advance the state of the art in the field.”
A figure from “Change Detection in VHR SAR Images via Unsupervised Deep Transcoding” by S. Saha, F. Bovolo, L. Bruzzone has been selected for the cover of the March 2021 issue of the IEEE Transactions on Geoscience and Remote Sensing.
The cover illustrates building change detection in Very High Resolution (VHR) Synthetic Aperture Radar (SAR) images using unsupervised deep transcoding. The images are corresponding to an area around the Department of Engineering and Computer Science, University of Trento, Trento, Italy. New buildings of varied sizes were built up in the site between 2011 and 2013/2014, which can be seen in (a) Pre-change (2011) and (b) Post-change (2014) optical images. RGB multitemporal composition of spotlight TerraSAR-X and TanDEM-X images (R: April, 2013; G: January, 2011; and B: April, 2013) is shown in (c). Changed buildings detected by an existing method is shown in (d). Results obtained by the unsupervised deep transcoding based method are shown in the bottom row: (e) Increase and decrease of deep feature space and (f) Detected changed buildings. For more information please refer to the manuscript.
Daniele Marinelli received the award for the Best Italian PhD Theses on Geoscience and Remote Sensing by the Italian Chapter of the IEEE Geoscience and Remote Sensing Society.
The award was presented to the best three PhD Theses defended in the period January 2019 – April 2020. The title of the PhD Thesis is “Advanced Methods for Change Detection in LiDAR Data and Hyperspectral Images” (supervisor : Prof. L. Bruzzone),
The EnVision Phase A study assessment study has been concluded and the related report, also known as the “yellow book”, has been prepared by the EnVision Science, Instruments and ESA Teams. It gives a complete description of the EnVision mission to Venus at the end of the phase A from a scientific, technical and operational points of view. It also reflects the (hard) work of tens of people across Europe and in the US in the last 3 years, and show what can be achieved when combining the best of science and engineering worlds.
EnVision Science Study Team Meetign #6 / Payload Instrument & Experiment Leads, Paris Observatory Library Hall, Feb 10-11 2020. Left to right: Pascal Rosenblatt, Jörn Helbert, Doris Breuer, Colin Wilson, Véronique Ansan, Francesca Bovolo, Caroline Dumoulin, Arno Wielders, Lorenzo Bruzzone, Séverine Robert, Dmitri Titov, Ann Carine Vandaele, Björn Grieger, Jens Romstedt, Thomas Widemann, Jayne Lefort, Thomas Voirin, Benjamin Lustrement, Luigi Colangeli, Emmanuel Marcq, Goro Komatsu, Richard Ghail, Walter Kiefer, Ana Rugina, Scott Hensley, Gabriel Guignan.
RSLab is deeply involved in EnVision as Lorenzo Bruzzone is the Lead for the Sub-surface Radar Sounder (SRS) instrument and Francesca Bovolo is a member of the ESA Science Study Team. Moreover many RSLab members have cotributed to the Phase A study of the SRS instrument.
The yellow book will be the basis for an independent scientific evaluation of the mission which is just starting – in parallel the EnVision study has also entered an extensive review by ESA (called the “Mission Selection Review”) to confirm its technical and programmatic feasibility.
The outcomes of these two parallel processes (scientific assessment and mission selection review) will feed the decision by ESA in June 2021 on the next Medium-class mission (“M5”) within ESA’s Cosmic Vision science programme , among the two remaining candidates : Theseus and EnVision.
Despite this complex situation, RSLab achieved important research results in 2020 on both Earth Observation and Planetary Exploration and the related topics. Some relevant numbers are as follows:
• 24 papers published on peer-reviewed international journals
• 19 papers accepted on peer-reviewed journal (in press in 2021)
• 4000+ (Source: Google Scholar) / 2900+ (Source: Scopus) citations in 2020
• 4 projects running with the role of Principal Investigator
• 3 projects running with the role of partner
• Top positions of the Lab in international ranking of research
• 5 international/national awards
• 4 graduated PhD students
• Many public outreach activities (newspaper and magazine interviews,
public presentations, etc.)
The figure reports the cloud of words built with the titles of the 2020 journal papers.
A new Moon crater database has been generated by using advanced deep learning and transfer learning methodologies applied to lunar images. More than 109,000 previously unrecognized craters have been identified on the Moon’s surface, dozens of times larger than the number previously recognized, and the ages of 18,996 of these has been estimated. The article has been published on “Nature Communications” this week.
RSLab is part of this research through the activity of Prof. Bruzzone. Moreover, the main author, Prof. Yang Chen, spent few years at RSLab before as visiting PhD student and then as Post-doc researcher.
NASA/GSFC/Arizona State University
Nature Press Release
Planetary science: Over 100,000 new craters identified on the Moon
More than 109,000 previously unrecognized craters have been identified on the Moon’s surface, reports a study published in Nature Communications this week.
Craters occupy most of the surface of the Moon. However, manual and automatic methods to detect the number of craters have resulted in inconsistencies as to the precise total. For example, it is often hard to detect irregular or degraded craters using automatic methods.
Chen Yang and colleagues set out to identify lunar impact craters using a transfer learning strategy — a machine learning approach in which previous knowledge gained is used to solve a further problem. The authors first trained a deep neural network using data from 7,895 previously identified and 1,411 dated craters. Using data from the Chang’E-1 and Chang’E-2 orbiters, the network was able to identify 109,956 new craters — dozens of times larger than the number previously recognized throughout the mid- and low-latitude regions of the Moon — including 46 with diameters ranging from 200 to 550 kilometres. Of the craters with a diameter larger than 8 kilometres, the network estimated the ages of 18,996 of these. The findings have resulted in the creation of a new lunar crater database of the mid- and low-latitude regions of the Moon.
The authors suggest that their approach could be adapted for use with other bodies in the Solar System and could help extract more information than is possible with manual analysis methods.
Read the full article on nature communications: https://www.nature.com/articles/s41467-020-20215-y
Read the interview on POPULAR SCIENCE: https://www.popsci.com/story/science/bot-counted-new-moon-craters/
About this:
The development of the JUICE mission (for which RSLab has the responsibility of the RIME instrument) is progressing fast despite the pandemic situation. A video showing the activities in progress at spacecraft level can be found here.
Lorenzo Bruzzone and Francesca Bovolo are in the top most cited researchers worldwide according to “World Ranking of Scientists” .
Lorenzo Bruzzone is in the top 0.4 % of the most cited scholars on the number of published papers and citations at global level in all the disciplines (the 2nd in the raking at University of Trento) and he is in the top 0.07% in his research area. The analysis considers the period 1996 – 2017.
Francesca Bovolo is the top 1.25% percent of the most cited scholars ranking in 2017. This ranking has been done to capture and compare performance of younger and more senior researchers.
The “World Ranking of Scientist” is a database created by Stanford University using a novel computing strategy. The database was compiled using six standardized citation metrics, and examining 22 scientific fields between 1996 and 2017. The result is a photograph of nearly 160,000 of the most influential scientists in the world, which represent 2 percent of over more than 6 million people and is based on data from Scopus (the main database for scientific publications). The study, conducted by John P. A. Ioannidis of Stanford University with Kevin W. Boyack and Jeroen Baas, appeared days ago in Plos Biology.
More info about this:
Thales Alenia Space recently delivered the protoflight model (PFM) of Radar for Icy Moon Exploration (RIME) that will explore Jupiter’s icy moons Europa, Ganymede and Callisto onboard the ESA’s JUICE mission. These are the final units of the instrument that now will be integrated inside the JUICE spacecraft to complete a long set of tests to ensure that every part is working nominally and, finally, being ready for the launch scheduled on June 2022.
RSLab has a leading role in this mission. Lorenzo Bruzzone is the RIME Principal Investigator while Francesca Bovolo is the instrument manager.
“Many theories have been proposed on the subsurface structure of Jupiter’s icy moons since their discovery by Galileo, theories that have sparked the imagination of so many scientists”, said Lorenzo Bruzzone. “This is a first step in the direction of advancing our scientific understanding of the Jupiter moons. For the first time, we may be able to solve some mysteries and take a look under the surface, searching for water”.
The JUICE spacecraft (right) and part of the RIME team together the EQM units of the instrument (left).
More info about this: