**About the Editors**

**Yakoub Bazi** received the State Engineer and M.Sc. degrees in electronics from the University of Batna, Batna, Algeria, in 1994 and 2000, respectively, and the Ph.D. degree in information and communication technology from the University of Trento, Trento, Italy, in 2005. From 2000 to 2002, he was a Lecturer at the University of M'sila, M'sila, Algeria. From January to June 2006, he was a Postdoctoral Researcher at the University of Trento. From August 2006 to September 2009, he was an Assistant Professor at the College of Engineering, Al-Jouf University, Al-Jouf, Saudi Arabia. He is currently a Professor in the Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia. His research interests include machine learning and pattern recognition methods for signal/image processing and analysis. Dr. Bazi is a referee for several international journals.

**Edoardo Pasolli** received the M.Sc. degree in Telecommunications Engineering and the Ph.D. degree in ICT from the University of Trento, Trento, Italy, in 2008 and 2011, respectively. He was a postdoctoral fellow at the University of Trento (2011–2012 and 2014–2016); NASA Goddard Space Flight Center, Greenbelt, MD, USA (2012–2013); and Purdue University, West Lafayette, IN, USA (2013–2014). He was a Marie Sklodowska-Curie Individual Fellow at the University of Trento from 2016 to 2018. Since 2018, he has been an Assistant Professor in the Department of Agricultural Sciences, University of Naples Federico II, Naples, Italy. His research interests aim at developing machine learning and data science methodologies for complex ecosystems including the processing of remote sensing images and data.

#### **Preface to "Advanced Deep Learning Strategies for the Analysis of Remote Sensing Images"**

The last two decades have unveiled that remote sensing (RS) has become an essential technology in monitoring urban, atmospheric, and ecological changes. The increased availability of satellites and airborne sensors with different spatial and spectral resolutions has made this technology a key component in decision making. In addition to these traditional platforms, a new era has been opened recently by the adoption of UAVs for diverse applications such as policing, precision farming, and urban planning.

The grea<sup>t</sup> potential provided in terms of observation capability introduces similarly grea<sup>t</sup> challenges in terms of information extraction. However, processing the massive amounts of data collected by these diverse platforms is impractical and ineffective using traditional image analysis methodologies. This calls for the adoption of powerful techniques that can extract reliable and impressive information. In this context, deep learning (DL) strategies have recently been shown to hold the grea<sup>t</sup> promise of addressing the challenging needs of the RS community. Indeed, the introduction of DL dates back decades ago, when the first steps towards building artificial neural networks were undertaken. However, due to the limited processing resources, it did not reach a cutting-edge success in data representation and classification tasks until the recent appearance of high-performance computing facilities. This in turn enabled the design of sophisticated deep neural architectures and boosted the precision of many problems to groundbreaking performances. In this context, this book presents several contributions for the analysis of remote sensing imagery, including interesting topics related to scene classification, semantic segmentation, and image retrieval.

> **Yakoub Bazi, Edoardo Pasolli** *Editors*
