OVERVIEW

The course introduces the key concepts associated with remote sensing for Earth observation in the framework of the applications to renewable energy. Machine learning concepts are also introduced in the context of these applications.

AIMS AND CONTENT

LEARNING OUTCOMES

Introducing the key concepts associated with Earth observation through remote sensing images for renewable energy applications. Providing the students with basic knowledge about remote sensing image acquisition and about mapping, through remote sensing image analysis, bio/geophysical parameters associated with renewable energy sources, including vegetation biomass, wind velocity field over sea water, solar irradiance, and air surface temperature.

AIMS AND LEARNING OUTCOMES

After the course, the student shall know basic notions about: remote sensing data collected by optical, radar, and laser sensors; vegetation biomass mapping from remote sensing; wind velocity field characterization over sea water from radar data; solar irradiance retrieval from geostationary optical data; air surface temperature estimation from thermal infrared data; and the methodological bases of machine learning for supervised classification and regression.

PREREQUISITES

No specific prerequisites, in addition to the normal bases of mathematics and physics that the students are supposed to have from their B.Sc. backgrounds in engineering.

TEACHING METHODS

Class lectures and software laboratory exercises.

SYLLABUS/CONTENT

1. Introduction to remote sensing for Earth observation: remote sensing and its applications in the energy field; spaceborne and airborne sensors and platforms; spatial, spectral, temporal, and radiometric resolutions; digital remote sensing images, their visualization, and contrast enhancement.
2. Remote sensing image acquisition: active radar imaging sensors, side-looking airborne radar and synthetic aperture radar; passive multispectral sensors; examples of space missions for Earth observation; calibration, georeferencing, and image registration; active laser sensors (LiDAR) and 3D data collection.
3. Vegetation biomass estimation through remote sensing: direct and indirect approaches; direct biomass estimation as a supervised regression problem; indirect biomass estimation through the mapping of vegetated land cover and the modeling of 3D structure; vegetated land cover mapping as an image classification problem; basic concepts of machine learning for pattern recognition; recalling probability theory and random variables; examples of non-contextual remote sensing image classifiers; 3D modeling using LiDAR data; applications to vegetation biomass retrieval at various spatial resolutions.
4. Wind velocity estimation over sea water through remote sensing: wind velocity over sea and ocean, small-scale roughness, and relationship to radar remote sensing; scatterometry-based methods for the estimation of wind velocity; application to siting offshore eolic systems.
5. Solar irradiance and air temperature estimation through remote sensing: estimation of irradiance and irradiation from visible imagery; clear-sky model; cloud cover indices; air temperature regression from thermal infrared imagery; application to the siting and monitoring of photovoltaic systems.
6. Denoising and filtering remote sensing images: noise and speckle in remote sensing images; denoising through linear and rank filters; multilooking and despeckling; applications to biomass mapping.

This unit also contributes to the achievement of the following Sustainable Development Goals of the UN 2030 Agenda: Objectives no. 4, 7, 8, and 13.

RECOMMENDED READING/BIBLIOGRAPHY

• Bishop C., Pattern recognition and machine learning, Springer, 2006
• Campbell J. B. and Wynne R. H., Introduction to remote sensing, Guilford Press, 2011
• Goodfellow I., Bengio Y., and Courville A., Deep learning, MIT Press, 2016
• Hastie T., Tibshirani R., and Friedman J., The elements of statistical learning, Springer, 2008
• Long D. and Ulaby F. T., Microwave radar and radiometric remote sensing, Artech House, 2015
• Manolakis D. G., Lockwood R. B., and Cooley T. W., Hyperspectral imaging remote sensing, Cambridge University Press, 2016
• Moser G., Analisi di immagini telerilevate per osservazione della Terra, ECIG, 2007
• Moser G. and Zerubia J. (eds.), Mathematical models for remote sensing image processing, Springer, 2018
• Sonka M., Hlavac V., Boyle R., Image processing, analysis, and machine vision, Cengage Learning, 2015
• Class slides will be provided to the students through AulaWeb.

TEACHERS AND EXAM BOARD

Exam Board

GABRIELE MOSER (President)

SILVANA DELLEPIANE

ROOZBEH RAJABI TOOSTANI

SEBASTIANO SERPICO (President Substitute)

LESSONS

LESSONS START

https://courses.unige.it/10170/p/students-timetable

EXAMS

EXAM DESCRIPTION

Oral examination on the topics included in the syllabus of the course.

Students with learning disorders ("disturbi specifici di apprendimento", DSA) will be allowed to use specific modalities and supports that will be determined on a case-by-case basis in agreement with the delegate of the Engineering courses in the Committee for the Inclusion of Students with Disabilities.

ASSESSMENT METHODS

Within the oral examination, the student's knowledge of the course topics and his/her capability to discuss how to address simple problems of remote sensing data analysis associated with energy applications shall be evaluated.

Exam schedule