This week, you will examine what remote sensing instruments measure and how image quality can be affected by radiometric and geometric distortions. You will learn how these errors arise and explore techniques used to correct them, helping ensure that remotely sensed images accurately represent real-world conditions.

This week, you will learn how image geometry is corrected using control points, resampling techniques, and image-to-image registration methods. You will also explore image interpretation and contrast enhancement approaches that improve the usability and visual quality of remote sensing data.

This week, you will explore the fundamentals of image classification and thematic mapping. You will examine covariance and correlation matrices and learn how principal components analysis can be used to reduce data complexity while preserving important information for image analysis.

This week, you will focus on the practical application of principal components analysis in remote sensing. Through worked examples and real-world use cases, you will learn how this technique supports image interpretation, feature extraction, and more efficient analysis of complex datasets.

This week, you will be introduced to the foundations of computer-based image interpretation and machine learning for remote sensing. You will explore the principles of supervised classification, examine how maximum likelihood classifiers make classification decisions, and learn how discrimination functions are used to separate image classes. You will also compare classification approaches and develop an understanding of how machine learning techniques support automated image analysis.

This week, you will learn how linear classifiers are trained and applied to remote sensing data. You will explore the development of support vector machines (SVMs), understand how they classify both linear and non-linear datasets, and examine practical examples of SVM implementation.

This week, you will examine the structure and operation of neural networks as classification tools. You will learn how neural networks are trained, how they identify patterns in data, and how they can be applied to solve remote sensing classification problems.

This week, you will explore the evolution from traditional neural networks to convolutional neural networks (CNNs). You will learn how CNNs are structured, how they are applied to remote sensing imagery, and how their performance compares with other classification approaches.

This week, you will study unsupervised classification techniques and the role of clustering in identifying patterns within unlabeled data. You will examine common clustering methods, including k-means clustering, and explore approaches designed to handle large-scale remote sensing datasets.

This week, you will learn techniques for reducing and selecting features in remote sensing datasets. You will explore transformation-based methods, separability measures, and the differences between distribution-based and distribution-free approaches used to improve classification performance and efficiency.

This week, you will examine how thematic map accuracy and classifier performance are evaluated. You will learn the distinction between classification accuracy and mapping accuracy and explore methodologies that combine supervised and unsupervised techniques to improve image interpretation outcomes.

This week, you will be introduced to imaging radar and synthetic aperture radar (SAR). You will explore radar scattering concepts, radar cross sections, and the phenomenon of speckle, gaining a foundation for understanding radar imagery and its applications in remote sensing.

This week, you will investigate how radar energy interacts with the Earth’s surface. You will examine surface and volume scattering, reflections from hard targets, sea-surface scattering, and the cardinal effect, developing a deeper understanding of radar image interpretation.

This week, you will explore advanced radar remote sensing concepts, including geometric distortions, radar calibration, interferometry, and tomography. You will also examine the benefits of combining optical and radar imagery and conclude the course by reviewing key concepts and applications covered throughout the program.