857323 Advanced methods in remote sensing: Machine learning and cloud computing
This page is available under these URLs:
- Lecture and exercise
- Semester hours
- Lecturer (assistant)
- Izquierdo-Verdiguier, Emma
- Offered in
- Wintersemester 2023/24
- Languages of instruction
Introduction to statistics and algebra.
2.1 Feature extraction: Spatial, spectral and temporal.
2.2 Clustering: k means.
2.3 Supervised classification methods:
2.5.1. Decision trees (DT).
2.5.2. Random Forest (RF).
2.5.3. Support Vectors Machines (SVM).
2.5.4. Neural networks (NN).
2.4 Real world example I: Object detection and classification using very high spatial resolution.
2.5 Real world example II: Classification of hyperspectral images.
From local laptop to Cloud computing: Google Earth Engine.
3.1 Real world example III: Spring plant phenology products.
3.2 How to use machine learning in the cloud: remote sensing classification.
3.3 Real world example IV: Classification using very high spatial resolution data.
3. 3 Real world example V: mapping phenoregions and correlating temperature and satellite based phenometrics.
- Previous knowledge expected
Basics programming skills. Basic principles of remote sensing and image classification.
- Objective (expected results of study and acquired competences)
During this course the students will learn to design and deploy machine learning algorithms as well as to use cloud computing for the analysis of remote sensing images. Both machine learning and cloud computing topics are explained using real world cases.
You can find more details like the schedule or information about exams on the course-page in BOKUonline.