The complete theoretical framework with experiments and results.

The Network Based Method Spectral Unmixing Framework

An introduction to the Network Based Method concept regarding the spectral unmixing of hyperspectral images. Bringing together several years of research performed in the unmixing domain, the readers can understand the principles behind the theory of the NBM framework and corresponding algorithms. A comprehensive analysis is also made on the current state-of-art of techniques and methods used to spectrally unmix remote sensing/hyperspectral data. The textbook course is intended for researchers, tutors, and students who want to read and understand the mathematical framework of NBM along with corresponding implemented algorithms. The full spectrum of spectral unmixing is covered, i.e. estimation of number of endmembers, endmember extraction, abundance estimation.

Course curriculum

  1. 01
    • Lesson 1: Introducing the contents of the textbook

  2. 02
    • Lesson 2: Spectral Mixing Models

    • Lesson 3: Linear Mixing Model

    • Lesson 4: Non-linear Mixing Model

  3. 03
    • Lesson 5: Overview of Spectral Unmixing

    • Lesson 6: Spectral Unmixing Frameworks (Part 1)

    • Lesson 7: Spectral Unmixing Frameworks (Part 2)

  4. 04
    • Lesson 8: Number of Endmembers and Endmember Extraction (Part 1)

    • Lesson 9: Number of Endmembers and Endmember Extraction (Part 2)

    • Lesson 10: Number of Endmembers and Endmember Extraction (Part 3)

    • Lesson 11: Number of Endmembers and Endmember Extraction (Part 4)

  5. 05
    • Lesson 12: Abundance Estimation (Part 1)

    • Lesson 13: Abundance Estimation (Part 2)

    • Lesson 14: Abundance Estimation (Part 3)

    • Lesson 15: Abundance Estimation (Part 4)

    • Lesson 16: Fully Constrained Least Squared Method (FCLS)

  6. 06
    • Lesson 17: Overview of the Network Concept in Hyperspectral Unmixing (Part 1)

    • Lesson 18: Overview of the Network Concept in Hyperspectral Unmixing (Part 2)

    • Lesson 19: Network Based Endmember Extraction (Part 1)

    • Lesson 20: Network Based Endmember Extraction (Part 2)

    • Lesson 21: Network Based Endmember Extraction (Part 3)

    • Lesson 22: Network Based Estimation of the number of endmembers

    • Lesson 23: Network Based Abundance Estimation

    • Lesson 24: Detection of an endmember not extracted by the previous unmixing steps

  7. 07
    • Lesson 25: The Fractional Distance Algorithm (Part 1)

    • Lesson 26: The Fractional Distance Algorithm (Part 2)

    • Lesson 27: The Fractional Distance Algorithm (Part 3)

    • Lesson 28: The NBM Algorithm (Part 1)

    • Lesson 29: The NBM Algorithm (Part 2)

  8. 08
    • Lesson 30: Synthetic Dataset (Part 1)

    • Lesson 31: Synthetic Dataset (Part 2)

    • Lesson 32: Real Dataset

  9. 09
    • Lesson 33: Synthetic Data - Number of Endmembers

    • Lesson 34: Synthetic Data - Endmember Extraction

    • Lesson 35: Synthetic Data - Endmember number estimation and extraction

    • Lesson 36: Real Data - Number of Endmembers

    • Lesson 38: Real Data - Endmember Extraction

    • Lesson 39: Real Data - Endmember number estimation and extraction

  10. 10
    • Lesson 40: Synthetic Dataset

    • Lesson 41: Real Dataset

  11. 11
    • Lesson 42: Synthetic Data

    • Lesson 43: Real Data

  12. 12
    • Lesson 44: Conclusions

    • Acknowledgements

    • Bibliography

What will you learn?

  • Spectral Unmxing

  • Endmember Extraction

  • Endmember Number Estimation

  • Network Based Method

  • Abundance Estimation

  • Synthetic and Real Remote Sensing Datasets

Any Prerequisites?

  • Practically none.

Student Profile?

  • Under/post graduate students

  • Professionals and Companies

  • Master students and PhD candidates

  • Researchers and Academics

Some more information

  • Certificates of Completion

    After you successfully finish the course, you can claim your Certificate of Completion with NO extra cost! You can add it to your CV, LinkedIn profile etc

  • Available at any time! Study at your best time

    We know hard it is to acquire new skills. All our courses are self paced.

  • Online and always accessible

    Even when you finish the course and you get your certificate, you will still have access to course contents! Every time an Instructor makes an update you will be notified and be able to watch it for FREE

About your Instructor

Dimitris Sykas is a Remote Sensing and Surveying Engineer with a Ph.D. in hyperspectral remote sensing from the National Technical University of Athens (2016). He has spent fifteen years turning satellite data into operational products: at the NTUA Remote Sensing Laboratory, at Planetek Hellas as Senior EO Engineer, at Neuropublic building machine-learning models for smart farming and CAP monitoring, as a postdoctoral researcher on deep learning for agricultural Earth observation at the National Observatory of Athens, and as CTO of the cloudeo group. In 2024 he co-founded GOVADI, an Athens-based company building sovereign, on-premises AI systems for the Greek public sector and large enterprises, where he leads the technical direction of its products: Greek speech-to-text, retrieval-augmented generation with local models and embedding stores, document OCR and PII anonymisation. He has taken part in more than 25 funded EU and ESA projects, has authored over 23 peer-reviewed publications in remote sensing, and holds an international patent in hyperspectral data compression. He founded GEO University to bring hands-on GIS and Earth observation training online.

Dimitris Sykas

Remote Sensing Engineer, Ph.D. · Co-founder and Director, GOVADI · Founder, GEO University

Check these out

  • Learn Hyperspectral Remote Sensing from the Scratch

    Understand primary concepts, methods and algorithms of imaging spectroscopy.

    Free

    Enroll Now
  • Hyperspectral Imaging Application: Oil Spill Mapping

    The textbook you need to learn how to map, identify and quantify oil spills in marine ecosystems using Earth Observation

    Free

    Enroll Now
  • A Machine learning approach for Object Parameter Estimation and Discrimination

    The textbook you need to understand spectroscopy for Remote Sensing

    Free

    Enroll Now