A machine learning approach for hyperspectral data

A Machine learning approach for Object Parameter Estimation and Discrimination Using Hyperspectral Data

The textbook you need to understand spectroscopy for Remote Sensing

Spectroscopy, Spectral Discrimination and Genetic Algorithms

A textbook to get started with automatic parameter estimation and discrimination

using hyperspectral data

So, what is object parameter estimation using spectral data, i.e. spectroscopy? What is spectral discrimination? Do they have something in common? Can a machine learning approach help to tackle both problem?

This textbook course answers all these questions and more! The textbook book course presents not only the basic theoretical principles of spectroscopy, spectral matching, labeling and discrimination, but also a new novel method, the k-step methodology, that automates the entire process. Both for object parameter estimation and spectral discrimination!

A machine learning approach is incorporated to achieve the full automation; the simple genetic algorithm.

For all these topics, extensive measurements were collected and experiments were performed in order to prove the concept.

Spectral measurements of  different varieties of plants (vetch and lentil) were used to showcase the subtle spectral discrimination concept.

Regarding the parameter estimation, soil spectral measurements were taken along with chemical analysis to quantify the soil organic matter.


how spectral measurements can help estimate desired parameters or even discriminate phenomenical similar objects!



  • Lesson 1: Introducing the contents of the textbook FREE TRIAL
  • Lesson 2: Object Parameter Estimation workflow or Spectroscopy FREE TRIAL
  • Lesson 3: Step by Step Analysis
  • Lesson 4: Spectral Discrimination

Background: Spectral Pre-Processing Algorithms

  • Lesson 5: Spectral Pre-Processing Algorithms (SPPAs) FREE TRIAL
  • Lesson 6: Smoothing
  • Lesson 7: Vector Normalization
  • Lesson 8: Value Normalization
  • Lesson 9: Discrete Fourier Transform
  • Lesson 10: Logarithm Transform
  • Lesson 11: Kubelka-Munck Transformation
  • Lesson 12: N Order Square Root Transformation
  • Lesson 13: Derivatives
  • Lesson 14: Continuum Removal
  • Lesson 15: Band Depth

Background: Spectral Matching & Labeling and Similarity Measures

  • Lesson 16: Spectral Matching and Labeling FREE TRIAL
  • Lesson 17: Similarity Measures
  • Lesson 18: Spectral Angle Mapper
  • Lesson 19: Cross Correlation
  • Lesson 20: Spectral Information Divergence
  • Lesson 21: SID – SAM Mixed Measure
  • Lesson 22: Continuum Intact Continuum Removed (CICR)

Background: Regression Algorithms

  • Lesson 23: Main Regression Algorithms Used
  • Lesson 24: Two Band Normalized Difference Regression (NDR)
  • Lesson 25: Multiple Linear Regression (MLR)
  • Lesson 26: Partial Least Squares Regression (PLSR)

Background: Machine Learning with the Simple Genetic Algorithm

  • Lesson 27: The Genetic Algorithm Concept

Methodological Approach

  • Lesson 28: Object Parameter Estimation (Part 1)
  • Lesson 29: Object Parameter Estimation (Part 2)
  • Lesson 30: Object Parameter Estimation (Part 3)
  • Lesson 31: Object Spectral Discrimination

Use case: Spectral Discrimination of Plant Species

  • Lesson 32: Data and experiment
  • Lesson 33: Experiment Results

Use case: Soil Parameter Estimation

  • Lesson 34: Data and experiment FREE TRIAL
  • Lesson 35: Experiment Results for NDR
  • Lesson 36: Experiment Results for MLR
  • Lesson 37: Experiment Results for PLSR


  • Lesson 38: Conclusions on Spectral Discrimination Use Case
  • Lesson 39: Conclusions on Parameter Estimation Use Case
  • Lesson 40: Overall Conclusions (Part 1)
  • Lesson 41: Overall Conclusions (Part 2)


  • References

Key Concepts Explained

Spectral Pre-Processing Algorithms

Regression Algorithms

Simple Genetic Algorithm


Spectral Matching, Labeling, Discrimination

Spectral Similarity Measures

About Your Instructor

Dimitris Sykas

Dimitris Sykas

Remote Sensing Expert

I'm a Remote Sensing and a Surveying Engineer. I received my degree from NTUA in 2010, where I also received my Ph.D. in hyperspectral remote sensing in 2016. From graduation in 2010, my career started as a Researcher Associate and Teaching Associate in the Laboratory of Remote Sensing of NTUA. From that time I also worked at several private companies as a Remote Sensing Expert and Geospatial Analyst. From the beginning of 2015 I was positioned as Senior Earth Observation Expert. During these years, I have participated in more than 20 funded European Commission and European Space Agency projects, have over 16 peer reviewed scientific publications in the field of Remote Sensing, and have an international patent in hyperspectral data compression.

My main research and professional interests are in the optical remote sensing area, where I specialize in data (images, point measurements) processing and algorithm design and development. Some of the software tools that I operate to accomplish my research and business dreams are SNAP, ENVI, IDL, QGIS, ERDAS Imagine, ArcGIS, and Python. I have been working with these tools since 2008.



$9.90 Regular Price Buy $9.90

Let's get started!

Click below to sign up!

Take the Course

Check these out

$9.90 Learn Hyperspectral Remote Sensing from the Scratch Buy Now

Want to get more knowledge?

$60.42 Earth Observation Courses Bundle! Buy Now