python-remote-sensing.Rmd

---
title: "Cloud Native Remote Sensing with Python (Full Course)"
author: "Ujaval Gandhi"
subtitle: A structured introduction to XArray, DuckDB, STAC and Dask for cloud-based remote sensing applications.
output:
  # pdf_document:
  #   toc: yes
  #   toc_depth: '3'
  #   latex_engine: xelatex 
  html_document:
    df_print: paged
    highlight: pygments
    toc: yes
    toc_depth: 2
    includes:
      in_header: 
        - copy-code.html
        - GA_Script.html
      after_body: comment.html
fontsize: 12pt
header-includes:
- \usepackage{fancyhdr}
- \pagestyle{fancy}
- \renewcommand{\footrulewidth}{0.4pt}
- \fancyhead[LE,RO]{\thepage}
- \geometry{left=1in,top=0.75in,bottom=0.75in}
- \fancyfoot[CE,CO]{{\includegraphics[height=0.5cm]{images/cc-by-nc.png}} Ujaval Gandhi
  http://www.spatialthoughts.com}
classoption: a4paper
---
\newpage

***

```{r echo=FALSE, fig.align='center', out.width='75%', out.width='250pt'}
knitr::include_graphics('images/spatial_thoughts_logo.png')
```

***

\newpage

# Introduction 

This is an intermediate-level course that covers tools and techniques for working with climate and earth observation datasets using modern cloud-native approach. With the growing ecosystem of cloud native data formats, open data catalogs and powerful open-source packages - remote sensing practitioners are now able to adopt open and vendor agnostic cloud-based data processing workflows. This class will cover how to implement these workflows using Python-based tooling with hands-on examples. 


[![View Presentation](images/python_remote_sensing/introduction.png){width="400px"}](https://docs.google.com/presentation/d/1YhT8OdrOm0JkkoTJ-eyQC89V2q6QiFXpA_57QW6caec/edit?usp=sharing){target="_blank"}

[Google Slides ↗](https://docs.google.com/presentation/d/1YhT8OdrOm0JkkoTJ-eyQC89V2q6QiFXpA_57QW6caec/edit?usp=sharing){target="_blank"} [PDF ↗](https://github.com/spatialthoughts/courses/releases/download/presentations/Cloud_Native_Remote_Sensing_with_Python_Introduction_and_Course_Overview.pdf){target="_blank"}

# Complete the Class Pre-Work

This class needs about 2-hours of pre-work. Please watch the following videos to get a good understanding of remote sensing and cloud native geospatial. 

* [Introduction to Remote Sensing](https://www.youtube.com/watch?v=xAyNu9HbK8s){target="_blank"}: This video introduces the remote sensing concepts, terminology and techniques. Take [Quiz-1](https://forms.gle/5WspCRrtCTL6gqL5A){target="_blank"} after you watch the video.
* [Introduction to Cloud Native Geospatial](https://www.youtube.com/watch?v=Q488KkRVaSA){target="_blank"}: This video introduces the concepts of cloud-native geospatial and gives you an overview of the open-source ecosystem. Take [Quiz-2](https://forms.gle/bCCdugupywMQ1D1R7){target="_blank"} after you watch the video.

# Get the Course Videos

The course is accompanied by a set of videos covering the all the modules. These videos are recorded from our live instructor-led classes and are edited to make them easier to consume for self-study. We have 2 versions of the videos:

## YouTube

We have created a YouTube Playlist with separate videos for each section and exercise to enable effective online-learning. [Access the YouTube Playlist ↗](https://youtube.com/playlist?list=PLJ6KzdqIbJJw&si=djahKMSn-7EzxKBM){target="_blank"}

## Vimeo

We are also making the module videos available on Vimeo. These videos can be downloaded for offline learning. [Access the Vimeo Playlist ↗](https://vimeo.com/showcase/12427471?share=copy&fl=sm&fe=fe){target="_blank"}


# Installation and Setting up the Environment 

All the notebooks in this course are structured so they can be run in any Jupyter-based notebook environment. We will run them in the cloud using Google Colab and on your own machine using Jupyter Lab. 

## Cloud Notebook Environment

We will be using Google Colab as the main cloud-based environment for executing the notebooks in this course.
[Google Colab](https://research.google.com/colaboratory/faq.html){target="_blank"} provides a cloud-hosted Jupyter notebook environment. 

**This does not require any setup and can be used with a Google account.**

The notebooks in this course can be accessed by clicking on the ![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg) buttons at the beginning of each section.

## Local Development Environment

To run the notebooks on your own machine, we first create a new conda environment and install the required packages. Then using Jupyter Lab, you can execute the notebook.

### Install Conda

Follow our step-by-step [Conda Installation Guide](install-conda.html){target="_blank"} to install Miniconda for your operating system.

### Create an Environment and Install Packages

We will use conda to install the required Python packages and manage local development environment. 

1. *(Windows users)*, search for Anaconda Powershell Prompt and launch it. *(Mac/Linux users)*: Launch a Terminal window. Run the following commands to create a fresh environment and activate it.

```{bash eval=FALSE}
conda create --name python_remote_sensing -y
conda activate python_remote_sensing
```

2. Now your environment is ready. We will install the required packages from `conda-forge`. Copy/paste the platform-appropriate code from below.

*Windows Users*

```{bash eval=FALSE}
conda install -c conda-forge -y `
  botocore `
  bottleneck `
  coiled `
  dask `
  distributed `
  duckdb `
  earthengine-api `
  exactextract `
  geopandas `
  geotessera `
  jupyterlab `
  jupyter-server-proxy `
  lonboard `
  matplotlib `
  netcdf4 `
  numpy `
  odc-algo `
  odc-stac `
  omnicloudmask `
  openpyxl `
  pandas `
  planetary-computer `
  pyproj `
  pystac-client `
  python-graphviz `
  rioxarray `
  scikit-learn `
  xarray `
  xarray-spatial `
  xee `
  xvec
```

*Mac/Linux Users*

```{bash eval=FALSE}
conda install -c conda-forge -y \
  botocore \
  bottleneck \
  coiled \
  dask \
  distributed \
  duckdb \
  earthengine-api \
  exactextract \
  geopandas \
  geotessera \
  jupyterlab \
  jupyter-server-proxy \
  lonboard \
  matplotlib \
  netcdf4 \
  numpy \
  odc-algo \
  odc-stac \
  omnicloudmask \
  openpyxl \
  pandas \
  planetary-computer \
  pyproj \
  pystac-client \
  python-graphviz \
  rioxarray \
  scikit-learn \
  xarray \
  xarray-spatial \
  xee \
  xvec
```

3. Some packages are not available on conda-forge, so we install them from PyPI using `pip`.

*Windows/Mac/Linux Users*

```{bash eval=FALSE}
conda install -c conda-forge -y pip
pip install aef-loader xrscipy 
```

Your local development environment is now ready.

# Development Tools

## Introduction to Google Colab

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/00_hello_colab.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/00_hello_colab.md'}
```

## Introduction to GeoLibre

[GeoLibre](https://geolibre.app/){target="_blank"} is an open-source cloud-native GIS platform that supports loading and visualizing a wide-variety of cloud-native geospatial data formats. It is well suited for cloud-native data work - exploring large datasets, collecting training samples, interactively visualizing outputs and more. 

We will be using the [GeoLibre Viewer](https://viewer.geolibre.app/){target="_blank"} in this course. Let's take a quick tour to get familiar with the interface and the capabilities.

1. Visit [https://viewer.geolibre.app/](https://viewer.geolibre.app/){target="_blank"} to open the GeoLibre Viewer. Select the *Advanced* interface.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre1.png')
```

2. The viewer is a static web app that runs on your browser.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre2.png')
```

3. GeoLibre can load data from your local machine as well as cloud locations. Let's load a vector layer. Go to **Add Data → Vector Layer**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre3.png')
```

4. In the *Add Vector Data* panel, click the *Drop file or click to browse* button. Locate the `capitals.gpkg` we downloaded in the previous section and click *Open*. A new layer `capitals` will be added to the viewer. Close the panel.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre4.png')
```

5. Let's add a raster layer next. Go to **Add Data → Raster Layer**. We will load a large Cloud Optimized GeoTiff (COG) of the VIIRS Nighttiem Lights dataset hosted in a cloud bucket. Paste the following URL and click *Load*.

```
https://storage.googleapis.com/spatialthoughts-public-data/ntl/viirs/viirs_ntl_2021_global.tif
```

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre5.png')
```

6. A new layer `viirs_ntl_2021_global.tif` will be added. You can change the default colormap to any other colormap of your choice and adjust the visualization settings. You can also insepct the pixel values by first enabling the *Inspect* button and then clicking on the map. When you are done, close the panel.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre6.png')
```

7. GeoLibre comes with many plugins that extend its core functionality. We will add a basemap layer next. Go to **Plugins → Basemaps → Activate**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre7.png')
```

8. Select the **Google Satellite** basemap and it will be added to the viewer. Adjust the *Opacity* slider to see the layer below.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/geolibre8.png')
```

In this course, we will also use GeoLibre for collecting samples for supervised classification. Detailed workflow for data creation is explained in Module 4.

## AI Coding Agents

### Google Gemini in Colab

We recommend using the built-in Gemini integration in Google Colab for writing, modifying and updating code in the provided notebooks.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gemini_colab.png')
```

### Claude Code

We have provided a Claude Code skill [cloud-native-remote-sensing](https://github.com/spatialthoughts/spatialthoughts-ai-skills/){target="_blank"} that captures the best-practices and workflows taught in this course. This approach is recommended when creating new notebooks or working on more complex updates. See the repository [README.md](https://github.com/spatialthoughts/spatialthoughts-ai-skills/blob/main/README.md){target="_blank"} for instructions on how to install and use this skill.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/claude_skill.png')
```


# Module 1: Introduction to Cloud Native Geospatial Tools

[![View Presentation](images/python_remote_sensing/cng_tools.png){width="400px"}](https://docs.google.com/presentation/d/1FPQ4ZQVqTXW5hQ2FVZG9knwZNDnR3aUoeJvpUOoRC6Y/edit?usp=sharing){target="_blank"}

[Google Slides ↗](https://docs.google.com/presentation/d/1FPQ4ZQVqTXW5hQ2FVZG9knwZNDnR3aUoeJvpUOoRC6Y/edit?usp=sharing){target="_blank"} [PDF ↗](https://github.com/spatialthoughts/courses/releases/download/presentations/Cloud_Native_Remote_Sensing_with_Python_Cloud_Native_Geospatial_Basics.pdf){target="_blank"}

## 1.1 XArray Basics

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_01/01_xarray_basics.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_01/01_xarray_basics.md'}
```

## 1.2 STAC and Dask Basics

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_01/02_stac_dask_basics.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_01/02_stac_dask_basics.md'}
```

## 1.3 DuckDB Basics

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_01/03_duckdb_basics.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_01/03_duckdb_basics.md'}
```

## 1.4 Creating a Median Composite

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_01/04_median_composite.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_01/04_median_composite.md'}
```

## Assignment 1

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_01/assignment1.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_01/assignment1.md'}
```


# Module 2: Remote Sensing Fundamentals


[![View Presentation](images/python_remote_sensing/remote_sensing.png){width="400px"}](https://docs.google.com/presentation/d/1_LlMfxZ54QESEb0iKpclYWLqruzGXVW_d3w9q5epenA/edit?usp=sharing){target="_blank"}

[Google Slides ↗](https://docs.google.com/presentation/d/1_LlMfxZ54QESEb0iKpclYWLqruzGXVW_d3w9q5epenA/edit?usp=sharing){target="_blank"} [PDF ↗](https://github.com/spatialthoughts/courses/releases/download/presentations/Cloud_Native_Remote_Sensing_with_Python_Remote_Sensing_Fundamentals.pdf){target="_blank"}

## 2.1 Calculating Spectral Indices

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_02/01_calculating_indices.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_02/01_calculating_indices.md'}
```

## 2.2 Masking Clouds

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_02/02_masking_clouds.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_02/02_masking_clouds.md'}
```

## 2.3 Extracting and Processing Time-Series

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_02/03_extracting_time_series.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_02/03_extracting_time_series.md'}
```

## Assignment 2

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_02/assignment2.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_02/assignment2.md'}
```


# Module 3: Computation and Data Processing

[![View Presentation](images/python_remote_sensing/computation.png){width="400px"}](https://docs.google.com/presentation/d/1rC3wh7hqZzWRmb5AP7hlteCJf3KbS5fL7csndGE7bNo/edit?usp=sharing){target="_blank"}

[Google Slides ↗](https://docs.google.com/presentation/d/1rC3wh7hqZzWRmb5AP7hlteCJf3KbS5fL7csndGE7bNo/edit?usp=sharing){target="_blank"} [PDF ↗](https://github.com/spatialthoughts/courses/releases/download/presentations/Cloud_Native_Remote_Sensing_with_Python_Computation_and_Data_Processing.pdf){target="_blank"}

## 3.1 Working with Landcover Data

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_03/01_working_with_landcover.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_03/01_working_with_landcover.md'}
```

## 3.2 Analyzing Landcover Change

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_03/02_analyzing_landcover_change.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_03/02_analyzing_landcover_change.md'}
```


## 3.3 Computing Zonal Statistics

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_03/03_zonal_statistics.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_03/03_zonal_statistics.md'}
```

## 3.4 Interoperability with Google Earth Engine

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_03/04_working_with_xee.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_03/04_working_with_xee.md'}
```

# Module 4: Machine Learning and AI

[![View Presentation](images/python_remote_sensing/machine_learning.png){width="400px"}](https://docs.google.com/presentation/d/1AHlQq75wm3G5H-KRDhnaAdjtfmVW1Gbm3tBQLCBx2Uk/edit?usp=sharing){target="_blank"}

[Google Slides ↗](https://docs.google.com/presentation/d/1AHlQq75wm3G5H-KRDhnaAdjtfmVW1Gbm3tBQLCBx2Uk/edit?usp=sharing){target="_blank"} [PDF ↗](https://github.com/spatialthoughts/courses/releases/download/presentations/Cloud_Native_Remote_Sensing_with_Python_Machine_Learning_and_AI.pdf){target="_blank"}

## 4.1 Preparing Data for Machine Learning

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_04/01_preparing_composites.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_04/01_preparing_composites.md'}
```

## 4.2 Unsupervised Classification

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_04/02_unsupervised_classification.ipynb){target="_blank"}


```{r child='python-remote-sensing-output/module_04/02_unsupervised_classification.md'}
```

## 4.3 Collecting Training Samples

For training a supervised classification model, we need to collect training samples with labels. We will be using visual interpretation of the Sentinel-2 composite image created in the [previous section](#preparing-data-for-machine-learning) to mark locations and label them with appropriate landcover class.

<table style="border-collapse: collapse;">
<tr><th style="border: 1px solid black; padding: 6px;">Class</th><th style="border: 1px solid black; padding: 6px;">Description</th><th style="border: 1px solid black; padding: 6px;">Value</th><th style="border: 1px solid black; padding: 6px;">Color</th></tr>
<tr><td style="border: 1px solid black; padding: 6px;">urban</td><td style="border: 1px solid black; padding: 6px;">All built surfaces - buildings, bridges, roads etc.</td><td style="border: 1px solid black; padding: 6px;">0</td><td style="border: 1px solid black; padding: 6px;">#cc6d8f</td></tr>
<tr><td style="border: 1px solid black; padding: 6px;">bare</td><td style="border: 1px solid black; padding: 6px;">All bare surfaces - exposed soil, sand, rock etc.</td><td style="border: 1px solid black; padding: 6px;">1</td><td style="border: 1px solid black; padding: 6px;">#ffc107</td></tr>
<tr><td style="border: 1px solid black; padding: 6px;">water</td><td style="border: 1px solid black; padding: 6px;">All surface water - lake, ponds, rivers, ocean etc.</td><td style="border: 1px solid black; padding: 6px;">2</td><td style="border: 1px solid black; padding: 6px;">#1e88e5</td></tr>
<tr><td style="border: 1px solid black; padding: 6px;">vegetation</td><td style="border: 1px solid black; padding: 6px;">All types of vegetation - trees, crops, grass etc.</td><td style="border: 1px solid black; padding: 6px;">3</td><td style="border: 1px solid black; padding: 6px;">#004d40</td></tr>
</table>

<br>

We will use the [GeoLibre Web](https://web.geolibre.app/){target="_blank"} for training data collection.

1. Open [GeoLibre Web](https://web.geolibre.app/){target="_blank"}. Go to **Add Data &rarr; Raster Layer**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gcp1.png')
```

2. Browse to the downloaded `multiband_composite.tif` created in the previous section and select *Open*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gcp2.png')
```

3. This will be the reference image for the sample collection. Next go to **Controls &rarr; Field Collection...**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gcp3.png')
```

4. Enter the *Layer name* as `gcps`. Add a field named `landcover` and select `Number` type. Check the `Required` box and click *Create layer*.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/gcp4.png')
```

5. Now the layer is ready. Click on the *Pick on map* button. Zoom to a location on the map and click on a point you want to add.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/gcp5.png')
```

6. Enter the *landcover* value for the location and click *Save point*.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/gcp6.png')
```

7. Collect approximately 5-10 samples for each class - ensuring good spatial distribution across your region of interest. If you need to edit or delete a point, you can use the *GeoEditor* plugin. Go to **Plugins &rarr; GeoEditor &rarr; Activate**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gcp7.png')
```

8. Toggle the editing mode by clicking on the layer menu for the `gcps` layer and selecting *Edit geometry*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gcp8.png')
```

9. Select the *Delete* button from the GeoEditor and click on the point you want to delete. Similarly, you may use the *Drag* button to move the point. Click *Save* once you are done editing.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gcp9.png')
```

10. Once you are done with sample collection, select on the layer menu for the `gcps` layer and go to **Export &rarr; GeoJSON**. Save the resulting file as `gcps.geojson`. 

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/gcp10.png')
```

Upload this file to your Google Drive in the data folder so we can use it in our next notebook.


## 4.4 Supervised Classification

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_04/03_supervised_classification.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/module_04/03_supervised_classification.md'}
```

## 4.5 Supervised Classification with AEF Embeddings

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_04/04_supervised_classification_embeddings.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/module_04/04_supervised_classification_embeddings.md'}
```


# Module 5: Computation Environments

This section demonstrates how the same processing can be done in different computing environments.

We will take a notebook and run it on different computing platforms.

- Run on your own local machine.
- Run on a Google Cloud Runtime with Google Colab
- Run on a Cloud VM with Coiled

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_05/cloudfree_s2_composite.ipynb){target="_blank"}

## 5.1 Running Computation on Your Hardware

Please following our [Installation and Setting up the Environment](#installation-and-setting-up-the-environment) instructions to install and configure your system. Once you have a working conda environment, you can use it to run the notebook.

### 5.1.1 Running Jupyter Notebooks

1. Open the notebook in Google Colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_05/cloudfree_s2_composite.ipynb){target="_blank"}. Go to **File &rarr; Download &rarr; Download .ipynb** and download the notebook to your computer. Save the file in a folder of your choice. We recommend saving it to a folder named `python_remote_sensing` on `Desktop`. Download your `aoi.geojson` file and keep it in a subfolder called `data`.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter1.png')
```

2. *(Windows users)*, search for Anaconda Powershell Prompt and launch it. *(Mac/Linux users)*: Launch a Terminal window. Run the following commands to activate your conda environment.

```{bash eval=FALSE}
conda activate python_remote_sensing
```

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter2.png')
```

3. Launch the *JupyterLab* application using the command below. This will initiate and run a local server in your system and opens in your default browser. 
> Note: Do not close your anaconda prompt after *JupyterLab* opens up. You need to keep it running as long as you want to use JupyterLab.

```{bash eval=FALSE}
jupyter-lab
```

*Windows* Jupyter Lab application can browse the files on the **C:** drive by default. If your notebook is on a separate drive, switch to the the drive first. On the command prompt, type the drive letter followed by `:` and press *Enter* to switch to the drive.

```
D:
```
```
jupyter-lab
```

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter3.png')
```

4. Locate the notebook in Jupyter Lab and open it. Ensure your `aoi.geojson` is present in a subfolder called `data/`. 

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter4.png')
```

5. Run the notebook from **Run &rarr; Run All Cells**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter5.png')
```

6. A local Dask cluster will be created on your machine and the data processing will be distributed across works on all the cores of your CPU. You can access the Dask Dashboard at [http://127.0.0.1:8787/](http://127.0.0.1:8787/){target="_blank"}

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter6.png')
```

7. Once the data processing finishes, the resulting cloudfree composite will be created in the `output/` folder.

> You may see some warnings and errors when shutting down the Dask cluster. These are harmless and can be ignored.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter7.png')
```

8. You can now stop the Jupyter server running in the Terminal/Powershell window by pressing the **Ctrl + C**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/jupyter8.png')
```


### 5.1.2 Running Batch Processing Scripts

You may often want to run longer running jobs un-attended on your machine or a remote server. Below is an example of a script that sets up a local dask cluster, queries a STAC catalog, fetches the required data and creates a median composite and shuts down the dask cluster. 

1. Create a new file named `batch_processing.py` with the following content. You can use any text editor to create this file. Ensure that the file is saved as a .`py` file without a `.txt` extension. Save the file in a folder of your choice. We recommend saving it to a folder named `python_remote_sensing` on `Desktop`. The key difference in the script compared to the notebook is that we use the Dask Distributed [Progress Bar](https://docs.dask.org/en/stable/diagnostics-distributed.html#progress-bar){target="_blank"} to monitor progress. This makes it easy to monitor the progress in the terminal in remote machines. 

```{python eval=FALSE, code=readLines('code/python_remote_sensing/module_05/batch_processing.py')}
```

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/batch1.png')
```

2. *(Windows users)*, search for Anaconda Powershell Prompt and launch it. *(Mac/Linux users)*: Launch a Terminal window. Run the following commands to activate your conda environment.

```{bash eval=FALSE}
conda activate python_remote_sensing
```

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/batch2.png')
```

3. Navigate to the directory containing the script using the `cd` command.

*Mac/Linux*
```{bash eval=FALSE}
cd Desktop/python_remote_sensing
```

*Windows*
```{bash eval=FALSE}
cd Desktop\python_remote_sensing
```


```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/batch3.png')
```

4. Run the script. It will start the process for creating the median composite. It will look for your input data `aoi.geojson` in a subfolder `data/`. If you want to use your own AOI, create this folder and add your file there before executing.

```{bash eval=FALSE}
python batch_processing.py
```

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/batch4.png')
```

5. Once the script finishes, the composite will be written to the `output/` folder and the Dask client with shutdown.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/batch5.png')
```

## 5.2 Using Google Cloud Runtime

Google Colab offers a seamless way to setup a VM in Google Cloud with a Colab Runtime and use it for executing your Colab Notebooks. This section requires a Google Cloud account. Follow our [Google Cloud Sign-up Guide](google-cloud-sign-up.html){target="_blank"} to setup your cloud project.

### Connect to a Cloud Runtime

1. Open the notebook in Google Colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_05/cloudfree_s2_composite.ipynb){target="_blank"}. Click the  *Additional connection options* dropdown next to the *Connect* button and select **Connect to Google Cloud Runtime**.

```{r echo=FALSE, fig.align='center', out.width='60%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime1.png')
```

2. Select a project in the *Google Cloud project*. If you do not have any VMs available, click *Manage runtimes*.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime2.png')
```

3. This will open the *Colab Enterprise* section in Google Cloud Console. You will be prompted to enable the APIs required for this service. Click on *Enable*.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime3.png')
```

4. Once the APIs are enabled, click on *Runtime templates*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime4.png')
```

5. In the *Runtime templates* tab, click on *+ New Template*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime5.png')
```

6. Enter a name for your template and click *Configure compute*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime6.png')
```

7. Select the type of machine you need. Higher number of CPU cores will allow more parallel computing and faster processing. Once selected, click *Create*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime7.png')
```

8. Once the template is created, click on the overflow menu *:* and select *Create runtime*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime8.png')
```

9. Confirm the details and click *Create*.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime9.png')
```

10. It will take a few minutes for the new runtime to be created. Wait till the *Status* shows **Healthy**.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime10.png')
```

11. Switch back to Google Colab and click the *Refresh* button. Your newly created VM should be listed. Select it and click *Connect*.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/colab_cloudruntime11.png')
```

### Run Your Notebook

Run your notebook as usual. Your analysis will run on the cloud VM.

### Delete the Runtime

If you do not delete the VM after you are done with the analysis, you will incur recurring charges for the compute and storage. It is advisable to delete any Runtimes that you are not using actively.

Once you are done with the analysis, go back to the *Colab Enterprise* section and select *Runtimes*. Click the *:* menu for any Runtime that are running and select *Delete*.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/colab_deleteruntime1.png')
```

## 5.3 Scaling Analysis in Cloud with Coiled

[Coiled](https://coiled.io/){target="_blank"} is a platform that allows you to easily setup cloud infrastructure for distributed processing. It provides a Python-package and a Notebook service that makes it very easy to scale your Xarray + Dask workflows to process large volumes of data. In this section, you will learn how to setup coiled and run a notebook in a cloud-hosted machine for creating a median cloud-free annual composite from Sentinel-2 imagery.

### Installation and Setting up the Environment

You need to install the `coiled` along with other required packages in your local Python environment and configure your account. Visit the [Coiled Documentation](https://docs.coiled.io/user_guide/setup/index.html){target="_blank"} for detailed setup instructions. 

#### Create an Account

[Sign-up](https://cloud.coiled.io/signup){target="_blank"} for a free coiled account.

#### Login to Coiled

We will use our existing conda environment to run the coiled notebook. Activate the environment and login to coiled.

```
conda activate python_remote_sensing
coiled login
```

#### Connect your Cloud Account

Next, you will need to configure it with your own cloud account. All popular cloud services (GCP, AWS, Azure) are supported. Below is the command required to configure it with your GCP account.

```
coiled setup gcp
```

Once setup, you can visit the [Coiled Dashboard](https://cloud.coiled.io/){target="_blank"} to verify the setup.

#### Setup Mutagen (Optional)

A great feature of the coiled notebook service is the ability to sync your local Python environment and files with the cloud machine. This requires installing the [Mutagen](https://docs.coiled.io/user_guide/notebooks.html#notebook-file-sync){target="_blank"} utility. On MacOS and Linux, this is straightforward using Homebrew.

```
brew install mutagen-io/mutagen/mutagen
```

#### Start a Notebook on a Cloud Machine

1. Change your local directory to a folder where you have your code.

```
cd Desktop/coiled
```

2. Start a notebook on a cloud machine. The default machine you get on GCP is the `e2-standard-4` VM with 4 vCPU and 16 GB memory. This is a decent and cheap option for small to medium sized workloads. You can always get bigger machine with more memory of more vCPUs. See how to specify [VM Size and Type](https://docs.coiled.io/user_guide/clusters/size-and-type.html){target="_blank"}.

```
coiled notebook start --sync
```

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/coiled_notebook_start.png')
```

### Run Your Notebook

1. Download the example notebook to your machine. Visit [coiled_s2_composite.ipynb](https://github.com/spatialthoughts/courses/blob/master/code/python_remote_sensing/module_05/cloudfree_s2_composite.ipynb){target="_blank"} and click the *Download raw file* button. Copy the file to your preferred directory where you started the coiled notebook. The file will appear in the Jupyter Lab instance that was launched by Coiled. Double-click to open the notebook.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/coiled_notebook_view.png')
```

2. Run the notebook to start the data processing. The notebook is running on a cloud machine and you can see the progress on the Dask Dashboard.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/coiled_notebook_run.png')
```

3. Once the processing finishes, the resulting composite `rgb_composite_2024.tif` will be available in the `output` folder which will be automatically synced to your machine.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/coiled_output.png')
```

4. The resulting Sentinel-2 RGB composite is now available on your machine and can be viewed using QGIS.

```{r echo=FALSE, fig.align='center', out.width='75%'}
knitr::include_graphics('images/python_remote_sensing/coiled_composite.png')
```

5. Once you are done with processing, remember to stop the notebook server. This will stop the cloud instance.

> If you forget to stop the server, you will continue getting charged for the running intance in the cloud. You can always visit the [Coiled Dashboard](https://cloud.coiled.io/){target="_blank"} to verify that there are no running clusters.

```{r echo=FALSE, fig.align='center', out.width='50%'}
knitr::include_graphics('images/python_remote_sensing/coiled_notebook_stop.png')
```

# Guided Projects

Below are step-by-step walk through of implementing real-world projects using cloud native remote sensing. You can continue their learning journey by implementing these projects for their region of interest after the class.

## Project: Extracting NDVI Time-Series for Multiple Field Boundaries

In this project, you will learn how to set up your notebook for a large-scale data extraction project. We will take 100 field boundaries spanning an entire district and see how we can extract the average NDVI values at each of the fields for the entire year and post-process the results into an analysis-ready output. 

This project is split across 3 notebooks.

- [01. Extract Field Boundaries](#extract-field-boundaries)
- [02. Create a Tiling Grid](#create-a-grid)
- [03. Extract NDVI Time-Series](#extract-ndvi-time-series)

These are meant to be run sequentially. Each generates an output which is used in the subsequent notebook. You can start from the first notebook below.

### 01. Extract Field Boundaries

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/projects/ndvi_time_series/01_extract_field_boundaries.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/projects/ndvi_time_series/01_extract_field_boundaries.md'}
```

### 02. Create a Tiling Grid

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/projects/ndvi_time_series/02_create_a_grid.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/projects/ndvi_time_series/02_create_a_grid.md'}
```

### 03. Extract NDVI Time-Series

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/projects/ndvi_time_series/03_extract_ndvi_time_series.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/projects/ndvi_time_series/03_extract_ndvi_time_series.md'}
```


# Supplement

## Using Planetary Computer Data Catalog

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/pc_extracting_time_series.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/pc_extracting_time_series.md'}
```

## Creating Pixel Composites

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/creating_pixel_composites.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/creating_pixel_composites.md'}
```


## Downloading Sentinel-2 Cloud Free Mosaics

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/s2_cloudfree_mosaics.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/s2_cloudfree_mosaics.md'}
```

## Extracting Building Heights from GlobalBuildingAtlas

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/extracting_building_heights.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/extracting_building_heights.md'}
```

## Cloud Masking with OmniCloudMask

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/cloud_masking_with_omnicloudmask.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/cloud_masking_with_omnicloudmask.md'}
```

## Cloud Masking with Cloud Score+

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/cloud_masking_with_cloudscoreplus.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/cloud_masking_with_cloudscoreplus.md'}
```

## Working with GLC-FCS30 LandCover Data

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/glc_fcs30d_landcover.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/glc_fcs30d_landcover.md'}
```


## Calculating Zonal Stats for Landcover Area

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/s2_cloudfree_mosaics.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/zonal_histogram.md'}
```


## Supervised Classification with TESSERA Embeddings

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/tessera_supervised_classification.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/tessera_supervised_classification.md'}
```

## Unsupervised Classification with TESSERA Embeddings

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/spatialthoughts/courses/blob/master/code/python_remote_sensing/supplement/tessera_unsupervised_classification.ipynb){target="_blank"}

```{r child='python-remote-sensing-output/supplement/tessera_unsupervised_classification.md'}
```

----

# Learning Resources

Here are curated learning materials to that cover additional topics and datasets.

## Courses and Workshops

* [Cloud Native Geospatial for Earth Observation Workshop](https://github.com/auspatious/cloud-native-geospatial-eo-workshop){target="_blank"}: A workshop by Alex Leith and Caitlin Adams introducing cloud native methods of working with Earth observation data products.
* [Cloud-Native Geospatial 101: A Practical Introduction to Modern Geospatial Workflows](https://github.com/thriveGEO/cng-101-workshop-2026){target="_blank"}:  An introductory workshop by Julia Wagemann and Guillaume Eynard-Bontemps on Cloud-Native Geospatial to understand how modern geospatial data formats work.

## Tutorials

* [Geospatial Python Tutorials](https://www.geopythontutorials.com/){target="_blank"}: A large collection of step-by-step tutorials by Spatial Thoughts covering XArray, STAC, Dask, XEE and more.
* [EOPF Xarray Notebooks](https://eopf-toolkit.github.io/eopf-101/06_eopf_zarr_in_action/64_flood_mapping_valencia.html){target="_blank"}: Case studies and applications of EOPF Sentinel Zarr products - including flood mapping, vegetation monitoring, fire mapping and more.
* [Copernicus Data Space Ecosystem Notebooks](https://github.com/eu-cdse/notebook-samples/tree/main){target="_blank"}: Notebooks showing how to use access the data from the [CDSE STAC Catalog](https://documentation.dataspace.copernicus.eu/APIs/STAC.html){target="_blank"} having data from all Sentinel missions as well as landcover data.
* [Earth Data Hub Tutorials](https://github.com/bopen/edh-learning/){target="_blank"}: Jupyter notebooks showing how to access and process climate and Earth observation Zarr data (ERA5, Sentinel-1 ARD, CMIP6, Copernicus DEM) via Python and Xarray.
* [Building an EVI Timeseries with ODC STAC](https://github.com/nasa/HLS-Data-Resources/blob/main/python/tutorials/EVI_timeseries_with_odc_stac.ipynb){target="_blank"}: A tutorial showing how to access Harmonized Landsat Sentinel-2 (HLS) data from NASA CMR-STAC and earthaccess.
* [Project Pythia Cookbooks](https://cookbooks.projectpythia.org/){target="_blank"}: A community learning resource for Python-based computing in the geosciences. Includes examples of remote sensing data such as [Landsat ML Cookbook](https://projectpythia.org/landsat-ml-cookbook/){target="_blank"}.
* [Exploring HLS data](https://github.com/auspatious/hls-experiments/tree/main){target="_blank"}: Loading and processing Harmonized Landsat and Sentinel-2 data with advanced cloud-masking using morphological operations.

## Guides and References

* [Cloud-Optimized Geospatial Formats Guide](https://guide.cloudnativegeo.org/){target="_blank"}: Methods for Generating and Testing Cloud-Optimized Geospatial Formats

# Data Credits

* Sentinel-2 Level 2A Scenes: Contains modified Copernicus Sentinel data (2025-02)
* Landsat imagery courtesy of the U.S. Geological Survey.
* Bangalore Ward Maps Provided by Spatial Data of Municipalities (Maps) Project by Data{Meet}.
* Admin boundaries: FieldMaps, geoBoundaries, U.S. Department of State, OpenStreetMap
* Populated Places: Made with Natural Earth. Free vector and raster map data @ naturalearthdata.com.
* Overture Maps Foundation Open Map Data. © Overture Maps Foundation. [https://overturemaps.org](https://overturemaps.org){target="_blank"}
* TerraClimate: Monthly Climate and Climatic Water Balance for Global Terrestrial Surfaces, University of Idaho: Abatzoglou, J.T., S.Z. Dobrowski, S.A. Parks, K.C. Hegewisch, 2018, Terraclimate, a high-resolution global dataset of monthly climate and climatic water balance from 1958-2015, Scientific Data 5:170191, doi:10.1038/sdata.2017.191
* Climate Hazards Center (2025). Climate Hazards Center Infrared Precipitation with Stations (CHIRPS) Data Repository. [https://doi.org/10.15780/G2JQ0P](https://doi.org/10.15780/G2JQ0P){target="_blank"}. Accessed 2026-05-01.
* Schiavina, M., Freire, S., Carioli, A., MacManus, K. (2023). GHS-POP R2023A - GHS population grid multitemporal (1975-2030). European Commission, Joint Research Centre (JRC). doi:10.2905/2FF68A52-5B5B-4A22-8F40-C41DA8332CFE
* Elvidge, C.D., Zhizhin, M., Ghosh, T., Hsu, F.C., Taneja, J. (2021). Annual time series of global VIIRS nighttime lights derived from monthly averages: 2012 to 2019. Remote Sensing, 13(5), 922. [https://doi.org/10.3390/rs13050922](https://doi.org/10.3390/rs13050922){target="_blank"}
* Takaku, J., Tadono, T., Tsutsui, K. (2014). Generation of High Resolution Global DSM from ALOS PRISM. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XL-4, pp. 243–248.
* Zhu, X. X., Chen, S., Zhang, F., Shi, Y., and Wang, Y.: GlobalBuildingAtlas: an open global and complete dataset of building polygons, heights and LoD1 3D models, Earth Syst. Sci. Data, 17, 6647–6668, [https://doi.org/10.5194/essd-17-6647-2025](https://doi.org/10.5194/essd-17-6647-2025){target="_blank"}, 2025.
* Potapov P, Hansen MC, Pickens A, Hernandez-Serna A, Tyukavina A, Turubanova S, Zalles V, Li X, Khan A, Stolle F, Harris N, Song X-P, Baggett A, Kommareddy I and Kommareddy A (2022) The Global 2000-2020 Land Cover and Land Use Change Dataset Derived From the Landsat Archive: First Results. Front. Remote Sens. 3:856903. doi: 10.3389/frsen.2022.856903
* Karra, Kontgis, et al. "Global land use/land cover with Sentinel-2 and deep learning." IGARSS 2021-2021 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2021.
* Zanaga, D., Van De Kerchove, R., De Keersmaecker, W., Souverijns, N., Brockmann, C., Quast, R., Wevers, J., Grosu, A., Paccini, A., Vergnaud, S., Cartus, O., Santoro, M., Fritz, S., Georgieva, I., Lesiv, M., Carter, S., Herold, M., Li, L., Tsendbazar, N.E., Ramoino, F., Arino, O. (2022). ESA WorldCover 10 m 2021 v200. [https://doi.org/10.5281/zenodo.7254221](https://doi.org/10.5281/zenodo.7254221){target="_blank"}
* Zhang, X., Zhao, T., Xu, H., Liu, W., Wang, J., Chen, X., and Liu, L. (2024). GLC_FCS30D: the first global 30 m land-cover dynamics monitoring product with a fine classification system for the period from 1985 to 2022. Earth Syst. Sci. Data, 16, 1353–1381. [https://doi.org/10.5194/essd-16-1353-2024](https://doi.org/10.5194/essd-16-1353-2024){target="_blank"}
* Brown, C. F., Kazmierski, M. R., Pasquarella, V. J., et al. (2025). AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data. arXiv:2507.22291.
* Earth Genome. Sentinel-2 Cloud Free Temporal Mosaics. [https://earthgenome.org](https://earthgenome.org){target="_blank"}

# References

* Cordeiro, M. C. R.; Martinez, J.-M.; Peña-Luque, S. Automatic Water Detection from Multidimensional Hierarchical Clustering for Sentinel-2 Images and a Comparison with Level 2A Processors. *Remote Sensing of Environment* 2021, 253, 112209.
* Chen, J., Jönsson, P., Tamura, M., Gu, Z., Matsushita, B., & Eklundh, L. (2004). A simple method for reconstructing a high-quality NDVI time-series data set based on the Savitzky–Golay filter. Remote Sensing of Environment, 91(3–4), 332–344. [https://doi.org/10.1016/j.rse.2004.03.014](https://doi.org/10.1016/j.rse.2004.03.014){target="_blank"}

# License

This course material is licensed under a [Creative Commons Attribution 4.0 International (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/){target="_blank"}. You are free to re-use and adapt the material but are required to give appropriate credit to the original author as below:

*Cloud Native Remote Sensing with Python* course by Ujaval Gandhi [www.spatialthoughts.com](https://spatialthoughts.com){target="_blank"}


***

&copy; 2026 Spatial Thoughts [www.spatialthoughts.com](https://spatialthoughts.com){target="_blank"}