Two types of combine:

First pass:

• Collect all common bands and return images with common bands, start with Landsat 5, 7, 8
• Get collections, merge, sort by date

Second step (later):

• Normalizing all images to match.

What is the objective of the proposed tutorial?
The Sentinel-1 missions of the ESA provide a fantastic source of free, weather-independent Earth observation data with revisit times of the order of 6-12 days. The Google Earth Engine team monitor and ingest the imagery data as fast as they are produced, thus removing the burden from the user of searching, pre-processing and georeferencing. In this tutorial we will analyze Sentinel-1 imagery archived on the GEE in order to detect statistically significant changes over time. As the adverb "statistically" hints, we will need a basic understanding of the statistical properties of SAR imagery in order to proceed, and the adjective "significant" implies that we learn the fundamentals of hypothesis testing.

What is the scope of the proposed tutorial?
Specifically, we will be analyzing the dual polarimetric intensity images in the GEE archive and developing, step-by-step, methods to detect changes, both in bitemporal as well as multitemporal imagery. The JavaScript and Python API's to the GEE can be easily programmed to analyze time series of Sentinel-1 acquisitions virtually anywhere on the globe. Detected changes, both short- and long-term can be related to landscape dynamics and human activity, and examples will be given.

Please provide an outline of the structure of the proposed tutorial?
I would suggest dividing the tutorial into three parts, each submitted as a separate pull request :

• Single and multi-look image statistics
• Hypothesis testing for change detection
• Applications

In what format will you be submitting the tutorial?
Colab

This request will be reviewed by the Earth Engine community maintainers, who will reply on this issue tracker with any questions or suggestions. Once approved, this issue will be assigned to you and you can begin work on the tutorial following instructions in Writing a tutorial. When ready, enter “Closes #issueno” in the description of your Pull Request to link the tutorial to this issue.

Issue labels:
proposal, tutorial

Exposing CCDC helper functions inside toolkit. Some should be clear where to incorporate.

bands: ['TC1', 'TC2', 'TC3']
bands: ['SWIR1', 'NIR', 'Red']
bands: ['SWIR1', 'NIR', 'Green']
bands: ['NIR', 'Red', 'Green']
bands: ['NIR', 'SWIR1', 'Red']

I have generally decent stretches for all of these.

e.g. The "Hansen" feature vector

Details TBD

Lots of images, but seems like it should handle it?

// TODO(gino-m): Replace with shared code repo.
var lct = require('users/google/toolkits:landcover/api.js');

// Create a new Landsat8 dataset.
var dataset = lct.Landsat8()
  // Filter by date.
  .filterDate('2018-06-01', '2019-01-01')
  // Filter by country boundary.
  .filterBounds(lct.Region.lsib('Tanzania'))
  // Add Tasseled Cap transformation bands.                 
  .addTasseledCap(); 

// Print a list of available bands.
print('Bands:', dataset.getImageCollection().first().bandNames());

// Add the resulting ImageCollection to the map, taking the median of
// overlapping pixel values.
var imageVisParam = {"opacity":1,"bands":["TC1","TC2","TC3"],"min":-819.3741274451727,"max":3228.7496002292146,"gamma":1};
Map.addLayer(
  dataset.getImageCollection().median(), imageVisParam);
Map.setCenter(33.776, -5.944, 5);

What is the objective of the proposed tutorial?
In this tutorial, an introduction to the GEE Python API is presented. After some setups and some exploration of the Earth Engine Data Catalog, we’ll see how to handle geospatial datasets with pandas and make some plots with matplotlib. Particularly, we’ll see how to get the timeseries of a variable on a region of interest.

What is the scope of the proposed tutorial?
An application of different principals will be illustrated to extract and compare Land Surface Temperature in an urban and a rural area near the city of Lyon (France) to illustrate the heat island effect of urban areas.

Please provide an outline of the structure of the proposed tutorial?

1. Introduction
2. Exploration of the Earth Engine Data Catalog
3. Installation of the earth-engine-api and start
   3.1 Some setups
   3.2 Start to play with collections
   3.3. Get some time series
   4.Static mapping of Land Surface Temperature and Ground Elevation
   4.1. Get a static map
   4.2. Clip an image on a region of interest
   4.3. Export a geotiff file
   5.Interactive mapping using folium

In what format will you be submitting the tutorial?
[Colab]

Others
I plan to adapt the current version of the tutorial I made regarding your guidelines: https://guillaumeattard.com/introduction-to-the-google-earth-engine-python-api-data-catalog-exploration-static-and-interactive-mapping/

I made this tutorial for my students.

This request will be reviewed by the Earth Engine community maintainers, who will reply on this issue tracker with any questions or suggestions. Once approved, this issue will be assigned to you and you can begin work on the tutorial following instructions in Writing a tutorial. When ready, enter “Closes #issueno” in the description of your Pull Request to link the tutorial to this issue.

Issue labels:
proposal, tutorial

To deal with saturated pixels, edge effects, etc.

The Rapid Classification of Croplands tutorial seems to be missing from the master branch:

• a shapefile layer labeled 'aoi'
• a csv: training-pts
• a csv: validation-pts

Incidentally, I was able to find version of training-pts.csv and validation-pts.csv on old branches but not 'aoi'. These files should be located here: 'projects/earthengine-community/tutorials/classify-maizeland-ng/'.

Layer 1: Layer error: reduce.count: Error in map(ID=LC08_018045_20180307):
Image.select: Pattern 'B8' did not match any bands.

Repro:
https://code.earthengine.google.com/abdc4cb0ff9685fc1489825ee76ca4a4

Reported in https://github.com/google/earthengine-community/pull/60/files#r334123160

Proposed by @gorelick-google #16.

What is the objective of the proposed tutorial?
This tutorial is an introduction to the Earth Engine App Creator (https://ee-app-creator.appspot.com/), an open source tool that allows developers to build rich Earth Engine applications. The tutorial will walk through building a sample app using the tool and converting into a functional UI on the code editor.

What is the scope of the proposed tutorial?
The tutorial covers the basic usage of the app creator, including a walk through of its features, and runs through multiple examples of building an Earth Engine App.

Please provide an outline of the structure of the proposed tutorial?

1. Introduction
   a. What is the Earth Engine App Creator?
   b. Purpose
2. Getting Started Guide
   a. Templates
   i. Structure
   ii. Selecting a template
   iii. Changing templates
   iv. Duplicating templates
   v. Importing templates
   vi. Exporting templates
   vii. Mobile templates
   b. Widgets
   i. Types
   ii. Adding widgets
   iii. Removing widgets
   iv. Editing widgets
   v. Sharing widgets
   d. Palettes
   i. Changing color palette
   e. Code Editor
   i. Importing template
   ii. Widget interface
   iii. Binding callbacks
   iv. Creating responsive apps
   v. Creating multi-themed apps
   vi. Creating multi-lingual apps
   vii. Creating multi-functional apps

In what format will you be submitting the tutorial?
Markdown

This request will be reviewed by the Earth Engine community maintainers, who will reply on this issue tracker with any questions or suggestions. Once approved, this issue will be assigned to you and you can begin work on the tutorial following instructions in Writing a tutorial. When ready, enter “Closes #issueno” in the description of your Pull Request to link the tutorial to this issue.

Issue labels:
proposal, tutorial

The following dataset methods add a constant band which has a mask unlike the associated image bands. Is there a good reason not to mask it based on the first band's mask, for instance?

addDateBand
addDayOfYearBand
addFractionalYearBand

Users will need to qualify fence language in order for this to work (i.e., "```js").

Requested by @jdbcode in #26 (review)

Issue Description:

when I try run the code, I get this error:

"Training points: Layer error: Collection.loadTable: Collection asset 'projects/earthengine-community/tutorials/classify-maizeland-ng/training-pts' not found."

Medoid appears to be much more common (153,000 search results) than medioid (4,220). Is there a reason to prefer "medioid"? @jdbcode was also asking about whether there's a reference for this.

Description

Technical Level
beginner | intermediate | advanced

Length
short (< 250 words) | medium (250-500 words) | long (1000 words )

@gorelick-google see private message re API and harmonization target.

Example:
https://code.earthengine.google.com/ab508cd405bb489b97b350f5e7ac1948

What is the objective of the proposed tutorial?
This tutorial will demonstrate an approach to assess forest vegetation condition using long term trends in vegetation status using MODIS data. It will walk through the choice of vegetation index and a particular season for computing annual composites, followed by trend analysis to compute trends in vegetation status change, a logic to infer vegetation condition, and visualize results. It will demonstrate calculating annual seasonal composites, reducers for trend analysis and area calculations, result charting and image visualizations. This is from a workshop I co-taught with a colleague at an earth engine summit last year

What is the scope of the proposed tutorial?
Forestry

Please provide an outline of the structure of the proposed tutorial?

1. Import images, features
2. Compute annual summertime composites
3. Apply regression and infer vegetation condition
4. Visualize results: extent and direction of change

In what format will you be submitting the tutorial?
Markdown

Issue labels:
proposal, tutorial

Map to dictionary if single are is a ee.ComputedObject. This is currently breaking filterBounds() and possibly other functions. Reported by @gorelick-google.

Note: Cloud masking is a little different for 4 5 and 8. See CCDC scripts.

I was planning to write a tutorial on developing and publishing apps on Earth Engine. I want to use my app (https://yceo.users.earthengine.app/view/uhimap) as an example template for the tutorial since I have used several ui functionalities there; plus it is easier than writing something from scratch.

The main issues is that some of the datasets used in the app are not in the Earth Engine data catalog. However, since my method and results are published (https://www.sciencedirect.com/science/article/pii/S0303243418304653), I could make the data available. So, a couple of queries:

1. How would I go about making this dataset available in the catalog? I know of similar datasets like from the Global Forest Watch that are available.

2. Do you think this tutorial is a good idea?

What is the objective of the proposed tutorial?
This tutorial will go through code to extract Landsat reflectance values for points. We will use Landsat 5, 7 and 8 to get values for every overpass from 1984-present, and will use a focal mean for each point (each point will get the mean of 9 pixels including the center).

What is the scope of the proposed tutorial?
This process is very common in ecology and forestry, and is applicable anywhere on earth.

Please provide an outline of the structure of the proposed tutorial?

1. Context
   a. Why point extraction
   b. Why focal mean
   c. Recognition that the mean reflectance of 90m x 90m is pretty large for some purposes, but recent work could use the same general methods with Sentinel 2 or another satellite for a focal mean with 30m resolution if you only need recent values.
   d. Suggestions of things to do with this data, including calculating NDVI and getting the max NDVI (Note: This could pretty easily be added to the tutorial and is almost certainly the most common use of these data, but I think it may make the structure a little confusing)
2. Import points (will supply with some random example points)
3. Prepare functions for Landsat preparation
   a. Cloud masks and renaming bands for both OLI and TM/ETM+
   b. Load L5, L7, and L8 image collections using the masks and band names
4. Reduce region to get values surrounding each point
   a. For each image, find each point and do a region reduction (mean in this tutorial)
   b. Add metadata for the satellite and date along with the reflectance values
   c. Flatten the collection of collections to get a single featureCollection with one row for each unique image-point combination
5. Export
   a. Export to Asset
   b. Export to Drive
6. References

In what format will you be submitting the tutorial?
Select one: [Markdown](https://guides.github.com/features/mastering-markdown/)

This request will be reviewed by the Earth Engine community maintainers, who will reply on this issue tracker with any questions or suggestions. Once approved, this issue will be assigned to you and you can begin work on the tutorial following instructions in Writing a tutorial. When ready, enter “Closes #issueno” in the description of your Pull Request to link the tutorial to this issue.

Issue labels:
proposal, tutorial

What is the objective of the proposed tutorial?
This tutorial attempt to explain the geospatial analysis we can make with Digital Elevation Model in Google Earth Engine.

What is the scope of the proposed tutorial?
The scope is of this tutorial is geoscience particulary hydrology.

Please provide an outline of the structure of the proposed tutorial?

1. Import Collection image
2. Outline Podor limit
3. Clip Data with Podor limit
4. Geoprocessing

In what format will you be submitting the tutorial?
Select one: Markdown

This request will be reviewed by the Earth Engine community maintainers, who will reply on this issue tracker with any questions or suggestions. Once approved, this issue will be assigned to you and you can begin work on the tutorial following instructions in Writing a tutorial. When ready, enter “Closes #issueno” in the description of your Pull Request to link t

DEM_Geoprocessing-master.zip

he tutorial to this issue.

Issue labels:
proposal, tutorial

IR-MAD: Iteratively reweighted multivariate alteration detection

Example:
https://code.earthengine.google.com/56e291064e159a732dbb3ded3ca8d460

Great tutorial!

• The Wang et al. citation in the reference section is probably not the right one
• The tutorial suggests that the NDSI is equivalent to a snow fraction. It would be more precise to note that the snow fraction can be considered as a linear function of the NDSI (Salomonson, V. V., & Appel, I. (2004). Estimating fractional snow cover from MODIS using the normalized difference snow index. Remote sensing of environment, 89(3), 351-360).

var lct =require('users/google/toolkits:landcover/api.js');
var roi = ee.FeatureCollection("users/wufvckshuo/HuangBoRiver");
Map.centerObject(roi,4);

var dataset = lct.Landsat5()
                  .filterDate('2009-04-01', '2009-09-30')
                  .filterBounds(roi)
                  .maskCloudsAndShadows();
Map.centerObject(roi);
Map.addLayer(roi);

Landsat8() is OK, but Landsat5() does not work!

What is the objective of the proposed tutorial?
A clear and concise description of what users can expect to learn from your tutorial.

What is the scope of the proposed tutorial?
The thematic (forestry, water resources, land cover classification, Earth Engine core libraries, etc) and specific geographic area, if relevant.

Please provide an outline of the structure of the proposed tutorial?

1. Section 1
   a. Subsection 1a
   b. Subsection 1b
2. Section 2
   .. et cetera. ..

In what format will you be submitting the tutorial?
Select one: Markdown or Colab

This request will be reviewed by the Earth Engine community maintainers, who will reply on this issue tracker with any questions or suggestions. Once approved, this issue will be assigned to you and you can begin work on the tutorial following instructions in Writing a tutorial. When ready, enter “Closes #issueno” in the description of your Pull Request to link the tutorial to this issue.

Issue labels:
proposal, tutorial

As discussed with @gorelick-google , in cases where there's only pure request-building logic to tests, we'll only test the outer layer of the result.

@gorelick-google FYI

Trying to do a better job of keeping track of open tasks, so filing the ones that are top of mind here. HTH.

When I change spatial extend of polygon the video is blank

What is the objective of the proposed tutorial?
The objective of this tutorial is to guide institutional and individual users to implement an automated routine/tool (in GEE) for classification of croplands within Nigeria's farming system, based on contextual peculiarities related to season and cropping practices. This tutorial is focused on developing the basic competency of the prospective user(s) to ingest ground-truth data and generate quick outputs about the regional estimate of land area sown with Maize.

What is the scope of the proposed tutorial?
Landcover classification for croplands

Please provide an outline of the structure of the proposed tutorial?

1. Introduction
   a. Need to classify croplands
   b. Value for users
   c. Data Sources

2. Data preparation and checking
   a. Groundtruth reference
   b. Importing boundary files
   c. Sentinel 2A Imageries

3. Analytics
   a. Defining model
   b. Selecting/optimizing Classifiers
   c. Generating results

4. Plotting the charts to generate insights

5. Exporting Outputs

In what format will you be submitting the tutorial?
Select one: Markdown

This request will be reviewed by the Earth Engine community maintainers, who will reply on this issue tracker with any questions or suggestions. Once approved, this issue will be assigned to you and you can begin work on the tutorial following instructions in Writing a tutorial. When ready, enter “Closes #issueno” in the description of your Pull Request to link the tutorial to this issue.

Issue labels:
proposal, tutorial