From 3419eac50ceabe539242fd781d8fe3e5576d6087 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Sun, 30 Jun 2024 19:18:03 +0000 Subject: [PATCH] Deployed 692d274 with MkDocs version: 1.6.0 --- index.html | 2 +- .../__pycache__/shortcodes.cpython-312.pyc | Bin 11304 -> 11304 bytes .../__pycache__/translations.cpython-312.pyc | Bin 5710 -> 5710 bytes search/search_index.json | 2 +- 4 files changed, 2 insertions(+), 2 deletions(-) diff --git a/index.html b/index.html index abfa8c71..790ef792 100644 --- a/index.html +++ b/index.html @@ -1,2 +1,2 @@ - TheroPoDa Documentation
Skip to content

Vinícius Mesquita / DALEE - theropod, jurassic landscape, digital art, hight quality

Time Series Extraction for Polygonal Data

Name

  • T(h)eroPoDa + - Time Series Extraction for Polygonal Data and Trend Analysis ⬛

Description

  • Toolkit created to extract Time Series information from Sentinel 2 🛰 data stored in Earth Engine, gap filling and trend analysis image

Author

Co-author

Version

  • 1.1.0

Requirements (installation order from top to bottom)

How to use

  • In this version of TheroPoDa (1.1.0), you could extract a series of median NDVI from Sentinel 2 for a Feature Collection of polygons simplily by passing arguments to the python code exemplified below:
argument usage example
--asset Choosed Earth Engine Vector Asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m
--id_field Vector column used as ID (use unique identifiers!) ID_POINTS
--output_name Output filename LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork

If you don't know how to upload your vector data in Earth Engine, you can follow the tutorial clicking this link.

Command line example

python theropoda.py --asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m --id_field ID_POINTS --output_name LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork
+ TheroPoDa Documentation      
 
 
  
 
  
 
 
 
 
  
 
 
 
 
 
  
 
 
 
 
       
Vinícius Mesquita / DALEE - theropod, jurassic landscape, digital art, hight quality
 
Time Series Extraction for Polygonal Data
 
Name
 
     
  • T(h)eroPoDa + - Time Series Extraction for Polygonal Data and Trend Analysis ⬛
    •  
 
Description
 
     
  • Toolkit created to extract Time Series information from Sentinel 2 🛰 data stored in Earth Engine, gap filling and trend analysis image
    •  
 
Author
  
Co-author
  
Version
 
     
  • 1.1.0
    •  
 
Requirements (installation order from top to bottom)
  
How to use
 
     
  • In this version of TheroPoDa (1.1.0), you could extract a series of median NDVI from Sentinel 2 for a Feature Collection of polygons simplily by passing arguments to the python code exemplified below:
    •  
 
  
 argument usage example 
   
 --asset Choosed Earth Engine Vector Asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m 
 
 --id_field Vector column used as ID (use unique identifiers!) ID_POINTS 
 
 --output_name Output filename LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork 
  
 
If you don't know how to upload your vector data in Earth Engine, you can follow the tutorial clicking this link.
 
Command line example
 
python main.py --asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m --id_field ID_POINTS --output_name LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork
 
 
Roadmap
 
     
  • Implement arguments to choose other zonal reducers (i.e. percentile, variance, etc.)
    •  
  • Implement arguments to choose other satellite data series (i.e. Landsat series, MODIS products)
    •  
  • Implement a visualization of the processed data (or samples of it)
    •  
 
 
  
  
  
 
 
 
     
\ No newline at end of file
diff --git a/material/overrides/hooks/__pycache__/shortcodes.cpython-312.pyc b/material/overrides/hooks/__pycache__/shortcodes.cpython-312.pyc
index add96c792bc3d7b52e17984939dca27c57c7889b..3615e5d157d31799b93e5435f15d3d6f91d50471 100644
GIT binary patch
delta 19
ZcmZ1xu_A)&G%qg~0}w>6-^eAW0{}UZ1qT2C

delta 19
ZcmZ1xu_A)&G%qg~0}xp9Zsd~F0RT0p1VsP<

diff --git a/material/overrides/hooks/__pycache__/translations.cpython-312.pyc b/material/overrides/hooks/__pycache__/translations.cpython-312.pyc
index f803007407c5273fdb4b2d7961483ca28e48f7f5..8ca1f94105d52ca94dabb9db598d19cde74d361a 100644
GIT binary patch
delta 19
ZcmX@7b54irG%qg~0}w>6-^k@61^_un1q%QG

delta 19
ZcmX@7b54irG%qg~0}xp9Zsc+i0{}H$1W5n@

diff --git a/search/search_index.json b/search/search_index.json
index 8041d7a0..ce741cfc 100644
--- a/search/search_index.json
+++ b/search/search_index.json
@@ -1 +1 @@
-{"config":{"lang":["en"],"separator":"[\\s\\u200b\\-_,:!=\\[\\]()\"`/]+|\\.(?!\\d)|&[lg]t;|(?!\\b)(?=[A-Z][a-z])","pipeline":["stopWordFilter"]},"docs":[{"location":"","title":"Home","text":""},{"location":"#time-series-extraction-for-polygonal-data","title":"Time Series Extraction for Polygonal Data","text":""},{"location":"#name","title":"Name","text":"
     
  • T(h)eroPoDa + - Time Series Extraction for Polygonal Data and Trend Analysis \u2b1b
    •  
"},{"location":"#description","title":"Description","text":"
     
  • Toolkit created to extract Time Series information from Sentinel 2 \ud83d\udef0 data stored in Earth Engine, gap filling and trend analysis 
    •  
"},{"location":"#author","title":"Author","text":"
     
  • Vin\u00edcius Vieira Mesquita - vinicius.mesquita@ufg.br (Main Theropoda)
    •  
"},{"location":"#co-author","title":"Co-author","text":"
     
  • Leandro Leal Parente - leal.parente@gmail.com (Gap Filling and Trend Analysis implementation)
    •  
"},{"location":"#version","title":"Version","text":"
     
  • 1.1.0
    •  
"},{"location":"#requirements-installation-order-from-top-to-bottom","title":"Requirements (installation order from top to bottom)","text":"
     
  • Python 3.10
    •  
  • GDAL
    •  
  • Rasterio 
    •  
  • Pandas
    •  
  • Geopandas
    •  
  • Scikit-learn
    •  
  • Joblib
    •  
  • Psutil
    •  
  • Earthengine-api
    •  
  • scikit-map
    •  
"},{"location":"#how-to-use","title":"How to use","text":"
     
  • In this version of TheroPoDa (1.1.0), you could extract a series of median NDVI from Sentinel 2 for a Feature Collection of polygons simplily by passing arguments to the python code exemplified below:
    •  
 argument usage example --asset Choosed Earth Engine Vector Asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m --id_field Vector column used as ID (use unique identifiers!) ID_POINTS --output_name Output filename LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork 
If you don't know how to upload your vector data in Earth Engine, you can follow the tutorial clicking this link.
"},{"location":"#command-line-example","title":"Command line example","text":"
python theropoda.py --asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m --id_field ID_POINTS --output_name LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork\n
"},{"location":"#roadmap","title":"Roadmap","text":"
     
  • Implement arguments to choose other zonal reducers (i.e. percentile, variance, etc.)
    •  
  • Implement arguments to choose other satellite data series (i.e. Landsat series, MODIS products)
    •  
  • Implement a visualization of the processed data (or samples of it)
    •  
"},{"location":"theropoda/","title":"Theropoda Module","text":"
This module includes functionalities related to theropoda.py code.
"},{"location":"theropoda/#overview","title":"Overview","text":"
The theropoda.py module provides functions to extract time series information from Sentinel 2 data stored in Earth Engine.
"},{"location":"theropoda/#attributes","title":"Attributes","text":"
     
  • asset (str): Choosed Earth Engine vector asset.
    •  
  • id_field (str): Vector column used as ID (use unique identifiers!).
    •  
  • output_name (str): Output filename.
    •  
"},{"location":"theropoda/#example-usage","title":"Example Usage","text":"
asset   = 'users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m'\nid_field = 'ID_POINTS'\noutput_name = 'LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork.csv'\n
"},{"location":"theropoda/#functions","title":"Functions","text":""},{"location":"theropoda/#1gettimeseries","title":"1.getTimeSeries","text":"
This function is responsible to get the time series of Sentinel 2 data throught Earth Engine. It needs a geometry object in the ee.Feature() formart and the choosed vector propertie ID as the id_field.
"},{"location":"theropoda/#parameters","title":"Parameters","text":"
     
  • geometry: An ee.Feature() object representing the area of interest.
    •  
  • bestEffort: A boolean indicating whether to use a larger pixel (10m to 30m) if the polygon area is too big (default is False).
    •  
"},{"location":"theropoda/#returns","title":"Returns","text":"
     
  • NDVI time series data along with other information for the specified geometry.
    •  
"},{"location":"theropoda/#2build_time_series","title":"2.build_time_series","text":"
Builds and writes NDVI time series data for a target vector asset, processing one polygon at a time.
"},{"location":"theropoda/#parameters_1","title":"Parameters","text":"
     
  • index: Index of the object being processed.
    •  
  • obj: Object ID for which the time series is being generated.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • outfile: Output file path to write the time series data.
    •  
  • asset: Earth Engine vector asset.
    •  
  • bestEffort: A boolean indicating whether to use a larger scale if needed (default is False).
    •  
"},{"location":"theropoda/#returns_1","title":"Returns","text":"
     
  • True if processing is successful, None if the polygon area is too small, False if an error occurs during processing and restart the process using the bestEffort approach.
    •  
"},{"location":"theropoda/#3build_time_series_check","title":"3.build_time_series_check","text":"
Checks the consistency of the NDVI time series library and handles errors during processing.
"},{"location":"theropoda/#parameters_2","title":"Parameters","text":"
     
  • index: Index of the object being processed.
    •  
  • obj: Object ID for which the time series is being checked.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • outfile: Output file path where time series data is stored.
    •  
  • asset: Earth Engine vector asset.
    •  
  • checker: A boolean indicating whether to check if the polygon has been processed before (default is False).
    •  
"},{"location":"theropoda/#returns_2","title":"Returns","text":"
     
  • A dictionary containing information about errors and processing time.
    •  
"},{"location":"theropoda/#4build_id_list","title":"4.build_id_list","text":"
Builds and writes a text file containing each Polygon ID used to extract the time series.
"},{"location":"theropoda/#parameters_3","title":"Parameters","text":"
     
  • asset: Earth Engine vector asset.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • colab_folder: Path of the folder where the text file will be saved.
    •  
"},{"location":"theropoda/#5run","title":"5.run","text":"
Manages the overall workflow by catching argument information and initiating the process of extracting NDVI time series data for specified polygonal areas.
"},{"location":"theropoda/#parameters_4","title":"Parameters","text":"
     
  • asset: Earth Engine vector asset.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • output_name: Name of the output file.
    •  
  • colab_folder: Path of the folder where the output file will be saved.
    •  
"},{"location":"trend_analysis/","title":"Trend Analysis Module","text":"
This module includes functionalities related to trend_analysis.py code.
"},{"location":"trend_analysis/#overview","title":"Overview","text":"
The trend_analysis module provides functions to gap filling and analyze trends in time series data.
"},{"location":"trend_analysis/#functions","title":"Functions","text":""},{"location":"trend_analysis/#1extract_ts","title":"1.extract_ts","text":"
Extracts time series data from the DataFrame for 5-day intervals.
"},{"location":"trend_analysis/#parameters","title":"Parameters","text":"
     
  • df: DataFrame containing the data.
    •  
  • dt_5days: List of 5-day intervals.
    •  
 
Returns: - Time series data and corresponding dates.
"},{"location":"trend_analysis/#2gapfill","title":"2.gapfill","text":"
Fills gaps in the time series data.
"},{"location":"trend_analysis/#parameters_1","title":"Parameters","text":"
     
  • ts: Time series data.
    •  
  • dates: List of dates corresponding to the time series data.
    •  
  • season_size: Size of the seasonal period.
    •  
 
Returns: - Filled time series data and updated dates.
"},{"location":"trend_analysis/#3sm_trend","title":"3.sm_trend","text":"
Applies seasonal decomposition and trend smoothing to the time series data.
"},{"location":"trend_analysis/#parameters_2","title":"Parameters","text":"
     
  • ts: Time series data.
    •  
  • season_size: Size of the seasonal period.
    •  
  • seasonal_smooth: Size of the seasonal smoothing.
    •  
 
Returns: - Trend analysis results and column names.
"},{"location":"trend_analysis/#4run","title":"4.run","text":"
Executes the trend analysis workflow for a given polygon ID.
"},{"location":"trend_analysis/#parameters_3","title":"Parameters","text":"
     
  • input_file: Input database file.
    •  
  • id_pol: ID of the polygon.
    •  
  • dt_5days: List of 5-day intervals.
    •  
  • season_size: Size of the seasonal period.
    •  
  • output_file: Output file path.
    •  
"},{"location":"blog/","title":"Blog","text":""}]}
\ No newline at end of file
+{"config":{"lang":["en"],"separator":"[\\s\\u200b\\-_,:!=\\[\\]()\"`/]+|\\.(?!\\d)|&[lg]t;|(?!\\b)(?=[A-Z][a-z])","pipeline":["stopWordFilter"]},"docs":[{"location":"","title":"Home","text":""},{"location":"#time-series-extraction-for-polygonal-data","title":"Time Series Extraction for Polygonal Data","text":""},{"location":"#name","title":"Name","text":"
     
  • T(h)eroPoDa + - Time Series Extraction for Polygonal Data and Trend Analysis \u2b1b
    •  
"},{"location":"#description","title":"Description","text":"
     
  • Toolkit created to extract Time Series information from Sentinel 2 \ud83d\udef0 data stored in Earth Engine, gap filling and trend analysis 
    •  
"},{"location":"#author","title":"Author","text":"
     
  • Vin\u00edcius Vieira Mesquita - vinicius.mesquita@ufg.br (Main Theropoda)
    •  
"},{"location":"#co-author","title":"Co-author","text":"
     
  • Leandro Leal Parente - leal.parente@gmail.com (Gap Filling and Trend Analysis implementation)
    •  
"},{"location":"#version","title":"Version","text":"
     
  • 1.1.0
    •  
"},{"location":"#requirements-installation-order-from-top-to-bottom","title":"Requirements (installation order from top to bottom)","text":"
     
  • Python 3.10
    •  
  • GDAL
    •  
  • Rasterio 
    •  
  • Pandas
    •  
  • Geopandas
    •  
  • Scikit-learn
    •  
  • Joblib
    •  
  • Psutil
    •  
  • Earthengine-api
    •  
  • scikit-map
    •  
"},{"location":"#how-to-use","title":"How to use","text":"
     
  • In this version of TheroPoDa (1.1.0), you could extract a series of median NDVI from Sentinel 2 for a Feature Collection of polygons simplily by passing arguments to the python code exemplified below:
    •  
 argument usage example --asset Choosed Earth Engine Vector Asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m --id_field Vector column used as ID (use unique identifiers!) ID_POINTS --output_name Output filename LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork 
If you don't know how to upload your vector data in Earth Engine, you can follow the tutorial clicking this link.
"},{"location":"#command-line-example","title":"Command line example","text":"
python main.py --asset users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m --id_field ID_POINTS --output_name LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork\n
"},{"location":"#roadmap","title":"Roadmap","text":"
     
  • Implement arguments to choose other zonal reducers (i.e. percentile, variance, etc.)
    •  
  • Implement arguments to choose other satellite data series (i.e. Landsat series, MODIS products)
    •  
  • Implement a visualization of the processed data (or samples of it)
    •  
"},{"location":"theropoda/","title":"Theropoda Module","text":"
This module includes functionalities related to theropoda.py code.
"},{"location":"theropoda/#overview","title":"Overview","text":"
The theropoda.py module provides functions to extract time series information from Sentinel 2 data stored in Earth Engine.
"},{"location":"theropoda/#attributes","title":"Attributes","text":"
     
  • asset (str): Choosed Earth Engine vector asset.
    •  
  • id_field (str): Vector column used as ID (use unique identifiers!).
    •  
  • output_name (str): Output filename.
    •  
"},{"location":"theropoda/#example-usage","title":"Example Usage","text":"
asset   = 'users/vieiramesquita/LAPIG_FieldSamples/lapig_goias_fieldwork_2022_50m'\nid_field = 'ID_POINTS'\noutput_name = 'LAPIG_Pasture_S2_NDVI_Monitoring_FieldWork.csv'\n
"},{"location":"theropoda/#functions","title":"Functions","text":""},{"location":"theropoda/#1gettimeseries","title":"1.getTimeSeries","text":"
This function is responsible to get the time series of Sentinel 2 data throught Earth Engine. It needs a geometry object in the ee.Feature() formart and the choosed vector propertie ID as the id_field.
"},{"location":"theropoda/#parameters","title":"Parameters","text":"
     
  • geometry: An ee.Feature() object representing the area of interest.
    •  
  • bestEffort: A boolean indicating whether to use a larger pixel (10m to 30m) if the polygon area is too big (default is False).
    •  
"},{"location":"theropoda/#returns","title":"Returns","text":"
     
  • NDVI time series data along with other information for the specified geometry.
    •  
"},{"location":"theropoda/#2build_time_series","title":"2.build_time_series","text":"
Builds and writes NDVI time series data for a target vector asset, processing one polygon at a time.
"},{"location":"theropoda/#parameters_1","title":"Parameters","text":"
     
  • index: Index of the object being processed.
    •  
  • obj: Object ID for which the time series is being generated.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • outfile: Output file path to write the time series data.
    •  
  • asset: Earth Engine vector asset.
    •  
  • bestEffort: A boolean indicating whether to use a larger scale if needed (default is False).
    •  
"},{"location":"theropoda/#returns_1","title":"Returns","text":"
     
  • True if processing is successful, None if the polygon area is too small, False if an error occurs during processing and restart the process using the bestEffort approach.
    •  
"},{"location":"theropoda/#3build_time_series_check","title":"3.build_time_series_check","text":"
Checks the consistency of the NDVI time series library and handles errors during processing.
"},{"location":"theropoda/#parameters_2","title":"Parameters","text":"
     
  • index: Index of the object being processed.
    •  
  • obj: Object ID for which the time series is being checked.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • outfile: Output file path where time series data is stored.
    •  
  • asset: Earth Engine vector asset.
    •  
  • checker: A boolean indicating whether to check if the polygon has been processed before (default is False).
    •  
"},{"location":"theropoda/#returns_2","title":"Returns","text":"
     
  • A dictionary containing information about errors and processing time.
    •  
"},{"location":"theropoda/#4build_id_list","title":"4.build_id_list","text":"
Builds and writes a text file containing each Polygon ID used to extract the time series.
"},{"location":"theropoda/#parameters_3","title":"Parameters","text":"
     
  • asset: Earth Engine vector asset.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • colab_folder: Path of the folder where the text file will be saved.
    •  
"},{"location":"theropoda/#5run","title":"5.run","text":"
Manages the overall workflow by catching argument information and initiating the process of extracting NDVI time series data for specified polygonal areas.
"},{"location":"theropoda/#parameters_4","title":"Parameters","text":"
     
  • asset: Earth Engine vector asset.
    •  
  • id_field: Field name representing the ID in the vector asset.
    •  
  • output_name: Name of the output file.
    •  
  • colab_folder: Path of the folder where the output file will be saved.
    •  
"},{"location":"trend_analysis/","title":"Trend Analysis Module","text":"
This module includes functionalities related to trend_analysis.py code.
"},{"location":"trend_analysis/#overview","title":"Overview","text":"
The trend_analysis module provides functions to gap filling and analyze trends in time series data.
"},{"location":"trend_analysis/#functions","title":"Functions","text":""},{"location":"trend_analysis/#1extract_ts","title":"1.extract_ts","text":"
Extracts time series data from the DataFrame for 5-day intervals.
"},{"location":"trend_analysis/#parameters","title":"Parameters","text":"
     
  • df: DataFrame containing the data.
    •  
  • dt_5days: List of 5-day intervals.
    •  
 
Returns: - Time series data and corresponding dates.
"},{"location":"trend_analysis/#2gapfill","title":"2.gapfill","text":"
Fills gaps in the time series data.
"},{"location":"trend_analysis/#parameters_1","title":"Parameters","text":"
     
  • ts: Time series data.
    •  
  • dates: List of dates corresponding to the time series data.
    •  
  • season_size: Size of the seasonal period.
    •  
 
Returns: - Filled time series data and updated dates.
"},{"location":"trend_analysis/#3sm_trend","title":"3.sm_trend","text":"
Applies seasonal decomposition and trend smoothing to the time series data.
"},{"location":"trend_analysis/#parameters_2","title":"Parameters","text":"
     
  • ts: Time series data.
    •  
  • season_size: Size of the seasonal period.
    •  
  • seasonal_smooth: Size of the seasonal smoothing.
    •  
 
Returns: - Trend analysis results and column names.
"},{"location":"trend_analysis/#4run","title":"4.run","text":"
Executes the trend analysis workflow for a given polygon ID.
"},{"location":"trend_analysis/#parameters_3","title":"Parameters","text":"
     
  • input_file: Input database file.
    •  
  • id_pol: ID of the polygon.
    •  
  • dt_5days: List of 5-day intervals.
    •  
  • season_size: Size of the seasonal period.
    •  
  • output_file: Output file path.
    •  
"},{"location":"blog/","title":"Blog","text":""}]}
\ No newline at end of file