Temperature and Humidity (Coarse Field Level @5km)

[kapildadheech]

Ticket Contents

Description

Mapping temperature and humidity at coarse field level (~5km resolution) allows assessment of climatic conditions over large Areas of Interest (AoI) and Micro Watersheds (MWS). These layers can support forest, crop, and environmental monitoring. Computation using Google Earth Engine (GEE) enables generation of raster datasets, which can then be vectorized for integration with other spatial analyses.

Goals

Goals

• Build raster layers of temperature and humidity at ~5km resolution using GEE.
• Vectorize raster outputs into coarse field-level or MWS-level polygons.
• Publish raster and vector outputs as Earth Engine assets with proper metadata.
• Enable visualization and spatial analysis of climatic conditions across AoI and MWS.

Expected Outcome

Expected Output

• Raster datasets (~5km resolution) representing:
  • Temperature (°C)
  • Humidity (%)
• Vectorized polygons with attributes:
  • Mean temperature
  • Mean humidity
  • Area (km²)
• Published Earth Engine assets (raster + vector) with metadata (source, resolution, computation date).
• GEE visualization showing spatial distribution of temperature and humidity.
• Validation report confirming coverage, spatial accuracy, and attribute completeness.

Ask ChatGPT

Acceptance Criteria

Acceptance Criteria

Data Acquisition

• Input datasets (e.g., MODIS, ERA5, or other climatic sources) must be preprocessed and clipped to AoI/MWS boundaries.
• Resolution standardized to ~5km.

Raster Computation

• Raster outputs must represent temperature and humidity per pixel.
• Entire AoI/MWS must be covered without gaps.
• Temporal resolution (daily, monthly, or annual averages) must be documented.

Vectorization

• Raster outputs converted to polygons using reduceToVectors() in GEE.
• Each polygon must include:
  • Mean temperature
  • Mean humidity
  • Area (km²)
• Polygons must align with AoI/MWS boundaries.

Asset Publishing

• Raster and vector datasets must be published as Earth Engine assets.
• Metadata must include source datasets, resolution, and processing date.

Quality & Validation

• Coverage check: all AoI/MWS included.
• Accuracy check: raster values match reference climatic data (MODIS, ERA5).
• Attribute check: all polygons include mean temperature, mean humidity, and area.
• Visualization in GEE confirms correct spatial distribution.

Implementation Details

Implementation Details

Data Sources

• MODIS Land Surface Temperature (LST) products
• ERA5 reanalysis data for humidity
• AoI and MWS boundary shapefiles

Processing

• Generate raster layers of temperature and humidity on GEE at ~5km resolution.
• Compute temporal averages (monthly, seasonal, or annual as required).
• Clip outputs to AoI/MWS boundaries.

Vectorization & Publishing

• Convert raster outputs into polygons using reduceToVectors().
• Include attributes: mean temperature, mean humidity, area.
• Upload raster and vector layers as Earth Engine assets with metadata.

Visualization

• Color-coded raster and vector layers in GEE (temperature gradient, humidity gradient).
• Overlay with AoI/MWS boundaries for field-level inspection.

Validation

• Compare raster outputs with reference datasets (e.g., ground stations or global climatic products).
• Spot-check vector polygons for correct attribute values.
• Generate validation report documenting coverage, accuracy, and attribute completeness.
  If you want, I can also make a compact version (Goals + Acceptance Criteria only) for this ticket so it’s quick to paste into GitHub.

Mockups/Wireframes

No response

Product Name

KYL

Organisation Name

C4GT

Domain

No response

Tech Skills Needed

Python

Organizational Mentor

@amanodt @kapildadheech @ankit-work7

Angel Mentor

No response

Complexity

Low

Category

Backend

[gitsofaryan]

@amanodt @kapildadheech @ankit-work7

Dear mentors,

I’m really interested in #230 – Temperature & Humidity @ 5km Coarse Field Level, especially because I’ve previously worked on similar geospatial projects using satellite data (MODIS, ERA5) and GEE for climate mapping.

I’ve already built a fully working Streamlit prototype with Open-Meteo:

• 10km grid over India
• Annual mean temp & humidity per cell
• Interactive map with values labeled on polygons
• CSV export + metadata

I’m excited to:

• Migrate this to Google Earth Engine
• Resample to ~5km resolution
• Vectorize with reduceToVectors()
• Publish raster + vector assets with full metadata

Happy to share the live demo and start contributing immediately.

Thank you!

[aaditeshwar]

Thanks @gitsofaryan for the interest. Also looks like @umaseershika45 has already initiated work on this #329 (comment), so will be great if both of you can self-organize on working together. Sharing some points:

• Start with identifying the metrics to compute. We would like, for example, to have on an annual basis the number of hot days, frigid days, and high wet-bulb temperature days. Explore the literature to identify meaningful metrics to compute.
• Then formulate the methodology and identify which underlying datasets to use. Most temperature data is published on a daily basis with the mean, max, min temperature of the day, at a spatial resolution of 5-10km. Explore the literature to see if any specific datasets are recommended for India.
• Look over the CoRE stack datasets like rainfall and drought incidence to understand how the computed data is to be published. For example, rainfall is published as a fortnightly time-series and drought in terms of the frequency and intensity of drought incidence, at micro-watershed (MWS) units for all MWSes in a tehsil.
• Then begin the implementation, compute sample outputs, and validate them against published reports on heat waves and such incidences.
• Finally integrate this as pipelines in the CoRE stack that can compute for a given tehsil AOI, for all MWSes in the AOI the time-series of max/min/mean temperature on a fortnightly basis, the number of high temperature days, low temperature days, high wet bulb temperature days, and the intensity of these extreme weather events, i.e. mean value of the temperature on the high temperature days, and so on.
• Downstream apps and dashboards like Know Your Landscape can then use the data.
• Please also see if you can find a factory mentor who can guide and validate the implementation.

@kapildadheech , @amanodt , @ankit-work7 , @nirzaree-cfpt , FYI.

[aaditeshwar]

Hi all, Do please join the discord channel and googlegroup linked from this announcement of the CoRE stack innovation challenge, and do participate in the challenge too: https://core-stack.org/core-stack-innovation-challenge-1st-edition/. Our first community call on Friday 3-4pm will be very useful to get started.

[aaditeshwar]

Hi @gitsofaryan and @umaseershika45 , We've been having weekly calls to discuss various ongoing contributions. Can you join the next call and take us through your methodology and implementation so far. Please do go over the recordings https://core-stack.org/core-stack-innovation-challenge-1st-edition/ and join the Google group https://groups.google.com/u/2/g/core-stack-dev and discord channel https://discord.gg/FpMArraM2X. We'll meet next Friday at 3pm. Please let us know if you can join.