Downscaled Climate Projections (Coarse Field Level @5/10km)

[kapildadheech]

Ticket Contents

Description

Downscaled climate projections provide high-resolution (~5–10km) datasets for analyzing climate impacts on agriculture, forests, health, and hazard patterns. By computing metrics such as max/mean rainfall, drought incidence, extreme rainfall, flood incidence, max/mean temperature, and heatwave frequency, stakeholders can assess spatial and temporal trends over the years. Google Earth Engine (GEE) will be used to generate raster outputs, vectorize them at MWS-level, and produce reports for analysis.

Goals

Goals

• Implement downscaled climate projections for AoI and MWS at ~5–10km resolution.
• Compute climate indicators:
  • Max/mean rainfall
  • Drought incidence
  • Extreme rainfall
  • Flood incidence
  • Max/mean temperature
  • Heatwave incidence
• Generate raster outputs for each indicator.
• Vectorize rasters to produce MWS-level polygons summarizing metrics.
• Publish raster and vector outputs as Earth Engine assets with metadata.
• Enable temporal and spatial analysis of climate patterns over multiple years.
• Produce MWS-level reports highlighting trends, changes, and hazard zones.

Expected Outcome

Expected Output

• Raster datasets (~5–10km resolution) for all climate indicators listed.
• Vectorized MWS-level polygons with attributes:
  • Indicator name
  • Metric value (e.g., total rainfall, max temperature, drought frequency)
  • Area (km²)
• Published Earth Engine assets (raster + vector) with metadata (source, resolution, processing date).
• GEE visualizations showing spatial distribution of climate indicators.
• Annual/seasonal reports summarizing trends and hazards.
• Validation report confirming coverage, accuracy, and consistency over years.

Acceptance Criteria

Acceptance Criteria

Data Acquisition

• Downscaled climate datasets (e.g., CORDEX, CHIRPS, ERA5-Land) must be preprocessed and clipped to AoI/MWS boundaries.
• Resolution standardized to ~5–10km.
• Temporal range documented for annual/seasonal projections.

Raster Computation

• Compute all climate indicators per pixel.
• Entire AoI/MWS must be covered without gaps.
• Thresholds and methodologies (e.g., drought index, heatwave criteria) must be documented.

Vectorization

• Raster outputs converted to MWS-level polygons using reduceToVectors() in GEE.
• Each polygon must include:
  • Indicator
  • Metric value
  • Area (km²)
• Polygons must align with MWS boundaries.

Asset Publishing

• Raster and vector datasets published as Earth Engine assets.
• Metadata includes source datasets, resolution, processing date, and methodology for each indicator.

Quality & Validation

• Coverage check: all AoI/MWS included.
• Accuracy check: raster outputs validated against historical datasets or reference models.
• Attribute check: all polygons include indicator name, metric value, and area.
• Visualization in GEE confirms correct spatial distribution.
• Annual/seasonal trends verified for consistency and plausibility.

Implementation Details

Implementation Details

Data Sources

• Downscaled climate projections (CORDEX, CHIRPS, ERA5-Land)
• AoI and MWS boundary shapefiles

Processing

• Compute raster layers for each indicator at ~5–10km resolution.
• Apply relevant indices for drought, heatwave, and flood detection.
• Clip outputs to AoI/MWS boundaries.

Vectorization & Publishing

• Convert raster outputs into MWS-level polygons using reduceToVectors().
• Include attributes: indicator, metric value, area.
• Upload raster and vector layers as EE assets with metadata.

Visualization

• Color-coded raster and vector layers in GEE for each climate indicator.
• Overlay with MWS boundaries for hazard and stress assessment.

Validation

• Compare raster outputs with historical data and reference datasets.
• Spot-check vector polygons for correct attribute values.
• Generate validation report documenting coverage, accuracy, and attribute completeness.

Mockups/Wireframes

No response

Product Name

KYL

Organisation Name

C4GT

Domain

No response

Tech Skills Needed

Python

Organizational Mentor

@ankit-work7 @amanodt @kapildadheech

Angel Mentor

No response

Complexity

Medium

Category

Backend

[abhishek-8081]

/assign

[harshala334]

Hi @kapildadheech @amanodt @ankit-work7 ,
I’d like to take up this issue. I have hands-on experience with Python,GEE and geospatial data processing including raster computation, vectorization.I can implement the complete workflow for generating and validating the downscaled climate projection indicators and publish the outputs as GEE assets with metadata and visualization.
Could you please assign this issue to me?I’d be happy to contribute!

[aaditeshwar]

Thanks @abhishek-8081 , @harshala334 for your interest. Will be great if you can self-organize and work on this jointly. Some comments:

• Identify some suitable downscaled datasets that exist. One is https://rmets.onlinelibrary.wiley.com/doi/10.1002/gdj3.266?af=R which provides a 10-km gridded hydrometeorological dataset at three temporal resolutions (daily, monthly and monthly climatology) for current (2006–2015), mid-century (2041–2050) and end-century (2091–2100) periods.
• Study various CoRE stack datasets to understand the kind of indicators we develop for current and historical periods, E.g. fortnightly rainfall, ET, runoff; seasonal drought; etc. We would want to develop similar indicators for future years using the climate projections. But we currently build our indicators at micro-watershed scales whereas even the downscaled datasets are at a 10km resolution only. So we can do future projections at watershed scales instead of micro-watershed scales.
• Then go indicator by indicator and build a plan of using the climate projection data to compute these indicators in the current period and future periods of 2050 and 2100. This will help us see, for example, how drought incidence in the current period will change by 2050, and then by 2100.
• To compute the indicators, study the current micro-watershed level pipelines and see how they can be altered/re-used at the watershed scale. Some like runoff will need to be reduced in fidelity from 30m to a 100m or 500m resolution to keep the computation tractable.
• Once sample outputs are ready and validated then the rest of the integration into the CoRE stack can begin to build into APIs, use in downstream apps and dashboards, etc.
• Will be great if you can find a faculty mentor who can also guide this closely, especially to check for correctness in the methodology 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 @harshala334 , 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.

[atrip0305]

Hi @ankit-work7 @amanodt @kapildadheech

I’d love to take up the Downscaled Climate Projections (KYL) task. I have experience working with Python for structured data processing, building clean analytical pipelines, and preparing standardized outputs for geospatial workflows.

I’m comfortable with raster computation, threshold-based climate indicators, vectorization, and publishing well-documented assets suitable for GEE and further analysis.

Could you please assign this issue to me?
Looking forward to contributing!

[aaditeshwar]

@atrip0305 please do join the weekly dev call on Fridays at 3pm and discuss before you begin, there are some details we'd like to highlight so that your work can be aligned. https://core-stack.org/core-stack-innovation-challenge-1st-edition/

[atrip0305]

Sure sir! @aaditeshwar

[ojask3150]

Hi @aaditeshwar and everyone, I see there's active interest in this issue. I have experience with Python, GEE, and worked on raster layers ,image segementation and classification of Sentinel-2 imagery. I'd love to collaborate with others who are interested.
I noticed the mention of a weekly dev call on Fridays. Can i join next friday to join the discussion?
If yes can you please share a link of the discord channel again(previous one has expired)
Thanks & regards.

[amit-spatial]

Hi all,

We'll have our dev call at 3pm on Friday as usual. There has also been a lot of interest on some issues we had created on github to add new datasets and pipelines to the CoRE stack. So we wanted to put out some guidelines to make this experience enriching and productive for all of us.

Many of the issues we had created and a wishlist of datasets we had published some time back are very domain specific and need to be technically correct before they can be included in the stack. For context, any of the layers currently on the CoRE stack that required some kind of geospatial algorithms or machine learning went through several months of testing, sometimes years, to examine the outputs carefully, understand when and where the models are performing well or not, how to handle missing data (satellite data can have cloud cover and needs specific methods to address this), and so on.

So if you are keen to pick up such issues then please share your intermediate progress with us during the dev calls. Help us understand how you are approaching the issue, show us the results, discuss problems, and it'll become much easier then to absorb your contributions. If you can inform us in advance about anything specific you'd like to discuss then we can also arrange for somebody who understands that area really well to also come on the call. Amongst so many research scholars and students who have contributed to the CoRE stack, there is a lot of expertise on LULC, computations on DEM layers, tree cover analysis, rainfall, drought, indexes like NDVI, census data, commodity pricing data, agriculture marketing, etc.

We are working hard to put up a developer website asap with all required documentation in one place, but here are two MUST read links before you begin to take up any substantial tasks.

Contribute datasets, pipelines and tools

Core-Stack Innovation Challenge

@ojask3150 @atrip0305 @harshala334 @abhishek-8081 See you in today's developer call!

Zoom Link
Meeting ID: 856 5729 0380
Passcode: 317250