Skip to main content
Back to challenges
Challenge

LangGraph Heatwave Risk Indexing for Urban Resilience

Urban centers lack real-time heat vulnerability scoring models that account for building efficiency, microclimate sensors, and demographic risk. Develop a LangGraph stateful workflow using Claude 4.1 Opus to synthesize Copernicus land surface temperature data and output neighborhood heat stress indexes.

Machine LearningHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Implement a stateful LangGraph agent pipeline integrating geospatial raster processing with Claude 4.1 Opus to evaluate heat risk.

Delivery guide

How work is evaluated

Evaluation

Evaluates state transition accuracy, spatial risk index precision, and warning threshold trigger reliability.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

alert_logic_test

Verifies extreme heat warning is accurately triggered above threshold

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

risk_score_mae

Mean absolute error of heat index score vs ground truth formula • target: 1.2 • range: 0-5

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Construct a multi-node LangGraph graph for stateful climate telemetry ingestion

  • Use Claude 4.1 Opus to evaluate complex environmental health risk triggers and vulnerability indices

  • Integrate Python rasterio/geopandas packages inside custom LangGraph node functions

Resources and assets

Reference links and supporting material

Dataset notes

European Heatwave Copernicus satellite thermal readings paired with census demographic shapefiles.

Challenge setup

Evaluates state transition accuracy, spatial risk index precision, and warning threshold trigger reliability.

Challenge input

JSON containing geojson coordinates, surface_temp_c, humidity_pct, and elderly_ratio

LangChain

Used with LangGraph for stateful multi-step agent execution

Claude 4.1 Opus

Provides climate resilience reasoning and qualitative intervention synthesis

Evaluated output

JSON with heat_index_score (0-100), alert_category, and intervention_recommendations

Evaluation checks
  • Verifies extreme heat warning is accurately triggered above threshold
  • Mean absolute error of heat index score vs ground truth formula • target: 1.2 • range: 0-5
Configured evaluation evidence
  • Benchmark: Climate-Heat-Bench
  • Risk Score Mae target: 1.2
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • LangGraph · Optional
  • Anyscale · Optional
Policy Serving
  • Claude 4.1 Opus · Required
Orchestration
  • LangGraph · Optional

Evaluation contract

  • alert_logic_test · Weight 1
  • risk_score_mae · Weight 1

Metrics

  • risk_score_mae · Target 1.2

Benchmarks

  • Climate-Heat-Bench
  • energy

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing geojson coordinates, surface_temp_c, humidity_pct, and elderly_ratio

    Output: JSON with heat_index_score (0-100), alert_category, and intervention_recommendations

    Execution harness: Python

Evaluation tools

  • LangChain · Agent Framework
  • Claude 4.1 Opus · LLM Model

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about LangGraph Heatwave Risk Indexing for Urban Resilience