Sustainability · Urban planning · 2026

Althil

Urban heat and shade planning prototype

Helps planners see where shade canopies would do the most for thermal comfort, using sun position, heat exposure and street imagery.

Role
Backend developer & cloud architecture contributor
Status
Hackathon prototype
Evidence
Private project evidence
Year
2026
Discuss similar work

Evidence

What a reviewer can check today — and what is not claimed.

Hackathon prototype
Status
Built with a team during the Intelligent Planet Hackathon (KFUPM × Google Cloud). A hackathon prototype — not used by a city.
Evidence
Not claimed
No city deployment and no measured temperature reduction are claimed.
Stack
  • Python
  • FastAPI
  • OpenCV
  • pysolar
  • Docker
  • Google Cloud

The hackathon design also called for BigQuery, Cloud Storage, Vertex AI and a conversational layer; those parts cannot be verified publicly.

Context

Team project built during the Intelligent Planet Hackathon, hosted by KFUPM in collaboration with Google Cloud.

The problem

Urban planners need to know where shade canopies will actually improve comfort. Heat exposure shifts with the sun’s path across the day and the year, which static plans rarely account for.

Constraints

  • Hackathon time limit
  • A team build — Abdulelah owned backend work and the cloud direction
  • Designed to run on Google Cloud

Solution

A map-based planning tool. The backend computes sun position for a place and time, scores heat exposure, analyses uploaded street imagery and recommends shade-canopy sites, with a report a planner can take away.

My responsibility

Backend developer & cloud architecture contributor

  • Built backend services for the analysis
  • Supported the Google Cloud architecture direction
  • Integrated the analysis services across the platform
  • Connected location data, analysis and explanations under hackathon constraints

Architecture & workflow

  1. 01 · Input

    Location & date

  2. 02 · Processing

    Sun path & heat scoring

  3. 03 · Intelligence

    Imagery analysis

  4. 04 · Output

    Shade recommendations & report

How it works

  • Sun altitude and azimuth are computed for the chosen location and time
  • Heat exposure is scored and candidate shade sites are ranked
  • Uploaded street imagery is analysed with OpenCV
  • A PDF report summarises the recommendations
  • The backend is containerised for Google Cloud Run

Decisions

  • Built for Google Cloud from the start

    The backend was packaged as a container for Cloud Run so the team could deploy it quickly inside the hackathon, with BigQuery, Cloud Storage and Vertex AI in the wider design.

  • Explain, don’t just compute

    Recommendations carry the sun-path and heat reasoning behind them, and the design added a conversational layer so planners are not asked to trust a bare score.

Verified outcome

A hackathon prototype that computes sun position and heat exposure for a location, analyses street imagery and proposes shade sites with a downloadable report. No city deployment and no measured cooling effect are claimed.

Limitations

  • The code is not public, so reviewers cannot inspect it.
  • The BigQuery, Cloud Storage, Vertex AI and conversational parts are described from the hackathon design and are not independently verifiable here.
  • Recommendations have not been validated with planners or with field temperature data.

What would come next

  • Publish a cleaned-up version of the code
  • Validate recommendations against measured street temperatures
  • Test the planning workflow with a municipal team

The idea, sketched

Looking back
This project strengthened my experience in cloud-native design, data-driven decisions and cross-functional collaboration under real constraints.
Concept visualizationIllustrative sketch of the idea — not a product screenshot.

Related projects

Working on something similar?

Tell me about the problem, or pick the CV that fits the role — either way you’ll get a direct reply.

Discuss similar work
Choose a CV