Click the earth to unearth what lies beneath
Enter Portfolio →

MASOOD
SULTAN

Geoscientist & AI Engineer — Berlin · Open to PhD positions

Masood Sultan

My career didn't begin in tech.
It began underground.

My foundation lies in interpreting the subsurface — 3D seismic surveys, geological models, wellbore data. I earned a BSc in Geophysics from Bahria University (3.55/4.00 CGPA) and placed 3rd in the Imperial Barrel Awards, Asia Pacific — one of the most competitive geoscience competitions organized by the AAPG, competing against teams from across the region.

I then moved to Berlin for an MSc in Global Change Geography at Humboldt University, where my focus shifted from subsurface to atmosphere — climate data, earth observation satellites, and computational modelling. When existing tools proved inadequate for the research questions I was asking, I taught myself to build them.

Today, my fieldwork is computational. I build LLM-powered systems and agentic architectures that crawl, extract, and adapt to complex environmental datasets — from real-time disaster APIs to satellite imagery. The geoscience training never left; it evolved into a different kind of excavation.

Technical Stack

Languages & Web

  • Python 3.x
  • TypeScript / Node.js
  • Express.js
  • HTML / CSS
  • R (RStudio)

AI & Automation

  • Agentic Systems (LLMs)
  • Open WebUI
  • Headless Web Scraping
  • Telegram Bots
  • Process Automation

Data & GeoScience

  • 3D Geomodelling (Petrel)
  • Spatial Analysis (QGIS)
  • Climate Data Analytics
  • Real-time APIs (FIRMS, USGS)
  • Pandas / NumPy

Infrastructure

  • Server-Sent Events (SSE)
  • REST API Architecture
  • Hugging Face Spaces
  • Docker / Appwrite
  • Git / PowerShell
01
TypeScriptNode.jsExpressSSE

TerraMind Core

A real-time global disaster intelligence platform entirely powered by open government APIs. Dynamically aggregates data from USGS Earthquakes, NASA EONET Wildfires, NOAA Weather Alerts, and NASA FIRMS Satellite Fire Detection into a unified stream. Features a built-in GeoScience AI Assistant.

4 Gov APIs UnifiedMulti-source normalizer pipeline
Server-Sent EventsReal-time push without polling
Interactive DashboardLive map markers + severity filters
View Terminal Output
terramind-core
$ npm start
[server] TerraMind API Engine booting on port 4100
[pipeline] Normalizing multi-source hazard feeds...
[usgs] Extracted 8 seismic anomalies
[nasa-firms] Scanning VIIRS 375m fire detections
[sse] Broadcasting delta update to connected clients →
[status] 22 active events cached. Next sweep in 120s.
$
02
PythonLLMsSelf-LearningMIT License

ai-scraper

A web scraper that teaches itself. Point it at any website — it figures out the structure, extracts data using LLMs, and remembers what worked. It builds domain-specific profiles, scores its own output quality, and auto-evolves its extraction prompts. Headless Chrome under the hood, with persistent memory that compounds over time.

Self-Evolving PromptsGets smarter with every scrape
Persistent MemoryDomain profiling compounds over time
Quality ScoringSelf-evaluates extraction accuracy
View Terminal Output
ai-scraper
$ python scraper.py --url "https://arxiv.org/list/physics.geo-ph"
[engine] No domain profile found. Learning...
[chrome] Headless browser launched
[llm] Analyzing page structure...
[learn] Domain profile created: arxiv.org
[learn] Extraction accuracy: 94.7%
[done] 127 papers extracted → papers.json
$
03
PythonTelegramAutomationAGPL-3.0

openhouse-bot

An adaptive, LLM-powered universal crawler that autonomously learns any website's structure — originally built to solve Berlin's housing crisis by scraping 50+ real estate portals worldwide. The underlying architecture is directly transferable to geoscience applications: scraping unstructured climate reports, policy documents, and global hydrological databases. Features real-time Telegram alerting and a Live Demo on Hugging Face.

50+ PortalsGlobal coverage, not just one platform
Instant Telegram AlertsNew listings hit your phone in seconds
Live HF DemoReal-time scraping in browser
View Terminal Output
openhouse-bot
$ python bot.py --city berlin --max-rent 900
[bot] Monitoring 54 portals...
[scan] immobilienscout24.de — 12 new
[scan] wg-gesucht.de — 4 new
[match] 2BR Kreuzberg €780 — SENT
[match] 1BR Neukölln €650 — SENT
[scan] Next cycle in 120s...
$
Master's Thesis 2025 Water Governance & Adaptation

A Critical Review of Participatory Approaches in Water Management for Climate Change Adaptation

My primary contribution to the field of Global Change Geography is the Conditional Enabling Framework (KIEA), developed to diagnose and evaluate participatory water governance under severe climate stress and hydrological non-stationarity.

Traditional models assume participation uniformly yields positive outcomes — my research demonstrates that participation often devolves into tokenism or elite capture unless four interdependent enabling conditions are met simultaneously:

K — Knowledge PerformanceData availability, scientific literacy, and knowledge co-production among stakeholders
I — Institutional PerformanceGovernance capacity, regulatory design, and formal/informal institutional coherence
E — Equity PerformanceEquitable stakeholder representation, inclusive decision-making, and distributive justice
A — Adaptive PerformanceFlexibility, iterative learning, and system resilience under uncertainty

When any single dimension falls below threshold — the binding constraint — the entire governance system underperforms, regardless of strength in other areas.

KIEA Weakest Link Logic
The KIEA Dimensions & Binding Constraint Logic
Diagnostic Pathways Hydrological
Diagnostic Pathways Social

Through a realist synthesis of 121 global water management studies, this diagnostic instrument directly shifts theoretical climate governance toward measurable, actionable, and prescriptive implementation.

Journal of Applied Geophysics 2020 3D Geomodelling

A case study of 3D geomodelling of Frontier Formation Second Wall Creek Sand, Teapot Dome, Wyoming, USA

Co-author · This study presents an advanced 3D geomodelling workflow applied to the Teapot Dome anticline in Wyoming — a publicly available dataset widely used in petroleum geoscience education. Using integrated well log correlation, seismic interpretation, and stochastic property modelling in Schlumberger Petrel, the research demonstrates best practices in reservoir characterization for the Second Wall Creek Sand of the Frontier Formation.

Sultan, M. et al. (2020). Journal of Applied Geophysics, Vol. 179, 104114.

DOI: 10.1016/j.jappgeo.2020.104114 →

Looking for a PhD position
in computational geoscience
or climate AI.

If you're seeking a researcher at the intersection of geoscience, AI, and climate adaptation — someone who can build the tools and do the science — let's connect. Based in Berlin.

Open to research positions
Download Academic CV →