“I will continue for now. Whether I solve all the problems, only half of them, or return in failure in the end…” (Han Kang, We Do Not Part)
About this notebook and me¶
Hello, and welcome! I’m Muen — a data scientist and a master’s student at Georgia Tech, specializing in Machine Learning.
My path into systems didn’t begin in computer science, but in Architecture and Urban Planning. I used to design physical spaces.
Over time, my curiosity for cities never changed, but my toolkit has shifted.
I became increasingly interested not just in designing physical environments, but in understanding the behavior of cities.
Cities, to me, are not objects, but complex adaptive systems: networks of infrastructure, human behavior, and environmental processes, tightly coupled and constantly changing.
Working in energy-tech exposed me to real-world data, uncertainty, and large-scale decision systems. Meanwhile, my studies in computer science pulled me toward a deeper question: How can we use data-driven methods to understand, model, and predict the behavior of complex physical systems under uncertainty?
These two threads converge into a broader question that guides this repository: How do large-scale urban and infrastructure systems adapt, reorganize, and sometimes fail under changing conditions?
This study notes repo is my attempt to answer that question slowly, imperfectly, but with curiosity. Think of this as a personal, evolving research notebook — incomplete, but structured by curiosity.
Kurz & bündig (German Edition)¶
Hallo! Ich bin Muen, Data Scientist und Masterstudentin an der Georgia Tech.
Ich habe meinen Bachelor in Architektur am KIT gemacht. Heute interessiert mich weniger die Form von Städten, sondern ihr Verhalten als komplexe Systeme.
Diese Notizen dokumentieren meinen Übergang von statischer Raumgestaltung hin zur Analyse und Modellierung dynamischer, gekoppelter Infrastruktursysteme.
关于这个笔记库和我¶
你好，我是 Muen，一名数据科学家，目前在 Georgia Tech 读硕士。
我最初的训练来自建筑学，但现在更关注城市作为复杂系统的行为： 它们如何在压力下变化、如何通过网络结构传播影响、以及如何在不确定性中做出“响应”。
这个笔记库记录的是我从“设计空间”转向“理解系统”的过程，内容主要围绕复杂系统、统计学习、系统建模以及它们在城市系统中的应用。
How to use this notebook¶
This notebook is organized as a method-first learning and research system, rather than a collection of isolated topics.
Structure Overview
The notes are grouped into three interconnected layers:
System Understanding: Foundations for describing and analyzing systems (e.g., System Representation, System Properties, System Dynamics)
System Prediction: Methods for modeling and forecasting system behavior (e.g., Inference, Learning)
System Intervention: Approaches for influencing or controlling system dynamics (e.g., Control & Intervention)
These layers reflect a core progression:
Understand → Predict → Intervene
How to Navigate
If you are interested in concepts, start from System Understanding
If you are interested in modeling and ML, go to System Prediction
If you are interested in decision-making and control, explore System Intervention
Notes are intentionally modular, but many topics are connected across sections.
What You Will Find Here
Conceptual notes on complex systems and urban systems
Method-focused breakdowns (statistics, ML, networks)
Small experiments and exploratory analyses
Occasional applied case studies
The emphasis is on building intuition and transferable methods, rather than covering topics exhaustively.
What This Repo Is Not
Not a textbook
Not a complete or authoritative reference
Not limited to a single discipline
Some notes may be incomplete, exploratory, or revised over time.
Intended Use
This repo is primarily built for:
Structuring long-term research thinking
Connecting methods across domains
It may also be useful for others exploring similar intersections of complex systems, machine learning, and real-world infrastructure.