Portrait of Daniel Jonas Mielke
Hey there, I'm Daniel Jonas!

Hey there, my name is Daniel,

a CS master's student focused on deep learning for the simulation of physical systems — and a student AI & Data Scientist at Statista+.

Download my CV GitHub LinkedIn

About me

Full CV

## Education

  1. 2024 — today

    M.Sc. Computer Science · AI & Data Science

    HAW Hamburg

    • GPA 1.0
    • Neural ODEs/PDEs & operators, transformers, VAEs, diffusion & flow matching

  2. 02/2026 — 07/2026

    Postgraduate Exchange Semester Scholarship

    UNSW Sydney

    • Led a five-student NLP research project on LLM context faithfulness — High Distinction

  3. 2020 — 2024

    B.Sc. Media Computer Science

    University of Flensburg

    • Programming, databases, artificial neural networks

## Experience

  1. 2025 — today

    Working Student · AI & Data Science

    Statista

    • RAG systems, data automation pipelines, scraping & structuring

  2. 2021 — 2025

    Working Student · Fullstack Development

    Jung von Matt TECH, SOFTSTACK, Events United

    • 4+ years of fullstack engineering — projects for dfb.de, bmw.com and more

## Honors

  1. Deutschlandstipendium

    Scholarship for Gifted and High-Achieving Students

Physics Simulation Series

start at part 01

series · 10 parts · 5 chapters

From ODEs to Neural Operators

Every part of this series builds on the one before it, nothing is used before it has been explained.

00warm-upGradient descent & backpropoptional, if you have never trained a neural network

  1. Differential equations

    1. 01ODEs & Neural ODEsnext
    2. 02PDEs & Neural PDEs

  2. The wave equation

    1. 03Deriving the wave equation
    2. 04A neural wave solver

  3. Numerical stability

    1. 05Von Neumann analysis
    2. 06The CFL condition

  4. Neural operators

    1. 07Neural operators & DeepONet
    2. 08The Fourier transform
    3. 09Fourier Neural Operators

  5. The Navier–Stokes equations

    1. 10The material derivative

the series is ongoing: new parts are added to the end of the path

Latest Posts

All posts
A velocity field with a fluid parcel drifting along its pathnavier–stokes 01/01
Educational

The Material Derivative: How a Fluid Parcel Accelerates

Newton's F = ma follows one fluid parcel, but the velocity field is only known at fixed points. This post bridges the gap between Eulerian and Lagrangian viewpoints, deriving the material derivative.

Diagram of the Fourier Neural Operator architecture with lifting, Fourier layers and projectionphysics simulation 09/10
Educational

Fourier Neural Operators (FNOs)

A step by step guide through the architecture of Fourier Neural Operators, their applications, and how they efficiently process global information through the Fourier transform.

DeepONet branch and trunk networks mixing basis functionsphysics simulation 07/10
Educational

Neural Operators and DeepONet

An introduction to neural operators, DeepONet, and how they can be used to learn mappings between function spaces.

Stable and unstable numerical wave solutions on either side of the CFL limitphysics simulation 06/10
Educational

The CFL Condition of the Wave Equation

A deep dive into the Von Neumann stability analysis of the wave equation and its connection to the CFL condition.

Numerical error of a finite difference scheme growing over timephysics simulation 05/10
Educational

Von Neumann Stability Analysis

A deep dive into the von Neumann stability analysis, its connection to the CFL condition, and how it determines the stability of numerical schemes.

Recent Projects

All projects

Dual MIDI Transformer

A MIDI Event based transformer architecture, utilizing two seperate transformers operating on the global MIDI events and local event parameters.

TransformerDecoderMIDIPyTorch

Basic MIDI Transformer

A basic transformer architecture for MIDI generation, utilizing a single decoder to enable faster training and inference speed.

TransformerDecoderMIDIPyTorch

MoodWave

A real-time streaming pipeline correlating German news sentiment (GDELT) with Spotify Top 200 musical features, using Kafka and Spark Streaming for dual-stream aggregation.

KafkaSparkPySparkNext.jsSupabase