# Eren Aygün

Eren Aygün is a remote worker on Himalayas, Bachelor Thesis at Data Science Department at Max Planck Institute for Astronomy, based in Germany.

Source: https://himalayas.app/@erenaygn

```text
Data scientist at HeiGIT building global geospatial pipelines that turn street-view imagery into road surface datasets.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | Germany |
| Authorized to work in | Germany |
| Salary expectations | 50k+ EUR |
| Job categories | Data Scientist, Geospatial Data Scientist, Machine Learning Engineer |
| Skills | Data Science, geospatial data analysis, Machine Learning, Deep Learning, Spatial Statistics, Geospatial Data Processing, Data Mining, Geodatabases, OpenStreetMap, Street Level Imagery, Satellite Imagery, Python, TensorFlow, C++, SQL |
| LinkedIn | https://linkedin.com/in/eren-ayguen |
| GitHub | https://github.com/erennere |

## About

```text
At HeiGIT, I built a reproducible pipeline that processed more than 105 million street-view image sequences into global road surface datasets, with continental F1 scores of 91–97%. I also co-authored a peer-reviewed paper and completed my M.Sc. Geography thesis on classifying road surface pavedness across 4 million km of roads.

At the Max Planck Institute for Astronomy, I built deep-learning pipelines to reconstruct astronomical imagery and automated workflows to evaluate photometric accuracy. My work brings together geospatial data, machine learning, and reproducible processing, including open data published to the Humanitarian Data Exchange.
```

## Experience

### Bachelor Thesis at Data Science Department (current)

Max Planck Institute for Astronomy. Dec 2024 - Present

```text
- Engineered Astronomical Image Reconstruction Pipelines: Built a TensorFlow/Keras deep learning framework evaluating U-Net and GAN architectures with attention-gated skip connections to reconstruct deep-observation-equivalent structure and photometry from noisy Hubble Space Telescope (WFC3/F160W) imagery.

- Designed Executed Systematic Scenario Sweeps: Executed 64-configuration hyperparameter an
```

### Research Study Assistant at Big Data Analytics (current)

HeiGIT. Oct 2023 - Present

```text
- Engineered Global Geospatial Pipelines: Built a reproducible, end-to-end processing pipeline using Mapillary Graph API, DuckDB, Parquet, and OpenStreetMap geometries to extract over 105M street-view image sequences; generated global road surface datasets with 91–97% continental F1 scores.

-Co-authored a peer-reviewed paper in ISPRS Journal of Photogrammetry and Remote Sensing (https://doi.org/1
```

### Apprenticeship at Big Data Analytics

HeiGIT. Jun 2023 - Aug 2023

```text
Big Spatial Data Analytics, Geodatabases, Geodata Processing/Geocomputation, Data Mining, Spatial Statistics, Machine Learning
```

### Apprenticeship at Spatial Planing

ALTUS AG. Oct 2019 - Dec 2019

```text
- searching and keeping dataset regarding the legal regulations pertaining
to wind turbines in 116 planing regions of Germany
- creating maps and presentations regarding the legal changes
- making suggestions of new wind turbine locations
```

## Education

### Heidelberg University

Bachelor of Science - BS, Physics. 2022 - 2025

```text
Thesis: Deep Learning in the Depths of Space: U-Net-Based Denoising for Shallow Extragalactic Surveys based on HST Infrared Images
```

### Heidelberg University

Master of Science - MS, Geography. 2020 - 2024

```text
Thesis: Volunteered Street View Imagery as a New Source of Geospatial Data?
Global Coverage Analysis of the Crowdsourced Street View Imagery Service Mapillary via OpenStreetMap and its Usage in Estimation of Worldwide Surface Condition
```

### Heidelberg University

Bachelor of Arts - BA, Political Sciences (50% B.A.), Geography (50% B.Sc. ). 2017 - 2020

### Koç University

Bachelor of Arts - BA, International Relations. 2015 - 2017

```text
transferred to University of Heidelberg
```

### Istanbul Cagaloglu Anadolu Lisesi

High School Diploma. 2010 - 2015

```text
DSD-Sprachdiplomschule
```

## Tech stack

- NumPy
- Pandas
- Slack
- Python
- C++
- TensorFlow
- Keras
- Leaflet
- OpenStreetMap
- Linux
- WSL
- Git
- Docker
- SQL
- Dagster
- DuckDB
- Bash

To contact Eren, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Lauraine Munkanta](https://himalayas.app/@laurainemunkanta): Working Student in Data Quality, Kloeckner.i GmbH
- [Aaron Artunduaga](https://himalayas.app/@aaronartunduaga): Student Assistant, Karlsruher Institut fu ¨r Technologie
- [Nidhi Sihag](https://himalayas.app/@nidhisihag): Junior Data Scientist, K2 Systems GmbH
- [Mika Martin Broese](https://himalayas.app/@mikamartinbroese): Student Assistant, Erason
- [Suresh Amgoth](https://himalayas.app/@sureshamgoth): Working Student (Software Development & XML Validation), Helmholtz Centre for Environmental Research (UFZ)
- [Sagar M A](https://himalayas.app/@sagarma): Data Science (Virtual Intrenship), British Airways
- [Humay Abbasli](https://himalayas.app/@humayabbasli): Student Assistant for Modern Optimization, Stiftung Universität Hildesheim
- [binish batool](https://himalayas.app/@binishbatool): Machine Learning Contributor, DrivenData
- [Nikita Teresenko](https://himalayas.app/@nikitateresenko): Bachelor Thesis Data Science / Machine Learning, Dr. Ing. h.c. F. Porsche AG
- [Shaunak Atul Kanikar](https://himalayas.app/@shaunakatulkanikar): Machine Learning Engineer, Society for the Advancement of Applied Computer Science (GFa
