# Helmholtz AI FFT seminar series #22

###### tags: `HelmholtzAI`,`FFT`

[ToC]

## :memo: Seminar details

**07 September 2022, 11:00 - 12:00**

Speakers and talk titles:
- **Chandrabali Karmakar** (PhD fellow @ DLR)
Title: XAI in Earth Observation
- **Ridvan Kuzu** (Post-doc, Helmholtz AI consultant @ DLR)
Title: Automatic detection of building displacements through LSTM-autoencoder-based feature representations from InSAR data
- **Antony Zappacosta**
Title: Detecting gamma-ray sources in CTA samples: from traditional image analysis to convolutional neural networks

Chair: **Daniela Espinoza** (Helmholtz AI consultant @ DLR)

### VC details

**Access to online venue (BlueJeans):**
https://bluejeans.com/938941173/8313

*Meeting ID: 938 941 173
Passcode: 8313*

**Want to dial in from a phone?**
Dial one of the following numbers and enter the meeting ID and passcode followed by #:
[phone] (Germany (Frankfurt, German))
[phone] (Switzerland (Zurich, German))

## :memo: Notes

:::info
:bulb: Write down notes and/or interesting information of the seminar. For example, observations auxiliar to the content which is not contained in the slidedeck.
:::

- Slides available on https://syncandshare.lrz.de/getlink/fiXrzvb9ouYzs63mYHSKgp/FFT

- **Ridvan Kuzu** (Post-doc, Helmholtz AI consultant @ DLR)
Title: Automatic detection of building displacements through LSTM-autoencoder-based feature representations from InSAR data
- https://en.wikipedia.org/wiki/Dynamic_time_warping
- implementations: https://pypi.org/project/dtw-python/

## :question: Questions for the speaker

:::info
:bulb: Write down any questions or topics you wish to discuss during the seminar
_(either with your initials or anonymously)_
:::

> Leave in-line comments! [color=#3b75c6]

- **Ridvan Kuzu** (Post-doc, Helmholtz AI consultant @ DLR)
Title: Automatic detection of building displacements through LSTM-autoencoder-based feature representations from InSAR data
+ PS: can you share a bit how long each time series was?
+ around 300 time points per time series, 5 years recorded, weekly samples
+ PS: can you share a bit about the tools you used? (which libraries you used)
+ everything in pytorch
+ github repo available https://github.com/ridvansalihkuzu/representlib
+ dtw: https://github.com/ridvansalihkuzu/representlib/blob/main/represent/losses/soft_dtw.py

## :question: Your Feedback

:::info
:bulb: Write down your feedback about the seminar
_(either with your initials or anonymously)_
:::

### Share something that you learned or liked :+1:

- ...

### Share something that you didn’t like or would like us to improve :-1:

- ...

:::info
:pushpin: Want to learn more? ➜ [HackMD Tutorials](https://hackmd.io/c/tutorials)
:::