---
title: "From topography to process: A Python toolkit for landscape evolution analysis - Ricarido Saturay"
tags: PyConTW2025, 2025-organize, 2025-共筆
---

# From topography to process: A Python toolkit for landscape evolution analysis - Ricarido Saturay

{%hackmd L_RLmFdeSD--CldirtUhCw %}

<iframe src=https://app.sli.do/event/2mBBZcSmLYxdkoyM8gMwxn height=450 width=100%></iframe>

:::success
本演講提供 AI 翻譯字幕及摘要，請點選這裡前往 >> [PyCon Taiwan AI Notebook](https://pycontw.connyaku.app/?room=IeW9LW8bnyjr19376twA)
AI translation subtitles and summaries are available for this talk. Click here to access >> [PyCon Taiwan AI Notebook](https://pycontw.connyaku.app/?room=IeW9LW8bnyjr19376twA)
:::

> Collaborative writing start from below
> 從這裡開始共筆

## mountains raised by uplift; lowered by erosion

以 https://download.gebco.net/ 作為範例圖稍微講了一下

## supervied ML

X: landscape (frontend)
Y: processes (backend)

backend: uplift, stream... etc

## 物理為基礎的landscape evolution model

一個來不及寫 也沒有要講的物理學式子 展示landscape怎麼模擬出來

https://landlab.csdms.io/

## Synthetic traindata

## Demo1: use landlab to generate landscapes

## for each landscape gen by Y, compute feature X

raster 資料不好分析 所以引入 networks x 來表示landscapes

Demo3 generate features

## ML model development

嘗試sklearn的nested model

## Model deployyment scenario

realworld landscape -> dem -> ...

---

Below is the part that speaker updated the talk/tutorial after speech
講者於演講後有更新或勘誤投影片的部份