---
title: Multiscaler
emoji: 🛰️
colorFrom: blue
colorTo: yellow
sdk: docker
pinned: false
license: mit
short_description: Illustrating "Optimizing Multi-Scale Representations"
---

# Overview 

This Shiny application allows users to visualize and explore results from the multi-scale representation approach described in the paper:

Fucheng Warren Zhu, Connor T. Jerzak, Adel Daoud. Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Application to Two Anti-Poverty RCTs. Forthcoming in *Proceedings of the Fourth Conference on Causal Learning and Reasoning (CLeaR)*, 2025.

The app focuses on how varying the scale of Earth Observation (EO) inputs can affect conditional average treatment effect (CATE) estimation. It provides both a 2D heatmap and a 3D surface plot, helping researchers analyze how model performance metrics change with different multi-scale representations.

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

# Reference

For more information, see arxiv.org/abs/2411.02134

```
@article{zhu2024encoding,
  title={Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs},
  author={Fucheng Warren Zhu and Connor T. Jerzak and Adel Daoud},
  journal={Forthcoming in Proceedings of the Fourth Conference on Causal Learning and Reasoning (CLeaR), Proceedings of Machine Learning Research (PMLR)},
  year={2025},
  volume={},
  pages={},
  publisher={}
}
```