Data Mining & Exploration

We make science discovery happen

  • Home
  • Software Services
  • Science Cases
  • Publications
  • Education & Lectures
  • Who's who

Contents

Go to Public Survey

Useful Material

Contact Us

Welcome to the River Zoo Project!

dameware

Main goal of this project is to perform a statistical evaluation of the classification of terrestrial and extraterrestrial drainage networks by human experts.
The idea is to analyze the degree of reliability of class assignment to drainage samples, driven by user expert decisions, taken just by looking at their image and choosing the right pattern type.

This initiative arose from the published research: Donadio, Brescia, Riccardo et al. 2020, "A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies", published by Scientific Reports (Nature Research).
The article is available online.
In this context, the project has a specific role to provide a reliable ground truth for supervised learning classification purposes.
 

This initiative is supported by:

unina Department of Earth, Environment and Resources Sciences of the University Federico II of Napoli, Italy


inaf INAF - Italian National Institute of Astrophysics - Astronomical Observatory of Capodimonte, Napoli, Italy


M. Brescia, C. Donadio

Public Survey

All Experts/Scientists interested in the field are kindly encouraged to participate to this project, by landing on the RiverZoo questionnaire and provide answers.

Your help as an Expert/Scientist is important. Please, take a time to give you contribution!

important
Click the banner below to participate to the River Zoo survey

riverzoo 

For each image, the user can select one or more class types, among those specified in the form. There are 131 drainage network examples from Earth, 23 from Mars and 2 from Titan.
We will collect all answers and provide publicly their related statistical analysis. The names of the participants will remain confidential!

back to top page

Material

Anyone is welcome to use all tools, code and materials, listed below, for their own work.
importantIn publications and/or presentations reporting any kind of activities/results done/obtained through these resources, we request that the authors explicitly cite the River Zoo project, by including this website link and the reference Donadio, Brescia, Riccardo et al. (2021), "A novel approach to the classification of terrestrial drainage networks based on deep learning and preliminary results on solar system bodies", Scientific Reports (Nature Research), 11, 5875

  • Available related material:
    • Drainage Networks Reference List
    • Earth original drainage network images
    • Earth reduced drainage network images
    • Mars and Titan original drainage network images
    • Mars and Titan reduced drainage network images
    • Python code for drainage network images data preparation
    • Python code for drainage network images classification (CNN examples)

back to top page


Copyright © 2020 DAME Collaboration. All right reserved.