Skip to content
forked from ESIPFed/Geoweaver

a web system to allow users to easily compose and execute full-stack Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) workflows in web browsers by taking advantage of the online spatial data facilities, high-performance computation platforms, and open-source deep learning libraries.

License

Notifications You must be signed in to change notification settings

uhhmed/Geoweaver

 
 

Repository files navigation

Build Status License Stars Forks Issues Coverage

2018 ESIP Lab Incubator Project

Geoweaver is a browser-based software allowing users to easily compose and execute full-stack deep learning workflows via taking advantage of online spatial data facilities, high-performance computation platforms, and open-source deep learning libraries. It provides all-in-one capacity including SSH client (e.g., Putty), FTP client, and scientific workflow software.

It can be run from local machines.

GeoWeaver is a community effort. Any contribution is welcome and greatly appreciated!

Geoweaver Online API

Table of Contents

Software Goals

  1. turning large-scale distributed deep network into manageable modernized workflows;

  2. boosting higher utilization ratio of the existing cyberinfrastructures by separating scientists from tedious technical details;

  3. enhancing the frequency and accuracy of classified land cover land use maps for agricultural purposes;

  4. enabling the tracking of provenance by recording the execution logs in structured tables to evaluate the quality of the result maps;

  5. proof the effectiveness of operationally using large-scale distributed deep learning models in classifying Landsat image time series.

Installation

Dependencies

Java 1.8+ (OpenJDK 8 or higher)

!(only for install via docker) Docker 18.09.1+

!(only for install via docker) Docker-compose 1.23.1+

Quick Install

(Recommended for Linux, Mac, and Windows)

  • Step 1: Download the latest version of geoweaver.jar

  • Step 2: Run the command:

java -jar geoweaver.jar 

Build from source

Use maven to build. In the command line go to the root folder and execute mvn install. After a success build, the Geoweaver jar package will be under the directory: Geoweaver/target/Geoweaver-<version>.jar.

Reset Password for Localhost

Geoweaver will automatically create a password for localhost. It will only show once at first run of Geoweaver. It is recommended to copy and save it at a safe place. If forget or missed that password, please run the following command to reset:

java -jar geoweaver.jar resetpassword

Demo

A live demo site is available in George Mason University.

Tutorial

Geoweaver Tutorial - A beginner tutorial about what Geoweaver can do and how it works

Citation

If you found Geoweaver helpful in your research, please cite us:

Sun, Ziheng, Liping Di, Annie Burgess, Jason A. Tullis, and Andrew B. Magill. "Geoweaver: Advanced cyberinfrastructure for managing hybrid geoscientific AI workflows." ISPRS International Journal of Geo-Information 9, no. 2 (2020): 119.

Dependencies

This project is impossible without the support of several fantastic open source libraries.

d3.js - BSD 3-Clause

graph-creator - MIT License

bootstrap - MIT License

CodeMirror - MIT License

JQuery Terminal - MIT License

License

MIT

About

a web system to allow users to easily compose and execute full-stack Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) workflows in web browsers by taking advantage of the online spatial data facilities, high-performance computation platforms, and open-source deep learning libraries.

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • JavaScript 82.6%
  • Java 13.7%
  • HTML 2.0%
  • CSS 1.5%
  • Shell 0.1%
  • Batchfile 0.1%