Published January 25, 2023 | Version 1

Summary ouput data - Wasteaware Cities Benchmark Indicators - WABI 2023 - Global data analytics - Machine learning vs. Non-linear Regression

  • 1. University of Leeds
  • 2. Imperial College London
  • 3. 0000-0002-6892-2204

Description

This is the output dataset for the research publication "Socio-economic development drives solid waste management performance in cities: A global analysis using machine learning". It features 

  • Metadata info used by R codes
  • Summary of results for two modelling approaches (machine learning: Conditional random-forest and non-linear regression)

The independent variables dataset analysed here refer to specific indicators of the WABI methodology (https://www.sciencedirect.com/science/article/pii/S0956053X14004905) that generates solid waste management and resource recovery profiles for cities. It was applied here for 40 cities around the world. The data input are available here: 10.5281/zenodo.7570174

Notes

We are grateful to UN-Habitat for funding the work on the initial version of the indicators, including 20 city profiles, and GIZ through their 'Operator Models' project which funded an intermediate version of the indicators and a further 5 city profiles. We acknowledge all the profilers of the individual cities – many are named in Table S2, and others in reference (Scheinberg et al. 2010). We thank past MSc students under the authors' supervision for offering preliminary partial data clearing and commentary: Henry Hickman (MSc dissertation at University of Leeds, supervised by C.A.V and D.C.W.) and Margaux Fargier (Final year MEng dissertation at Imperial College London, supervised by S.M.G, D.C.W and C.A.V.). We are grateful to Dr Josh Cottom and Mr Ed Cook at the University of Leeds for input on the GDP version selection. We acknowledge the support of Dr Ljiljana Rodic for contributing in data quality control.

Files

Files (35.7 kB)

Name Size
md5:8f27342333a6ef81d0280959c34cbbf0
35.7 kB Download