Urban Forests on Urban Forests on the UN Global the UN Global - - PowerPoint PPT Presentation

▶
urban forests on urban forests on the un global the un
SMART_READER_LITE
LIVE PREVIEW

Urban Forests on Urban Forests on the UN Global the UN Global - - PowerPoint PPT Presentation

Sep 04, 2022 192 likes •445 views

Urban Forests on Urban Forests on the UN Global the UN Global Platform Platform Joe Peskett Joe Peskett @joepeskett @joepeskett #UNGlobalPlatform #UNGlobalPlatform Overview Overview Data Science Campus project and methodology

slide-1
SLIDE 1

#UNGlobalPlatform #UNGlobalPlatform

Urban Forests on Urban Forests on the UN Global the UN Global Platform Platform

Joe Peskett Joe Peskett

@joepeskett @joepeskett

slide-2
SLIDE 2

#UNGlobalPlatform #UNGlobalPlatform

Overview Overview

  • Data Science Campus project and

methodology

  • Implementation on the UN Global

Platform services

slide-3
SLIDE 3

#UNGlobalPlatform #UNGlobalPlatform

Urban Forests drivers Urban Forests drivers

  • Collaboration with the Natural Capital

team within UK ONS. ○ There is a clear stakeholder. ○ There is are clear learnings that can be reused and novel techniques to be used.

slide-4
SLIDE 4

#UNGlobalPlatform #UNGlobalPlatform

Alternative methodologies Alternative methodologies

  • Survey
  • Crowdsourcing information
  • Satellite imagery
slide-5
SLIDE 5

#UNGlobalPlatform #UNGlobalPlatform

Urban Forests Methodology Urban Forests Methodology

  • 1. Use Open Street Map (OSM) to

generate sample points around 112 towns & cities in the UK

  • 2. Street view images taken at these

points

  • 3. Images are segmented to provide a

value for percentage vegetation

slide-6
SLIDE 6

#UNGlobalPlatform #UNGlobalPlatform

Urban Forest Methodology Urban Forest Methodology

slide-7
SLIDE 7

#UNGlobalPlatform #UNGlobalPlatform

Urban Forest Methodology Urban Forest Methodology

  • 1. Percentage of green pixels
  • a. Using LAB colour space, random

forest used to increase accuracy

  • 2. Pyramid -scene-parsing network (PSP -

net) trained on CityScapes dataset to segment each image

slide-8
SLIDE 8

#UNGlobalPlatform #UNGlobalPlatform

Urban Forest Methodology Urban Forest Methodology

slide-9
SLIDE 9

#UNGlobalPlatform #UNGlobalPlatform

PSP PSP- net Segmentation net Segmentation

slide-10
SLIDE 10

#UNGlobalPlatform #UNGlobalPlatform

Methodology Comparison Methodology Comparison

slide-11
SLIDE 11

#UNGlobalPlatform #UNGlobalPlatform

Results from the Campus Results from the Campus

  • Total dataset ~17.1 million images
  • Technical report
  • Open source pipeline on GitHub
  • Collaboration with ONS visualisation

team

  • Implementation on the UN Global

Platform

slide-12
SLIDE 12

#UNGlobalPlatform #UNGlobalPlatform

Implementation within the Implementation within the UNGP Methods Service UNGP Methods Service

  • Hosting algorithms, methods and

microservices

  • Dependencies managed per method

using containers

  • Run on cloud infrastructure, allowing

quick scaling

  • Methods are called using APIs
  • Easy access to cloud datastores
slide-13
SLIDE 13

#UNGlobalPlatform #UNGlobalPlatform

  • 1. Image processing
  • Same PSPnet as used for the original pipeline
  • You can see that Phil, one of the lead Data

Scientists developed this code.

  • The model file is loaded in using a function – the

model file is saved in the developers storage, though is made available to be used in methods that he has developed.

slide-14
SLIDE 14

#UNGlobalPlatform #UNGlobalPlatform

slide-15
SLIDE 15

#UNGlobalPlatform #UNGlobalPlatform

  • 2. Considerations for cloud
  • 2. Considerations for cloud

implementation implementation

  • Keep outputs small
  • Can outputs be formatted as inputs

for the following method in the pipeline?

  • Keep scaling in mind
slide-16
SLIDE 16

#UNGlobalPlatform #UNGlobalPlatform

  • 3. Methods for the pipeline
  • 3. Methods for the pipeline

OSM points Street-view images Segment images Create composites Generate points for requesting images Download images into cloud storage, filed into way ids. Analyse images/return value

  • f vegetation for each image

Use segmentation data with

  • riginal image to show classes

with colours

slide-17
SLIDE 17

#UNGlobalPlatform #UNGlobalPlatform

  • 3. Methods for the pipeline
  • 3. Methods for the pipeline

HighwayScrapeR method

slide-18
SLIDE 18

#UNGlobalPlatform #UNGlobalPlatform

slide-19
SLIDE 19

#UNGlobalPlatform #UNGlobalPlatform

  • 3. Methods for the pipeline:
  • 3. Methods for the pipeline:

Image downloader Image downloader

  • All images are saved in cloud -based

storage

  • Coordinates are kept in the image

filename, way_id is in the folder name

slide-20
SLIDE 20

#UNGlobalPlatform #UNGlobalPlatform

  • 4. Composing the pipeline
  • 4. Composing the pipeline

OSM points Street-view images Segment images Create composites

slide-21
SLIDE 21

#UNGlobalPlatform #UNGlobalPlatform

  • 5. Asynchronous processing
  • 5. Asynchronous processing
slide-22
SLIDE 22

#UNGlobalPlatform #UNGlobalPlatform

  • 6. Calling the pipeline locally
  • 6. Calling the pipeline locally
slide-23
SLIDE 23

#UNGlobalPlatform #UNGlobalPlatform

Pros and Cons of this pipeline Pros and Cons of this pipeline

  • Use of street -view images
  • Incomplete coverage using street
  • view images
  • Timing of street -view image capture
  • Ensuring access to data
  • 1. Learning how to work in new ways
  • 2. Modular design of pipeline, allowing reuse of code
slide-24
SLIDE 24

#UNGlobalPlatform #UNGlobalPlatform

“

Thanks for listening. Any questions?