Data Science for Water Utilities

Get Started. It's Free
or sign up with your email address
Rocket clouds
Data Science for Water Utilities by Mind Map: Data Science for Water Utilities

1. Reservoirs

1.1. bathymetry

1.1.1. Visualise

1.1.1.1. 2D

1.1.1.2. 3D

1.1.2. Volume

1.1.2.1. non-convex hull

1.1.2.2. capacity chart

1.2. Meteorology

1.3. Hydrology

2. Water treatment plants

2.1. SCADA

2.1.1. Spike detection

2.1.2. Virtual tags

2.1.3. Time series analysis

2.2. Health-Based Targets

3. Asset Data

3.1. Asset life prediction

4. Governance

4.1. Water system index

4.2. Business Intelligence

4.2.1. Reports

4.2.2. Dashboards

4.2.3. Data applications

5. Water Networks

5.1. Water taste testing

5.2. Statistical analysis

5.2.1. Percentiles

5.3. Snow's Cholera analysis

5.3.1. Cluster analysis

5.4. Consumption prediction

5.5. Leak analysis

6. Customers

6.1. Perception

6.1.1. Service quality

6.1.1.1. Data collection

6.1.1.2. Data cleaning

6.1.1.3. Data visualisation

6.1.2. Factor Analysis

6.1.2.1. Exploratory

6.1.2.2. Confirmatory

6.2. Surveys

6.2.1. Question types

6.2.2. Best practice

6.3. Complaints

6.3.1. Spatial analysis

6.3.2. Text analysis

6.4. Contacts

6.4.1. Contact centre modeling

6.4.1.1. Call volumes

6.4.1.2. Erlang C

6.4.2. Time price

6.4.2.1. Contacts per customer per year

7. Economics

7.1. Cost estiation

7.2. Monte carlo simulation

8. Data Science

8.1. Data science definition

8.1.1. Conway Venn Diagram

8.1.2. Trivium

8.1.2.1. Soundness

8.1.2.2. USefulness

8.1.2.2.1. Actionable intelligence

8.1.2.2.2. Data pyramid

8.1.2.2.3. Importance of relaity-based analysis

8.1.2.3. Aesthetics

8.1.2.3.1. Data to Pixel Ratio

8.1.3. Reproducibility

8.1.3.1. Open Source versus closed source

8.1.3.2. Literate programming

8.2. Data Science Continuum

8.3. Introduction to R

8.3.1. Background

9. Implementation

9.1. Organisation

9.2. Workflow