The value and challenges of micro- component domestic water consumption datasets Jo Parker Working as part of the ESPRC - ARCC water project with the support.

Slides:



Advertisements
Similar presentations
Code for sustainable homes Water efficiency and surface water runoff Jonathan Reed Atkins Water & Environment.
Advertisements

Correlation and Regression Analysis Many engineering design and analysis problems involve factors that are interrelated and dependent. E.g., (1) runoff.
ECON 251 Research Methods 11. Time Series Analysis and Forecasting.
Operation Research By Anitha Chandran Chitra.R Radha.R Sudhit Sethi.
SWITCH Training Kit: Pilot Training, Entebbe, July 2010 Water Demand Management in the City of the Future Forecasting water demand – why is accurate.
TEST YOUR READING SKILLS : See a day of the week written in French. Say what you think it is. Click to check your answer.
In Belgium: questions…at school… Teachers and pupils: Europaschool! How many times a day do you flush the toilet? How many glasses of water a day do you.
Ain't It A Shame 1-4 Aint it a shame to work on Sunday, Aint it a shame, (a working shame,) Aint it a shame to work on Sunday, Aint it a shame, (a working.
1 The seven days of the week. 2 Monday is our washing day. Scrub, scrub, scrub.
Datamining and statistical learning - lecture 9 Generalized linear models (GAMs)  Some examples of linear models  Proc GAM in SAS  Model selection in.
BA 555 Practical Business Analysis
A few tips on writing a good forecast discussion: Monday, January 24 NWS Discussion as an example Atmo 456 Conlee/Seroka.
Lecture 19: Tues., Nov. 11th R-squared (8.6.1) Review
Lecture 20 Simple linear regression (18.6, 18.9)
Statistical Analysis SC504/HS927 Spring Term 2008 Session 7: Week 23: 7 th March 2008 Complex independent variables and regression diagnostics.
Saturday May 02 PST 4 PM. Saturday May 02 PST 10:00 PM.
1 Econometric Load Forecasting Peak and Energy Forecast 06/14/2005 Econometric Load Forecasting Peak and Energy Forecast 06/14/2005.
7/2/ Lecture 51 STATS 330: Lecture 5. 7/2/ Lecture 52 Tutorials  These will cover computing details  Held in basement floor tutorial lab,
2011 Long-Term Load Forecast Review ERCOT Calvin Opheim June 17, 2011.
Statistical hypothesis testing – Inferential statistics II. Testing for associations.
Correlation & Regression
Remote Sensing of Drought Lecture 9. What is drought? Drought is a normal, recurrent feature of climate. It occurs almost everywhere, although its features.
WATER SAVING. Recycled Water Recycled water is a good alternative because you can reused again and again. It can be used in household and businesses.
1 BA 275 Quantitative Business Methods Please turn in Progress Report #2 Quiz # 5 Simple Linear Regression Introduction Case Study: Housing Prices Agenda.
Idaho Weather and Climate Outlook IDWR Briefing, February 14, 2014 Temperature and Precipitation Summary Snowpack Forecast for next 7 days 3 Month Outlook.
Chapter 12 Multiple Regression and Model Building.
Idaho Weather and Climate Outlook IDWR Briefing, February Troy Lindquist, NOAA National Weather Service Temperature and Precipitation Summary Snowpack.
Public Health and Ecological Forecasting Ben Zaitchik Johns Hopkins University.
Objectives (IPS Chapter 2.1)
Lecture 11.   Modular arithmetic is arithmetic in which numbers do not continue forever.  Modulo 7 has numbers 0, 1, 2, 3, 4, 5, and 6.  Modulo 5.
Modeling Electricity Demand: A Neural Network Approach Christian Crowley GWU Department of Economics INFORMS Meeting October 26, 2004, Denver, CO.
Bellwork 1- Monday, February 27, 2012 How can Microsoft Excel 2007 help you to be more productive?
Regression Analysis Week 8 DIAGNOSTIC AND REMEDIAL MEASURES Residuals The main purpose examining residuals Diagnostic for Residuals Test involving residuals.
Multiple Regression Petter Mostad Review: Simple linear regression We define a model where are independent (normally distributed) with equal.
Graphs.  Graphs are used to present numerical information in picture form.  Two common types of graphs are bar graphs and broken-line graphs. New Car.
OThree Chemistry MM5/CAMx Model Diagnostic and Sensitivity Analysis Results Central California Ozone Study: Bi-Weekly Presentation 2 T. W. Tesche Dennis.
Automated QA/QC Technique for Climate Sensor Data EPSCoR Hawaii HGDR Scientific Data Management Portal Development Team.
Alternatively, dependent variable and independent variable. Alternatively, endogenous variable and exogenous variable.
Tutorial 4 MBP 1010 Kevin Brown. Correlation Review Pearson’s correlation coefficient – Varies between – 1 (perfect negative linear correlation) and 1.
Electric / Gas / Water Information collection, analysis and application Knowledge to Shape Your Future 1 Meter Verification Research Approach –Identify.
Introduction to Statistics for the Social Sciences SBS200, COMM200, GEOG200, PA200, POL200, or SOC200 Lecture Section 001, Spring 2015 Room 150 Harvill.
Weekly Weather Briefing 12/11/ Bill Parker Warning Coordination Meteorologist National Weather Service Shreveport, Louisiana.
Do Now – Math Joke Monday
V Bandi and R Lahdelma 1 Forecasting. V Bandi and R Lahdelma 2 Forecasting? Decision-making deals with future problems -Thus data describing future must.
Mean, Median, and Mode An Introduction to Data Management: Measures of Central Tendencies.
Modelling sample data from smart-type meter electricity usage Susan Williams NTTS Conference, March 2015, Brussels.
Hybrid Load Forecasting Method With Analysis of Temperature Sensitivities Authors: Kyung-Bin Song, Seong-Kwan Ha, Jung-Wook Park, Dong-Jin Kweon, Kyu-Ho.
Ch15: Multiple Regression 3 Nov 2011 BUSI275 Dr. Sean Ho HW7 due Tues Please download: 17-Hawlins.xls 17-Hawlins.xls.
Climate and Agricultural Risk Drs. Reddy, Amor Ines, Sheshagiri Rao.
Main Themes Few vs. Many Variables Linear vs. Non-Linear Statistics vs. Machine Learning.
© British Gas Trading Limited 2011 NDM Data Sample Option C: Regression Analysis.
Expense Report Total Miles MONDAY 5 5 TUESDAY WEDNESDAY 6 6 THURSDAY FRIDAY SATURDAY 0 SUNDAY0 TOTAL 23.
Tutorial 5 Thursday February 14 MBP 1010 Kevin Brown.
The birthday calendar 2B : Unit 6 Days of the week Days of the week.
Happy Days by Charles Fox and Norman Gimbel PowerPoint by Camille Page.
Daily Math Review September 2-6, Monday Solve the following problems with strategies and/or algorithms 5, = 9, = 3, =
Statistics for Business and Economics Module 2: Regression and time series analysis Spring 2010 Lecture 6: Multiple Regression Model Building Priyantha.
THE PRESENT SIMPLE : For actions which occur regularly, habits, permanent situations and general truths.
Introduction Many problems in Engineering, Management, Health Sciences and other Sciences involve exploring the relationships between two or more variables.
CCSS.Math.Content.8.SP.A.1 Construct and interpret scatter plots for bivariate measurement data to investigate patterns of association between two quantities.
BUILDING AND RUNNING THE HYDROLOGICAL MODEL
STATS 330: Lecture 16 Case Study 7/17/ lecture 16
Regression Analysis Week 4.
Residuals The residuals are estimate of the error
What is Regression Analysis?
Georgi Iskrov, MBA, MPH, PhD Department of Social Medicine
UIG Task Force Progress Report
Multiple Linear Regression
Adequacy of Linear Regression Models
Presentation transcript:

The value and challenges of micro- component domestic water consumption datasets Jo Parker Working as part of the ESPRC - ARCC water project with the support of Anglian Water Services (AWS)

Study aim Examine the sensitivity of long-term water demand micro- components to climate variability and change. Jo Parker

What are micro-components? Source: Ofwat

Estimating/forecasting household water demand? Traditionally water into supply. Complexity of household water demand. Micro-component data provides us with the ability to investigate water use at the household scale. Jo Parker

The ‘Golden 100’ Micro-componentsSocio-economic variablesMeteorological variablesOther variables BathOccupancy rateMinimum temperature ( o C)Day of week ShowerRegionMaximum temperature ( o C)Month of year BasinBilling typeRainfall (mm)Bank holiday WCACORN classificationSunshine (hours per day) Kitchen sinkRateable value Washing machine Dishwasher External tap More than 22million data points. Too large to handle in excel. 100 households.

The ‘Golden 100’

Error checking algorithm 1.Basic error checks. 2.Remove large outliers  percentile approach. 3.Stratification. 4.Second screening. 5.Apply transformation. 6.Regression analysis.

1. Basic error checks Remove gross errors. Completeness checks. Dummy variables. Remove 0l/d PCC. Sunday Monday Tuesday Wednesday Thursday Friday Saturday000001

2. Percentile approach Remove PCC outliers (0.05% threshold determined via sensitivity testing). e.g., one rogue entry purported 98,020 litres/day for a single occupancy household.

3. Stratification

4. Second Screening User defined threshold. e.g., secondary screening (250l/d threshold) removed values such as l/d in bath usage for a 3 occupancy household. Excluding external usage.

5. Transformation The Kolmogorov-Smirnov normality test. Box-Cox transformation.

6. Regression – One approach doesn’t fit all Jo Parker Metered households, East region, single occupancy. BasinBath

Bath (non-zero) Jo Parker Metered households, East region, single occupancy.

6. Regression Analyse the frequency of usage and non- usage (Logistic regression) Is this weather, bank holiday, day of the week etc. sensitive? Analyse the volume used (Multiple linear regression) Is this weather, bank holiday, day of the week etc. sensitive? Jo Parker

Variables modelled Observed data input (subpopulation) Micro-components modelled Explanatory variables used MeteredBathMean temperature ( o C) UnmeteredShowerTemperature range ( o C) BasinSunshine (hr) WCRainfall (mm) Kitchen sink7 day rainfall (mm) Washing machine Regional soil moisture deficit index (mm) DishwasherDay of week External tapMonth of year Year Bank holiday Occupancy rate ACORN category

Basin water usage vs. Daily mean Temp. Relatively insensitive to Mean T What is causing striations? Understand peak users (>40l/d)?

Bath water usage vs. Daily mean Temp. Relatively insensitive to Mean T What is causing striations between l/d? Understand peak users (>80l/d)?

Dishwasher water usage vs. Daily mean Temp. Metered Relatively insensitive to Mean T Understand peak users (2 uses per day)? Unmetered Slight negative correlation with Mean T Metered households Unmetered households

Shower water usage vs. Daily Mean Temp. If we look at peak cluster  positive correlation with Mean T.

External water usage vs. Mean Temp. Non-linear sensitivity to Mean T Where is the tipping point? Metered households Unmetered households

Thank you Jo Parker