Tools for Individuals: Difference between revisions

Content deleted Content added

Inline

Revision as of 17:46, 25 August 2020

Individuals and households constantly make decisions that affect their carbon footprint, and many wish to reduce their impact. ML can help quantify the climate impact of consumer products and actions, estimate the benefits resulting from personal behavior change, provide appliance-level residential energy use data, identify households with high potential for efficiency gain, and optimize appliances to operate when low-carbon electricity is available. ML can also help effectively inform people and provide them constructive opportunities by modeling consumer behavior and simplifying information on climate-relevant laws and policies.

Data

Many of the existing datasets involve individual or household level information regarding energy consumption, transportation and consumer habits. Some useful datasets include:

Global Footprint Data: Ecological Footprint data for different countries and different levels of granularity.
Individual household electric power consumption data set.: Measurements of electric power consumption in one household with a one-minute sampling rate over a period of almost 4 years.
Residential energy use survey results: results of a 2005 national survey that collects residential energy-related data for over 4,381 households in the United States.
Commercial and Residential Hourly Load Profiles: contains hourly load profile data for 16 commercial building types and residential buildings in the United States.
Buildings Performance Database, sample residential data: a non-proprietary subset of the Department of Energy's Buildings Performance Database.

Methods and Software

Tomorrow Project - Calculates impact of your climate behaviors by using ML to read your data.
WattTime - Predicts marginal emissions cost of energy consumption in real time.
Ecological Footprint Explorer - an interactive tool to explore the Ecological Footprint and biocapacity for over 200 countries and regions, updated annually.

@@ Line 1: / Line 1: @@
-''This page is about the intersection of individual decision-making and machine learning in the context of climate change. For an overview of human decision-making as a whole, please see the [https://en.wikipedia.org/wiki/Decision-making Wikipedia page] on this topic.''
 Individuals and households constantly make decisions that affect their carbon footprint, and many wish to reduce their impact. ML can help quantify the climate impact of consumer products and actions, estimate the benefits resulting from personal behavior change, provide appliance-level residential energy use data, identify households with high potential for efficiency gain, and optimize appliances to operate when low-carbon electricity is available. ML can also help effectively inform people and provide them constructive opportunities by modeling consumer behavior and simplifying information on climate-relevant laws and policies.
+== Data ==
+Many of the existing datasets involve individual or household level information regarding energy consumption, transportation and consumer habits. Some useful datasets include:
+* [https://data.world/footprint Global Footprint Data]: Ecological Footprint data for different countries and different levels of granularity.
-== Machine Learning Application Areas ==
+* [https://archive.ics.uci.edu/ml/datasets/individual+household+electric+power+consumption Individual household electric power consumption data set.]: Measurements of electric power consumption in one household with a one-minute sampling rate over a period of almost 4 years.
+* [https://openei.org/datasets/dataset/residential-energy-consumption-survey-results-total-energy-consumption-expenditures-and-intensiti Residential energy use survey results]: results of a 2005 national survey that collects residential energy-related data for over 4,381 households in the United States.
+* [https://openei.org/datasets/dataset/commercial-and-residential-hourly-load-profiles-for-all-tmy3-locations-in-the-united-states Commercial and Residential Hourly Load Profiles]: contains hourly load profile data for 16 commercial building types and residential buildings in the United States.
+* [https://openei.org/datasets/dataset/doe-buildings-performance-database-sample-residential-data Buildings Performance Database, sample residential data]: a non-proprietary subset of the Department of Energy's Buildings Performance Database.
+== Methods and Software ==
-* '''[[Understanding Personal Carbon Footprint|Understanding personal carbon footprint]]:''' Individuals and households constantly make decisions that affect their carbon footprint, and many wish to reduce their impact. ML can help quantify the climate impact of consumer products and actions, estimate the benefits resulting from personal behavior change, provide appliance-level residential energy use data, identify households with high potential for efficiency gain, and optimize appliances to operate when low-carbon electricity is available.
-* '''[[Facilitating Behavior Change|Facilitating behavior change]]:''' Many individuals are eager to contribute to climate change solutions, and engaging them can be highly impactful. ML can help effectively inform people and provide them constructive opportunities by modeling consumer behavior and simplifying information on climate-relevant laws and policies.
+* [https://www.tmrow.com/ Tomorrow Project] - Calculates impact of your climate behaviors by using ML to read your data.
-== Background Readings ==
+* [https://www.watttime.org/ WattTime] - Predicts marginal emissions cost of energy consumption in real time.
+* [http://data.footprintnetwork.org/#/ Ecological Footprint Explorer] - an interactive tool to explore the Ecological Footprint and biocapacity for over 200 countries and regions, updated annually.
-=== General ===
+== Recommended Readings ==
+=== Overall ===
-*'''Climate Change Needs Behavior Change: Making the case for behavioral solutions to reduce global warming (2018)'''<ref>{{Cite web|url=https://rare.org/wp-content/uploads/2019/02/2018-CCNBC-Report.pdf|title=Climate Change Needs Behavior Change: Making the Case for Behavioral Solutions to Reduce Global Warming|author=Katie Williamson, Aven Satre-Meloy, Katie Velasco, Kevin Green|year=2018}}</ref>: a report on the foundations of climate change and the role for human behavior in slowing it down. [https://rare.org/wp-content/uploads/2019/02/2018-CCNBC-Report.pdf Available here.]
+* K. Williamson, A. [https://rare.org/wp-content/uploads/2019/02/2018-CCNBC-Report.pdf Climate Change Needs Behavior Change: Making the case for behavioral solutions to reduce global warming.] 2018.
 === Individual and Household Consumption ===
+* Swan, L.J. et al., [https://www.sciencedirect.com/science/article/pii/S1364032108001949 Modeling of end-use energy consumption in the residential sector: A review of modeling techniques]. (2009)
-*'''Modeling of end-use energy consumption in the residential sector: A review of modeling techniques (2009)'''<ref>{{Cite journal|last=Swan|first=Lukas G.|last2=Ugursal|first2=V. Ismet|date=2019|title=Modeling of end-use energy consumption in the residential sector: A review of modeling techniques|url=https://linkinghub.elsevier.com/retrieve/pii/S1364032108001949|journal=Renewable and Sustainable Energy Reviews|language=en|volume=13|issue=8|pages=1819–1835|doi=10.1016/j.rser.2008.09.033|via=}}</ref>: a review of the various modeling techniques used for modeling residential sector energy consumption.
+* Jones, C.M. et al., [https://pubs.acs.org/doi/abs/10.1021/es102221h Quantifying carbon footprint reduction opportunities for US households and communities.] (2011)
-*'''Quantifying carbon footprint reduction opportunities for US households and communities (2011)'''<ref>{{Cite journal|last=Jones|first=Christopher M.|last2=Kammen|first2=Daniel M.|date=2011|title=Quantifying Carbon Footprint Reduction Opportunities for U.S. Households and Communities|url=https://pubs.acs.org/doi/10.1021/es102221h|journal=Environmental Science & Technology|language=en|volume=45|issue=9|pages=4088–4095|doi=10.1021/es102221h|issn=0013-936X|via=}}</ref> ''':''' this study uses consumption-based life cycle accounting techniques to quantify the carbon footprints of typical U.S. households and to quantify greenhouse gas and financial savings from 13 potential mitigation actions. [https://pubs.acs.org/doi/abs/10.1021/es102221h Available here.]
+* Remani, T. et. al., [https://ieeexplore.ieee.org/document/8426048 Residential load scheduling with renewable generation in the smart grid: A reinforcement learning approach.] (2018)
-*'''Residential load scheduling with renewable generation in the smart grid: A reinforcement learning approach (2018)'''<ref>{{Cite journal|last=Remani|first=T.|last2=Jasmin|first2=E.A.|last3=Ahamed|first3=T.P. Imthias|date=2019|title=Residential Load Scheduling With Renewable Generation in the Smart Grid: A Reinforcement Learning Approach|url=https://ieeexplore.ieee.org/document/8426048/|journal=IEEE Systems Journal|volume=13|issue=3|pages=3283–3294|doi=10.1109/JSYST.2018.2855689|issn=1932-8184|via=}}</ref>: this paper proposes of a comprehensive, Reinforcement Learning-based model with implementable solution considering consumer comfort, stochastic renewable power, and tariffs. [https://ieeexplore.ieee.org/document/8426048 Available here.]
 === Behavior Change ===
+* Klenert, D. et al., [https://www.nature.com/articles/s41558-018-0201-2 Making carbon pricing work for citizens.] (2018)
-*'''Making carbon pricing work for citizens (2018)''' <ref>{{Cite journal|last=Klenert|first=David|last2=Mattauch|first2=Linus|last3=Combet|first3=Emmanuel|last4=Edenhofer|first4=Ottmar|last5=Hepburn|first5=Cameron|last6=Rafaty|first6=Ryan|last7=Stern|first7=Nicholas|date=2018|title=Making carbon pricing work for citizens|url=http://www.nature.com/articles/s41558-018-0201-2|journal=Nature Climate Change|language=en|volume=8|issue=8|pages=669–677|doi=10.1038/s41558-018-0201-2|issn=1758-678X|via=}}</ref>: this paper synthesizes findings regarding the optimal use of carbon revenues from both traditional economic analyses and studies in behavioural and political science. [https://www.nature.com/articles/s41558-018-0201-2 Available here.]
+* Jones, C. et al., [https://onlinelibrary.wiley.com/doi/abs/10.1111/risa.12601 The future is now: reducing psychological distance to increase public engagement with climate change.] (2017)
-*'''The future is now: reducing psychological distance to increase public engagement with climate change (2017)'''<ref>{{Cite journal|last=Jones|first=Charlotte|last2=Hine|first2=Donald W.|last3=Marks|first3=Anthony D. G.|date=2017|title=The Future is Now: Reducing Psychological Distance to Increase Public Engagement with Climate Change: Reducing Psychological Distance|url=http://doi.wiley.com/10.1111/risa.12601|journal=Risk Analysis|language=en|volume=37|issue=2|pages=331–341|doi=10.1111/risa.12601|via=}}</ref> : a study that looks at climate change communication intervention and how it can increase public engagement by reducing the psychological distance of climate change. [https://onlinelibrary.wiley.com/doi/abs/10.1111/risa.12601 Available here.]
-*'''Predictive segmentation of energy consumers (2016)'''<ref>{{Cite journal|last=Albert|first=Adrian|last2=Maasoumy|first2=Mehdi|date=2016|title=Predictive segmentation of energy consumers|url=https://linkinghub.elsevier.com/retrieve/pii/S0306261916307334|journal=Applied Energy|language=en|volume=177|pages=435–448|doi=10.1016/j.apenergy.2016.05.128|via=}}</ref>: this paper proposes a predictive segmentation technique for identifying sub-groups in a large population that are both homogeneous with respect to certain patterns in customer attributes, and predictive with respect to a desired outcome. [https://www.researchgate.net/profile/Mehdi_Maasoumy/publication/303895476_PredictiveSegmentationOfEnergyConsumers/links/575b0b9e08aed884620d990a/PredictiveSegmentationOfEnergyConsumers.pdf Available here.]
+* Albert, A. and Maasoumy, M. [https://www.researchgate.net/profile/Mehdi_Maasoumy/publication/303895476_PredictiveSegmentationOfEnergyConsumers/links/575b0b9e08aed884620d990a/PredictiveSegmentationOfEnergyConsumers.pdf Predictive segmentation of energy consumers.] (2016)
+== Community ==
-== Online Courses and Course Materials ==
-{{SectionStub}}
-== Conferences, Journals, and Professional Organizations ==
+=== Journals and conferences ===
-{{SectionStub}}
-=== Major conferences ===
+=== Societies and organizations ===
-=== Major journals  ===
+=== Past and upcoming events ===
+== Important considerations ==
-=== Major societies and organizations ===
-== Libraries and Tools ==
-*[https://www.tmrow.com/ '''Tomorrow Project'''] - Calculates impact of your climate behaviors by using ML to read your data.
-*'''[https://www.watttime.org/ WattTime] -''' Predicts marginal emissions cost of energy consumption in real time.
-*[http://data.footprintnetwork.org/#/ '''Ecological Footprint Explorer'''] - an interactive tool to explore the Ecological Footprint and biocapacity for over 200 countries and regions, updated annually.
-*[https://carbonintensity.org.uk/ '''Carbon Intensity API'''] - 96+ hour ahead forecast of UK carbon intensity in real time.
-== Data ==
-Many of the existing datasets involve individual or household level information regarding energy consumption, transportation and consumer habits. Some useful datasets include:
+== Next steps ==
-*'''[https://data.world/footprint Global Footprint Data]:''' Ecological Footprint data for different countries and different levels of granularity.
-* [https://archive.ics.uci.edu/ml/datasets/individual+household+electric+power+consumption '''Individual household electric power consumption data set.''']: Measurements of electric power consumption in one household with a one-minute sampling rate over a period of almost 4 years.
-* [https://openei.org/datasets/dataset/residential-energy-consumption-survey-results-total-energy-consumption-expenditures-and-intensiti '''Residential energy use survey results''']: results of a 2005 national survey that collects residential energy-related data for over 4,381 households in the United States.
-* [https://openei.org/datasets/dataset/commercial-and-residential-hourly-load-profiles-for-all-tmy3-locations-in-the-united-states '''Commercial and Residential Hourly Load Profiles''']: contains hourly load profile data for 16 commercial building types and residential buildings in the United States.
-* [https://openei.org/datasets/dataset/doe-buildings-performance-database-sample-residential-data '''Buildings Performance Database, sample residential data''']: a non-proprietary subset of the Department of Energy's Buildings Performance Database.
 == References ==
-<references />