Tackling Climate Change

With Machine Learning

 

Benjamin Akera

Deep Learning IndabaX - Cameroon 🇨🇲

 

PART 0

WhoAmI ?

McGill University | Mila - Quebec AI Inst.

Sunbird AI

Benjamin Akera

Part 1: Climate Change

A Brief Overview

Climate Change

Need net-zero greenhouse gas emissions by 2050 (IPCC 2018)

  • Across energy, transport, buildings., industry, agriculture etc.

How does ML fit into this picture? 

Impacts felt globally

Disproportionate impacts on most disadvantaged populations

 

Takeaways and how to get involved

Part 1

The state of climate Change

Temperature change

Human Activity as a Driving Factor

Approaches to Addressing Climate Action

01 - 

02 - 

03 - 

04 - 

05 - 

The state of

Climate Change

Has induced major changes in climate

  • Climate = "average weather"
  • Extreme heatwaves, precipitation, droughts, hurricanes

Earth has already warmed over 1 º C compared to pre-industrial period

Due to Excess greenhouse gas (GHG) -- emissions from human activities 

  • E.g carbon dioxide, methane, nitrous oxide

The state of

Climate Change

Earth has already warmed over 1 º C compared to pre-industrial period

 

 

https://showyourstripes.info/

Greenhouse gas  Emissions from human activities is a major contributing factor

  • E.g carbon dioxide, methane, nitrous oxide

Approaches to Addressing climate Change

Axes of Action

Climate Science: Understanding and predicting climate change 

Mitigation: Reducing or preventing greenhouse gas emissions

Adaptation: Responding to the effects of a changing climate

Approaches to Addressing climate Change

Axes of Action

Climate Science: Understanding and predicting climate change 

Mitigation: Reducing or preventing greenhouse gas emissions

Adaptation: Responding to the effects of a changing climate

Important Frameworks

Climate Justice: An equity-centered approach to climate change

Co-benefits: Explicitly considering linkages betweeen climate action and other UN Sustainable Development Goals (SDGs)

Climate Change Mitigation

Reducing or preventing GHG Emissions

Sectors

Energy supply 

Transportation

Buildings

Industry

Agriculture

Forestry

.

.

.

Approaches to Addressing climate Change

Axes of Action

Climate Science: Understanding and predicting climate change 

Mitigation: Reducing or preventing greenhouse gas emissions

Adaptation: Responding to the effects of a changing climate

Important Frameworks

Climate Justice: An equity-centered approach to climate change

Co-benefits: Explicitly considering linkages betweeen climate action and other UN Sustainable Development Goals (SDGs)

Adaptation: Responding to the effects of a changing climate

Rising Temperatures

Changing Rain Patterns

Rising sea levels

Ocean acidification

Climate Impacts

Drougts & Heatwaves

More intense storms & flooding

More Frequent wildfires

Loss of Ecosystem services 

Downstream Effects

Biodiversity Loss

Spread of disease vectors & pests

Fig. adapted from Kris Sankaran

Adaptation: Responding to the effects of a changing climate

How ? 

  1. Measuring and predicting risks
    • Risk: Impact X probability 
  2. Strengthening adaptive capacity
    • Robustness: Withstanding a range of outcomes with no/minimal impact
    • Resilience: Recovering Quickly after impact

Approaches to Addressing climate Change

Axes of Action

Climate Science: Understanding and predicting climate change 

Mitigation: Reducing or preventing greenhouse gas emissions

Adaptation: Responding to the effects of a changing climate

Important Frameworks

Climate Justice: An equity-centered approach to climate change

Co-benefits: Explicitly considering linkages betweeen climate action and other UN Sustainable Development Goals (SDGs)

Part 2

 

 

Climate Change

 

Machine Learning

 

 

Part 2

Opportunities for ML in climate action

Considerations for Research and Deployment

Is ML a help or a hinderance? 

Take Aways and How to get involved

01 - 

02 - 

03 - 

04 - 

⚡🔌

🏘️

🏘️

🏘️

🏢

Buildings

Electricity Systems 

☁️

⛈️

☀️

Climate Prediction

Industry

Society

Roles for ML in Mitigation, adaptation & Climate Science

01 - Distilling Raw Data into Actionable information

03 - Optimizing Complex Systems

04 - Improving Predictions

02 - Accelerating Scientific Discovery

05 - Approximating Time-intensive simulations

01 - Distilling Raw Data

Usecase - Glacier Mapping with Satellite Data

Deep Learning &
Semantic Segmentation
Accelerated Mapping of Melting Glaciers 

01 - Distilling Raw Data

Other Examples

Mapping deforestation and carbon stock [M]

Gathering data on building footprints/heights [M]

 

Evaluating coastal flood risk [A]

 

Open buildings John Quinn et al.

02 - Accelerating Scientific Discovery

Role: Suggesting experiments in order to speed up the design process

Relevant ML Areas:  Generative Models, Active Learning, Reinforcement Learning, Graph Neural Networks

👨‍🔬⚗️🧪💊gg

03 - Improving Predictions

Role: Forecasts and timeseries predictions

Relevant ML Areas:  Timeseries analysis, Computer Vision, Bayesian methods

Examples

- Nowcasting for Solar/wind power

- Forecasting electricity demand

- Predicting crop yield from satellite imagery

- Bird species distribution Modelling 

04 - Optimizing Complex Processes

Role: Improving efficient operation of complex, automated systems

Relevant ML Areas:  Optimization, Control, Reinforcement Learning

Examples

- Controlling heating/cooling systems

- Optimizing rail and multimodel transport 

- Demand response in electrical grids 

05 - Approximating simulations

Role: Accelerating time-intensive, often physics-based simulations

Relevant ML Areas:  physics informed ML, Computer Vision, Interpretability, Causal ML

Examples

- Superresolution of predictions from climate models 

- Simulating portions of car aerodynamics

- Speeding up planning models for electric grids

Roles for ML in Mitigation, adaptation & Climate Science

01 - Distilling Raw Data into Actionable information

03 - Optimizing Complex Systems

04 - Improving Predictions

02 - Accelerating Scientific Discovery

05 - Approximating Time-intensive simulations

Recap

ML is not a silver bullet

High-impact applications are not always flashy

Interdisciplinary collaboration is key

  • Scoping the right problems

Sophisticated algorithms can be required but aren't always

Equity Consideration

Key Considerations

  • Incorporating relevant domain information
  • Sharpening pathways to impact
  • Empowering diverse stakeholders
  • Selecting and prioritizing problems
  • Ensuring data is representative

Sophisticated algorithms can be required but aren't always

Opportunities for Innovation

Any innovations should be shaped by needs of the relevant applications

Physics/Engineering constraits or robustness guarantees

Interpretability or causality

Uncertainty quantification

Generalization e.g across geographies, under non-stationarity, or with limited data

Pathways to Impact

Domain identification

Project Scoping

Development

Analysis

Deployment

Other tools

Dataset/Env

ML

Pathways to Impact

Domain identification

Project Scoping

Development

Analysis

Deployment

Other tools

Dataset/Env

ML

Consider the full pathway to impact, including

Data, simulators, Evaluation metrics 

Responsible AI & Climate considerations

Stakeholder engagement

Takeaways and how to get involved

Conclusion & Recap

Introduction to climate change

Opportunities for ML in climate action 

Considerations for research and deployment 

Climatechangeai.org

Credit to Dr. David Rolnick, Dr. Priya Donti & CCAI from whom key points in this presentation are derived.

Thank You ! 

Questions: 

 

akeraben@gmail.com

🤗

DL Indaba X Cameroon

By Benjamin Akera

DL Indaba X Cameroon

  • 28