Learn AI's role in addressing complex challenges
Build skills combining human and machine intelligence for positive real-world impact using AI.
What you’ll get from this course
- Master a step-by-step framework for the development of AI projects.
- Analyze data and build AI models for projects focused on air quality, wind energy, biodiversity monitoring, and disaster management.
- Explore real-world case studies related to public health, climate change, and disaster management.
Learn through real-world projects
Apply computer vision techniques to detect and classify animals for the purpose of biodiversity monitoring.
Develop an AI model to make wind power generation more predictable by providing forecasts 24 hours into the future.
Use natural language processing techniques to analyze trends in a corpus of text messages sent in the aftermath of the 2010 earthquake in Haiti.
Use neural networks and other AI techniques to estimate air quality throughout the city of Bogotá, Colombia.
Build an image classification pipeline to perform damage assessment using satellite images taken after Hurricane Harvey in the U.S. in 2017.
Apply computer vision techniques to detect and classify animals for the purpose of biodiversity monitoring.
Develop an AI model to make wind power generation more predictable by providing forecasts 24 hours into the future.
Your Instructor
You’ll learn from instructor Robert Monarch, who has over 20 years of experience building AI products in industry and working at the intersection of AI and public health and disaster management. Robert is also the author of Human-in-the-Loop Machine Learning, a book focused on human-centered AI applications.
We are also grateful to Sasha Luccioni, Climate Lead and Researcher at HuggingFace for her help in forming the high-level program structure, outlining what kinds of topics and case studies would work best for these courses, and recruiting many of the experts that either appear in guest speaker videos or have contributed behind the scenes.
In partnership with Microsoft’s AI for Good Lab
These courses were built in partnership with researchers at the Microsoft AI for Good Lab who offered their subject matter expertise throughout the development of the program.
We live in a rapidly changing world and a world that is facing big challenges. Yet we have never been in a better position to use technology to help address these issues and positively influence the lives of millions on our planet as well as the planet itself.
Juan Lavista Ferres
VP Data Science, AI for Good Lab, Microsoft
Who should join?
The AI for Good Specialization is designed to be accessible for everyone. We recommend some experience working with data, and performing some basic analysis on your data using tools such as spreadsheets. Whether you’re a student, professional, or someone passionate about making a positive impact on society and the environment, this program provides the tools and knowledge you will need to work on AI for Good initiatives.
“While focused on humanitarian and environmental projects, people who take this specialization can expect to learn how to effectively develop any product that uses AI.”
– Robert Monarch, AI for Good Instructor
Skills you will gain
- AI for Good project framework
- Jupyter Notebooks
- Supervised Machine Learning
- Computer Vision
- Natural Language Processing
- Exploratory Data Analysis
- Time Series Analysis
- Air Quality Monitoring
- Biodiversity Monitoring
- Wind Power Generation Modeling
- Topic Modeling
- Damage Assessment
What Learners Are Saying
I found the AI and Climate Change course extremely interesting and useful. It was a unique combination of two of the most important topics of our time – artificial intelligence and climate change. The course material was deep and insightful, providing me with valuable knowledge and practical skills. I learnt how to use AI to analyse and predict climate change, which I am sure will be an important tool in my future career. Overall, I highly recommend this course to anyone interested in AI and climate change.
I was always interested in climate change and have been involved in Climate Tech startups in the past. This course has inspired me to consider a new AI tech startup in the area. Appreciate your guidance and explaining the case studies that can help me formulate a few ideas of my own.
I deeply appreciate your comments about how defining the problem you’re trying to solve can take weeks or months, and also appreciated the inclusion that the system you built did not work out in the end in AI and Public Health. Both are excellent lessons for students to learn.
The lab notebooks are wonderfully clear, and there are some neat techniques in your utils.py files.
Overall, it was a great course.
This is a fantastic course. Really inspirational. And the code is an excellent way to learn how to sustainably fish for yourself! Thanks and all the best, David
I am a mother of 2 teen ager girls and we all are involved in finding solutions for problems defined under the UN sustainable goal development.
I loved the course, you made it so easy to follow along with Python code and through project-based learning.
I found the AI and Climate Change course extremely interesting and useful. It was a unique combination of two of the most important topics of our time – artificial intelligence and climate change. The course material was deep and insightful, providing me with valuable knowledge and practical skills. I learnt how to use AI to analyse and predict climate change, which I am sure will be an important tool in my future career. Overall, I highly recommend this course to anyone interested in AI and climate change.
I was always interested in climate change and have been involved in Climate Tech startups in the past. This course has inspired me to consider a new AI tech startup in the area. Appreciate your guidance and explaining the case studies that can help me formulate a few ideas of my own.
I deeply appreciate your comments about how defining the problem you’re trying to solve can take weeks or months, and also appreciated the inclusion that the system you built did not work out in the end in AI and Public Health. Both are excellent lessons for students to learn.
The lab notebooks are wonderfully clear, and there are some neat techniques in your utils.py files.
Overall, it was a great course.
This is a fantastic course. Really inspirational. And the code is an excellent way to learn how to sustainably fish for yourself! Thanks and all the best, David
I am a mother of 2 teen ager girls and we all are involved in finding solutions for problems defined under the UN sustainable goal development.
I loved the course, you made it so easy to follow along with Python code and through project-based learning.
I found the AI and Climate Change course extremely interesting and useful. It was a unique combination of two of the most important topics of our time – artificial intelligence and climate change. The course material was deep and insightful, providing me with valuable knowledge and practical skills. I learnt how to use AI to analyse and predict climate change, which I am sure will be an important tool in my future career. Overall, I highly recommend this course to anyone interested in AI and climate change.
I was always interested in climate change and have been involved in Climate Tech startups in the past. This course has inspired me to consider a new AI tech startup in the area. Appreciate your guidance and explaining the case studies that can help me formulate a few ideas of my own.
I deeply appreciate your comments about how defining the problem you’re trying to solve can take weeks or months, and also appreciated the inclusion that the system you built did not work out in the end in AI and Public Health. Both are excellent lessons for students to learn.
The lab notebooks are wonderfully clear, and there are some neat techniques in your utils.py files.
Overall, it was a great course.
This is a fantastic course. Really inspirational. And the code is an excellent way to learn how to sustainably fish for yourself! Thanks and all the best, David
I am a mother of 2 teen ager girls and we all are involved in finding solutions for problems defined under the UN sustainable goal development.
I loved the course, you made it so easy to follow along with Python code and through project-based learning.
Syllabus
Week 1: Introduction to AI for Good
Learning Objectives:
- Define AI for Good and identify AI for Good examples
- Explain at a high level what artificial intelligence, machine learning, and deep learning are, and their relationship with one another
- Describe some AI limitations, concerns and ethical questions surrounding it
- Identify the key components of supervised learning
- List various examples of machine learning algorithms
- Summarize the importance of data for an AI project
Lesson 1: Specialization and Course Introduction
- Video: Welcome to AI for Good
- Video: What is “AI for Good”?
- Video: The Courses in this Specialization
- Project Spotlight Video: Charles Onu – Identifying Asphyxiation in Babies’ Cries
Lesson 2: Introduction to Artificial Intelligence and Machine Learning
- Video: Quick Summary – What is AI?
- Video: Quick Summary – How Supervised Learning Works
- Video: Considering the Impact of Your AI for Good Project
- Video: Juan Lavista Ferres – Microsoft AI for Good Lab
- Graded Quiz: What is AI for Good?
- Video: Week 1 Summary
- Project Spotlight Video: Felipe Oviedo – Anomaly Detection in Breast Cancer Imaging
- Reading: Acknowledgements
- Reading: Week 1 Resources
Week 2: AI for Good Project Framework
Learning Objectives:
- Describe the AI for Good project development framework
- List the expected outcomes from every phase of the framework
- Recognize how the AI for good framework is applied in real-world projects
- Explore a real-world problem (air quality in Bogotá) using the AI for Good framework to:
- Define the problem
- Identify the stakeholders of your project, including the end-user
- Determine where AI could fit and whether it is necessary or not
- Interpret common exploratory data analysis (EDA) graphs
- Use a Jupyter Notebook to run Python code to explore air-quality data
Lesson 1: AI for Good Framework
- Video: AI for Good Framework
- Video: Maternal and Infant Health in Nigeria
- Video: Explore Phase – Problem Definition and Stakeholders
- Video: Explore Phase – Could AI Add Value?
- Video: Design Phase
- Video: Implement Phase
- Video: Evaluate Phase
- Project Spotlight Video: Iva Gumnishka – Building an Ethical Supply Chain
- Graded Quiz “AI for Good Framework”
Lesson 2: Exploring Air Quality
- Video: Air Quality
- Video: Sources of Air Pollution
- Video: Measuring Air Quality
- Video: Bogotá Air Quality Monitoring Network (RMCAB)
- Project Spotlight Video: Bogotá District Secretariat of Environment – Tackling Air Pollution
- Video: Air Quality – Explore Phase
- Video: Introduction to Jupyter Notebook Labs
- Video: Air Quality – Explore and Visualize Missing Data
- Video: Air Quality – Explore Correlations
- Reading: (Optional) Downloading your Notebook and Refreshing your Workspace
- Notebook: Explore Phase – Exploring Air Quality Data
- Video: Air Quality – Explore Phase Checkpoint
- Graded quiz “Exploring Air Quality”
- Reading: Week 2 resources
Week 3: Air Quality in Bogotá Colombia
Learning Objectives:
- Clarify how to approach to an AI problem and why
- List various challenges you may encounter in such AI related project
- Summarize the tasks you do in the design and implement phase
- Describe some approaches for missing data imputation
- Determine the models performance using MAE
- Differentiate between models based on their performance using MAE
- Interpret common exploratory data analysis (EDA) graphs and heatmaps
- Design and Implement the AI4G project, including:
- The model strategy
- The user experience
- Determine how to ensure data protection and privacy
- Use a Jupyter Notebook to run Python code to explore air-quality data
Lesson 1: Designing and Implementing Your Air Quality Project
- Video: Air Quality – Design and Implement Phases
- Video: Air Quality – Establish a Baseline
- Video: Air Quality – Train and Test a Neural Network
- Notebook: Design Phase – Estimating Missing PM2.5 Values
- Video: Air Quality – Nearest Neighbor Method
- Video: Air Quality – Design Phase Checkpoint
- Video: Air Quality – Implement Phase
- Notebook: Lab – Estimating Between Sensors and Constructing a Map
- Video: Air Quality – Project Wrap Up
- Graded Quiz Air Quality Design and Implementation
- Video: Tapiwa Chiwewe – Air Pollution in South Africa
- Video: Course Wrap-Up
- Reading: Week 3 Resources
Week 1: Introduction to AI and Climate Change
Learning Objectives:
- Describe how increased greenhouse gas emissions are creating rising temperatures on Earth (i.e. greenhouse effect)
- Describe ways in which climate change is causing social or environmental crises
- Describe the difference between mitigation and adaptation, as it relates to climate change.
- Identify contexts and problems in which AI has been used and can be used in the context of climate change
Lesson 1: Course Introduction
- Video: Welcome to AI and Climate Change
- Reading: Acknowledgements
- Video: What is Climate Change?
- Video: Introduction to Jupyter Notebook Labs
- Video: Global Temperature Change
- Reading: (Optional) Downloading your Notebook and Refreshing your Workspace
- Notebook: Exploring Global Temperature Change
- Video: Impacts of Climate Change
- Video: AI and Climate Change
- Project Spotlight Video: Caleb Robinson – Siting Renewable Energy Sources
- Graded quiz Climate Change & Global Warming
- Video: Week 1 Summary
- Reading: Week 1 Resources
Week 2: Wind Power Forecasting
Learning Objectives:
- Assess the applicability/relevance of AI technologies for wind power forecasting
- Determine how machine learning approaches can be used for predicting wind power generation
- Determine what metrics are helpful to measure the performance of a regression model
- Explore a real-world wind power forecasting problem using the AI for Good framework to:
- Define the problem
- Identify the stakeholders of your project
- Determine where AI could fit and whether it is necessary or not
- Explore the data of the project
- Design the AI4G project
Lesson 1: Exploring Wind Power
- Video: Introduction to Wind Power
- Project Spotlight Video: Jack Kelly: Predicting Solar Energy with Machine Learning
- Video: AI for Good Framework
- Video: Wind Power – Explore Phase
- Video: Wind Power – Explore the Data
- Video: Wind Power – Visualize the Data
- Notebook: Explore Phase – Distribution of the Wind Power Data
- Video: Wind Power – Explore Phase Checkpoint
Lesson 2: Designing and Implementing Wind Power Forecasting
- Video: Wind Power – Establish a Baseline Model
- Video: Wind Power – Improve the Baseline Model
- Video: Wind Power- Train a Neural Network Model
- Notebook: Design Phase – Feature Engineering on the Wind Power Data
- Video: What is a Sequence Model?
- Video: Wind Power – Establish Baseline Forecasts
- Video: Wind Power – Improve Performance with Sequence Models
- Video: Wind power – Include Wind Speed Forecasts
- Notebook: Design Phase – Forecasting Wind Power 24 Hours in Advance
- Video: Wind Power – Design Phase Checkpoint
- Video: Wind Power – Project Wrap Up
- Project Spotlight Video: Lester Mackey – Climate Modeling and Prediction
- Graded quiz Wind Power Forecasting
- Video: Week 2 Summary
- Reading: Week 2 Resources
Week 3: Monitoring Biodiversity
Learning Objectives:
- Describe the impact of climate change on habitat loss and diversity loss
- Determine how biodiversity loss and climate change are related
- Explain how and why image data is important in the fight against climate change
- Satellite (images/infrared/LIDAR), camera traps, citizen science/crowdsourcing)
- Use different techniques for processing and transforming image data
- Determine how camera trap data is currently analyzed by scientists and what kind of automatic analysis would be helpful to them
Lesson 1: Introduction
- Video: Welcome to Week 3
- Video: Climate Change & Biodiversity
- Video: Monitoring Biodiversity
Lesson 2: Classifying Animals in South Africa
- Video: Snapshot Karoo
- Video: Biodiversity – Explore the Data
- Video: Biodiversity – Visualize the Data
- Project Spotlight Video: Sara Beery – Why Monitor Biodiversity?
- Notebook: Explore Phase – Exploring the Karoo Image Data
- Video: Biodiversity – Explore Phase Checkpoint
- Video: Week 3 Summary
- Graded quiz Biodiversity Monitoring
- Reading: Week 3 Resources
Week 4: Monitoring Biodiversity Loss
Learning Objectives:
- Define what Convolutional Neural Networks (CNNs) are
- Implement a CNN for classifying different types of animals on camera trap data
- Define the difference between training from scratch and fine-tuning a pre-trained model
- Demonstrate the utility of using models trained on general-purpose data that can be fine-tuned on domain-specific datasets
- Evaluate how the model does using confusion matrices and derivative metric(s)
Lesson 1: Convolutional Neural Networks
- Video: Welcome to Week 4
- Video: Convolutional Neural Networks and Pre-Training
- Video: Biodiversity – MegaDetector
- Notebook: Lab – Design Phase – Using the MegaDetector
- Video: Transfer Learning and Fine-Tuning
- Video: Biodiversity – Transfer Learning
- Notebook: Lab – Design Phase – Fine-Tuning Your Classification Model
- Video: Biodiversity – Design Phase Checkpoint
Lesson 2: Implementing Model for Detecting and Classifying Animals
- Video: Biodiversity – Implement Phase
- Notebook: Implement Phase – Object Detection Pipeline
- Video: Biodiversity – Project Wrap Up
- Project spotlight: Priya Donti – Tackling Climate Change with Machine Learning
- Video: Week 4 and Course Summary
- Graded quiz AI Models
- References Reading: Week 4 Resources
Learning Objectives:
By the end of this course, you will:
- Identify ways in which AI techniques including natural language processing and computer vision can be used to produce insights, inform decision-making, and respond in crisis situations.
- Examine the different elements of an AI-driven pipeline in the context of disaster management and the importance of domain partnerships to ensure that the technological tools created are relevant and appropriate given regional and contextual needs and constraints.
- Analyze the data and performance of various AI models applied to disaster management case studies.
Week 1: Introduction to AI and Disaster Management
Learning Objectives:
- Examine the immediate and long-term impacts disasters have on communities.
- Define the four phases of the disaster management cycle and the actions involved at each phase.
- Describe ethical considerations and leadership guidelines when working with communities affected by disasters.
Lesson 1: Introduction to Disaster Management
- Video: Welcome to AI and Disaster Management
- Reading: Acknowledgements
- Video: What is a Disaster?
- Video: The Disaster Management Cycle
- Video: Cyclones Idai & Kenneth
- Video: Cyclones Idai & Kenneth – Response & Recovery
- Video: Cyclone Idai & Kenneth – Mitigation & Preparation
Lesson 2: AI and Impact in Disaster Management
- Video: AI and Disaster Management
- Video: Helping Communities Help Themselves
- Video: Working Toward Impactful Solutions
- Video: Data Privacy and Related Risks
- Video: Getting Involved and Doing No Harm
- Graded Quiz: Disaster Management and Ethical Practices
- Project Spotlight: Mark Belinsky – Misinformation and Hate Speech Detection
- Video: Week 1 Summary
- Reading: Week 1 Resources
Week 2: Satellite Imagery to Detect Disaster Locations
Learning Objectives:
- Explore satellite images from Hurricane Harvey in 2017 to:
- Define the problem
- Identify the stakeholders of your project
- Determine where AI could fit and whether it is necessary or not
- Explore the data of the project
- Design the AI4G project
- Define a use case when satellite data can provide precious resources to guide disaster response
- Identify ethical and privacy constraints when working with aerial imagery in the aftermath of a disaster.
- Implement a CNN for classifying satellite images
- Evaluate how the model does using confusion matrices and derivative metric(s)
- Compare the advantages and disadvantages of using imagery from satellites, aircraft, or drones.
Lesson 1: Overhead Imagery in Disaster Management
- Video: Welcome to Week 2
- Video: AI for Good Framework
- Video: Damage Assessment – Explore Phase
- Video: Damage Assessment – Explore the Data
- Reading: (Optional) Downloading your Notebook and Refreshing your Workspace
- Notebook: Explore Phase – Exploring the Hurricane Harvey Satellite Image Data
- Video: Damage Assessment – Explore Phase Checkpoint
Lesson 2: Analyzing Satellite Data from Hurricane Harvey
- Video: Damage Assessment – Design Phase
- Notebook: Design Phase – Classifying Images with a Convolutional Neural Network
- Video: Damage Assessment – Design Phase Checkpoint
- Video: Damage Assessment – Implement Phase
- Notebook: Implement Phase – Analyzing Classification Features and Develop a Geo-Locator
- Video: Damage Assessment – Project Wrap Up
- Graded Quiz: Damage Assessment for Disaster Response and Recovery
- Video: Week 2 Summary
- Project Spotlight Video: Shahrzad Gholami – Damage Assessment with Satellite Imagery
- Reading: Week 2 Resources
Week 3: Analyzing Text Data to Gain Insights
Learning Objectives:
- Explore the Haiti Earthquake disaster from 2010 to:
- Define the problem
- Identify the stakeholders of your project
- Determine where AI could fit and whether it is necessary or not
- Explore the data of the project
- Design the AI4G project
- Describe how to process text data for natural language applications
- Implement LDA for topic modeling and assess its performance using coherence metric.
Lesson 1: How Text Data Can Help Guide Disaster Response
- Video: Welcome to Week 3
- Video: Haiti Earthquake 2010
- Video: Topic Modeling – Explore Phase
- Video: Topic Modeling – Explore the Data
- Video: Topic Modeling – Visualize the Data
- Notebook: Explore Phase – Exploring the Haiti Earthquake Text Message Data
- Video: Topic Modeling – Explore Phase Checkpoint
Lesson 2: Processing Text Data
- Video: Processing Text Data
- Video: Topic Modeling – Process Text Messages
- Notebook: Design Phase – Cleaning and Processing Text Data
- Video: Topic Modeling – Latent Dirichlet Allocation (LDA)
- Notebook: Design Phase – Performing Topic Modeling on Text Messages with LDA
- Video: Topic Modeling – Project Wrap Up
- Graded Quiz: Text Analysis for Disaster Mitigation and Preparation
- Video: Week 3 and Course Summary
- Reading: Week 3 Resources
- Embracing AI to preserve dying languages
Course Slides:
You can download the annotated version of the course slides below.