Conclusion

Congratulations! You have made it to the end of this text. We hope that this brief guide will provide you with the tools you need for success in environmental data science. You may have noticed the introduction of each chapter ends with “Let’s begin.” Really this phrase represents you, and your journey through environmental data science.

We realize that the field of environmental science is more broad than some of the topics here. In fact, when we asked “what is environmental data science” to AI, its response centered on the following topics:

Collecting Data From various sources like:

Remote sensing (e.g., satellite imagery)
Sensors and IoT devices (e.g., air/water quality monitors)
Weather stations
Ecological fieldwork
Government and research databases

Analyzing Data Using tools from:

Statistics (e.g., regression, hypothesis testing)
Machine learning (e.g., classification, prediction models)
Geospatial analysis (e.g., mapping deforestation, tracking pollution)

Modeling and Visualization

Creating predictive models of environmental change (e.g., climate models, species distribution models)
Using visualization to communicate patterns and insights (e.g., dashboards, interactive maps)

Decision-making and Policy

Informing environmental policy and resource management
Supporting climate adaptation, conservation planning, and sustainable development

We recognize that we can’t cover it all in a single book, and so this is the end of the beginning. There are so many helpful resources and organizations.

Where to begin

Collecting Data
Analyzing Data

Grus (2015)
Wickham and Grolemund (2017)
Wickham (2019)

Modeling and Visualization

Zobitz (2023) (shameless plug, John knows)
Dietze (2017)

We would also add the following resources on project-design: - The Turing Way Community (2025) - Zandonella Callegher and Massidda (2022)

Decision-making and Policy / ethics

Wiggins and Jones (2023)
Noble (2018)
Costanza-Chock (2020)
Buolamwini (2023)
Benjamin (2019)
Benjamin (2022)
Ajunwa (2023)
D’Ignazio and Klein (2020)

Environmental data science is part of a larger community of data science practitioners. We invite you to explore organizations involved with intersections between data science, justice, equity, environment, and inclusion:

Build a plan

Now that we have identified some resources, create a multi-year plan of what skills you will develop in environmental data science and how you plan to accomplish them. As you Be specific as possible. Include actionable steps and specific timelines.

Part of what we encourage you to do is to develop a professional development plan. What skills would you like to emphasize moving forward, and how will you accomplish them?

And now begin.