
Tristan B
- Research Program Mentor
PhD at Stanford University
Expertise
Data science, AI, machine learning, sustainability, renewable energy, weather, climate, ecology, endangered species conservation, marine biology, biodiversity, microplastics, satellite data, remote sensing
Bio
I'm excited to mentor students who are curious about using data and AI to tackle real-world challenges—whether that's climate change, public health, social issues, or any problem that matters to you. My research background spans climate science and statistics (AI/ML), with projects exploring everything from water quality and drought to wildfires and even duck migration patterns. But here's what I want you to know: working with me isn't about becoming a climate expert (unless that's your goal!). It's about learning how to ask good questions, wrangle messy data, build models that actually work, and communicate your findings clearly. I love helping students develop both technical skills and the confidence to apply them creatively. Whether you're just starting to code or already comfortable with Python, I'll meet you where you are. During my undergraduate and PhD research, I worked on climate models for predicting heatwave and drought risks, and I've spent time in the field too—ask me about measuring ocean acidification at sea for 28 days straight! These days I work at an AI startup focused on climate, weather, and sustainability, which means I can share insights on both academic research and industry applications. Outside of work, I like to ride my bike and am learning how to kitesurf. I'm genuinely looking forward to working with you and helping you discover what you can build with data!Project ideas
AI and Statistics for Climate Science
Recent years have seen an explosion of advancements in AI, and the climate and environmental sciences have only begun to adopt these latest methods. This project explores how cutting-edge AI techniques and statistical frameworks can help us understand climate change impacts and extreme events. Students can choose to focus on learning specific AI methods (computer vision, natural language processing, time series forecasting with transformers) or dive into detection and attribution science—the framework scientists use to determine whether climate change influenced specific extreme events like hurricanes, heatwaves, or droughts. Potential project directions include: 1) Using computer vision models to classify wildfire smoke plumes or enhance the spatial resolution of climate forecasts, 2) Training time series models to forecast temperature, precipitation, or sea level, 3) Applying natural language processing to classify climate misinformation in text data, 4) Quantifying how climate change affected the likelihood of a recent extreme event by comparing scenarios with and without human influence, or 5) Analyzing climate model data to understand future risks of specific hazards. Learning outcomes include experience with end-to-end data science projects on real-world climate data, in-depth knowledge of AI algorithms or statistical attribution methods, and Python coding skills. Students will work with datasets from sources like NASA climate models, satellite imagery, or historical weather records. Likely outcome is an advanced research paper that can be submitted to high school research journals or science competitions.
Understanding Climate Risks in Your Community
What climate hazards does your hometown face? This project explores expected climate change impacts on your local area—whether that's your city, a place you care about, or any location of interest. You'll learn the fundamentals of climate science and use real data from sources like NASA climate models to understand how risks like wildfires, droughts, heatwaves, flooding, or sea level rise might change by 2050 or 2100. Students will gain hands-on experience analyzing historical weather data and future climate projections to identify which hazards pose the greatest threat to their community. The project can emphasize statistical analysis of climate trends, explore policy frameworks (like the Paris Climate Accord) and adaptation strategies, or examine public health dimensions of climate impacts. Students are welcome to think creatively about secondary effects—for example, how droughts can trigger migration, how sea level rise exacerbates inequality, or how warmer temperatures increase disease spread. Potential outcomes include research papers, data analyses, interactive visualizations, or policy recommendations for local decision-makers. This project is highly customizable to student interests and can range from beginner-friendly explorations to advanced statistical analyses. Likely outcome ranges from beginner to advanced research paper, with the advanced route being capable of submission to high school research journals.
Endangered or Invasive Species Modeling
One of the greatest ecological impacts from climate change will be the shifting of habitats suitable to different species. Of particular concern are shrinking habitats for endangered species, and expanding habitats for invasive species. In this project, a student may select a particular animal/plant species of interest. We will then identify a candidate dataset of locations the species has been observed, such as iNaturalist's database. Then the student can pair that data with information on the typical climate of that region, putting it into what is referred to as a 'species distribution model', a subset of machine learning with the simplest model version being a logistic regression but also including options like random forest. Optionally, the student can then take this trained model and see how expected climates in 2050 and beyond lead to different model predictions of the habitat range. Skills built on in such a project include species distribution modeling, an important area of ecology, as well as in depth research into a specific species. Programming skills for this project require some familiarity with Python or R. Likely outcome is an advanced research paper that can be submitted to high school research journals.
Will the world become too warm for the winter Olympics?
Climate change is increasingly posing significant threats to the Olympics, challenging the tradition of global sports competition. Increasing temperatures and unpredictable weather patterns can disrupt outdoor events. Winter Olympics face particular risks, as warming temperatures jeopardize reliable snow and ice conditions, potentially leading to cancellations or relocations of events. In this project, students will begin by researching the current literature on vulnerabilities of various sports to weather and climate phenomena. Next, the student can compile a list of all previous and/or future planned Olympics locations. We can then see what the projected changes from climate models are in temperature and other relevant variables discovered in your readings to see whether these cities could remain suitable Olympics venues in the years to come. For a more beginner research paper level, the research can focus on readings and data analysis such as through Microsoft Excel. A more advanced research paper level would include working with some of the raw climate model data in Python and more detailed data analysis and data science approaches.
Renewable Energy Optimization and Forecasting
The transition to renewable energy is one of the most important challenges of our time, but solar and wind power come with unique complications—they're intermittent and weather-dependent. In this project, students can explore questions around optimizing renewable energy systems. Potential directions include: 1) Using machine learning to forecast solar or wind energy production based on weather data, 2) Analyzing the economics of renewable energy adoption in different regions, 3) Modeling optimal battery storage strategies to handle renewable energy variability, 4) Investigating how geographic placement of wind farms or solar arrays affects efficiency, or 5) Comparing the lifecycle carbon footprint of different renewable technologies. Students will gain experience with time series forecasting, optimization algorithms, or economic modeling depending on their interests. This project offers flexibility to emphasize either technical data science skills or policy/economic analysis. Likely outcome is an advanced research paper that can be submitted to high school research journals.
Understanding AI's Environmental Footprint: Data Centers, Energy, and Sustainability
As AI systems like ChatGPT, Google's Gemini, and other large language models become ubiquitous, their environmental impact is coming under increasing scrutiny. Training and running these models requires massive data centers that consume enormous amounts of electricity and water for cooling. In this project, students will investigate the environmental costs of AI by analyzing data on data center energy consumption, water usage, and carbon emissions. We can explore questions like: How much energy does it take to train GPT-4 versus smaller models? What are the trade-offs between model performance and environmental impact? How do different regions' energy grids (renewable vs. fossil fuel-based) affect AI's carbon footprint? Students will learn to find and analyze real-world data on tech infrastructure, create compelling visualizations, and think critically about the sustainability of emerging technologies. This project is perfect for students interested in both AI and environmental issues, and can lead to policy recommendations or technical analyses. No prior AI experience needed—just curiosity! Likely outcome is a beginner to advanced research paper.
Satellite Imagery Analysis: Finding Patterns from Space
Satellite imagery has become freely accessible through platforms like Google Earth Engine, opening up exciting possibilities for high school students to explore our planet from space. In this project, students can apply computer vision and machine learning techniques to detect and classify objects in satellite images. Google Earth Engine provides a cloud-based platform with access to decades of satellite imagery and allows for planetary-scale analysis without requiring powerful local computers. Potential project directions include: 1) Tracking deforestation by comparing satellite images over time using vegetation indices like NDVI (Normalized Difference Vegetation Index), 2) Detecting buildings, roads, or infrastructure in urban areas using object detection models, 3) Finding sports fields, solar panels, or agricultural areas using classification techniques, 4) Monitoring changes in water bodies or coastal erosion over time, or 5) Analyzing urban expansion and land use changes in your hometown. Students will learn to work with multispectral imagery, apply spectral indices, use machine learning for image classification, and create compelling visualizations. The project can range from beginner-friendly approaches using pre-built tools to advanced implementations involving training custom deep learning models. Many tutorials and datasets are freely available, making this an accessible entry point into geospatial data science. No prior remote sensing experience needed—just curiosity about seeing Earth from a new perspective! Likely outcome is a beginner to advanced research paper that can include interactive visualizations or web applications.
Product Carbon Footprints: Understanding the Climate Impact of What We Buy
Every product we purchase—from smartphones to sneakers to groceries—has a hidden carbon footprint that extends far beyond what we see on the shelf. This project explores how to calculate and compare the full lifecycle carbon emissions of consumer products using Watershed's Open CEDA (Comprehensive Environmental Data Archive), a free global emissions database covering 148 countries and 400 industries. Students will learn to estimate product carbon footprints by analyzing components, manufacturing locations, and supply chains. Potential directions include: 1) Comparing carbon footprints of similar products (electric vs. gas cars, local vs. imported foods, different smartphone brands), 2) Building a calculator or interactive tool for estimating purchase impacts, 3) Analyzing how manufacturing location affects emissions—the same product can have up to 70% higher emissions depending on the country due to different energy grids, or 4) Identifying "carbon hotspots" in supply chains where the biggest reductions could happen. Students will develop skills in lifecycle assessment, supply chain analysis, and understanding Scope 3 emissions (indirect emissions that make up the majority of most companies' carbon footprints). This project combines environmental science, economics, and data science while addressing real-world questions about sustainable consumption. The technical level ranges from beginner (spreadsheets) to advanced (Python with supply chain modeling). Likely outcome is a beginner to advanced research paper, potentially with an interactive tool useful for real consumers.
Coding skills
Python, RTeaching experience
I've been mentoring students here for over five years, and it's been incredibly rewarding to see students tackle such a wide range of projects. My mentees have explored weather prediction, AI applications, statistical modeling, microplastics, invasive species modeling, wildfire risk assessment, drought prediction, water quality analysis, and ecology—among other topics. What excites me most is helping each student find their unique angle on a problem and building the skills to investigate it rigorously. I'm especially proud that several students have chosen to return for a second project with me—it's the best feedback I could ask for! My goal is to prepare students for the kind of research they'll encounter at the university level and beyond. That means not just learning to code or run analyses, but developing critical thinking skills: how to formulate good research questions, design sound methodologies, interpret results carefully, and communicate findings effectively. Many of my students have showcased their work at prestigious venues including science fairs, academic competitions, and some have even presented at conferences. Whether you're aiming for a specific competition or simply want to build a strong research portfolio for college applications, I'll help you set ambitious but achievable goals. I also love introducing students to cutting-edge tools and approaches. Depending on your project, you might learn to work with leading AI models from organizations like Google, NVIDIA, or OpenAI, use satellite data and remote sensing techniques, apply machine learning to real-world datasets, or develop interactive visualizations of your findings. The technical skills you build will be valuable no matter what field you pursue. Most importantly, I want you to finish our work together feeling confident in your ability to tackle complex problems independently—that's the foundation for success in any STEM career.Credentials
Work experience
Education
Reviews
"Working with Tristan was an absolutely wonderful experience. Tristan helped me learn coding in R and data science (from scratch), then apply it to analyse data for my project, and finally complete my research paper, all within 3 months (8-9 sessions). Working with Tristan has been, by far, one of the best academic experience that I have ever had. He made understanding complex topics simple, the approach to writing long research papers natural and easy (as compared to strenuous and difficult), and learning -- FUN. With his insightful feedback, curated assignments, and extremely thorough knowledge eventually outdo my expectations for my Polygence project, and also gain more confidence with Data Science. He was very flexible with scheduling, very understanding when it came to my other commitments (like test prep, college app), and super easy to communicate with through and between my sessions. Tristan also inspired me to spark personal growth and find more clarity with my career goals. He made sure that I achieved all my goals for my Polygence Project, and always gave me extra time post our general discussions to make sure that my Polygence learning experience could great as possible. I feel fortunate to have worked with Tristan."