Thesis pitches

We are always looking for bright minds who want to work with us. If you are interested in what you see (or are inspired by the outlines), get in touch!

Technology scale-up

Modeling emerging technology scale-up
Read More

Interactive search query development and evaluation tools

This project aims to design and implement interactive query-building tools using Elasticsearch/Solr index statistics and AI-driven recommendations to help researchers transparently optimise precision, recall, and topical coverage for systematic literature searches.
Read More

Comparing frontier few/single-shot LLM wrappers to conventional classifiers

Tools like Jev promise a convenient and fast way to classify textual data. How well does it compare to conventional supervised models?
Read More

Extracting geographic locations from text

Develop and benchmark a modular NLP pipeline that uses smart gazetteer filtering and context extraction to reliably identify, resolve, and interpret study locations mentioned in scientific literature.
Read More

The great move? Understanding the climate debate’s shift across social media platforms

Recent years have seen a move of social media users from the environmental fields from X/Twitter to Bluesky and other platforms. This project aims to better understand this shift by combining previously gathered X/Twitter data with new data from Bluesky.
Read More

Climate solutions going viral: investigation of factors for successful communication about climate technologies

Technological solutions to climate change are a major part of climate debates on social media. But which factors explain user’s engagement with solutions?
Read More

Exploring climate justice topics in climate adaptation (and/or mitigation) literature

Update and expand existing analysis: Women are under-represented in adaptation policy research and are more likely to emphasise justice topics - IOPscience
Read More

Exploring the scope for automation in rigorous systematic review processes

Climate policies need to be informed by the best and most recent evidence. However, it is a common problem at the science-policy interface that this evidence is often not available when decision-makers need it. “
Read More

Identifying and explaining rapid emissions increases

This project aims to use a policy analysis to explore the effects of policy reversals, weakening legislation, interest group obstruction, and other non-climate policy effects on emissions.
Read More

Identifying the frontiers of emissions reductions

This project aims to quantify the frontiers of emissions reductions and identify where slowdowns in emissions reductions should be anticipated without more stringent action in those sectors.
Read More

When to stop in machine-learning prioritized screening? Bayesian updating for robust stopping rules

In prioritised screening for systematic reviews, the question is when to stop the screening process in a way that the reviewer can be confident to reach a desirable recall target.
Read More

What interventions to safe energy in buildings work, under what conditions and why

A variety of behavioral, information and monetary interventions have been proposed to reduce energy consumption in residential buildings
Read More

Visual metaphors for CDR and/or climate change

What images do different media outlets choose for their content on climate change or different CDR methods?
Read More

Do carbon pricing policies work?

A systematic review and meta-analysis of ex-post evidence
Read More

Automated text translation

Often research states "this is limited to English-language literature". We need to get away from that!
Read More

CDR on social media

Links to external sources and/or qualitative analysis
Read More

Tracking CDR deployments

What is the true scale of implemented carbon capture?
Read More

When and how can ChatGPT help us to save hand labeling efforts

We spend a lot of time and money on students to annotate text data. Some of them are used to train ML text classification models. Can ChatGPT be used to save some of the resources?
Read More