Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards unearthing neglected climate innovations from scientific literature using Large Language Models

César Quilodrán-Casas, Christopher Waite, Nicole Alhadeff, Diyona Dsouza, Cathal Hughes, Larissa Kunstel-Tabet, Alyssa Gilbert

TL;DR

This study employs a curated dataset sourced from OpenAlex, a comprehensive repository of scientific papers to evaluate title-abstract pairs from scientific papers on seven dimensions, covering climate change mitigation potential, stage of technological development, and readiness for deployment, and suggests LLM-based models can effectively augment human expertise, uncovering climate solutions that are potentially impactful but with far greater speed, throughput and consistency.

Abstract

Climate change poses an urgent global threat, needing the rapid identification and deployment of innovative solutions. We hypothesise that many of these solutions already exist within scientific literature but remain underutilised. To address this gap, this study employs a curated dataset sourced from OpenAlex, a comprehensive repository of scientific papers. Utilising Large Language Models (LLMs), such as GPT4-o from OpenAI, we evaluate title-abstract pairs from scientific papers on seven dimensions, covering climate change mitigation potential, stage of technological development, and readiness for deployment. The outputs of the language models are then compared with human evaluations to assess their effectiveness in identifying promising yet overlooked climate innovations. Our findings suggest that these LLM-based models can effectively augment human expertise, uncovering climate solutions that are potentially impactful but with far greater speed, throughput and consistency. Here, we focused on UK-based solutions, but the workflow is region-agnostic. This work contributes to the discovery of neglected innovations in scientific literature and demonstrates the potential of AI in enhancing climate action strategies.

Towards unearthing neglected climate innovations from scientific literature using Large Language Models

TL;DR

This study employs a curated dataset sourced from OpenAlex, a comprehensive repository of scientific papers to evaluate title-abstract pairs from scientific papers on seven dimensions, covering climate change mitigation potential, stage of technological development, and readiness for deployment, and suggests LLM-based models can effectively augment human expertise, uncovering climate solutions that are potentially impactful but with far greater speed, throughput and consistency.

Abstract

Climate change poses an urgent global threat, needing the rapid identification and deployment of innovative solutions. We hypothesise that many of these solutions already exist within scientific literature but remain underutilised. To address this gap, this study employs a curated dataset sourced from OpenAlex, a comprehensive repository of scientific papers. Utilising Large Language Models (LLMs), such as GPT4-o from OpenAI, we evaluate title-abstract pairs from scientific papers on seven dimensions, covering climate change mitigation potential, stage of technological development, and readiness for deployment. The outputs of the language models are then compared with human evaluations to assess their effectiveness in identifying promising yet overlooked climate innovations. Our findings suggest that these LLM-based models can effectively augment human expertise, uncovering climate solutions that are potentially impactful but with far greater speed, throughput and consistency. Here, we focused on UK-based solutions, but the workflow is region-agnostic. This work contributes to the discovery of neglected innovations in scientific literature and demonstrates the potential of AI in enhancing climate action strategies.

Paper Structure

This paper contains 18 sections, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background and Literature Review
  3. Methods
  4. Human and LLM evaluation
  5. Data Collection from OpenAlex
  6. Human Evaluation via Survey
  7. Large Language Model (LLM) Evaluation
  8. Data Processing and Analysis
  9. Results
  10. Comparison of LLM scenarios against human reasoning
  11. Evaluation of abstracts identified by LLM
  12. Climate change mitigation potential
  13. Weighted scoring of Q2-7 determined by Logistic Regression
  14. Extending LLM reasoning with a scalar scoring system
  15. Qualitative assessment of research works identified
  16. ...and 3 more sections

Figures (5)

  • Figure 1: Scoring of positive control abstracts under each scenario
  • Figure 2: Pearsons coefficient of correlation between questions and scenarios
  • Figure 3: Mitigation potential of research abstracts (Q1)
  • Figure 4: Optimisation of test abstract identification by LLM (100 abstracts) and Independent validation of optimised LLM scenario and scoring algorithm for 1000 unseen abstracts
  • Figure A.1: Keyword frequency in the 100 and 1000 titles and abstracts datasets.