Climate Policy Transformer: Utilizing NLP to track the coherence of Climate Policy Documents in the Context of the Paris Agreement

Prashant Pratap Singh, Erik Lehmann, Mark Tyrrell

Keywords: NLP, Climate, NDC, Policy

TL;DR: We show how to utilize NLP to classifying climate targets, actions, policies, and plans, along with their sector, mitigation-adaptation, and greenhouse gas (GHG) components in policy documents

Abstract:

Climate policy implementation is pivotal in
global efforts to mitigate and adapt to climate
change. In this context, this paper explores the
use of Natural Language Processing (NLP) as a
tool for policy advisors to efficiently track and
assess climate policy and strategies, such as
Nationally Determined Contributions (NDCs).
These documents are essential for monitoring
coherence with the Paris Agreement, yet their
analysis traditionally demands significant la-
bor and time. We demonstrate how to leverage
NLP on existing climate policy databases to
transform this process by structuring informa-
tion extracted from these otherwise unstruc-
tured policy documents and opening avenues
for a more in-depth analysis of national and re-
gional policies. Central to our approach is the
creation of a machine-learning (ML) dataset
’CPo-CD’, based on data provided by the Inter-
national Climate Initiative (IKI) and Climate
Watch (CW). The CPo-CD dataset is utilized
to fine-tune Transformer Models on classify-
ing climate targets, actions, policies, and plans,
along with their sector, mitigation-adaptation,
and greenhouse gas (GHG) components. We
publish our model and dataset on a Hugging
Face repository.

Archival Submission: arxival

Arxival Submission: arxival

Submission Number: 1