Artificial Intelligence in Climate Science: A Review of Advances in Forecasting, Adaptation, and Future Directions

Abstract

Climate change poses both pressing scientific and societal challenges requiring accurate
prediction of extreme events and rigorous adaptation approaches. While classical methods
such as numerical weather prediction (NWP) and general circulation (GCM) models are still
central to climate depictions, these models are computationally expensive and, therefore,
struggle at real-time applications and inherently, in their accuracy .
New advancements in artificial intelligence (AI) suggests that, at the very least, machine
learning (ML) and deep learning (DL) could provide a revolutionary and complementary
alternative to the physics-based modelling shown previously. In this review, we outline 70
peer-reviewed papers (2019-2025), we selected the studies using the literature review
according PRISMA to cover the AI application in prediction. Which highlight the risk of
using AI for climate forecasting and adaptation. Quantitative evidence indicates that
GraphCast surpasses ECMWF HRES in roughly 90% of forecasting metrics; GenCast
delivers 97% higher accuracy compared with ensemble means; and MetNet-2 extends
precipitation forecasting horizons to nine hours with improved precision. In adaptation, AI
has helped predict agricultural yield with up to 88% accuracy, alert farmers of imminent
drought two months in advance, provide early warnings of dengue fever with a reported AUC
of 0.89, and improve urban flood resilience with accuracy levels as high as 92% . This review
focus on both chances and challenges and highlight the constraints in AI applications like the
dataset and difficulty in weather explanation models.
However, despite these advances, challenges remain due to data bias, limited visibility into
deep learning models, high energy consumption, and unequal access to technology. The
review sets out an evaluation of opportunities and challenges from which AI might be
effectively applied to climate science and climate-related policy, and suggests a three-pillar
framework incorporating sustainability, transparency and equity which can enhance
responsible use within climate adaptation and resilience