ChatClimate: Grounding conversational AI in climate science

Abstract

Large Language Models have made remarkable progress in question-answering tasks, but challenges like hallucination and outdated information persist. These issues are especially critical in domains like climate change, where timely access to reliable information is vital. One solution is granting these models access to external, scientifically accurate sources to enhance their knowledge and reliability. Here, we enhance GPT-4 by providing access to the Sixth Assessment Report of the Intergovernmental Panel on Climate Change (IPCC AR6), the most comprehensive, up-to-date, and reliable source in this domain (refer to the ’Data Availability’ section). We present our conversational AI prototype, available at www.chatclimate.ai, and demonstrate its ability to answer challenging questions in three different setups: (1) GPT-4, (2) ChatClimate, which relies exclusively on IPCC AR6 reports, and (3) Hybrid ChatClimate, which utilizes IPCC AR6 reports with in-house GPT-4 knowledge. The evaluation of answers by experts show that the hybrid ChatClimate AI assistant provide more accurate responses, highlighting the effectiveness of our solution.

Geo-WC: Custom Web Components for Earth Science Organizations and Agencies

“…Agencies such as USGS, NOAA among others play a crucial role by having station-ready data for potential impacts and development of preventative measures, specifically in the changing nature of flooding exacerbated by climate change (Demir et al, 2022;Mallakpour & Villarini, 2015). Moreover, with the utilization of large language models (Pursnani et al, 2023) for the development and integration of climate data into conversational interfaces (Vaghefi et al, 2023;Sermet & Demir, 2021), web components can be leveraged to create more integrated and scalable web applications. Considering the latter, the framework can be used to acquire and visualize data from multiple sources with data stations easily incorporated into the framework.…”

Potential Role and Challenges of ChatGPT and Similar Generative Artificial Intelligence in Architectural Engineering

“…In response to climate change and evolving environmental challenges, architects and engineers are increasingly focused on creating adaptive and resilient buildings. Generative AI can assist in designing structures that can adapt to changing environmental conditions, such as rising sea levels or extreme weather events (Vaghefi et al, 2023;Muccione et al, 2023). By analyzing historical data and predictive models, ChatGPT can propose designs that are resilient to future challenges, ensuring the longevity and functionality of architectural projects.…”

A blockchain AI solution to climate change

“…LLMs' effectiveness is contingent upon the availability of vast, high-quality datasets. Curating specialty-specific training data will further enhance the ability of LLMs to assist with addressing climate change (16). The challenge lies in aggregating and preprocessing climate data to meet this requirement, ensuring that LLMs can generate reliable and actionable insights.…”