Skip to main content

Climate Q&A by Ekimetrics, AI with a purpose

 


Hugging Face, Ekimetrics  and Gradio an example of connected narrow AI at it's most useful

Ekimetrics describes itself as "a pioneering leader in data science and AI-powered solutions for sustainable business performance." I've just discovered their Climate Q&A on Hugging Face. Put simply it's the best tool I've come across, by far, for interrogating the IPCC reports. 

Hugging Face

In case you haven't come across Hugging Face it's a company that develops tools to help people build machine learning applications. Its most notable product is the Transformers library, which is a collection of pre-trained machine learning models for natural language processing tasks. Hugging Face also operates a platform that allows users to share machine learning models and datasets.

Hugging Face's products and services:

  • Transformers library: The Transformers library is a collection of pre-trained machine learning models for natural language processing tasks. These models can be used to perform a variety of tasks, such as text classification, text generation, and question answering.
  • Hugging Face Hub: The Hugging Face Hub is a platform that allows users to share machine learning models and datasets. The Hub is a valuable resource for researchers and developers who are working on machine learning projects.
  • Hugging Face is a leading provider of tools for building machine learning applications. Its products and services are used by researchers, developers, and businesses around the world.

Climate Q&A 🌍

Ask climate-related questions to the IPCC reports at https://huggingface.co/spaces/Ekimetrics/climate-question-answering

Ekimetrics 

'We help companies get more from their data and implement pre-packaged AI solutions, so they can combine high impact with long-term business purpose.

Information regarding climate change can be complex to interpret. In order to bridge the gap to make science more accessible, Climate Q&A allows you to ask questions about the @IPCC_CH  reports and easily understand the answers.' 

The Query

You can see the query I tested Climate Q&A with in the screenshot below. What was impressive was the detailed referencing provided, as can be seen



The answer given by Climate Q&A was: 

Based on the available documents, there is no specific information on how the 2023 El Niño is expected to affect European temperatures. However, the following information can be inferred:

- Extreme El Niño events are projected to occur about twice as often in the 21st century compared to the 20th century, and they are likely to intensify existing hazards, with drier or wetter responses in several regions across the globe [docs 2, 3].

- With increasing warming, the frequency, intensity, and duration of heat-related events, including heatwaves, are projected to continue to increase through the 21st century, particularly in the Mediterranean region and southern Africa [doc 1].

- Mean and maximum temperatures, frequencies of warm days and nights, and heatwaves have increased since 1950, while the corresponding cold indices have decreased with average warming projected to be larger than the global mean in all of Europe, with the largest winter warming in NEU and EEU and the largest summer warming in MED [doc 4].

- Extreme precipitation is projected to increase in both boreal winter and summer over Europe, with regional differences, and the most intense precipitation events observed today in Europe are projected to almost double in occurrence for each 1degC of further global warming [docs 5, 9].

- Warming in Europe will continue to rise faster than the global mean, widening risk disparities across Europe in the 21st century, with largely negative impacts projected for southern regions and some short-term benefits anticipated in the north [docs 7].

- There is high confidence that most coastal/ocean-related climatic impact-drivers in Europe will increase over the 21st century for all scenarios and time horizons, with relative sea level rise extremely likely to continue around Europe, contributing to increased coastal flooding in low-lying areas and shoreline retreat along most sandy coasts [doc 8].

- Projections for the 21st century show increases in storms across all of Europe for >2degC GWL with a decrease in their frequency in the MED [doc 10].

In summary, while there is no specific information on the impact of the 2023 El Niño on European temperatures, it is likely that Europe will continue to experience warming temperatures, with an increase in extreme weather events such as heatwaves and extreme precipitation. The Mediterranean region is expected to be particularly affected, with negative impacts projected for southern regions. 

This isn't all, plenty of further, useful in formation is available, including a full list of references.


Climate Q&A was built by built using the Gradio app 'the fastest way to demo your machine learning model with a friendly web interface so that anyone can use it, anywhere!'

All round it's very impressive. To add the cherry on top of the cake, Climate Q&A reported that: "one question asked to ClimateQ&A is around 0.482gCO2e - equivalent to 2.2m by car (https://datagir.ademe.fr/apps/impact-co2/) Or around 2 to 4 times more than a typical Google search."

Which begs a question, a big one: how large will the CO2e increase with due to the popularity of AI tools, in the next year? 



Labels:

Comments

Post a Comment

Popular posts from this blog

The Whispers in the Machine: Why Prompt Injection Remains a Persistent Threat to LLMs

 Large Language Models (LLMs) are rapidly transforming how we interact with technology, offering incredible potential for tasks ranging from content creation to complex analysis. However, as these powerful tools become more integrated into our lives, so too do the novel security challenges they present. Among these, prompt injection attacks stand out as a particularly persistent and evolving threat. These attacks, as one recent paper (Safety at Scale: A Comprehensive Survey of Large Model Safety https://arxiv.org/abs/2502.05206) highlights, involve subtly manipulating LLMs to deviate from their intended purpose, and the methods are becoming increasingly sophisticated. At its core, a prompt injection attack involves embedding a malicious instruction within an otherwise normal request, tricking the LLM into producing unintended – and potentially harmful – outputs. Think of it as slipping a secret, contradictory instruction into a seemingly harmless conversation. What makes prompt inj...
Post a Comment
Read more

AI Agents and the Latest Silicon Valley Hype

In what appears to be yet another grandiose proclamation from the tech industry, Google has released a whitepaper extolling the virtues of what they're calling "Generative AI agents". (https://www.aibase.com/news/14498) Whilst the basic premise—distinguishing between AI models and agents—holds water, one must approach these sweeping claims with considerable caution. Let's begin with the fundamentals. Yes, AI models like Large Language Models do indeed process information and generate outputs. That much isn't controversial. However, the leap from these essentially sophisticated pattern-matching systems to autonomous "agents" requires rather more scrutiny than the tech evangelists would have us believe. The whitepaper's architectural approaches—with their rather grandiose names like "ReAct" and "Tree of Thought"—sound remarkably like repackaged versions of long-standing computer science concepts, dressed up in fashionable AI clot...
Post a Comment
Read more

Podcast Soon Notice

I've been invited to make a podcast around the themes and ideas presented in this blog. More details will be announced soon. This is also your opportunity to be involved in the debate. If you have a response to any of the blog posts posted here, or consider an important issue in the debate around AGI is not being discussed, then please get in touch via the comments.  I look forward to hearing from you.
Post a Comment
Read more