Viridien HPC, AI and Cloud’s Post

Want to know more about the latest advances in Climate modelling? Join me for a conversation with Nicholas G. Heavens to understand more about how HPC is supporting the next generation of high resolution climate models.

Understanding world disaster risks dynamics on a global scale represents a invaluable asset for climate change impact mitogation. A unique approach based on machine learning is presented in this paper to enhance scenario modeling on a short-term basis.

Thanks to this amazing group of badgers for a great semester of CBE 562: Stats for ChemEs We concluded Today with presentations on their final projects: - Analysis of national park visitor data - Tutorial of Aspen’s AI Model Builder - Reduction of objectives in multi-objective optimization using PCA - Analysis of global climate change data - Prediction of catalyst properties #statistics #chemicalengineering #wisconsin

https://lnkd.in/gAxpkGFP Because scientific modeling and data based, assumption driven models have HUGE limitations PLUS inherent biases... HENCE, the expression or saying as a solid Heuristic: The map 🗺️🗾 is not 🚫 the territory! BECAUSE of Complexity, the Unknown Unknowns Data Set 📐 or Quadrant space 🌌 is absolutely massive, almost combinatorially explosive 🧨. HERE'S WAZZUP with THIS in LESS than 30 minutes:

The latest issue of Cell Press One Earth spotlights the theme 'Living with Fire,' featuring an invited commentary by our executives Marta Yebra and Robert Mahony alongside insights from our Centre Ambassador, the Honourable Bob Debus AM “Anthropogenic climate change is driving extreme fire seasons, challenging the effectiveness of fire management practices developed over the last 50 years. New and diverse strategies are needed to achieve safe coexistence in an age of megafires. A redefinition of the wildfire management paradigm is central to the shift, placing greater emphasis on the adoption of high-tech solutions for early fire detection and rapid ignition suppression” Read the full article 👇👇 https://lnkd.in/g5pMTTBg

An important topic of creating a chatbot specifically for climate sciences led to interesting questions around the audience and use of this type of GPT but exciting for research and industry-wide problems. #ClimateInformatics 2024

Discover the power of open water data as enabled by Stream: Unlocking Water Data. Dive into Tasha Renwick’s – Data Engineer at Aiimi – insightful exploration of the impact of climate change on reservoir levels. Using machine learning and forecasted weather, she tries to predict future reservoir behaviour over the next two decades >>> https://lnkd.in/e7EJm_MZ This analysis is one example that showcases the importance of standardised water data formats to help the water sector address some of the challenges it faces to the benefit of customers, society, and the environment. Stay tuned for part two! #watersector #opendata #machinelearning #climatechange #water

The data set for the art installation "Dialectics of Climate Futures" was presented at our last #4CultureCommunityPlenary, now it has been persistently cataloged in the Knowledge Portal of the Arts of the Universität der Künste Berlin University Library and is available at #RADAR4Culture via DOI: https://lnkd.in/eBc78qDf #data #visualization #RADAR4culture #NFDIrocks

📢 Exciting News! 📢 I’m thrilled to announce that the new version of one of my work-in-progress articles has been published on arXiv! 🎉 The paper, a joint work with Simone Vantini and Massimo Tavoni is titled “Global Sensitivity and Domain-Selective Testing for Functional-Valued Responses: An Application to Climate Economy Models”. It delves into the complexities of climate change models and the associated uncertainties. It underscores the importance of these models in designing robust policy actions and highlights the need for model auditing to better understand their results. Our work extends Global Sensitivity Analysis (GSA) methodologies to tackle the case of stochastic functional outputs with finite change inputs. This extension broadens the applicability of these techniques to time-varying variables such as future pathways of greenhouse gases. We introduce a novel, domain-selective inferential technique for sensitivity indices and demonstrate its robustness and efficacy in detecting sensitivity patterns through a simulation study. The application of our method to real-world data can provide practitioners and policymakers with additional information about the time dynamics of sensitivity patterns and information about robustness. I invite you all to read the abstract and the full paper on arXiv at the following link: https://lnkd.in/dG2Hxasr Your feedback and thoughts are most welcome! #climatechange #modelauditing #sensitivityanalysis #arxiv #preprint

What is the potential of artificial intelligence in advancing climate solutions? 🤔💭🤖🌱 The Bonn AI & Climate Expert Meeting brings you this interesting discussion, focusing on developing & least developed countries! Register to join virtually: https://lnkd.in/eV2hMRRy