Applied Machine Learning Days 2020:
AI & Climate Change Conference Track

Announcements

Video recordings of the workshop are linked under the Schedule below (or here as a playlist).

Climate change is one of the greatest problems society has ever faced, with increasingly severe consequences for humanity. While no silver bullet, machine learning can be an invaluable tool in tackling climate change via a wide array of applications and techniques. These applications require close collaboration with diverse fields and practitioners, and many call for algorithmic innovations in machine learning. We are organizing a conference track at the Applied Machine Learning Days (AMLD) at EPFL as a forum for work at the intersection of machine learning and climate change.

Invited Speakers

Felix Creutzig (MCC Berlin, TU Berlin) Marta Gonzalez (UC Berkeley, Lawrence Berkeley National Laboratory) Slava Jankin Mikhaylov (Hertie School of Governance) Kristina Orehounig (Empa) Enik? Székely (Swiss Data Science Center, EPFL/ETH Zürich) Olivier Corradi (Tomorrow) Buffy Price (Element AI) Liam F. Beiser-McGrath (ETH Zürich)

About the Conference

AMLD is a five-day conference of talks, tutorials & workshops on applied machine learning. AMLD is organized by EPFL in Lausanne, Switzerland, from January 25 to 29, 2020.

About the Track

Date: January 27 (afternoon) and 28 (morning), 2020 Location: SwissTech Convention Center, Lausanne, Switzerland Conference website: https://appliedmldays.org/tracks/ai-climate-change Submission site (through AMLD): <https://www.appliedmldays.org/call-presentations-posters> Submission deadline: Friday November 1st, 2019, 23:59 UTC Contact: lynn.kaack@gess.ethz.ch and milojevic@mcc-berlin.net

Schedule

Monday afternoon (1:30 PM – 7:00 PM)

Session: Climate Science and Adaptation
1:30 PM - Welcoming remarks
1:55 PM - Enik? Székely: A direct approach to detection and attribution of climate change (Invited talk)
2:20 PM - Soon Hoe Lim: Predicting Rare Events in Climate Science
2:30 PM - Matthias Meyer: Monitoring Climate Change at the Edge of the Cloud
2:40 PM - Nicholas Jones: Monitoring the built environment for urban resilience planning
2:50 PM - Marius Zumwald: Mapping urban temperature using crowd-sensing data and machine learning
3:00 PM - Break

Session: Climate Policy
3:30 PM - Marta González: Data Science for Resilient and Healthier Urban Networks (Invited talk)
3:55 PM - Slava Jankin: Tracking the Connections Between Public Health and Climate Change (Invited talk)
4:20 PM - Max Callaghan: Machine learning for systematically mapping the climate change literature
4:30 PM - Liam F. Beiser-McGrath: Understanding the Politics of Climate Change with AI and Machine Learning (Invited talk)
4:55 PM - Closing remarks day 1
5:00 PM - Joint Poster Session with all Tracks

Tuesday morning (9:00 AM – 12:30 PM)

Session: Climate Change Mitigation
9:00 AM - Olivier Corradi: Estimation of marginal carbon emissions in electricity networks using electricityMap (Invited talk)
9:25 AM - Mohamed Kafsi: Quantifying the Carbon Footprint of Mobility from Telcom Data
9:35 AM - David Dao: Scaling Natural Climate Solutions with Machine Learning
9:45 AM - Kristina Orehounig (with Emmanouil Thrampoulidis): The role of buildings to mitigate climate change (Invited talk)
10:10 AM - Chris Heinrich: Roof Age Determination for the Automated Site-Selection of Rooftop Solar
10:20 AM - Daniel De Barros Soares: Predicting the Solar Potential of Rooftops using Image Segmentation and Structured Data
10:30 AM - Break

Session: Effective Climate Action with ML
11:00 AM - Buffy Price: Co-developing applications: Lessons from partnerships (Invited talk)
11:25 AM - Felix Creutzig: Leveraging ML for sustainable urbanization (Invited talk)
11:50 AM - Panel discussion with Felix Creutzig, Olivier Corradi, Kristina Orehounig, Liam F. Beiser-McGrath, Buffy Price, Enik? Székely

Posters:

Monday evening (5:00 PM – 7:00 PM)

(1) Victor Kristof et al.: A User Study of Perceived Carbon Footprint
(2) Martin Brutsche et al.: How Reinforcement Learning can reduce CO2 emissions in shipping: Route Optimized Power Management Control for Hybrid 2-Stroke Marine Diesel Engines
(3) Raphaela Kotsch et al.: Machine learning in revealing trading patterns in the international carbon market
(4) Anne Jelmar Sietsma et al.: Exploring the use of NLP for MRV and Climate Change Adaptation
(5) Benjamin Franchetti et al.: Deep Learning in Vertical Farming under Artificial Lighting
(6) Anusua Trivedi et al.: Smoke Detection using AI to prevent Forest Fire
(7) Daniel de Barros Soares et a.: Predicting the Solar Potential of Rooftops using Image Segmentation and Structured Data
(8) Max Callaghan et al.: Machine learning for systematically mapping the climate change literature
(9) Emmanouil Thrampoulidis et al.: Using machine learning to generalize the building retrofit process for the whole Swiss residential building stock.
(10) Matthias Meyer et al.: Monitoring Climate Change at the Edge of the Cloud
(11) Chris Heinrich et al.: Roof Age Determination for the Automated Site-Selection of Rooftop Solar
(12) Mohamed Kafsi et al.: Quantifying the Carbon Footprint of Mobility from Telcom Data

Call for Submissions through the AMLD Conference

The call for submissions of presentations and posters through the AMLD conference is now open. You can submit directly to our track by choosing it from the dropdown menu on the AMLD submission website. We invite submissions of work using machine learning to address problems in climate mitigation, adaptation, or modeling, including but not limited to the following topics:

Power generation and grids Transportation Urban studies Buildings Industry Carbon capture and sequestration Agriculture, forestry and other land use Climate science Extreme weather events Disaster management and relief Adaptation Ecosystems and natural resources Data presentation and management Climate finance

Organizers

Lynn Kaack (ETH Zürich)
Nikola Milojevic-Dupont (MCC Berlin, TU Berlin)

相關(guān)知識(shí)

Tackling Climate Change with Machine Learning
學(xué)校魚菜共生：動(dòng)手學(xué)習(xí)健康飲食和健康地球。
Detecting health misinformation in online health communities: Incorporating behavioral features into machine learning based approaches
RisePearl
[2025] 150 Courses & Webinars on AI in Healthcare — Class Central
Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision
Dimensions of wellness: Change your habits, change your life
Research into language learning and motivation has changed direction over the pa
Simple, Practical Wellness Tips For A Healthy Lifestyle
國(guó)內(nèi)外氣候變化健康適應(yīng)策略現(xiàn)狀分析

網(wǎng)址: Tackling Climate Change with Machine Learning http://www.u1s5d6.cn/newsview1646714.html