Malte Toetzke

Malte Toetzke is a PhD candidate at SusTec focusing on the global transition towards net-zero emissions. In this context, his research aims at informing public policy through development and applications of novel techniques from data science and machine learning. Main research areas are climate finance, carbon markets, and innovation of clean-tech. His research has been published and presented in leading academic journals (Nature Sustainability, Nature Climate Change) and machine learning conferences (NeurIPS, ICLR).

Malte holds a Master of Science in DownloadManagement, Technology and Economicsvertical_align_bottom with specialization in data science from ETH Zurich and a Bachelor of Science in Industrial Engineering with specialization in electrical engineering from DownloadTechnical University of Dresdenvertical_align_bottom. During his studies, he was awarded scholarships from the DownloadGerman National Academic Foundationvertical_align_bottom, the DownloadUlderup Foundationvertical_align_bottom, and the DownloadGerman Academic Exchange Servicevertical_align_bottom.

In the course of his PhD, Malte spent a research visit at the Center for DownloadEnvironment, Energy and Natural Resource Governancevertical_align_bottom of the DownloadUniversity of Cambridgevertical_align_bottom, hosted by DownloadProfessor Laura Diaz Anadonvertical_align_bottom. Prior to joining SusTec, Malte spent one year as a PhD researcher at the former chair of Management Information Systems (MIS) at ETH. When the chair moved to DownloadLMU in Munichvertical_align_bottom, he rejoined SusTec where he had previously been engaged as a research assistant. During his Master studies, Malte co-founded a tech company based on natural language processing and computer vision technology. He has also worked as a trainee at Science, Technology and Innovation Department (STI) the DownloadOECDvertical_align_bottom (2016/17) and interned in a global digitalization project at DownloadSiemensvertical_align_bottom (2015/16). Next to his doctoral studies, he volunteers as a board member of the World Economic Forum's Zurich Hub of the DownloadGlobal Shapers Communityvertical_align_bottom.

In his spare time, Malte enjoys playing the piano, spending time in the mountains, and trying out (Mediterranean) languages.

Google Scholar Profile: 

DownloadMalte Toetzke - Google Scholarvertical_align_bottom

Peer-reviewed Journal Articles:

• Toetzke, M., Probst, B. & Feuerriegel, S. Leveraging Large Language Models to Monitor Climate Technology Innovation. Environ. Res. Lett. in press (2023). doi:Downloadhttps://doi.org/10.1088/1748-9326/acf233vertical_align_bottom
• Toetzke, M., Stünzi, A. & Egli, F. Consistent and replicable estimation of bilateral climate finance. Nature Climate Change (2022). doi:Downloadhttps://doi.org/10.1038/s41558-​022-01482-7vertical_align_bottom
  
• Toetzke, M., Banholzer, N. & Feuerriegel, S. Monitoring global development aid with machine learning. Nat Sustain (2022). doi:Downloadhttps://doi.org/10.1038/s41893-022-00874-zvertical_align_bottom

Conference Contributions (peer-reviewed):

• Toetzke M., Re F., Probst B., Feuerriegel S., Hoffmann V., Anadon L. D. Mapping global innovation networks around clean energy technologies. Tackling Climate Change with Machine Learning: workshop at ICLR 2023 (proposals track). 2023.
  
• Toetzke M., Probst B., Tatar Y., Feuerriegel S., Hoffmann V. Analyzing the global energy discourse with machine learning. Tackling Climate Change with Machine Learning: workshop at NeurIPS 2022 (proposals track). 2022.
• Ganter, M., Toetzke, M., Feuerriegel, S.: Mining points-​of-interest data to predict urban inequality: Evidence from Germany and France. ICWSM, 2022.

Invited Talks:

• Checking contentious counting: how machine learning can help to verify international climate finance | AI4ER Seminar University of Cambridge (Feb 2023)
• Using Natural Language Processing to Inform Public Policy in the Energy Transition | CEENRG Seminar University of Cambridge (Jan 2023)
• Supervised and unsupervised machine learning methods to inform development policies | ETH NADEL advanced seminar for leaders in public organizations (Jun 2022)
• Analyzing the newspaper discourse around clean energy technologies | International research workshop on AI in climate politics hosted at ETH Zurich (May 2022)
• Machine learning in global development | Presentation to the German AI delegation organized by the Swiss Foreign Office (May 2022)
• Monitoring global development aid with machine learning | AI-keynotes seminar series by LMU Munich and University of Cologne (Feb 2022)
   

Working Papers:

• Probst, B., Toetzke, M., Hoffmann, V., Kontoleon, A., Anadon., L. D. (2022). Systematic review of the actual emission reductions and costs of carbon offsets across all major offset sectors.

Blogs:

• ETH Zukunftsblog (2023). Voluntary carbon offsets often fail to deliver what they promise. Link.
• ClimateChangeAI Blog (2022). Using Machine Learning to Track International Climate Finance. DownloadLinkvertical_align_bottom.
• World Economic Forum Agenda Blog (2022). 3 strategies to leverage AI in the development sector. DownloadLinkvertical_align_bottom.
• ETH Zukunftsblog (2022). COP27: Climate finance needs more transparency (main authoring by Florian Egli). Link.

Current Projects:

• With AI towards Net Zero: Using public media to forecast innovation and deployment of clean energy technologies. With Benedict Probst, Stefan Feuerriegel, and Volker Hoffmann.
• The association of firm networks with industrial development of clean energy technologies. With Benedict Probst, Stefan Feuerriegel, and Volker Hoffmann.