Lily-belle Sweet
@lilybellesweet
Followers
514
Following
1K
Media
32
Statuses
278
PhD student @ufz_de @tudresden_de - interested in explainable, generalisable and causal ml for agriculture and food security 🌾 @lilybellesweet.bsky.social
Leipzig, Deutschland
Joined December 2018
Can we learn from the recent past to predict future climate change impacts using machine learning? We have created a new benchmark dataset designed to help answer this question, and you can take part in the challenge:
2
21
55
RT @insilicoplants: Machine Learning for Agricultural Research (AgML) workshop.Leipzig, Germany | November 3-5, 2025. Registration Required….
0
2
0
RT @cat_frampton: Finally, I’m in the papers, and not for doing something dodgy!.(Yes probably paywalled, but one….
thetimes.com
Farmers and residents across the country were quick to spot inaccuracies in Defra’s map — and worry that policy decisions will be erroneous
0
60
0
@inathens @Ron_van_Bree @krsnapaudel @AlexRuane @ZscheischlerJak @AgMIPnews If you, like us, think that these kinds of activities are needed, we warmly invite you to get involved. So far, we've created benchmark datasets, organised a workshop, Kaggle competition and there's so much more we'd like to do - join our mailing list:
0
0
0
Written together with @inathens, @Ron_van_Bree , Andres Castellano, Pierre Martre, @krsnapaudel, @AlexRuane, @ZscheischlerJak. Thank you to everyone involved in AgML and @AgMIPnews - the enthusiasm and passion of this community is so special.
1
1
1
Transdisciplinary coordination is essential for advancing agricultural modelling with machine learning. The opportunities are great, but to avoid pitfalls, we need benchmarks, evaluation criteria and best practices. Our perspective: @OneEarth_CP.
cell.com
Crop models play a key role in understanding and improving the climate-change resilience of food systems. If appropriately used, machine learning can help tackle some of the critical challenges of...
1
1
0
Wow, this is totally unexpected. I am completely surprised.
2018: Saliency maps give plausible interpretations of random weights, triggering skepticism and catalyzing the mechinterp cultural movement, which now advocates for SAEs. 2025: SAEs give plausible interpretations of random weights, triggering skepticism and .
0
0
2
RT @Bevacqua_E: In @NatureClimate, we show that a year above 1.5 °C signals that Earth is most probably within the 20-year period that will….
nature.com
Nature Climate Change - What a first year with temperature 1.5 °C above the pre-industrial baseline implies for long-term temperature goals is unclear. Here the authors show that such a...
0
15
0
RT @m_de_Brito: Register for our 1-day text as data workshop here in Leipzig next year: . Apply until 01.02.2025.
docs.google.com
The use of text data from diverse sources such as newspapers, scientific publications, and social media is increasingly prominent in hydrology, natural hazards, and climate change research. This...
0
6
0
RT @EuroGeosciences: Congratulations to Mariana Madruga de Brito (@m_de_Brito) for being awarded an Arne Richter Award for Outstanding Earl….
egu.eu
The European Geosciences Union is honouring 49 people at all stages of their careers who have made substantial contributions to the Earth, planetary, and space sciences.
0
1
0
RT @EnvDataScience: Recent article!. Identifying compound weather drivers of forest biomass loss with generative deep learning. 👉 https://t.….
0
3
0
RT @XaidaProject: End of the 3rd XAIDA GA in #Leipzig .Such intense days to discuss about #AI & #Climateextremes . 🙏@ZscheischlerJak and @D….
0
5
0
RT @Ellis_Unit_Jena: Reminder: 5 postdoc positions in Machine Learning & Earth/Climate Sciences are available with Prof. Gustau Camps-Valls….
0
7
0
Only two more days to enter our hackathon to explore if ML can be used for projections of climate change impacts to agriculture! Train your model on data from 1980-2020, then predict up to 2100:
kaggle.com
Predict global gridded maize and wheat yields from soil and daily weather data under a high-emissions climate change scenario
0
3
19
RT @Compound_Event: Apply now for the 3rd Como Training School on Compound Events!. 🗓️ Dates: Sept 24 - Oct 4, 2024.📝 Deadline for applicat….
0
4
0
RT @yuqirose: We are looking for a postdoc to work on scientific foundation models! If you are excited about multi-modal #LLM #AI4Science,….
0
40
0
RT @isp_uv_es: We're entering the last day of the AI for Learning Weather & Climate workshop. Jonathan Wider is bringing us the talk "Valid….
0
3
0
Also, Ron van Bree has prepared a new Kaggle notebook that trains a baseline CNN model - feel free to fork and edit to get started:
kaggle.com
Explore and run machine learning code with Kaggle Notebooks | Using data from The FutureCrop Challenge
0
0
3
We're halfway through our Kaggle competition runtime, with 148 submissions so far!.Despite using the same training data (1980-2020), submitted data-driven yield projections vary widely (median and interquartile range plotted). Try it for yourself ;)
1
2
8
On the way to #ICML2024? Procrastinate on preparing your slides and enter our Kaggle competition instead đź‘Ľ Help us figure out if we can use ML to create projections of future climate change impacts!.
Can we learn from the recent past to predict future climate change impacts using machine learning? We have created a new benchmark dataset designed to help answer this question, and you can take part in the challenge:
0
2
2