Sign in

Hammed Akande

@drhammed.bsky.social
30 followers 22 following 9 posts

Researcher| Mastercard Scholar'18 |Data Scientist| Quantitative Ecology| #AI, #R, #Python, #ML, #AWS, #GIS. Views = mine. Likes/RTs ≠ endorsements

PostsRepliesMedia
Hammed Akande @drhammed.bsky.social · 05/03/2026
Many thanks to Schmidt Sciences and the organizers of the Shaping the Future of AI for Conservation workshop at Oxford, UK, for bringing us together and supporting this work. Great initiative 👏 #AI #LLM #Ecology
010
Hammed Akande @drhammed.bsky.social · 05/03/2026
What would a 'Foundation Model' for ecology look like? In our new preprint, we explore this emerging idea & outline a roadmap for foundation models in Ecology (ecoFMs)👇 Really great working with @rachelparkinson.bsky.social @hcerbone.bsky.social @polarprem.bsky.social et al doi.org/10.32942/X2V...
doi.org
Towards ecologically meaningful foundation models
133
Hammed Akande @drhammed.bsky.social · 09/12/2025
6/6. EcoCast aims to support climate resilience and biodiversity protection across Africa by enabling timely, data-driven ecological forecasting. 👉The article can be downloaded: arxiv.org/abs/2512.02260
arxiv.org
EcoCast: A Spatio-Temporal Model for Continual Biodiversity and Climate Risk Forecasting
Increasing climate change and habitat loss are driving unprecedented shifts in species distributions. Conservation professionals urgently need timely, high-resolution predictions of biodiversity risks...
010
Hammed Akande @drhammed.bsky.social · 09/12/2025
5/n. Our pilot study in Africa shows promising improvements in forecasting distributions of selected bird species compared to a Random Forest baseline, highlighting EcoCast’s potential to inform targeted conservation policies.
100
Hammed Akande @drhammed.bsky.social · 09/12/2025
4/n. We describe a three-phase approach: (1) constructing a large-scale, pre-trained spatio-temporal architecture, (2) continually fine-tuning with new data streams, and (3) developing interactive dashboards for conservation practitioners.
100
Hammed Akande @drhammed.bsky.social · 09/12/2025
3/n.Utilizing multisource satellite imagery, climate data, and citizen science occurrence records, EcoCast predicts near-term shifts in species distributions.
100
Hammed Akande @drhammed.bsky.social · 09/12/2025
2/n. In this work, co-authored with Abdulrauf A. Gidado. We proposed EcoCast, a novel spatio-temporal model designed for continual biodiversity and climate risk forecasting.
100
Hammed Akande @drhammed.bsky.social · 09/12/2025
I’m excited to share that our paper, “EcoCast: A Spatio-Temporal Model for Continual Biodiversity and Climate Risk Forecasting,” was presented at the Tackling Climate Change with Machine Learning Workshop at #NeurIPS2025 (One of the premier ML conferences). www.climatechange.ai/papers/neuri...
climatechange.ai
EcoCast: A Spatio-Temporal Model for Continual Biodiversity and Climate Risk Forecasting
Climate Change AI - NeurIPS 2025 Accepted Work
140
Reposted by Hammed Akande
arXiv q-bio.QM Quantitative Methods @qbioqm-bot.bsky.social · 03/12/2025
Hammed A. Akande, Abdulrauf A. Gidado: EcoCast: A Spatio-Temporal Model for Continual Biodiversity and Climate Risk Forecasting arxiv.org/abs/2512.02260 arxiv.org/pdf/2512.02260 arxiv.org/html/2512.02260
012
Reposted by Hammed Akande
Climate Change AI @climatechangeai.bsky.social · 17/12/2024
We're excited to announce the next edition of our workshop "Tackling Climate Change with Machine Learning" at #ICLR2025 in Singapore! ▶️ Mentorship program deadline: Dec 27, 2024 ▶️ Paper submission deadline: Jan 31, 2025 Learn more & submit: climatechange.ai/events/iclr2...
1184
Hammed Akande @drhammed.bsky.social · 26/01/2024
Congratulations 🎉!
000
Reposted by Hammed Akande
Robert Fletcher @fletcherecology.bsky.social · 19/01/2024
I am delighted to announce that I have accepted the Miriam Rothschild Professorship of Conservation Biology in the Zoology Dept at the Univ of Cambridge! I am thrilled for this next chapter & look forward to working with the Cambridge Conservation Initiative & the Conservation Research Institute.
2194