Joshua Dimasaka

using cluster-level constraints, multitask optimization, and multilabel conditionality, under a weak supervision setup.

#HelmholtzAI #AI4ER #DeepClustering #EO #UrbanMorphology #DisasterRisk #SpatialAudit #SpatialDisaggregation #Constraints

31.07.2025 10:24 — 👍 0    🔁 0    💬 0    📌 0

Our proposed novel DeepC4, a deep constrained clustering model, advances the existing classical spatial disaggregation techniques using deep learning and EO data to understand the distribution of various urban morphology characteristics at large scales, ...

31.07.2025 10:24 — 👍 0    🔁 0    💬 1    📌 0

Our non-peer-reviewed preprint "Deep Conditional Census-Constrained Clustering (DeepC4) for Large-scale Multitask Disaggregation of Urban Morphology" is now available on arXiv! This work is the highlight contribution of my first-year PhD-ing, which deals with "spatial auditing".

31.07.2025 10:24 — 👍 0    🔁 0    💬 1    📌 0

Online Scholar Q&A (Zoom) | Alumni Joshua Dimasaka '19 and Ling Ritter '21

✅ 𝗥𝗲𝗴𝗶𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻: apply.knight-hennessy.stanford.edu/register/?id...

05.06.2025 10:44 — 👍 0    🔁 0    💬 0    📌 0

Mayroon po ba kayong mga tanong sa ating mga iskolar? Ling Ritter and I will be doing our 𝟯𝗿𝗱 𝗢𝗻𝗹𝗶𝗻𝗲 𝗦𝗰𝗵𝗼𝗹𝗮𝗿 𝗤&𝗔 on 𝗝𝘂𝗻𝗲 𝟮𝟵𝘁𝗵, 𝗦𝘂𝗻𝗱𝗮𝘆, 𝟭𝟮-𝟭𝗽𝗺 (𝗣𝗵𝗶𝗹𝗶𝗽𝗽𝗶𝗻𝗲 𝗦𝘁𝗮𝗻𝗱𝗮𝗿𝗱 𝗧𝗶𝗺𝗲), in a mix of English, Filipino/Tagalog 🇵🇭.

Pakibahagi po! Maraming salamat po.

#PinoyScientists #GraduateScholarship

05.06.2025 10:44 — 👍 2    🔁 0    💬 1    📌 0

This is tomorrow! We're excited. Don't forget to register if you'd like to meet our friendly AI4ER community and visit Cambridge for a day with our energizing sunshine ☀️ 🚣 and an afternoon filled with AI + environmental risk research! 🌏 🛰️ 🧠 Kitakits!

19.05.2025 06:11 — 👍 0    🔁 0    💬 0    📌 0

some of our newest and exciting updates in how we align the use of AI with the practice of catastrophe modeling and disaster risk science!

#AI #DRR #EnvironmentalRisk #Cambridge #AI4ER #CDT #regional #disaster #risk #catastrophe #EO #ML #CAT #graphML #Bayesian

10.05.2025 08:25 — 👍 0    🔁 0    💬 0    📌 0

and physical vulnerability, regionally, given the vast amount of Earth Observation (EO) data and advanced machine learning (ML) techniques like spatiotemporal graph deep learning and Bayesian ML? That's what I will share high-level in our AI4ER CDT Showcase, including ...

10.05.2025 08:25 — 👍 0    🔁 0    💬 1    📌 0

When I began my journey in disaster risk science, it was fascinating to understand the mathematics behind probabilistic (seismic, tsunami, flood, blast, wildfire, etc.) hazard analysis. What if, in our risk equation, there's also probabilistic distribution of building exposure ...

10.05.2025 08:25 — 👍 0    🔁 0    💬 1    📌 0

AI for the study of Environmental Risks (AI4ER) CDT Showcase 2025 Join us at the AI4ER CDT Showcase 2025 to explore how artificial intelligence can help us understand and address environmental risks!

Our annual AI4ER CDT Showcase is back this 2025! If you'll be free on May 20th, come and join us at the University of Cambridge (UK) and get to know some of the amazing research we do in the intersection of AI and environmental risks.

RSVP: www.eventbrite.co.uk/e/ai-for-the...

10.05.2025 08:25 — 👍 0    🔁 0    💬 1    📌 1

Filipinos, Pinoy, or Philippines 🇵🇭 at #AGU24? We'll have a group dinner (hapunan) tomorrow. 📩 DM me for more details.

11.12.2024 13:14 — 👍 0    🔁 0    💬 0    📌 0

And, that's it! 4 hrs! #AGU24

Very thankful to our visitors who gave encouraging words on our proposed algorithm, have already expressed their intention in reading our preprint, & shared the same perspectives how AI should reasonably be used in DRR practice. Love y'all! ❤️

11.12.2024 05:16 — 👍 1    🔁 0    💬 1    📌 0

Understanding rural exposure of agricultural areas towards building food resiliency 🥦🍚 #AGU24

Addressing rural vulnerability by electrifying our capacity and accessibility. 😄⚡ #AGU24

Just also sharing my #AGU24 Photo Contest 📸 entries here, and also showcasing how beautiful my 🇵🇭 is. These were taken while I was having a writing break and walking around our neighborhood - farms! #PhDChat See you next week, everyone! Captions in the ALT textboxes.

05.12.2024 06:15 — 👍 3    🔁 1    💬 0    📌 0

Deep Conditional Census-Constrained Clustering (DeepC4) for Large-scale Multi-task Spatial Disaggregation of Urban Morphology This Zenodo record contains the datasets of our research (Spatial Disaggregation of Rwandan Building Exposure and Vulnerability via Weakly Supervised Conditional Census-Constrained Clustering (C4) usi...

Applying AI 💻 & EO 🛰️ to exposure & vulnerability modelling, as my mentors also say, is indeed a "messy" one, yet it's widely recognized as a serious "data gap" in #DRR 🌍. Here's an online copy of our "very large" poster! 😄

✅ doi.org/10.5281/zeno...

30.11.2024 00:03 — 👍 1    🔁 0    💬 1    📌 0

One week before #AGU24 @agu.org ✈️ in Washington, D.C., let me share a big update of our PhD work at AI4ER-CDT, presenting 🥁 "DeepC4", from being specific a few months ago to a possibly flexible & general approach in modelling our urban fabric. Kitakits! See you!

30.11.2024 00:03 — 👍 5    🔁 0    💬 1    📌 0

@acescicomm.bsky.social and I met here and realized we both were looking for more #SciSky #PinoyScientists 🇵🇭🧪! So, we joined the starter pack bandwagon ... 😅

We also want to highlight folx and what they do ✨ Please fill out the form if you're interested in joining: forms.gle/h4WUpE1T9jHt...

14.11.2024 21:51 — 👍 31    🔁 19    💬 1    📌 1