Felipe Santibañez-Leal

Felipe Santibañez-Leal

he/him

I&F Decision Science Assoc. Manager @ Accenture | Applied Scientific Researcher

Synthetic Geology

1 minute read

Published:

Synthetic geology

Added three new geological field generators to the optimal sampling framework. The existing channelized and branching models were good for testing the entropy-based sampling algorithms, but they only captured one type of geological pattern. Real mineral deposits have much more variety.

Sampling strategy comparison

New field types

Porphyry copper deposit: Concentric rings with radial veins, mimicking the alteration zones around a copper porphyry intrusion. The center is offset randomly to avoid the algorithm “learning” that the interesting zone is always in the middle.

Vein networks: Thin branching structures generated by random walks with 5% branching probability at each step. These are the hardest for regular grid sampling to capture — the veins are narrow and the information is spatially concentrated along sparse linear features.

Faulted blocks: Angular fault-bounded domains with distinct properties in each block. The faults are linear discontinuities that regular sampling often misses entirely unless a sample happens to land near the boundary.

The sampling question:
Given N measurements, where do you place them to minimize H(Xf | Xf)?
H = posterior entropy. Xf = sampled locations. Xf = unsampled field.

The adaptive entropy algorithm (AdSEMES) should excel on veins — it concentrates samples along high-uncertainty boundaries, exactly where the thin structures are. Regular grids waste most of their budget on empty background.

Also built a comparison page where you can see all field types side by side with different sampling strategies. The visual difference between random sampling and entropy-driven sampling on a vein network is striking.

Information theory concepts

The porphyry generator uses np.sin(r * 0.3) > 0.3 for the concentric rings and np.sin(angle * k) > 0.7 for radial veins, where k is randomly chosen between 3 and 8. Simple trigonometry producing surprisingly realistic-looking alteration halos.

Here’s the adaptive sampling algorithm in action on these fields:

You May Also Enjoy

Week in review: From developer portfolios to executive narratives

2 minute read

Published:

This week’s biggest change wasn’t technical – it was narrative. I restructured six industry portfolio entries to lead with business impact instead of algorithms. The shift reflects a real career evolution: from implementing models to owning their business outcomes.

Week in review: Vectorization, numerical stability, and biological accuracy

3 minute read

Published:

Modernizing eight research codebases at once sounds like a terrible idea, and some weeks it feels like one. But working across optics, biophysics, robotics, and geostatistics in parallel has surfaced a pattern: the same three engineering challenges keep showing up in every domain, wearing different clothes.

The first SOFI implementation in Chile, modernized

2 minute read

Published:

In 2012, I started working on Super-resolution Optical Fluctuation Imaging at SCIAN-Lab, Universidad de Chile, collaborating remotely with researchers at the III Physics Institute of the University of Gottingen in Germany. Working across continents and time zones with the Gottingen team was both challenging and exhilarating – SOFI was a relatively new technique at the time, and there was limited local expertise in Chile to draw on. Every implementation decision, from the cumulant computation pipeline to the deconvolution strategy, required careful coordination through emails and video calls, often debugging numerical issues with a six-hour time difference. The goal was to implement SOFI from the ground up – cumulant computation, synthetic quantum dot simulators, deconvolution – and apply it to biological samples. After months of work, we achieved the first successful SOFI super-resolution imaging in Chile, resolving structures below the diffraction limit using nothing more than temporal statistics from blinking fluorescent emitters. The pride of being the first group in Chile to produce these results was immense – it proved that cutting-edge computational optics could be done here, not just in European labs with larger budgets and established traditions in the field. That work contributed to a publication at SPIE Photonics West, presenting the cumulant-based framework and validation results.