Skip to content
Daniel Wamriew

Projects

Building intelligent technology

Research projects, technology products and research software, from scientific method development to platforms people use.

Research

Scientific projects in generative AI, microseismic monitoring and experimental geomechanics.

Illustrative
Research

Conditional Diffusion Models for Microseismic Localization

Generative AI for a classic geophysical inverse problem: locating microseismic events directly from noisy waveform gathers, without arrival-time picking, and with uncertainty estimates from repeated sampling.

Problem
Locating microseismic events from noisy recordings is an ill-posed inverse problem. Travel-time methods depend on accurate arrival picks and velocity models, and deterministic deep learning returns a single answer with no measure of reliability.
Approach
A conditional diffusion model that generates the event location as two Gaussian heatmaps (X–Z and Y–Z), conditioned on features extracted from the recorded three-component waveforms.
My role
Formulated event localization as conditional heatmap generation, combining waveform preprocessing, learned features and quantitative baseline evaluation, and investigated noise sensitivity and repeated stochastic sampling to characterize uncertainty.
Results
Mean absolute error below 22 m and R² above 0.81 on each axis across 1,774 semi-synthetic test samples with recorded field noise. Lower MAE than a CNN baseline on every axis, while the CNN had higher R² and lower error standard deviation. A real field event was located within 11.5 m of the catalog solution.
  • Conditional diffusion models
  • PyTorch
  • Convolutional neural networks
  • Signal processing
View project
Illustrative
Research

HydraFrac Experimental Research

A multidisciplinary KAUST project investigating hydraulic fracturing through controlled laboratory experiments, monitored with acoustic emission sensors and fiber-optic distributed acoustic sensing. I lead the project.

Problem
Understanding how hydraulic fractures initiate and propagate in rock, and how acoustic signals can be used to monitor, image, and characterize fracture development.
Approach
Integrating controlled laboratory hydraulic fracturing experiments with acoustic emission monitoring, fiber-optic distributed acoustic sensing (DAS), and advanced computational methods for fracture characterization.
My role
I lead a multidisciplinary team of researchers and laboratory technicians, overseeing experimental design, instrumentation, data acquisition, computational analysis, and scientific interpretation.
Results
Published work on DAS monitoring of laboratory hydraulic fractures, cryogenic preconditioning to lower breakdown pressure, and focal mechanisms of the induced events, plus two analysis tools: HydraFrac Studio and the open-source ae-picker package.
  • Experimental geomechanics
  • Acoustic emission monitoring
  • Distributed acoustic sensing
  • Signal processing
View project

Products

Technology products I founded and build, from educational technology to project execution.

Revision Base logo
Product

Revision Base

An educational technology platform for Kenya's CBE and KCSE curricula, bringing curriculum-aligned resources, holiday learning, parent and teacher tools and tutoring into one web and Android ecosystem.

Problem
Learners, parents and teachers in Kenya rely on fragmented, often expensive sources for revision materials, homework oversight, teaching resources and tutoring, a gap widened by the transition to Competency-Based Education.
Approach
One platform that combines curriculum-aligned resources, structured holiday homework, a parent learning dashboard, teacher planning tools and tutoring, with free content alongside subscriptions and individual purchases.
My role
Founded Revision Base and lead its product and technical direction, from the web platform and Android app to subscriptions, digital payments and an AI-assisted marketing system.
Results
Live at revision-base.com. The Revision Base Android app was released in August 2026.
  • React
  • Vite
  • Tailwind CSS
  • React Native / Expo
View project
Illustrative
Product

AI Powered Marketing Intelligence

A multi-agent marketing application for Revision Base that researches the market, plans campaigns and drafts copy, graphics and video, with a human approval gate before anything is published.

Problem
A small education business needs consistent, well-targeted marketing across Facebook and WhatsApp without a marketing team, but unreviewed AI-generated content is a brand and accuracy risk.
Approach
Six specialized AI agents for research, strategy, copy, design, video and publishing, working from verified product information, with human approval required before any content is published.
My role
Direct the AI-assisted development and testing of the application; configure its integrations and evaluate the campaign plans and draft content it produces.
Results
Tests established connectivity with the Revision Base product API and Facebook publishing. Scheduled, unattended publishing is still under development.
  • Large language models
  • Multi-agent systems
  • Automated video production
  • Social media publishing
View project
PangaOS logo
Product

PangaOS

Deadline-driven project execution: track workdays left, burn down your plan, and clear the gates that stand between you and shipping.

Problem
General project management tools are built around teams and feature lists. A person shipping something hard by a fixed date needs to see how much working time is left and whether the plan is still on track.
Approach
A planning tool built around a hard deadline: workdays left, a burndown of the dated plan, decision gates, and a daily checklist derived from the plan.
My role
Founded PangaOS and develop it, from the product concept and planning model to the web application itself.
  • React
  • Vite
  • Tailwind CSS
View project

Research software

Scientific software developed from my research, including an open-source package on PyPI.

Illustrative
Research software

HydraFrac Studio

Software for picking, locating and analyzing acoustic emissions in laboratory rock experiments, combining a deep learning picker with classical methods. Used internally by researchers in the HydraFrac group.

Problem
Laboratory hydraulic fracturing experiments produce hours of multichannel acoustic emission recordings, while each event lasts a fraction of a millisecond. Events must be detected, their arrivals picked and their sources located before the data says anything about how the rock cracked.
Approach
An interactive workflow: load the recordings, let a picker find the arrivals, correct picks directly on the trace, invert the picks for a source position, and set the result against the injection pump record.
My role
Built the application, including a PyTorch convolutional neural network for acoustic emission detection and picking, and the review, localization and pump-comparison workflow.
Results
In internal use by researchers in the HydraFrac group. On real triggered records, the deep learning picker and the independent AIC picker agree to within 2 µs on 69% of the picks both are confident about, and to within 10 µs on 92%.
  • Python
  • PyTorch
  • NumPy
  • SciPy
View project
Illustrative
Research software

ae-picker

An open-source Python package for automatic first-arrival picking in acoustic emission, microseismic and seismic waveforms, developed from the HydraFrac project and published on PyPI.

Problem
Picking the first arrival on every channel of every event is the bottleneck between raw acoustic emission recordings and located sources, and doing it by hand does not scale.
Approach
Interpretable, physically parameterized pickers (AIC and a refined STA/LTA with envelope-based onset refinement), frequency-adaptive presets, batch processing, quality control and plotting, packaged as a library and a command-line tool.
My role
Designed, implemented and released the package, from the picking algorithms to the readers, presets, QC, plotting and command-line interface.
Results
Published on PyPI under the MIT license (version 0.3.0, November 2026) with a citable Zenodo DOI. Handles laboratory acoustic emission, sonic (PS) logs and refraction surveys.
  • Python
  • NumPy
  • SciPy
  • pandas
View project