Architecture, engineering, and computation

Jashua Luna

A multidisciplinary researcher and designer translating complex technical ideas into clear, buildable, and computationally rigorous work.

My work sits between architecture, civil engineering, and AI-oriented research, with projects ranging from Arctic infrastructure studies and foundation design to synthetic data pipelines, generative models, and high-performance scientific software.

01 Architecture + engineering background
02 Independent computational research
03 Technical writing and implementation

Selected work

Research and systems work with visible evidence.

The portfolio is organized around projects that connect technical writing, implementation, and visual artifacts.

Doppler-Domain Micro-Motion Tomography

A reproduction, critical analysis, and benchmark of single-SLC Doppler-domain micro-motion tomography: the published method rebuilt as an extended CUDA pipeline, then tested against synthetic ground truth and falsification-oriented null tests.

Role: Independent researcher and software engineer
Methods: C++, CUDA, OpenMP, TerraSAR-X SSC processing, synthetic ground truth, null tests, 48-hour benchmark suite
Outcome: Proves five signal-level structural results the source papers omit, implements the corrections they imply, and separates what the method delivers from what it does not: the front end recovers injected micro-motion, while tomographic localization does not clear its own pre-registered shuffle-pairs and sign-flip floors.

View Project

Deep Wave Research

Wavelet-Domain ENSO Forecasting

Eleven linked documents on forecasting tropical-Pacific sea-surface temperature inside an exactly invertible complex-wavelet space: a standalone publication, a measurement charter, and nine reports running from system validation to a live-deployment handoff.

Role: Independent researcher and ML systems engineer
Methods: Dual-tree complex wavelets, Earthformer cuboid attention, CMIP6 forecast pretraining, sequence diffusion, EMOS and ECC-Q calibration, hash-gated sealed testing, moving-block bootstrap governance
Outcome: Threads a whole research programme together with its evidence tiers intact: one pristine sealed-test win, two controlled studies that narrowed the design space, a probabilistic stack whose validation advantage only partly transferred, and a deployment contract handed to a prospective live test.

View Project

Practice

Four areas with enough behind them to be useful.

Different subjects, different tools, different literatures. Each names the work that stands behind it.

Scientific computing and applied machine learning

Research software and empirical studies: forecasting systems, invertible signal representations, GPU-accelerated reconstruction, and the evaluation protocols that decide whether any of it worked.

Evidence Wavelet-domain ENSO forecasting, regime-adaptive probabilistic forecasting, Doppler tomography

Built-environment research and data

Questions about buildings, housing, and public infrastructure answered with archival sources, interviews, site observation, and structured records rather than assertion.

Evidence Architectural Conservancy of Ontario, Ottawa Community Housing

Civil and construction project support

Field records, drawing review, inspection workflows, and the documentation continuity that lets a multi-party project follow its own issues and decisions.

Evidence MMM Group / WSP municipal infrastructure, Ottawa Community Housing

Technical documentation and explanation

Turning scattered source material — methods, field information, literature — into something a reader can follow, check, and act on. Twenty-plus published reports behind it, and eight years of tutoring before that.

Evidence Published report series, tutoring, methods documentation

More about the practice Capabilities, with sources

Cross-section

Four at random from the whole body of work.

Reshuffled on every load, and drawn from the unfolded set: individual reports appear here alongside the series and collections that contain them. Every card opens the complete page, with its original prose, figures, tables, and references preserved.

Series 2026

Deep Wave Research

Wavelet-Domain ENSO Forecasting

Open series

Report July 2026

Deep Wave Research Wavelet-Domain ENSO Forecasting

Building and Validating a Complex-Wavelet Earthformer Forecasting System

A methods-validation study of the leakage-safe pipeline running from monthly tropical-Pacific sea-surface temperature, through a complete three-level dual-tree complex wavelet pyramid, into the official Earthformer backbone and back to reconstructed forecast maps.

Open report

Series 2026

Deep Wave Research

Regime-Adaptive Probabilistic Forecasting

A staged research programme on distributional forecasting of BTCUSDT perpetual futures: groundwork on frozen foundation-model embeddings, a pre-registered scan of where the series carries learnable signal, and a completed walk-forward comparison of from-scratch and foundation-model forecasters staged on those verdicts.

Open series

Report July 2026

Deep Wave Research Wavelet-Domain ENSO Forecasting

Deterministic Complex-Wavelet SST Forecasting under Limited Observations

Nine controlled ablation families on 335 observed training windows: architecture access, trainability boundary, amplitude and skill-aware objectives, and persistence-residual target parameterizations.

Open report