Abdullah Ashraf

Model · Tabular regression

sentinel-mumbai-hybrid-pinn-keras

Abdullah Ashraf

Sentinel-Mumbai Hybrid PINN is an attention-augmented Physics-Informed Neural Network (PINN) developed in Keras 3 and optimized for high-throughput GPU inference (Tesla T4 mixed-precision float16). The network incorporates a 24-hour temporal sequence lookback and enforces hydraulic mass conservation via a partial differential equation (PDE) continuity constraint during gradient descent: $$\text{PDE Residual} = \frac{\partial \hat{y}}{\partial t} - (\text{Rainfall} - \text{Infiltration}) = 0$$ Where $\text{Infiltration} \approx 0.0$ on impervious urban concrete surfaces (landcover class 80). Released under the MIT License.

Model · Tabular regression

sentinel-v7-deep-flood-lstm

Abdullah Ashraf

Sentinel-V7 Deep Hydrological Bi-LSTM is a specialized recurrent neural sequence model engineered for real-time flood risk scoring and inundated area forecasting. It maps multi-sensor remote sensing inputs (Copernicus Sentinel-1 SAR radar backscatter, digital elevation models, river network proximity, ECMWF GEOGloWS river discharge, and precipitation metrics) to a continuous flood vulnerability metric. The model is packaged in Keras 3 format along with its fitted Scikit-Learn MinMaxScaler (scaler.joblib), ensuring seamless deployment on edge systems and cloud microservices. Released under the MIT License.

Model · Tabular regression

sentinel-mumbai-pinn-v1

Abdullah Ashraf

Sentinel-Mumbai PINN v1 is a high-capacity Physics-Informed Neural Network (PINN) engineered for hyper-local urban flood depth forecasting and storm surge dynamics across Mumbai / Salsette Island. Trained across multi-decadal telemetry (rainfall, cumulative precipitation, tidal surge oscillations, elevation, urban impermeability, and drainage networks), the model embeds physical boundary laws directly into its optimization objective, preventing unphysical mass disappearance during coastal hydraulic lock events. The model optimizes a composite objective balancing empirical data fidelity against hydraulic conservation of mass: $$\mathcal{L}{\text{total}} = \alpha \cdot…

Dataset · Text to code

aegis-wgsl-webgpu-shaders

Abdullah Ashraf

The Aegis WGSL WebGPU Shader Instruction Dataset is a high-precision code-generation and conversational dataset mapping natural language physical simulation queries to executable WebGPU Shading Language (WGSL) compute and fragment shaders. Modern browsers and edge devices utilize WebGPU for 60-120 FPS hardware-accelerated scientific visualization. This dataset trains or fine-tunes LLMs to act as specialized graphics engineers capable of translating hydrodynamic, thermal, seismic, acoustic, and aeration queries directly into functional WGSL shader code. 1. Sentinel HUFP Fluid Dynamics: Eulerian fluid flow vectors, wave interference patterns, Navier-Stokes approximations, and coastal storm…

Dataset · Text generation

aegis-persona-sovereign-node

Abdullah Ashraf

The Aegis Sovereign Node Persona & Technical Dialogue Dataset is an augmented ChatML instruction-tuning dataset designed to condition autonomous agents with the visionary, commanding, and authoritative cadence of an elite technology founder while rigorously defending complex engineering architecture. The dataset pairs high-intensity investor/architectural queries against the Aegis Sovereign Node, balancing macro-strategic vision (inspired by legendary product keynotes) with micro-technical depth (BACnet/LonWorks edge gateways, automated facade drone maintenance, and structural PINN telemetry). Released under the MIT License.

Dataset · Tabular regression

alaska-arctic-hydrology-matrix

Abdullah Ashraf

The Alaska Arctic Hydrology Harmonization Matrix is a multi-source geospatial hydro-climatic dataset containing 50,000 spatial coordinate vectors sampled across sub-arctic and hydrological basins. It unifies digital elevation models (DEM), permanent surface water occurrence percentages, seasonal water transition classifications, historical rainfall averages, and human demographic proxies into an aligned tabular feature matrix. This dataset was generated in-house via the LocalDataHarmonizer engine in ALASKASANDBOX, utilizing high-throughput spatial sampling algorithms (rasterio.sample.samplegen) to extract raster values at exact coordinate centroids. Distributed under the Creative Commons…