Earth Observation · ML

AI & Remote Sensing Specialist

Google Cloud ML Engineer · Python Expert · AI for EO · Cloud‑native geospatial

Mohanad Albughdadi portrait

Selected Projects

Visualization of a Mixture‑of‑Experts Masked Autoencoder for EO

Lightweight Metadata‑Aware Mixture‑of‑Experts MAE for EO

Pre‑train a lightweight MoE‑MAE for Earth Observation and fine‑tune it for downstream EO tasks.

Change detection animation using CLAY embeddings

CLAY Foundation Model for Change Detection

Use CLAY embeddings to detect flood‑induced changes from Sentinel‑1 and Sentinel‑2 data.

STAC services deployment diagram

Deploy STAC Catalog Services with Docker Compose

Deploy and manage STAC catalog components using a simple, reproducible Docker Compose setup.

Super‑resolution results for Sentinel‑2 to VENµS

Sentinel‑2 → VENµS Super‑Resolution

Enhance Sentinel‑2 imagery to 5 m resolution using learning‑based super‑resolution.

ERA‑5 temperature super‑resolution visualization

ERA‑5 Temperature Super‑Resolution

Super‑resolve ERA‑5 temperature fields to match CERRA spatial resolution.

ERA‑5 wind speed super‑resolution visualization

ERA‑5 Wind Speed Super‑Resolution

Super‑resolve ERA‑5 wind speed fields to match CERRA spatial resolution.

Sentinel‑2 processing API dashboard

Sentinel‑2 Processing API

Cloud‑native API with Docker, Kubernetes, Celery, Redis, and Flower to download and process Sentinel‑2 imagery.

YOLOv8 oriented bounding box detection on aerial imagery

Object Detection on VHR Satellite/Aerial Images

Oriented bounding box (OBB) detection with YOLOv8 for very‑high‑resolution remote sensing imagery.

Interactive segmentation dashboard powered by SAM

Promptable Sentinel‑2 Segmentation with SAM

Interactive segmentation dashboard for Sentinel‑2 imagery using Segment Anything (SAM).

Fine‑tuning SAM for remote sensing tasks

Fine‑Tuning SAM for Remote Sensing

Adapt SAM foundation model for downstream remote sensing tasks via efficient fine‑tuning.

Field boundary delineation results

Field Boundary Delineation in Sentinel‑2

Deep‑learning approach to extract agricultural field boundaries for precision agriculture.

Super‑resolved Sentinel‑2 imagery to 2.5 m

Super‑Resolved Sentinel‑2 Images

Enhance Sentinel‑2 imagery to 2.5 m resolution using super‑resolution techniques.

Fire risk mapping with BDORTHO imagery

Fire Risk Zoning Using BDORTHO

Map fire‑risk zones with deep learning and aerial/satellite imagery to support disaster management.

LAI estimation visualization from Sentinel‑2

Large‑Scale LAI Estimation from Sentinel‑2

Fast, scalable estimation of Leaf Area Index (LAI) over large areas using deep learning.

Swimming pool detection across French communes

Swimming Pool Detection with BDORTHO

Detect swimming pools across French communes to support circular‑economy initiatives.