Laeeq Aslam, PhD

Postdoctoral Research Fellow · Guangdong Technion–Israel Institute of Technology (GTIIT)

laeeq.aslam.100@gmail.com Shantou, Guangdong, China Google Scholar GitHub

Research Interests

Physics-informed machine learning; aerial wind sensing and wind-field reconstruction using multirotor drones; short-horizon wind and load forecasting for grid reliability; urban climate-risk intelligence and heat-stress early warning; edge AI deployment on memory- and power-constrained hardware.

Education

  1. PhD in Control Science & Machine Learning

    Central South University, Changsha, China

    Sept 2020 – Dec 2025

    Dissertation: Physics-informed learning for wind forecasting, grid reliability, and urban climate resilience. CSC Scholarship.

  2. MS in Electronic Engineering Gold Medalist

    International Islamic University, Islamabad, Pakistan

    Sept 2015 – Aug 2017

  3. BS in Electronic Engineering

    International Islamic University, Islamabad, Pakistan

    Sept 2006 – Aug 2010

Professional Appointments

  1. Postdoctoral Research Fellow

    Guangdong Technion–Israel Institute of Technology (GTIIT)

    Mar 2026 – Present

    Low-cost drone-based wind estimation and PINN-based wind-field reconstruction.

  2. AI/ML Consultant — Edge Computing & Computer Vision

    Bond and Built Pvt Ltd

    Jul 2024 – Mar 2025

    Footwear analytics pipeline handling 60+ video streams and ~50,000 daily inferences.

  3. Machine Learning Engineer — Vision & Deployment

    DLISION

    May 2021 – Sept 2022

    Semantic segmentation and real-time detection pipelines with UNet variants.

  4. Lecturer & Research Assistant — Embedded Systems / AI

    iUSE School of Engineering & IIUI

    2013 – 2020

    Taught embedded systems, programming, and signal processing. Built Instrumentation & Measurement Lab.

Selected Publications

6 first-author papers (2024–2025). Full list →

Physics-Informed Ensemble Learning for City-Center Grid Cell Temperature Prediction During Thermal Extremes

Urban Climate (Elsevier), 2025

Physics-Informed Spatio-Temporal Network with Trainable Adaptive Feature Selection for Short-Term Wind Speed Prediction

Computers & Electrical Engineering (Elsevier), 2025

A Shallow Hybrid Model with Dynamic Bayesian Optimisation for Wind Speed Prediction on Memory-Constrained Devices

Computers & Electrical Engineering (Elsevier), 2025

Dynamic Optimization of Recurrent Networks for Wind Prediction on Edge Devices

IEEE Access, 2025

Technical Skills

ML/AI: Deep Learning, Computer Vision, Time-Series Forecasting, PINNs, Ensemble Learning, Transformers, LSTM, TCN
Languages: Python, MATLAB, C++
Frameworks: TensorFlow, PyTorch, OpenCV, Edge Impulse
Deployment: Docker, AWS EC2, Triton Inference Server, Git
Hardware: Raspberry Pi, NVIDIA Jetson, Arduino Nano BLE Sense
Data: Pandas, NumPy, Matplotlib, Seaborn, Feature Engineering

Awards, Grants & Memberships

  • Chinese Government CSC Scholarship (PhD)
  • Hunan Provincial Key R&D Program — wind energy & grid optimization (Project 2020WK2007)
  • Gold Medalist — MS in Electronic Engineering
  • Registered Engineer, Pakistan Engineering Council (ELECTRO/22837)
  • Member, IEEE