Skip to content
View murad-geoAi's full-sized avatar
6 followers · 10 following

Block or report murad-geoAi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
murad-geoAi/README.md

Hi, I'm Golam Murad 👋

Research Engineer | Scientific ML & GeoAI

Google Scholar ORCID LinkedIn Email

Integrating physics-informed neural networks (PINNs) and Bayesian deep learning for robust geohazard assessment and environmental monitoring.

🔬 What I Work On

Geospatial machine learning for natural hazards — landslide susceptibility, flood impact, and explainable, uncertainty-aware deep learning applied to real-world environmental risk.

🛠️ Technical Stack

Category Tools & Frameworks
Deep Learning PyTorch Lightning Hugging Face TensorFlow Keras
Scientific Computing NumPy Pandas Scikit-Learn
Optimization & UI Optuna Gradio
Languages Python C C++ JavaScript
Databases & Tools Neo4j Git GitHub

📝 Recent Research

  • Preprint — Uncertainty-aware machine learning for landslide susceptibility, available on EarthArXiv
  • Under Review — Spatial Sparsity-Aware Explainable Deep Learning-Based Landslide Susceptibility Mapping, Canadian Geotechnical Journal
  • Under Review — Advanced Machine Learning and Explainable AI for Predicting Vegetation Dynamics, Environmental Monitoring and Assessment

Pinned Loading

  1. DL_Application_for_Landslide_Susceptibility_Mapping DL_Application_for_Landslide_Susceptibility_Mapping Public

    Deep learning framework for Landslide Susceptibility Mapping using geospatial and environmental data. Employs DNN, 1D CNN, and LSTM with DBSCAN clustering to mitigate data sparsity. Features model …

    Jupyter Notebook 6

  2. Landslide-Susceptibility-Bayesian-Neural-Network- Landslide-Susceptibility-Bayesian-Neural-Network- Public

    Bayesian Deep Neural Network in PyTorch for landslide susceptibility mapping with predictive uncertainty estimation.

    Jupyter Notebook 1

  3. Soft_Computing_for_NDVI_Prediction Soft_Computing_for_NDVI_Prediction Public

    Implementation of soft computing techniques for NDVI prediction using satellite imagery and environmental data. Utilizes CatBoost, GBM, LightGBM, and XGBoost models to enhance vegetation health mon…

    Jupyter Notebook 1

  4. ml_flood_susceptibility_mapping ml_flood_susceptibility_mapping Public template

    Leakage-aware flood susceptibility mapping using classical machine learning and strict spatial holdout, with reproducible preprocessing, explainability analysis, and benchmark comparison across eig…

    Python

  5. LSM_ChittagongMetropolitonArea LSM_ChittagongMetropolitonArea Public

    Bayesian landslide susceptibility mapping for Chittagong, Bangladesh, with benchmark model comparison and uncertainty-aware deployment using Gaussian Process Classification.

    Python

  6. rainfall-timeseries-forecasting rainfall-timeseries-forecasting Public

    A reproducible pipeline for rainfall time-series dataset generation in Google Earth Engine and forecasting with deep learning and machine learning models.

    Python