This page hosts freely accessible material and databases compiled from past and recent works. The databases will be occasionally updated once relevant research articles are published. All databases are also uploaded at Mendeley Data and can be found under my profile. 

 

[Download lecture notes, datasets, Python and R scripts] from my textbook: Machine Learning for Civil & Environmental Engineers: A Practical Approach to Data-driven Analysis, Explainability, and Causality [ISBN: 978-11198976061]

  

Databases

1. Database for RC columns tested under fire conditions

2. Database for timber members tested under fire conditions

3. Database on Bridge failures

4. ACI FRP databases for FRP-reinforced & FRP-strengthened RC members

5. Database on the compressive strength of 3D printed concrete [Paper] [doi] [Dataset]

6. Dataset on fire resistance analysis of FRP-strengthened concrete beams. Data in Brief. [Paper]. [Dataset and input files] 

7. Benchmarking databases [paper] [link] [Thanks to our collaborators and please remember to cite the original sources of these databases]

Database 1: concrete-filled steel tubular (CFST) columns

Database 2: shear strength of cold-formed steel (CFS) channels with slotted webs 

Database 3: fire spalling of RC columns 

​

6. Database for YODO to design Ultra-High-Performance Concretes [doi] [Paper] [Dataset]

​

AI-/ML-based Apps

1. RAI: a Rapid, Autonomous, and Intelligent AI-powered App to identify fire-vulnerable bridges (v1.0 Beta) [Paper] [Download] 

2. Please try my experimental app, spAIng below, or download it! (Please remember to read the Notes)

3. Try our plug-&-play cracking detection deep learning model [Paper] [Download]

4. The App for YODO [You Only Design Once (YODO): Gaussian Process-Batch Bayesian Optimization framework for Mixture Design of Ultra-High-Performance Concrete] [doi] [Paper] 

5. Python script for Verifying Domain Knowledge and Theories on Fire-induced Spalling of Concrete through eXplainable Artificial Intelligence [doi] [Pre-print draft] [Code]

6. Python script for Machine Learning for Wildfire Classification: Exploring Blackbox, eXplainable, Symbolic, and SMOTE Methods. [doi] [Pre-print draft] [code]

7. Try our new algorithm (SPINEX: Similarity-based Predictions with Explainable Neighbors Exploration) [doi] [Download Python Scripts]