Excited to share our latest article titled "A Probabilistic Crowd–AI Framework for Reducing Uncertainty in Postdisaster Building Damage Assessment " published in the Journal of Engineering Mechanics (JEM).

This paper is now available at: https://doi.org/10.1061/JENMDT.EMENG-6992

I am thrilled to share that I received the "2023 Award for Excellence in Research at the Ph.D. Level" in the Zachry Department of Civil and Environmental Engineering at Texas A&M Unversity. This remarkable achievement comes as the perfect culmination of my journey as a Ph.D. student at TAMU, being awarded on my very last day of this wonderful academic endeavor!

I'm excited to announce that our team, InfernotiX, succeeded at the 2023 TAMIDS Data Science Competition hosted by Texas A&M Institute of Data Science. Our project, titled "Remote-Sensing and Environmental Data Fusion for Wildfire Propagation Prediction: A CNN-Segmentation and Pixel-Based Enhanced Support Vector Machine," won multiple awards including 1st Place, Best Use of Additional Data, and Best Progress Graphic Prize. This event has left an indelible mark on the final stage of my Ph.D. study in Zachry Department of Civil and Environmental Engineering at Texas A&M University!

I would like to thank Xukai Zhang and Bahareh Alizadeh for their strong support and all the hard work throughout the competition. I also want to thank our advisors, Dr. Arash Noshadravan and Dr. Amir H. Behzadan, for their wonderful guidance and mentorship.

I'm delighted to announce that I have completed the Academy for Future Faculty (AFF) program at Texas A&M University. I want to sincerely thank Dr. Maria Koliou for being an exceptional mentor throughout the program. Her guidance and suggestions were invaluable in preparing me for a future career in academia!

I am excited to share that our paper, which is my very first journal publication, has been one of the most downloaded articles in the Journal of Computer-Aided Civil and Infrastructure Engineering.

Cheng, C. S., Behzadan, A. H., & Noshadravan, A. (2021). Deep learning for post‐hurricane aerial damage assessment of buildings. Computer‐Aided Civil and Infrastructure Engineering. https://doi.org/10.1111/mice.12658 

I am thrilled to celebrate the 3MT Cup finding its FIRST home in the Zachry Department of Civil and Environmental Engineering for the next academic year (2022-2023). 

I am thankful for having strong support from my advisors, Dr. Arash Noshadravan (2nd from the left) and Dr. Amir Behzadan (1st from the left). Also, I would like to express my gratitude to Dr. Fuhui Tong (3rd from the right), Dr. John Hurtado (2nd from the right), Dr. Zachary Grasley (3rd from the left), and Dr. Yunlong Zhang (1st from the right) for their inspiring remarks and support for me.

This event has left an indelible mark on me, and I will cherish its memory in my life!

Participating in the CSGS Annual Meeting in Tampa, FL was a truly memorable experience. I feel fortunate to have represented Texas A&M University in the Three Minute Thesis (3MT) competition and am grateful for the strong support I received from the Texas A&M Graduate and Professional School.

3MT Title: Artificial Intelligence and drones for disaster recovery

I am excited to announce that I have successfully defended my doctoral dissertation titled "Post-Disaster Damage Assessment with Artificial Intelligence and Uncertainty Quantification." This marks a significant achievement in my professional career!

I am glad to be featured on the ASCE DSA Podcast Series to present our research. Check this out if your are interested in our published DoriaNET dataset! 

https://feeds.captivate.fm/asce-dsa/ 

I am thrilled to share that I won the 10th 2022-2023 3MT competition in the Doctoral Category at Texas A&M University!!!

Full story: Texas A&M Today and tx.ag/Cheng

Glad to have the opportunity today to share my research with the Department of Computer Science and Engineering (CSCE) advisory council members in the Center for Infrastructure Renewal (CIR) at Texas A&M University.

Excited to share our latest article titled "Post‐disaster damage classification based on deep multi‐view image fusion" published in the computer-aided civil and infrastructure engineering (CACAIE) journal. The paper is now available online!

DOI: https://doi.org/10.1111/mice.12890

It was a great experience to share my Ph.D. research topics with the summer student interns in the civil engineering department (CAE division) at National Taiwan University. I was also inspired by many great questions and comments from the audience!

I am excited to share the latest article titled "Uncertainty‐aware convolutional neural network for explainable AI‐assisted disaster damage assessment " published in the structural control and health monitoring (SCHM) journal. This paper is now available as an early view version!

DOI: https://doi.org/10.1002/stc.3019

Thrilled to participate in this in-person Engineering Mechanics  Institute (EMI) 2022 conference hosted by Johns Hopkins University. The presented topic is titled "Hybrid crowd-AI framework to reduce uncertainty in post-disaster damage assessment".

Glad to present our work on Exploring the Generalizability of Deep Convolutional Neural Networks for Post-Hurricane Damage Assessment at the ASCE Lifelines 2022 conference hosted by the University of California, Los Angeles (UCLA). 

I am thrilled to share our latest article titled "Drone Mapping of Damage Information in GPS-Denied Disaster Sites" published in the journal of Advanced Engineering Informatics (ADVEI). The paper is now available online!

DOI: https://doi.org/10.1016/j.aei.2021.101450

I am excited to share our latest visual dataset, DoriaNET, which has been published in DesignSafe and is now available online with a DOI. DoriaNET is a synthetic dataset for unmanned aerial vehicle (UAV)-based post-hurricane building damage assessment. Overall, DoriaNET is a first-of-a-kind visual dataset for hurricane damage assessment based on the FEMA HAZUS Hurricane guideline, and can be used to train and test future visual recognition models to assist human inspection of damaged buildings and infrastructures. 

DOI: https://doi.org/10.17603/ds2-gqvg-qx37

My colleague, Md Nazmus Sakib, and I flew a drone in our CIBER lab CIR drone room. I was excited to test our developed deep learning model's ability to detect "toy" buildings on these drone footages. After fine-tuning on a relatively small dataset, our model's detection performance is pretty promising!

CIBER Lab Website 

I am glad to share our latest research topic: A novel Automated Post-disaster Damage Assessment based on Multi-view Imagery presented by my colleague, Asim B. Khajwal, at the MMLDT_CSET 2021 conference hosted by University of California San Diego.

DOI: https://doi.org/10.26226/morressier.612f6737bc981037241008a5

I’m honored to present our research paper on uncertainty-aware post-disaster damage assessment using Artificial Intelligence (AI) and serve as a session chair at the i3CE 2021 conference hosted by the University of Florida. 

My honor to present our research on AI-based post-disaster damage assessment at the IMAC XXXIX conference (virtual). This was my very first conference presentation in the US.

I am glad to share my very first journal paper on post-disaster building damage assessment using drone footage and deep convolutional networks published in the computer-aided civil and infrastructure engineering (CACAIE) journal (IF: 11.775). The full paper is now available online.

Cheng, C. S., Behzadan, A. H., & Noshadravan, A. (2021). Deep learning for post‐hurricane aerial damage assessment of buildings. Computer‐Aided Civil and Infrastructure Engineering. https://doi.org/10.1111/mice.12658