I’m Abrar Faiaz — a researcher and engineer working at the intersection of scientific machine learning, multimodal AI, and decision-support systems. My work spans cyclone forecasting, geospatial intelligence, AI-powered search, and LLM systems for real-world impact.
I’m a Civil Engineering graduate from BUET, researching machine-learning methods for complex environmental and physical systems. My work explores physics-informed learning, representation learning, and multimodal AI for forecasting, retrieval, and decision support in high-impact real-world settings.
B.Sc. Civil Engineering
Bangladesh University of Engineering & Technology (BUET) · 2021–2026
Notre Dame College, Dhaka — HSC
A product studio in Dhaka. We design, build, and ship software — for ourselves, and for the few we choose to build with.
Flagship ProductThe search engine for everything you wear. 400+ stores. One search.
Lead the development of an AI-driven cyclone-forecasting and localized preparedness-guidance system with the Bangladesh Meteorological Department, integrating impact-based forecasting, geospatial risk information, and retrieval-augmented generation. The project was featured in the EW4All report developed with contributions from the World Meteorological Organization, UNDRR, ITU, and IFRC.
01
Abrar Faiaz, Alphy Shaharin, Md. Mafizur Rahman, Md. Bazlur Rashid, S.M. Quamrul Hasan
DOI: 10.1016/j.eswa.2026.131972 ↗
02
Abrar Faiaz, Rajit Raihan, Md. Mafizur Rahman, Md. Bazlur Rashid, S.M. Quamrul Hasan
03
Rafi Uddin, Abrar Faiaz, Sk. Rakibul Islam
DOI: 10.1007/978-981-97-0751-5_19 ↗
04
Abrar Faiaz, Alphy Shaharin, Mostafijur Rahman Farhad, Md. Mafizur Rahman
A storm-grouped chronological benchmark for landfall occurrence, timing and coastal location, combining censored survival learning with lead-time-stratified conformal uncertainty.
Framework & case-study results · Hover or focus to compare
05
Abrar Faiaz
Evaluating ECMWF TIGGE ensemble track uncertainty and coastline-aware landfall calibration through independent-storm verification, selective track correction and probabilistic post-processing.
Track errors & landfall calibration · Hover or focus to compare
Abrar Faiaz, Dipankar Mitra, Ranat Das Prangon
DOI: 10.1145/3704522.3704541 ↗Abrar Faiaz, Nowshin Nawar
DOI: 10.1145/3704522.3704549 ↗Civil Engineering Conference in the Asian Region (CECAR10)
From a building brief to a checked steel structure. A generative design loop proposes frames, runs structural analysis, revises failing members and compares alternatives—then produces drawings, quantities and calculation reports for engineering review.
An interactive exploration of Louisiana’s coastal future. The Hysteresis Blueprint 2130 connects historical land change, sediment dynamics and nature-based restoration through animated maps, scenario comparisons and a guided 3D story.
Software that predicts how your audience will feel—modeling emotional responses to creative content using Tribe V2, proprietary models and custom scoring equations.
Visit the dashboard ↗ Innovation · HardwareSolving the 4-million-riders problem—ANSYS-simulated HEPA filtration with sensor-driven brushless-DC airflow, prototyped through 3D printing.
View the design ↗
