DeCoDE Lab is based in the Mechanical Engineering department at MIT. Our vision is to create a world where humans and AI design together to solve our biggest challenges. We study machine learning and optimization methods to better design complex mechanical systems and assist teams of human designers in creating better products.

Our work lies at the intersections of Mechanical Engineering, Artificial Intelligence, and Human-Computer Interaction. A few questions we are interested in: How can algorithms synthesize high-performing designs that meet real-world requirements? How can algorithms help discover or create creative designs that have never been seen before? How can we enable distributed teams of people to create better products? How can we design, develop, and deploy advanced engineering material systems for complex non-linear inverse problems? How can we quickly and reliably evaluate thousands of ideas to accelerate innovation? While these questions address different areas, our underlying approach is to mathematically characterize these questions as generalizable machine learning and optimization problems, make testable predictions for new problems, and tie together or understand individual empirical results that researchers have generated.

Our techniques apply to a wide range of problems in Engineering. We aim to transform the way humans design products and measure our success by the impact of our work on society. We believe in reproducible and open-source science and do our part by making most of our research code and papers available online.

Selected Publications [See all]


Giannone, G., Regenwetter, L., Srivastava, A., Gutfreund, D., Ahmed, F.
Learning from Invalid Data: On Constraint Satisfaction in Generative Models
Under review
PDF     Web Link     Abstract

Giannone, G., Srivastava, A., Winther, O., Ahmed, F.
Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
Under review
PDF     Web Link     Abstract

Regenwetter, L., Obaideh, Y. A., Ahmed, F.
Counterfactuals for Design: A Model-Agnostic Method For Design Recommendations
In IDETC 2023
PDF     Project Page     Web Link     Abstract

Song, B., Yuan, C., Permenter, F., Arechiga, N., Ahmed, F.
Surrogate Modeling of Car Drag Coefficient with Depth and Normal Renderings
In IDETC 2023
PDF     Project Page     Web Link     Abstract

Su, H., Song, B., Ahmed, F.
Multi-modal Machine Learning for Vehicle Rating Predictions Using Image, Text, and Parametric Data
In IDETC 2023
PDF     Project Page     Web Link     Abstract

Heyrani Nobari, A., Rey, J., Kodali, S., Jones, M., Ahmed, F.
Autosurf: Automated Expert-Guided Meshing with Graph Neural Networks and Conformal Predictions
In IDETC 2023
PDF     Project Page     Abstract

Picard, C., Schiffmann, J., Ahmed, F.
DATED: Guidelines for Creating Synthetic Datasets for Engineering Design Applications
In IDETC 2023
PDF     Web Link     Abstract

Bagazinski, N.J., Ahmed, F.
Ship-D Ship Hull Dataset for Design Optimization Using Machine Learning
In IDETC 2023
PDF     Abstract

Edwards, K., Song, B., Porciello, J., Engelbert, M., Huang, C., Ahmed, F.
ADVISE: AI-accelerated Design of Evidence Synthesis for Global Development
In IDETC 2023
PDF     Web Link     Abstract

Giannone, G., Ahmed, F.
Diffusing the Optimal Topology: A Generative Optimization Approach
In IDETC 2023
PDF     Web Link     Abstract

Song, B., Zhou, R., Ahmed, F.
Multi-modal Machine Learning in Engineering Design: A Review and Future Directions
Under review
PDF     Web Link     Abstract

Regenwetter, L., Srivastava, A., Gutfreund, D., Ahmed, F.
Beyond Statistical Similarity: Rethinking Metrics for Deep Generative Models in Engineering Design
In Computer Aided Design 2023
PDF     Web Link     Abstract

Song, B., Miller, S., Ahmed, F.
Attention-enhanced Multimodal Learning For Conceptual Design Evaluations
In Journal of Mechanical Design 2023
PDF     Web Link     Dataset     Abstract

Mazé, F., Ahmed, F.
Diffusion Models Beat GANs on Topology Optimization
In AAAI 2023
PDF     Project Page     Web Link     Abstract

Heyrani Nobari, A., Srivastava, A., Gutfreund, D., Ahmed, F.
LINKS: A dataset of a hundred million planar linkage mechanisms for data-driven kinematic design
In IDETC 2022
PDF     Project Page     Web Link     Dataset     Abstract

Regenwetter, L., Heyrani Nobari, A., Ahmed, F.
Deep Generative Models in Engineering Design: A Review
In Journal of Mechanical Design 2022
PDF     Web Link     Dataset     Abstract

Announcements


We are organizing a new workshop titled, 'From Data to Design - Challenges and Opportunities across Industry and Academia' at ASME IDETC 2023 conference. We encourage attendees to sign up for the free workshop during conference registration. The workshop organizers include Cyril Picard (MIT), Daniele Grandi (Autodesk), Namwoo Kang (KAIST), Akash Srivastava (IBM), and Faez Ahmed (MIT). Checkout the webpage here.

Prospective Ph.D. students - If you are interested in joining the DeCoDE lab, you can apply to the Computational Science and Engineering Program or to the Mechanical Engineering department at MIT.

If you are interested in joining the DeCoDE lab, drop me an email with the following text in your subject line "Join DeCoDE:" followed by the position you are interested in (for example, a postdoc, intern, visiting student, etc.).

Datasets


The following list contains engineering design datasets collected by DeCoDE lab. Kindly acknowledge the corresponding paper that introduced the dataset if you utilize a dataset for your work.

LINKS dataset - A dataset of 100 million planar linkage mechanisms and 1.1 billion coupler curves obtained from kinematic simulations. The dataset also contains curated curves, 100 million negative samples, and a publicly available simulation software.

Turbo-compressors dataset - A dataset of 22 million turbo-compressors and their performance under different operating conditions.

Airfoil dataset - A synthetic dataset of 48,503 airfoils and their aerodynamic performance computed using OpenFOAM.

Topodiff topology optimization dataset - A dataset of 33,000 images corresponding to optimal topologies for diverse boundary conditions. The dataset also contains their physical fields, compliance values, and an additional 42000 non-optimal topologies.

SHIP-D dataset - A dataset of 30,000 ship hulls each with design and functional performance information, including parameterization, mesh, point-cloud, and image representations, as well as 32 hydrodynamic drag measures under different operating conditions.

3D cars dataset - A diverse dataset of 9,070 high-quality 3D car meshes labeled by drag coefficients computed from computational fluid dynamics simulations.

BIKED dataset - A dataset of 4,500 community-designed bicycles in tabular and image format, along with images corresponding to different bike parts for each bicycle.

FRAMED dataset - A dataset of 4,500 bicycle frames and ten performance metrics obtained from structural simulations.

Aircraft dataset - A dataset of lift and drag performance values of 4,045 3D aircraft models from Shapenet.

Milk Frother dataset - A multimodal dataset of 1,126 milk frother sketches and their text descriptions. The dataset is derived from a milk frother dataset collected at the Brite lab.

Autosurf aircraft dataset A dataset of 1,050 airplane models with segmentation labels, created using NASA's Open Vehicle Sketch Pad (OpenVSP).

Principal Investigator

Faez Ahmed

d'Arbeloff Career Development Assistant Professor
Department of Mechanical Engineering
Massachusetts Institute of Technology
Email: faez at mit dot edu

Faez Ahmed is the d'Arbeloff career development assistant professor in the Department of Mechanical Engineering at MIT, where he leads the Design Computation and Digital Engineering (DeCoDE) lab. His research focuses on developing new machine learning and optimization methods to study complex engineering design problems. Before joining MIT, Ahmed was a postdoctoral fellow at Northwestern University and completed his Ph.D. in mechanical engineering at the University of Maryland. He also worked in the railway and mining industry in Australia, where he pioneered data-driven predictive maintenance and renewal planning efforts.

Current Members [See all members]


Binyang Song
Binyang Song

Binyang Song

Postdoctoral Associate

binyangs@mit.edu

Cyril Picard
Cyril Picard

Cyril Picard

Postdoctoral Fellow

cyrilp@mit.edu

Ferdous Alam
Ferdous Alam

Ferdous Alam

Postdoctoral Associate

mfalam@mit.edu

Amin Heyrani Nobari
Amin Heyrani Nobari

Amin Heyrani Nobari

Ph.D. Candidate

ahnobari@mit.edu

Kristen Edwards
Kristen Edwards

Kristen Edwards

Ph.D. Candidate

kme@mit.edu

Lyle Regenwetter
Lyle Regenwetter

Lyle Regenwetter

Ph.D. Candidate

regenwet@mit.edu

Noah Joseph Bagazinski
Noah Joseph Bagazinski

Noah Joseph Bagazinski

Ph.D. Candidate

noahbagz@mit.edu

Rui Zhou
Rui Zhou

Rui Zhou

Graduate Student

zhourui@mit.edu

Nicholas Wei Yong Sung
Nicholas Wei Yong Sung

Nicholas Wei Yong Sung

Graduate Student

nicksung@mit.edu

Nomi Yu
Nomi Yu

Nomi Yu

Graduate Student

yunomi@mit.edu

Rosen Yu
Rosen Yu

Rosen Yu

Graduate Student

rosenyu@mit.edu

Annie Clare Doris
Annie Clare Doris

Annie Clare Doris

Graduate Student

adoris@mit.edu

Kaira M Samuel
Kaira M Samuel

Kaira M Samuel

Graduate Student

kmsamuel@mit.edu

Giorgio Giannone
Giorgio Giannone

Giorgio Giannone

Visiting Graduate Student

ggiorgio@mit.edu

Hanqi Su
Hanqi Su

Hanqi Su

UROP

hanqisu@mit.edu

Nicholas J Cerone
Nicholas J Cerone

Nicholas J Cerone

UROP

ceronj26@mit.edu

Noah J Wiley
Noah J Wiley

Noah J Wiley

UROP

njwiley@mit.edu

Eric Zhou
Eric Zhou

Eric Zhou

UROP

ericz217@mit.edu

Tyler Butler
Tyler Butler

Tyler Butler

Administrative Assistant

tjbutler@mit.edu

Fun fact: According to the Mathematics Genealogy Project, our academic ancestors include: Poisson, Laplace, Lagrange, Euler, Bernoulli, Leibniz, Copernicus, Nasir al-Din al-Tusi, and many more. Check out our academic family tree.

News