The Design Computation and Digital Engineering (DeCoDE) Lab, situated in the Mechanical Engineering department at MIT, works at the intersection of Engineering Design and Artificial Intelligence. We envision a world where humans and AI design together to solve our world's biggest challenges. To achieve this vision, we explore fundamental machine learning and optimization methods to enhance the design of complex mechanical systems and aid human design teams in creating better products. We aim to develop versatile methods that are applicable to a broad spectrum of engineering problems at different scales, complexity, wickedness and disciplinarity. We approach design challenges by mathematically formulating them as machine learning and optimization problems that can be generalized. By harnessing advanced machine learning techniques, we are reinventing the product design process, aiming to foster greater innovation and accelerate the creation of better designs.

At DeCoDE Lab, our core values - Integrity, Inclusivity, Collaboration, and Excellence - guide us to conduct research with honesty and transparency, foster a diverse and welcoming environment, recognize the power of teamwork, and continually strive for the highest quality in all our endeavors. We are also advocates for reproducible and open-source science, and we contribute by sharing most of our research code and papers online.

Selected Publications [See all]


Heyrani Nobari, A., Rey, J., Kodali, S., Jones, M., Ahmed, F.
Conformal Predictions Enhanced Expert-guided Meshing with Graph Neural Networks
In Journal of Mechanical Design 2024
PDF     Project Page     Dataset     Abstract

Edwards, K., Song, B., Porciello, J., Engelbert, M., Huang, C., Ahmed, F.
ADVISE: Accelerating the Creation of Evidence Syntheses for Global Development using Natural Language Processing-supported Human-AI Collaboration
In Journal of Mechanical Design 2024
PDF     Web Link     Abstract

Picard, C., Ahmed, F.
Untrained and Unmatched: Fast and Accurate Zero-Training Classification for Tabular Engineering Data
In Journal of Mechanical Design 2024
Project Page     Web Link     Abstract

Picard, C., Edwards, K.M., Doris, A.C., Man, B., Giannone, G., Alam, Md F., Ahmed, F.
From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design
Under review
PDF     Project Page     Web Link     Abstract

Bagazinski, N.J., Ahmed, F.
ShipGen: A Diffusion Model For Parametric Ship Hull Generation with Multiple Objectives and Constraints
In Journal of Marine Science and Engineering 2023
PDF     Project Page     Web Link     Abstract

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
In NeurIPS 2023
PDF     Project Page     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

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

Song, B., Zhou, R., Ahmed, F.
Multi-Modal Machine Learning in Engineering Design: A Review and Future Directions
In Journal of Computer and Information Science in Engineering 2023
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


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.

VLM dataset - A dataset of 1000+ tasks to evaluate vision language models.

Car Drag Coefficient - A dataset of 4,948 3D car meshes, their renderings, and their drag coefficients.

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).

Other engineering datasets A collection of datasets from the engineering design community, curated for our JMD review paper. Note that this list was made in 2022 and is not regularly updated.

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]


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

Brandon Man
Brandon Man

Brandon Man

Graduate Student

bm557@mit.edu

Ashley Margetts
Ashley Margetts

Ashley Margetts

SuperUROP

amargett@mit.edu

Mohamed Elrefaie
Mohamed Elrefaie

Mohamed Elrefaie

Visiting Graduate Student

moatef@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