Lento Manickathan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lento Manickathan has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Claudio Mucignat
Laboratory for Computational Engineering, Swiss Federal Laboratories for Materials Science and Technology, Dübendorf, Switzerland
3 shared publications - Ivan Lunati
Laboratory for Computational Engineering, Swiss Federal Laboratories for Materials Science and Technology, Dübendorf, Switzerland
3 shared publications - Jiggar Shah
Laboratory for Multiscale Studies in Building Physics, Swiss Federal Laboratories for Materials Science and Technology, Dübendorf, Switzerland
2 shared publications - Thomas Rösgen
Institute of Fluid Dynamics, Department of Mechanical and Process Engineering, ETH Zürich, Zürich, Switzerland
2 shared publications
Latest Publications
- Open Access
- 27 September 2023
- Published by Springer Nature in Experiments in Fluids
- Vol. 64 (10) , 1-17
A lightweight neural network designed for fluid velocimetry
We devise a novel lightweight image matching architecture (), which is designed and optimized for particle image velocimetry (PIV). is a convolutional neural network (CNN) that performs symmetric image matching and employs an iterative residual refinement strategy, which allows us to optimize the total number of refinement steps to balance accuracy and computational efficiency. The network is trained on kinematic datasets with a loss function that penalizes larger gradients. We consider a six-level () and a four-level () version of the network and demonstrate that they are considerably leaner and faster than a state-of-the-art network designed for optical flow. reconstructs the velocity field from synthetic and experimental PIV images with an accuracy comparable or superior both to existing CNNs as well as to state-of-the-art cross-correlation methods (i.e., a commercial implementation of ). Although less accurate, allows a significant reduction of the computational costs with respect to any other method considered. All CNNs prove more robust than with respect to particle loss and allow effective error reduction by increasing the particle seeding density. Thanks to reduced computational cost and memory requirement, we envision the deployment of on low-cost devices to provide affordable, real-time inference of the flow field during PIV measurements.
- 27 September 2023
- Published by Springer Nature in Experiments in Fluids
- Vol. 64 (10) , 1-17
Open AccessA lightweight neural network designed for fluid velocimetry
We devise a novel lightweight image matching architecture (), which is designed and optimized for particle image velocimetry (PIV). is a convolutional neural network (CNN) that performs symmetric image matching and employs an iterative residual refinement strategy, which allows us to optimize the total number of refinement steps to balance accuracy and computational efficiency. The network is trained on kinematic datasets with a loss function that penalizes larger gradients. We consider a six-level () and a four-level () version of the network and demonstrate that they are considerably leaner and faster than a state-of-the-art network designed for optical flow. reconstructs the velocity field from synthetic and experimental PIV images with an accuracy comparable or superior both to existing CNNs as well as to state-of-the-art cross-correlation methods (i.e., a commercial implementation of ). Although less accurate, allows a significant reduction of the computational costs with respect to any other method considered. All CNNs prove more robust than with respect to particle loss and allow effective error reduction by increasing the particle seeding density. Thanks to reduced computational cost and memory requirement, we envision the deployment of on low-cost devices to provide affordable, real-time inference of the flow field during PIV measurements.
- Open Access
- 21 March 2023
- Published by Springer Nature in Experiments in Fluids
- Vol. 64 (4) , 1-16
A lightweight convolutional neural network to reconstruct deformation in BOS recordings
We introduce a Convolutional Neural Network (CNN) that is specifically designed and trained to post-process recordings obtained by Background Oriented Schlieren (BOS), a popular technique to visualize compressible and convective flows. To reconstruct BOS image deformation, we devised a lightweight network () that has comparatively fewer parameters to train than the CNNs that have been previously proposed for optical flow. To train , we introduce a novel strategy based on the generation of synthetic images from random-irrotational deformation fields, which are intended to mimic those provided by real BOS recordings. This allows us to generate a large number of training examples at minimal computational cost. To assess the accuracy of the reconstructed displacements, we consider test cases consisting of synthetic images with sinusoidal displacement as well as images obtained in the experimental studies of a hot plume in air and a flow past and inside a heated hollow hemisphere. By comparing the reconstructed deformation fields using the or conventional post-processing techniques used in Direct Image Correlation () or conventional image cross-correlation, we show that is more accurate and robust in the synthetic test case. When applied to experimental BOS recordings, all methods provide similar and consistent deformation fields. As is capable of achieving a comparable or better accuracy at a fraction of the computational costs, it represents a valuable alternative to conventional post-processing techniques for BOS experiments.
- 21 March 2023
- Published by Springer Nature in Experiments in Fluids
- Vol. 64 (4) , 1-16
Open AccessA lightweight convolutional neural network to reconstruct deformation in BOS recordings
We introduce a Convolutional Neural Network (CNN) that is specifically designed and trained to post-process recordings obtained by Background Oriented Schlieren (BOS), a popular technique to visualize compressible and convective flows. To reconstruct BOS image deformation, we devised a lightweight network () that has comparatively fewer parameters to train than the CNNs that have been previously proposed for optical flow. To train , we introduce a novel strategy based on the generation of synthetic images from random-irrotational deformation fields, which are intended to mimic those provided by real BOS recordings. This allows us to generate a large number of training examples at minimal computational cost. To assess the accuracy of the reconstructed displacements, we consider test cases consisting of synthetic images with sinusoidal displacement as well as images obtained in the experimental studies of a hot plume in air and a flow past and inside a heated hollow hemisphere. By comparing the reconstructed deformation fields using the or conventional post-processing techniques used in Direct Image Correlation () or conventional image cross-correlation, we show that is more accurate and robust in the synthetic test case. When applied to experimental BOS recordings, all methods provide similar and consistent deformation fields. As is capable of achieving a comparable or better accuracy at a fraction of the computational costs, it represents a valuable alternative to conventional post-processing techniques for BOS experiments.
- Open Access
- 4 January 2023
- Published by Springer Nature in Research Square
A lightweight convolutional neural network to reconstruct deformation in BOS recordings
We introduce a Convolutional Neural Network (CNN) that is specificallydesigned and trained to post-process recordings obtained by BackgroundOriented Schlieren (BOS), a popular technique to visualize compressibleand convective flows. To reconstruct BOS image deformation, we deviseda lightweight network (LIMA) that has comparatively fewer parameters totrain than the CNNs that have been previously proposed for optical flow.To train LIMA, we introduce a novel strategy based on the generation of synthetic images from random-irrotational deformation fields, which areintended to mimic those provided by real BOS recordings. This allows us to generate a large number of training examples at minimal compu-tational cost. To assess the accuracy of the reconstructed displacements,we consider test cases consisting of synthetic images with sinusoidal dis-placement as well as images obtained in the experimental studies of a hotplume in air and a flow past and inside a heated hollow hemisphere. By comparing the reconstructed deformation fields using the LIMA or conven-tional post-processing techniques used in Direct Image Correlation (dic)or conventional image cross-correlation, we show that LIMA is more accu-rate and robust in the synthetic test case. When applied to experimentalBOS recordings, all methods provide similar and consistent deformation fields. As LIMA is capable of achieving a comparable or better accuracyat a fraction of the computational costs, it represents a valuable alternative to conventional post-processing techniques for BOS experiments.
- 4 January 2023
- Published by Springer Nature in Research Square
Open AccessA lightweight convolutional neural network to reconstruct deformation in BOS recordings
We introduce a Convolutional Neural Network (CNN) that is specificallydesigned and trained to post-process recordings obtained by BackgroundOriented Schlieren (BOS), a popular technique to visualize compressibleand convective flows. To reconstruct BOS image deformation, we deviseda lightweight network (LIMA) that has comparatively fewer parameters totrain than the CNNs that have been previously proposed for optical flow.To train LIMA, we introduce a novel strategy based on the generation of synthetic images from random-irrotational deformation fields, which areintended to mimic those provided by real BOS recordings. This allows us to generate a large number of training examples at minimal compu-tational cost. To assess the accuracy of the reconstructed displacements,we consider test cases consisting of synthetic images with sinusoidal dis-placement as well as images obtained in the experimental studies of a hotplume in air and a flow past and inside a heated hollow hemisphere. By comparing the reconstructed deformation fields using the LIMA or conven-tional post-processing techniques used in Direct Image Correlation (dic)or conventional image cross-correlation, we show that LIMA is more accu-rate and robust in the synthetic test case. When applied to experimentalBOS recordings, all methods provide similar and consistent deformation fields. As LIMA is capable of achieving a comparable or better accuracyat a fraction of the computational costs, it represents a valuable alternative to conventional post-processing techniques for BOS experiments.