Inferring dissipation maps from videos using convolutional neural networks
In the study of living organisms at mesoscopic scales, attaining a measure of dissipation or entropy production (EP) is essential to gain an understanding of their nonequilibrium dynamics. However, when tracking the relevant variables is impractical, it is challenging to figure out where and to what...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Physical Society
2022-08-01
|
| Series: | Physical Review Research |
| Online Access: | http://doi.org/10.1103/PhysRevResearch.4.033094 |
| _version_ | 1797210671684780032 |
|---|---|
| author | Youngkyoung Bae Dong-Kyum Kim Hawoong Jeong |
| author_facet | Youngkyoung Bae Dong-Kyum Kim Hawoong Jeong |
| author_sort | Youngkyoung Bae |
| collection | DOAJ |
| description | In the study of living organisms at mesoscopic scales, attaining a measure of dissipation or entropy production (EP) is essential to gain an understanding of their nonequilibrium dynamics. However, when tracking the relevant variables is impractical, it is challenging to figure out where and to what extent dissipation occurs from recorded time-series images from experiments. In this paper we develop an estimator that can, without detailed knowledge of the given systems, quantify the stochastic EP and produce a spatiotemporal pattern of the EP (or dissipation map) from videos through an unsupervised learning algorithm. Applying a convolutional neural network (CNN), our estimator allows us to visualize where the dissipation occurs as well as its time evolution in a video by looking at an attention map of the CNN's last layer. We demonstrate that our estimator accurately measures the stochastic EP and provides a locally heterogeneous dissipation map, which is mainly concentrated in the origins of a nonequilibrium state, from generated Brownian videos of various models. We further confirm high performance even with noisy, low-spatial-resolution data and partially observed situations. Our method will provide a practical way to obtain dissipation maps and ultimately contribute to uncovering the source and the dissipation mechanisms of complex nonequilibrium phenomena. |
| first_indexed | 2024-04-24T10:14:18Z |
| format | Article |
| id | doaj.art-b99fcd08195a49e7946a9c7933472bc5 |
| institution | Directory Open Access Journal |
| issn | 2643-1564 |
| language | English |
| last_indexed | 2024-04-24T10:14:18Z |
| publishDate | 2022-08-01 |
| publisher | American Physical Society |
| record_format | Article |
| series | Physical Review Research |
| spelling | doaj.art-b99fcd08195a49e7946a9c7933472bc52024-04-12T17:23:20ZengAmerican Physical SocietyPhysical Review Research2643-15642022-08-014303309410.1103/PhysRevResearch.4.033094Inferring dissipation maps from videos using convolutional neural networksYoungkyoung BaeDong-Kyum KimHawoong JeongIn the study of living organisms at mesoscopic scales, attaining a measure of dissipation or entropy production (EP) is essential to gain an understanding of their nonequilibrium dynamics. However, when tracking the relevant variables is impractical, it is challenging to figure out where and to what extent dissipation occurs from recorded time-series images from experiments. In this paper we develop an estimator that can, without detailed knowledge of the given systems, quantify the stochastic EP and produce a spatiotemporal pattern of the EP (or dissipation map) from videos through an unsupervised learning algorithm. Applying a convolutional neural network (CNN), our estimator allows us to visualize where the dissipation occurs as well as its time evolution in a video by looking at an attention map of the CNN's last layer. We demonstrate that our estimator accurately measures the stochastic EP and provides a locally heterogeneous dissipation map, which is mainly concentrated in the origins of a nonequilibrium state, from generated Brownian videos of various models. We further confirm high performance even with noisy, low-spatial-resolution data and partially observed situations. Our method will provide a practical way to obtain dissipation maps and ultimately contribute to uncovering the source and the dissipation mechanisms of complex nonequilibrium phenomena.http://doi.org/10.1103/PhysRevResearch.4.033094 |
| spellingShingle | Youngkyoung Bae Dong-Kyum Kim Hawoong Jeong Inferring dissipation maps from videos using convolutional neural networks Physical Review Research |
| title | Inferring dissipation maps from videos using convolutional neural networks |
| title_full | Inferring dissipation maps from videos using convolutional neural networks |
| title_fullStr | Inferring dissipation maps from videos using convolutional neural networks |
| title_full_unstemmed | Inferring dissipation maps from videos using convolutional neural networks |
| title_short | Inferring dissipation maps from videos using convolutional neural networks |
| title_sort | inferring dissipation maps from videos using convolutional neural networks |
| url | http://doi.org/10.1103/PhysRevResearch.4.033094 |
| work_keys_str_mv | AT youngkyoungbae inferringdissipationmapsfromvideosusingconvolutionalneuralnetworks AT dongkyumkim inferringdissipationmapsfromvideosusingconvolutionalneuralnetworks AT hawoongjeong inferringdissipationmapsfromvideosusingconvolutionalneuralnetworks |