RECORD
Adversarially trained LSTMs on reduced order models of urban air pollution simulations
Machine Learning · Submitted 5 Jan 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Once trained, the adversarially trained LSTM outperforms a LSTM trained in a classical way.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
This paper presents an approach to improve computational fluid dynamics simulations forecasts of air pollution using deep learning. Our method, which integrates Principal Components Analysis (PCA) and adversarial training, is a way to improve the forecast skill of reduced order models obtained from the original model solution. Once the reduced-order model (ROM) is obtained via PCA, a Long Short-Term Memory network (LSTM) is adversarially trained on the ROM to make forecasts. Once trained, the adversarially trained LSTM outperforms a LSTM trained in a classical way. The study area is in London, including velocities and a concentration tracer that replicates a busy traffic junction. This adversarially trained LSTM-based approach is used on the ROM in order to produce faster forecasts of the air pollution tracer.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | This paper presents an approach to improve computational fluid dynamics simulations forecasts of air pollution using deep learning. | contribution 0.97 | 0.79 | 0.12 | asserted 0.99 |
| s1 | Our method, which integrates Principal Components Analysis (PCA) and adversarial training, is a way to improve the forecast skill of reduced order models obtained from the original model solution. | contribution 0.62 | 0.89 | 0.20 | asserted 0.99 |
| s2 | Once the reduced-order model (ROM) is obtained via PCA, a Long Short-Term Memory network (LSTM) is adversarially trained on the ROM to make forecasts. | method 1.00 | 0.86 | 0.07 | asserted 0.99 |
| s3 | Once trained, the adversarially trained LSTM outperforms a LSTM trained in a classical way. | result 1.00 | 0.90 | 0.59 | asserted 1.00 |
| s4 | The study area is in London, including velocities and a concentration tracer that replicates a busy traffic junction. | method 0.86 | 0.69 | 0.02 | asserted 0.99 |
| s5 | This adversarially trained LSTM-based approach is used on the ROM in order to produce faster forecasts of the air pollution tracer. | method 0.57 | 0.85 | 0.12 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
This paper presents an approach to improve computational fluid dynamics simulations forecasts of air pollution using deep learning. Our method, which integrates Principal Components Analysis (PCA) and adversarial training, is a way to improve the forecast skill of reduced order models obtained from the original model solution. Once the reduced-order model (ROM) is obtained via PCA, a Long Short-Term Memory network (LSTM) is adversarially trained on the ROM to make forecasts. Once trained, the adversarially trained LSTM outperforms a LSTM trained in a classical way. The study area is in London, including velocities and a concentration tracer that replicates a busy traffic junction. This adversarially trained LSTM-based approach is used on the ROM in order to produce faster forecasts of the air pollution tracer.
Human review
How the literature uses it
4 arXiv papers cite this in 6 sentences
Papers citing it · 3 sentences without a confident label
Compares with it 1 paper
-
This approach outperforms [ref] in terms of data compression and [ref] in terms of forecast length.
Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations · Results and discussion · 1.00
Cites it as background 2 papers
-
Non-intrusive ROMs and RNNs have been used together in previous studies, e.g. [ref] where the surrogate forecast systems can easily reproduce a time-step in the future accurately.
Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations · Introduction · 0.81
-
Recently, non-intrusive reduced-order methods (sometimes referred to as model identification methods [ref] or described by the more general term of digital twins [ref] ) have taken advantage of machine learning techniques, using multi-layer perceptrons [ref] , cluster analysis [ref] , LSTMs [ref] and Gaussian Process Regression [ref] .
Digital twins based on bidirectional LSTM and GAN for modelling the COVID-19 pandemic · Introduction · 0.95
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.