MapLUR: Exploring a new Paradigm for Estimating Air Pollution using Deep Learning on Map Images

@article{Steininger2020MapLUREA,
  title={MapLUR: Exploring a new Paradigm for Estimating Air Pollution using Deep Learning on Map Images},
  author={Michael Steininger and Konstantin Kobs and Albin Zehe and Florian Lautenschlager and Martin Becker and Andreas Hotho},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.07493}
}
Land-use regression (LUR) models are important for the assessment of air pollution concentrations in areas without measurement stations. While many such models exist, they often use manually constructed features based on restricted, locally available data. Thus, they are typically hard to reproduce and challenging to adapt to areas beyond those they have been developed for. In this paper, we advocate a paradigm shift for LUR models: We propose the Data-driven, Open, Global (DOG) paradigm that… 

Evaluating the multi-task learning approach for land use regression modelling of air pollution

This work compared prediction results from singletask and multi- task learning multilayer perceptron models on measurements taken from the OpenSense dataset and the London Atmospheric Emissions Inventory dataset to show multi-task learning with sufficient data significantly improves the performance of a LUR model.

Deep Learning for Climate Model Output Statistics

The CNN architecture ConvMOS is proposed specifically designed for reducing errors in climate model outputs and applied to the climate model REMO, showing a considerable reduction of errors and mostly improved performance compared to three commonly used MOS approaches.

Error Prediction of Air Quality at Monitoring Stations Using Random Forest in a Total Error Framework

A method that predicts the p-value of each observation as a value between 0 and 1 is proposed, which theoretically described a one-site AQ prediction based on a multi-site network using Random Forest for regression in a Total Error framework.

Data Cleaning to fine-tune a Transfer Learning approach for Air Quality Prediction

Air pollution is a serious environmental danger to people, specifically those who live in urbanised regions. Air pollution is also responsible for the climate crisis. Latest researches have shown the

Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities

This paper proposes a novel transferable traffic forecasting framework: Domain Adversarial Spatial-Temporal Network (DASTNet), which is the first to employ adversarial multi-domain adaptation for network-wide traffic forecasting problems.

Do Different Deep Metric Learning Losses Lead to Similar Learned Features?

A two-step analysis is conducted to extract and compare the learned visual features of the same model architecture trained with different loss functions and shows that some seemingly irrelevant properties can have significant influence on the resulting embedding.

Air Pollution Prediction with Multi-Modal Data and Deep Neural Networks

A novel approach evaluating four different architectures that utilize camera images to estimate the air pollution in those areas and achieves robust accuracy of up to 0.88, which is comparable to sequence models and conventional models that utilize air pollution data.

References

SHOWING 1-10 OF 73 REFERENCES

End-to-end learning for image-based air quality level estimation

An effective convolutional neural network to estimate air quality based on images by designing an ensemble CNN for air quality estimation which is expected to obtain more accurate and stable results than a single classifier.

A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN

Experiments show that the proposed DRNN framework outperforms both DFNN and GBDT, therefore validating the capacity of the proposed framework and providing useful insights for better understanding of different strategies that handle missing values.

A Comprehensive Analysis of Deep Regression

The results reinforce the hypothesis according to which, in general, a general-purpose network adequately tuned can yield results close to the state-of-the-art without having to resort to more complex and ad-hoc regression models.

Using user generated online photos to estimate and monitor air pollution in major cities

This study proposes to employ the state of the art in computer vision techniques to analyze photos that can be easily acquired from online social media and establishes the correlation between the haze level computed directly from photos with the official PM 2.5 record of the taken city at the taken time.

Exploring the Limits of Weakly Supervised Pretraining

This paper presents a unique study of transfer learning with large convolutional networks trained to predict hashtags on billions of social media images and shows improvements on several image classification and object detection tasks, and reports the highest ImageNet-1k single-crop, top-1 accuracy to date.

Hourly PM2.5 concentration forecast using stacked autoencoder model with emphasis on seasonality

Air Pollution Mapping Using Nonlinear Land Use Regression Models

The present research deals with a new development of nonlinear LUR models based on machine learning algorithms and their abilities to model the NO2 pollutant in the urban zone of Geneva.

Empirical Evaluation of Rectified Activations in Convolutional Network

The experiments suggest that incorporating a non-zero slope for negative part in rectified activation units could consistently improve the results, and are negative on the common belief that sparsity is the key of good performance in ReLU.

Striving for Simplicity: The All Convolutional Net

It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks.

Pushing the spatio-temporal resolution limit of urban air pollution maps

This paper analyzes one of the largest spatially resolved UFP data set publicly available today containing over 25 million measurements and achieves a 26% reduction in the root-mean-square error-a standard metric to evaluate the accuracy of air quality models-of pollution maps with semi-daily temporal resolution.
...