Dense Forecasting of Wildfire Smoke Particulate Matter Using Sparsity Invariant Convolutional Neural Networks

• URL: http://arxiv.org/abs/2009.11362v1
• Date: Wed, 23 Sep 2020 20:13:35 GMT
• Title: Dense Forecasting of Wildfire Smoke Particulate Matter Using Sparsity Invariant Convolutional Neural Networks
• Authors: Renhao Wang, Ashutosh Bhudia, Brandon Dos Remedios, Minnie Teng, Raymond Ng
• Abstract summary: Forecasts of fine particulate matter (PM 2.5) from wildfire smoke are crucial to safeguarding public cardiopulmonary health. Existing forecasting systems are trained on sparse and inaccurate ground truths, and do not take sufficient advantage of important spatial inductive biases. We present a convolutional neural network which preserves sparsity invariance throughout, and leverages multitask learning to perform dense forecasts of PM 2.5values.
• Score: 2.2835610890984164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate forecasts of fine particulate matter (PM 2.5) from wildfire smoke are crucial to safeguarding cardiopulmonary public health. Existing forecasting systems are trained on sparse and inaccurate ground truths, and do not take sufficient advantage of important spatial inductive biases. In this work, we present a convolutional neural network which preserves sparsity invariance throughout, and leverages multitask learning to perform dense forecasts of PM 2.5values. We demonstrate that our model outperforms two existing smoke forecasting systems during the 2018 and 2019 wildfire season in British Columbia, Canada, predicting PM 2.5 at a grid resolution of 10 km, 24 hours in advance with high fidelity. Most interestingly, our model also generalizes to meaningful smoke dispersion patterns despite training with irregularly distributed ground truth PM 2.5 values available in only 0.5% of grid cells.

Related papers

• Advancing operational PM2.5 forecasting with dual deep neural networks (D-DNet) [0.3848364262836075]
  We propose a dual deep neural network (D-DNet) prediction and data assimilation system that efficiently integrates real-time observations. D-DNet excels in global operational forecasting for PM2.5 and AOD550, maintaining consistent accuracy throughout the entire year of 2019. It demonstrates notably higher efficiency than the Copernicus Atmosphere Monitoring Service (CAMS) 4D-Var operational forecasting system.
  arXiv  Detail & Related papers  (2024-06-27T13:14:20Z)
• Back to the Future: GNN-based NO$_2$ Forecasting via Future Covariates [49.93577170464313]
  We deal with air quality observations in a city-wide network of ground monitoring stations. We propose a conditioning block that embeds past and future covariates into the current observations. We find that conditioning on future weather information has a greater impact than considering past traffic conditions.
  arXiv  Detail & Related papers  (2024-04-08T09:13:16Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Deep Learning for Day Forecasts from Sparse Observations [60.041805328514876]
  Deep neural networks offer an alternative paradigm for modeling weather conditions. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 has a high temporal and spatial resolution, respectively, up to 2 minutes and 1 km as well as a low operational latency.
  arXiv  Detail & Related papers  (2023-06-06T07:07:54Z)
• SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting [18.464408838231957]
  We develop a data-driven model SwinRDM which integrates an improved version of SwinRNN with a diffusion model. SwinRDM performs predictions at 0.25-degree resolution and achieves superior forecasting accuracy to IFS.
  arXiv  Detail & Related papers  (2023-06-05T05:11:03Z)
• Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data [86.1450118623908]
  We investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs) We forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future. Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days.
  arXiv  Detail & Related papers  (2022-02-10T11:37:00Z)
• Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting [98.57851612518758]
  Probabilistic time series forecasting involves estimating the distribution of future based on its history. We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks. We show in experiments that our model produces accurate and sharp probabilistic forecasts.
  arXiv  Detail & Related papers  (2021-01-31T06:49:33Z)
• A Novel Prediction Approach for Exploring PM2.5 Spatiotemporal Propagation Based on Convolutional Recursive Neural Networks [7.131106953836335]
  The prediction system of PM2.5 propagation provides more detailed and accurate information as an early warning system to reduce health impacts on the community. This research was conducted by using dataset of air quality monitoring systems in Taiwan. In general, the model is able to provide accurate predictive results by considering the bonds among measurement nodes in both spatially and temporally.
  arXiv  Detail & Related papers  (2021-01-15T17:00:04Z)
• A Novel Hybrid Framework for Hourly PM2.5 Concentration Forecasting Using CEEMDAN and Deep Temporal Convolutional Neural Network [2.2175470459999636]
  This study develops a novel hybrid forecasting model based on complete ensemble empirical mode decomposition with adaptive noise. The forecasting accuracy of the proposed CEEMDAN-DeepTCN model is verified to be the highest when compared with the time series model, artificial neural network, and the popular deep learning models. The new model has improved the capability to model the PM2.5-related factor data patterns, and can be used as a promising tool for forecasting PM2.5 concentrations.
  arXiv  Detail & Related papers  (2020-12-07T15:22:01Z)
• A generative adversarial network approach to (ensemble) weather prediction [91.3755431537592]
  We use a conditional deep convolutional generative adversarial network to predict the geopotential height of the 500 hPa pressure level, the two-meter temperature and the total precipitation for the next 24 hours over Europe. The proposed models are trained on 4 years of ERA5 reanalysis data from 2015-2018 with the goal to predict the associated meteorological fields in 2019.
  arXiv  Detail & Related papers  (2020-06-13T20:53:17Z)
• PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting [15.587337304295819]
  We develop a novel graph based model, PM2.5-GNN, being capable of capturing long-term dependencies. The proposed model has been deployed online to provide free forecasting service.
  arXiv  Detail & Related papers  (2020-02-10T03:33:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.