scholarly journals Deep learning for Chinese NOx emission inversion and the integration of in situ observations: a case study on the COVID-19 pandemic

2021 ◽  
Author(s):  
Tai-Long He ◽  
Dylan Jones ◽  
Kazuyuki Miyazaki ◽  
Kevin Bowman ◽  
Zhe Jiang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Reanalysis Data ◽  
Data Sets ◽  
Computationally Efficient ◽  
Transport Models ◽  
The Neural Network ◽  
In Situ Observations ◽  
Typical Variation

<p>The COVID-19 pandemic led to the lockdown of over one-third of Chinese cities in early 2020. Observations have shown significant reductions of atmospheric abundances of NO<sub>2</sub> over China during this period. This change in atmospheric NO<sub>2</sub> implies a dramatic change in emission of NO<sub>x</sub>, which provides a unique opportunity to study the response of the chemistry of the atmospheric to large reductions in anthropogenic emissions. We use a deep learning (DL) model to quantify the change in surface emissions of NO<sub>x</sub> in China that are associated with the observed changes in atmospheric NO<sub>2</sub> during the lockdown period. Compared to conventional data assimilation systems, deep neural networks are free of the potential errors associated with parameterized subgrid-scale processes. Furthermore, they are not susceptible to the chemical errors typically found in atmospheric chemical transport models. The neural-network-based approach also offers a more computationally efficient means of inverse modeling of NO<sub>x</sub> emissions at high spatial resolutions. Our DL model is trained using meteorological predictors and reanalysis data of surface NO<sub>2</sub> from 2005 to 2017. The evaluation is conducted using in-situ measurements of NO<sub>2</sub> in 2019 and 2020. The Baidu 'Qianxi' migration data sets are used to evaluate the model's performance in capturing the typical variation in Chinese NOx emissions during the Chinese New Year holidays. The TROPOMI-derived TCR-2 chemical reanalysis is used to evaluate the DL analysis in 2020. We show that the DL-based approach is able to better reproduce the variation in anthropogenic NO<sub>x</sub> emissions and capture the reduction in Chinese NO<sub>x</sub> emissions during the period of the COVID-19 pandemic.</p>

Pattern-Based Deep Learning Method to Extract Information from the Log Dataset

2021 ◽  
pp. 2150296
Author(s):  
Xi Li ◽  
Ting Wang ◽  
Shexiong Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Data Sets ◽  
Learning Method ◽  
Statistical Features ◽  
Log Data ◽  
The Neural Network ◽  
Testing Data ◽  
Extract Information

It draws researchers’ attentions how to make use of the log data effectively without paying much for storing them. In this paper, we propose pattern-based deep learning method to extract the features from log datasets and to facilitate its further use at the reasonable expense of the storage performances. By taking the advantages of the neural network and thoughts to combine statistical features with experts’ knowledge, there are satisfactory results in the experiments on some specified datasets and on the routine systems that our group maintains. Processed on testing data sets, the model is 5%, at least, more likely to outperform its competitors in accuracy perspective. More importantly, its schema unveils a new way to mingle experts’ experiences with statistical log parser.

scholarly journals The extreme runoff index for flood early warning in Europe

2014 ◽  
Vol 14 (6) ◽  
pp. 1505-1515 ◽  
Author(s):  
L. Alfieri ◽  
F. Pappenberger ◽  
F. Wetterhall
Keyword(s):  
Early Warning ◽  
Input Data ◽  
Weather Forecasting ◽  
Spatial Inhomogeneity ◽  
Optimal Timing ◽  
Numerical Predictions ◽  
In Situ Observations

Abstract. Systems for the early detection of floods over continental and global domains have a key role in providing a quick overview of areas at risk, raise the awareness and prompt higher detail analyses as the events approach. However, the reliability of these systems is prone to spatial inhomogeneity, depending on the quality of the underlying input data and local calibration. This work proposes a simple approach for flood early warning based on ensemble numerical predictions of surface runoff provided by weather forecasting centers. The system is based on a novel indicator, referred to as an extreme runoff index (ERI), which is calculated from the input data through a statistical analysis. It is designed for use in large or poorly gauged domains, as no local knowledge or in situ observations are needed for its setup. Daily runs over 32 months are evaluated against calibrated hydrological simulations for all of Europe. Results show skillful flood early warning capabilities up to a 10-day lead time. A dedicated analysis is performed to investigate the optimal timing of forecasts to maximize the detection of extreme events. A case study for the central European floods of June 2013 is presented and forecasts are compared to the output of a hydro-meteorological ensemble model.

Spatial variation and temporal trends of solar radiation over Morocco based on ground observations and CMSAF data records.

2020 ◽  
Author(s):  
Sara Moutia
Keyword(s):  
Solar Radiation ◽  
Satellite Data ◽  
Sunshine Duration ◽  
Temporal Trends ◽  
General Tendency ◽  
Data Sets ◽  
Alternative Source ◽  
In Situ Observations ◽  
Source Of Information

<p>The main advantage of remote sensing products is that they are reasonably good in terms of temporal and special coverage, and they are available in a near real time. Therefore, an understanding of the strengths and weaknesses of satellite data is useful to choose it as an alternative source of information with acceptable accuracy.  On the first hand, this study assesses an Inter-comparison between CMSAF Sunshine Duration (SD) data records and ground observations of 30 data sets from 1983 to 2015. the correlation is very significant and the satellite data fits very closely to in situ observations. On the other hand, trend analysis is applied to SD and Solar Incoming Direct radiation (SID) data, a number of stations show a statistically significant decreasing trend in SD and also SID shows a decreasing trend over Morocco in most of regions especially in summer. The results indicate a general tendency of decrease in incoming solar radiation mostly during summer which could be of some concern for solar energy.</p>

scholarly journals An Intercomparison of GPS RO Retrievals with Colocated Analysis and In Situ Observations within Tropical Cyclones

2010 ◽  
Vol 2010 ◽  
pp. 1-10 ◽  
Author(s):  
Henry R. Winterbottom ◽  
Qingnong Xiao
Keyword(s):  
Tropical Cyclones ◽  
Global Positioning System ◽  
Global Analysis ◽  
Reanalysis Data ◽  
Satellite Mission ◽  
Data Set ◽  
Global Positioning ◽  
In Situ Observations ◽  
Atmospheric State

Observations from four Global Position System (GPS) Radio Occultation (RO) missions: Global Positioning System/Meteorology, CHAallenging Minisatellite Payload, Satellite de Aplicaciones Cientificas-C, and Constellation Observing System for Meteorology, Ionosphere and Climate and Taiwan's FORMOsa SATellite Mission #3 (COSMIC/FORMOSAT-3) are collected within a 600 km radius and ±180 minute temporal window of all observed tropical cyclones (TCs) from 1995 to 2006 that were recorded in the global hurricane best-track reanalysis data set (Jarvinen et al. (1984); Davis et al. (1984)). A composite analysis of tropical cyclone radial mean temperature and water vapor profiles is carried out using the GPS RO retrievals which are colocated with global analysis profiles and available in situ radiosonde observations. The differences between the respective observations and analysis profiles are quantified and the preliminary results show that the observations collected within TCs correspond favorably with both the analysis and radiosonde profiles which are colocated. It is concluded that GPS RO observations will contribute significantly to the understanding and modeling of TC structures, especially those related to vertical variability of the atmospheric state within TCs.

Variational Data Assimilation for Renewable Wind Energy Predictions: China Inner Mongolia Case Study

2011 ◽  
Vol 383-390 ◽  
pp. 3685-3689 ◽  
Author(s):  
Hai Feng Wang ◽  
Wen Jun Yin ◽  
Meng Zhang ◽  
Jin Dong
Keyword(s):  
Data Assimilation ◽  
Inner Mongolia ◽  
Forecast Error ◽  
Scale Model ◽  
Initial Condition ◽  
Short Term ◽  
In Situ Observations ◽  
Meso Scale

Advanced data assimilation method is used for the short-term wind power forecasting based on a meso-scale model. Considerable forecast error reduction is concluded from a case study in China, where a better resolved high-resolution initial condition is introduced via assimilating various in-situ observations.

scholarly journals SEA-LEVEL PRESSURE TRENDS IN THE SOUTHERN OCEAN AND ANTARCTICA FROM REANALYSIS AND IN SITU DATA

2021 ◽  
Vol 49 (4) ◽  
pp. 63-85
Author(s):  
P. Yu. Romanov ◽  
N. A. Romanova
Keyword(s):  
Time Series ◽  
Sea Level ◽  
Reanalysis Data ◽  
Environmental Research ◽  
Sea Level Pressure ◽  
Mean Values ◽  
Level Pressure ◽  
High Latitude Region ◽  
In Situ Observations

Trends in the mean sea-level pressure (SLP) in Antarctica in the last four decades (1980– 2020) have been examined using in situ observations and reanalysis data. The analysis involved time series of monthly mean, season-mean and yearly-mean values of the SLP derived from four reanalysis datasets, NCEP/NCAR, ERA5, JRA55, MERRA2, and from surface observations acquired from the Reference Antarctic Data for Environmental Research (READER) dataset. With this data we have evaluated the trends, characterized their seasonal peculiarities and variation across the high-latitude region of the Southern Hemisphere. The results of the analysis confirmed the dominance of decreasing trends in the annual mean SLP in Antarctica. Larger negative trends were found in the Western Antarctica with the most pronounced pressure drop in the South Pacific. The long-term decrease in the annual mean SLP in Antarctica was due to strong negative pressure trends in the austral summer and fall season whereas in winter and in spring the trends turn to mixed and mostly positive. The comparison of multiyear time series of SLP reanalysis data with in situ observations at Antarctic stations revealed a considerable overestimate of negative SLP trends in the NCEP/NCAR dataset. Among the four examined reanalysis datasets, ERA5 provided the best agreement with the station data on the annual mean and monthly mean SLP trend values.

Sign in / Sign up

Export Citation Format

Share Document