Importance of satellite observations for high-resolution mapping of near-surface NO2 by machine learning

Nitrogen oxides (NOx&#160; = NO+ NO2) are harmful to human health and are precursors of other key air pollutants like ozone (O3) and particulate matter (PM). Since the lifetime of NOx is short and its main sources are anthropogenic emissions like fuel combustion from traffic and industry, near-surface NOx concentrations are highly variable in space and time. To assess the impact of NO2 on public health, maps of high spatial and temporal resolution are critical. In this study, we present hourly near-surface NO2 concentrations at 100 m resolution for Switzerland and northern Italy that are produced using machine learning, specifically an extreme gradient-boosted tree ensemble. The model was trained with in situ observations from European Air Quality e-Reporting data repositories (Airbase). Satellite NO2 observations from the TROPospheric Monitoring Instrument (TROPOMI) were compiled together with land use data, meteorological data and topography as covariates. Evaluation against in situ observations not used for the training shows that the dynamic maps produced in this study reproduce the spatio-temporal variation in near-surface NO2 concentrations with high accuracy (R2 = 0.59, MAE = 7.69 &#181;g/m3). In addition, we demonstrate how public health studies can utilize such high-resolution maps for unbiased assessment of population exposure that can account for home addresses and mobility of individuals. Comparing the relative importance of the different covariates based on two different metrics, total information gain and averaged local feature importance, show a leading contribution of the TROPOMI observations despite their rather coarse resolution (3.5 km &#215; 5.5 km) and daily update. TROPOMI NO2 observations were particularly important for the quality of the NO2 maps during periods of unusual NO2 reductions (e.g., during COVID19 lockdown) and when detailed emission-related covariates like traffic density, that may not be available in other regions of the globe, were not included in the model. Since all data used in our study are publicly available, our approach can be readily extended to other regions in Europe or applied worldwide.

Download Full-text

Augmenting biologging with supervised machine learning to studyin situbehavior of the medusaChrysaora fuscescens

10.1101/657684 ◽

2019 ◽

Author(s):

Clara Fannjiang ◽

T. Aran Mooney ◽

Seth Cones ◽

David Mann ◽

K. Alex Shorter ◽

...

Keyword(s):

Machine Learning ◽

High Resolution ◽

Laboratory Data ◽

Supervised Machine Learning ◽

Motion Sensors ◽

Fine Scale ◽

Video Footage ◽

Research Findings ◽

Summary Statement

AbstractZooplankton occupy critical roles in marine ecosystems, yet their fine-scale behavior remains poorly understood due to the difficulty of studying individualsin situ. Here we combine biologging with supervised machine learning (ML) to demonstrate a pipeline for studyingin situbehavior of larger zooplankton such as jellyfish. We deployed the ITAG, a biologging package with high-resolution motion sensors designed for soft-bodied invertebrates, on 8Chrysaora fuscescensin Monterey Bay, using the tether method for retrieval. Using simultaneous video footage of the tagged jellyfish, we develop ML methods to 1) identify periods of tag data corrupted by the tether method, which may have compromised prior research findings, and 2) classify jellyfish behaviors. Our tools yield characterizations of fine-scale jellyfish activity and orientation over long durations, and provide evidence that developing behavioral classifiers onin siturather than laboratory data is essential.Summary StatementHigh-resolution motion sensors paired with supervised machine learning can be used to infer fine-scalein situbehavior of zooplankton for long durations.

Download Full-text

The impact of near-surface soil moisture assimilation at subseasonal, seasonal, and inter-annual timescales

Hydrology and Earth System Sciences ◽

10.5194/hess-19-4831-2015 ◽

2015 ◽

Vol 19 (12) ◽

pp. 4831-4844 ◽

Cited By ~ 19

Author(s):

C. Draper ◽

R. Reichle

Keyword(s):

Soil Moisture ◽

Data Assimilation ◽

Surface Soil ◽

Root Zone ◽

Surface Model ◽

Surface Soil Moisture ◽

Near Surface ◽

In Situ Observations ◽

The Impact

Abstract. A 9 year record of Advanced Microwave Scanning Radiometer – Earth Observing System (AMSR-E) soil moisture retrievals are assimilated into the Catchment land surface model at four locations in the US. The assimilation is evaluated using the unbiased mean square error (ubMSE) relative to watershed-scale in situ observations, with the ubMSE separated into contributions from the subseasonal (SMshort), mean seasonal (SMseas), and inter-annual (SMlong) soil moisture dynamics. For near-surface soil moisture, the average ubMSE for Catchment without assimilation was (1.8 × 10−3 m3 m−3)2, of which 19 % was in SMlong, 26 % in SMseas, and 55 % in SMshort. The AMSR-E assimilation significantly reduced the total ubMSE at every site, with an average reduction of 33 %. Of this ubMSE reduction, 37 % occurred in SMlong, 24 % in SMseas, and 38 % in SMshort. For root-zone soil moisture, in situ observations were available at one site only, and the near-surface and root-zone results were very similar at this site. These results suggest that, in addition to the well-reported improvements in SMshort, assimilating a sufficiently long soil moisture data record can also improve the model representation of important long-term events, such as droughts. The improved agreement between the modeled and in situ SMseas is harder to interpret, given that mean seasonal cycle errors are systematic, and systematic errors are not typically targeted by (bias-blind) data assimilation. Finally, the use of 1-year subsets of the AMSR-E and Catchment soil moisture for estimating the observation-bias correction (rescaling) parameters is investigated. It is concluded that when only 1 year of data are available, the associated uncertainty in the rescaling parameters should not greatly reduce the average benefit gained from data assimilation, although locally and in extreme years there is a risk of increased errors.

Download Full-text

Effects of high spatial and temporal resolution Earth observations on simulated hydrometeorological variables in a cropland (southwestern France)

Hydrology and Earth System Sciences ◽

10.5194/hess-21-5693-2017 ◽

2017 ◽

Vol 21 (11) ◽

pp. 5693-5708 ◽

Cited By ~ 3

Author(s):

Jordi Etchanchu ◽

Vincent Rivalland ◽

Simon Gascoin ◽

Jérôme Cros ◽

Tiphaine Tallec ◽

...

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Land Surface ◽

Agricultural Landscapes ◽

Surface Model ◽

Spatial And Temporal Variability ◽

Area Index ◽

The Impact ◽

Sentinel 2

Abstract. Agricultural landscapes are often constituted by a patchwork of crop fields whose seasonal evolution is dependent on specific crop rotation patterns and phenologies. This temporal and spatial heterogeneity affects surface hydrometeorological processes and must be taken into account in simulations of land surface and distributed hydrological models. The Sentinel-2 mission allows for the monitoring of land cover and vegetation dynamics at unprecedented spatial resolutions and revisit frequencies (20 m and 5 days, respectively) that are fully compatible with such heterogeneous agricultural landscapes. Here, we evaluate the impact of Sentinel-2-like remote sensing data on the simulation of surface water and energy fluxes via the Interactions between the Surface Biosphere Atmosphere (ISBA) land surface model included in the EXternalized SURface (SURFEX) modeling platform. The study focuses on the effect of the leaf area index (LAI) spatial and temporal variability on these fluxes. We compare the use of the LAI climatology from ECOCLIMAP-II, used by default in SURFEX-ISBA, and time series of LAI derived from the high-resolution Formosat-2 satellite data (8 m). The study area is an agricultural zone in southwestern France covering 576 km2 (24 km  ×  24 km). An innovative plot-scale approach is used, in which each computational unit has a homogeneous vegetation type. Evaluation of the simulations quality is done by comparing model outputs with in situ eddy covariance measurements of latent heat flux (LE). Our results show that the use of LAI derived from high-resolution remote sensing significantly improves simulated evapotranspiration with respect to ECOCLIMAP-II, especially when the surface is covered with summer crops. The comparison with in situ measurements shows an improvement of roughly 0.3 in the correlation coefficient and a decrease of around 30 % of the root mean square error (RMSE) in the simulated evapotranspiration. This finding is attributable to a better description of LAI evolution processes with Formosat-2 data, which further modify soil water content and drainage of soil reservoirs. Effects on annual drainage patterns remain small but significant, i.e., an increase roughly equivalent to 4 % of annual precipitation levels with simulations using Formosat-2 data in comparison to the reference simulation values. This study illustrates the potential for the Sentinel-2 mission to better represent effects of crop management on water budgeting for large, anthropized river basins.

Download Full-text

Exploring the use of machine-learning techniques to integrate ground- and remote sensing-based observations for efficient near-surface soil moisture mapping

10.5194/egusphere-egu2020-9092 ◽

2020 ◽

Author(s):

Sarah Schönbrodt-Stitt ◽

Paolo Nasta ◽

Nima Ahmadian ◽

Markus Kurtenbach ◽

Christopher Conrad ◽

...

Keyword(s):

Machine Learning ◽

Soil Moisture ◽

Spatial Resolution ◽

Surface Soil ◽

Bare Soil ◽

Small Scale ◽

Surface Soil Moisture ◽

Near Surface ◽

Campania Region

Mapping near-surface soil moisture (&#952;) is of tremendous relevance for a broad range of environment-related disciplines and meteorological, ecological, hydrological and agricultural applications. Globally available products offer the opportunity to address &#952; in large-scale modelling with coarse spatial resolution such as at the landscape level. However, &#952; estimation at higher spatial resolution is of vital importance for many small-scale applications. Therefore, we focus our study on a small-scale catchment (MFC2) belonging to the &#8220;Alento&#8221; hydrological observatory, located in southern Italy (Campania Region). The goal of this study is to develop new machine-learning approaches to estimate high grid-resolution (about 17 m cell size) &#952; maps from mainly backscatter measurements retrieved from C-band Synthetic Aperture Radar (SAR) based on Sentinel-1 (S1) images and from gridded terrain attributes. Thus, a workflow comprising a total of 48 SAR-based &#952; patterns estimated for 24 satellite overpass dates (revisit time of 6 days) each with ascendant and descendent orbits will be presented. To enable for the mapping, SAR-based &#952; data was calibrated with in-situ measurements carried out with a portable device during eight measurement campaigns at time of satellite overpasses (four overpass days in total with each ascendant and descendent satellite overpasses per day in November 2018). After the calibration procedure, data validation was executed from November 10, 2018 till March 28, 2019 by using two stationary sensors monitoring &#952; at high-temporal (1-min recording time). The specific sensor locations reflected two contrasting field conditions, one bare soil plot (frequently kept clear, without disturbance of vegetation cover) and one non-bare soil plot (real-world condition). Point-scale ground observations of &#952; were compared to pixel-scale (17 m &#215; 17 m), SAR-based &#952; estimated for those pixels corresponding to the specific positions of the stationary sensors. Mapping performance was estimated through the root mean squared error (RMSE). For a short-term time series of &#952; (Nov 2018) integrating 136 in situ, sensor-based &#952; (&#952;insitu) and 74 gravimetric-based &#952; (&#952;gravimetric) measurements during a total of eight S1 overpasses, mapping performance already proved to be satisfactory with RMSE=0.039 m&#179;m-&#179; and R&#178;=0.92, respectively with RMSE=0.041 m&#179;m-&#179; and R&#178;=0.91. First results further reveal that estimated satellite-based &#952; patterns respond to the evolution of rainfall. With our workflow developed and results, we intend to contribute to improved environmental risk assessment by assimilating the results into hydrological models (e.g., HydroGeoSphere), and to support future studies on combined ground-based and SAR-based &#952; retrieval for forested land (future missions operating at larger wavelengths e.g. NISARL-band, Biomass P-band sensors).

Download Full-text

The effect of climate change and emission scenarios on ozone concentrations over Belgium: a high-resolution model study for policy support

Atmospheric Chemistry and Physics ◽

10.5194/acp-14-5893-2014 ◽

2014 ◽

Vol 14 (12) ◽

pp. 5893-5904 ◽

Cited By ~ 7

Author(s):

D. Lauwaet ◽

P. Viaene ◽

E. Brisson ◽

N.P.M. van Lipzig ◽

T. van Noije ◽

...

Keyword(s):

Climate Change ◽

Air Quality ◽

High Resolution ◽

Emission Scenario ◽

Emission Scenarios ◽

Near Surface ◽

Study Results ◽

The Impact ◽

Near Future ◽

Surface O3

Abstract. Belgium is one of the areas within Europe experiencing the highest levels of air pollution. A high-resolution (3 km) modelling experiment is employed to provide guidance to policymakers about expected air quality changes in the near future (2026–2035). The regional air quality model AURORA (Air quality modelling in Urban Regions using an Optimal Resolution Approach), driven by output from a regional climate model, is used to simulate several 10-year time slices to investigate the impact of climatic changes and different emission scenarios on near-surface O3 concentrations, one of the key indices for air quality. Evaluation of the model against measurements from 34 observation stations shows that the AURORA model is capable of reproducing 10-year mean concentrations, daily cycles and spatial patterns. The results for the Representative Concentration Pathways (RCP)4.5 emission scenario indicate that the mean surface O3 concentrations are expected to increase significantly in the near future due to less O3 titration by reduced NOx emissions. Applying an alternative emission scenario for Europe is found to have only a minor impact on the overall concentrations, which are dominated by the background changes. Climate change alone has a much smaller effect on the near-surface O3 concentrations over Belgium than the projected emission changes. The very high horizontal resolution that is used in this study results in much improved spatial correlations and simulated peak concentrations compared to a standard 25 km simulation. An analysis of the number of peak episodes during summer revealed that the emission reductions in RCP4.5 result in a 25% decrease of these peak episodes.

Download Full-text

Analysis of the Impact of Sustained Load and Temperature on the Performance of the Electromechanical Impedance Technique through Multilevel Machine Learning and FBG Sensors

Sensors ◽

10.3390/s21175755 ◽

2021 ◽

Vol 21 (17) ◽

pp. 5755

Author(s):

Ricardo Perera ◽

Lluis Torres ◽

Francisco J. Díaz ◽

Cristina Barris ◽

Marta Baena

Keyword(s):

Machine Learning ◽

Mechanical Performance ◽

Mechanical Impedance ◽

Machine Learning Techniques ◽

Sustained Load ◽

False Alarms ◽

Engineering Structures ◽

Near Surface ◽

Electromechanical Impedance ◽

The Impact

The electro-mechanical impedance (EMI) technique has been applied successfully to detect minor damage in engineering structures including reinforced concrete (RC). However, in the presence of temperature variations, it can cause false alarms in structural health monitoring (SHM) applications. This paper has developed an innovative approach that integrates the EMI methodology with multilevel hierarchical machine learning techniques and the use of fiber Bragg grating (FBG) temperature and strain sensors to evaluate the mechanical performance of RC beams strengthened with near surface mounted (NSM)-fiber reinforced polymer (FRP) under sustained load and varied temperatures. This problem is a real challenge since the bond behavior at the concrete–FRP interface plays a key role in the performance of this type of structure, and additionally, its failure occurs in a brittle and sudden way. The method was validated in a specimen tested over a period of 1.5 years under different conditions of sustained load and temperature. The analysis of the experimental results in an especially complex problem with the proposed approach demonstrated its effectiveness as an SHM method in a combined EMI–FBG framework.

Download Full-text

Assessing the efficiency of a “buried wall” barrier in the establishment of near-surface long-term storage and disposal facilities for RW

Radioactive waste ◽

10.25283/2587-9707-2021-1-96-105 ◽

2021 ◽

Vol 14 (1) ◽

pp. 96-105

Author(s):

V. V. Suskin ◽

◽

I. V. Kapyrin ◽

F. V. Grigorev ◽

◽

...

Keyword(s):

Near Surface ◽

Transfer Processes ◽

Long Term Storage ◽

Mass Transfer Processes ◽

High Degree ◽

The Impact ◽

Term Storage

The article evaluates the impact of a “buried wall” barrier on the long-term safety during the long-term storage1 or in-situ disposal of nuclear legacy facilities, in particular, industrial reservoirs, as well as during the development of near-surface disposal facilities for radioactive waste (RWDF). For assessment purposes, filtration and mass transfer processes have been numerically modelled in the GeRa code based on a case study of a reference near-surface facility. The study explores in which way the available covering screen affects the dynamics of contaminant spread. It evaluates the sensitivity of the results to the dispersion parameter commonly characterized by a high degree of uncertainty.

Download Full-text

Closing the gap on institutional delivery in northern India: a case study of how integrated machine learning approaches can enable precision public health

BMJ Global Health ◽

10.1136/bmjgh-2020-002340 ◽

2020 ◽

Vol 5 (10) ◽

pp. e002340

Author(s):

Vincent S Huang ◽

Kasey Morris ◽

Mokshada Jain ◽

Banadakoppa Manjappa Ramesh ◽

Hannah Kemp ◽

...

Keyword(s):

Public Health ◽

Machine Learning ◽

Financial Incentives ◽

Large Scale ◽

Institutional Delivery ◽

Uttar Pradesh ◽

Limited Resources ◽

Precision Public Health ◽

The Impact ◽

Delivery Location

IntroductionMeeting ambitious global health goals with limited resources requires a precision public health (PxPH) approach. Here we describe how integrating data collection optimisation, traditional analytics and causal artificial intelligence/machine learning (ML) can be used in a use case for increasing hospital deliveries of newborns in Uttar Pradesh, India.MethodsUsing a systematic behavioural framework we designed a large-scale survey on perceptual, interpersonal and structural drivers of women’s behaviour around childbirth (n=5613). Multivariate logistic regression identified factors associated with institutional delivery (ID). Causal ML determined the cause-and-effect ordering of these factors. Variance decomposition was used to parse sources of variation in delivery location, and a supervised learning algorithm was used to distinguish population subgroups.ResultsAmong the factors found associated with ID, the causal model showed that having a delivery plan (OR=6.1, 95% CI 6.0 to 6.3), believing the hospital is safer than home (OR=5.4, 95% CI 5.1 to 5.6) and awareness of financial incentives were direct causes of ID (OR=3.4, 95% CI 3.3 to 3.5). Distance to the hospital, borrowing delivery money and the primary decision-maker were not causal. Individual-level factors contributed 69% of variance in delivery location. The segmentation analysis showed four distinct subgroups differentiated by ID risk perception, parity and planning.ConclusionThese findings generate a holistic picture of the drivers and barriers to ID in Uttar Pradesh and suggest distinct intervention points for different women. This demonstrates data optimised to identify key behavioural drivers, coupled with traditional and ML analytics, can help design a PxPH approach that maximise the impact of limited resources.

Download Full-text

COVID-19: A Comparison of Time Series Methods to Forecast Percentage of Active Cases per Population

Applied Sciences ◽

10.3390/app10113880 ◽

2020 ◽

Vol 10 (11) ◽

pp. 3880 ◽

Cited By ~ 10

Author(s):

Vasilis Papastefanopoulos ◽

Pantelis Linardatos ◽

Sotiris Kotsiantis

Keyword(s):

Public Health ◽

Machine Learning ◽

Time Series ◽

Health System ◽

Total Population ◽

Outbreak Detection ◽

Time Series Modeling ◽

Learning Time ◽

Raising Awareness ◽

The Impact

The ongoing COVID-19 pandemic has caused worldwide socioeconomic unrest, forcing governments to introduce extreme measures to reduce its spread. Being able to accurately forecast when the outbreak will hit its peak would significantly diminish the impact of the disease, as it would allow governments to alter their policy accordingly and plan ahead for the preventive steps needed such as public health messaging, raising awareness of citizens and increasing the capacity of the health system. This study investigated the accuracy of a variety of time series modeling approaches for coronavirus outbreak detection in ten different countries with the highest number of confirmed cases as of 4 May 2020. For each of these countries, six different time series approaches were developed and compared using two publicly available datasets regarding the progression of the virus in each country and the population of each country, respectively. The results demonstrate that, given data produced using actual testing for a small portion of the population, machine learning time series methods can learn and scale to accurately estimate the percentage of the total population that will become affected in the future.

Download Full-text

Overlapping Interests: The Impact of Geographic Coordinate Assumptions on Limited-Area Atmospheric Model Simulations

Monthly Weather Review ◽

10.1175/mwr-d-12-00351.1 ◽

2013 ◽

Vol 141 (6) ◽

pp. 2120-2127 ◽

Cited By ~ 3

Author(s):

Andrew J. Monaghan ◽

Michael Barlage ◽

Jennifer Boehnert ◽

Cody L. Phillips ◽

Olga V. Wilhelmi

Keyword(s):

Land Use ◽

High Resolution ◽

Input Data ◽

Atmospheric Model ◽

Earth Model ◽

Limited Area ◽

Near Surface ◽

Geographic Coordinate System ◽

Earth Models ◽

The Impact

Abstract There is growing use of limited-area models (LAMs) for high-resolution (<10 km) applications, for which consistent mapping of input terrestrial and meteorological datasets is critical for accurate simulations. The geographic coordinate systems of most input datasets are based on spheroid-shaped (i.e., elliptical) Earth models, while LAMs generally assume a perfectly sphere-shaped Earth. This distinction is often neglected during preprocessing, when input data are remapped to LAM domains, leading to geolocation discrepancies that can exceed 20 km at midlatitudes. A variety of terrestrial (topography and land use) input dataset configurations is employed to explore the impact of Earth model assumptions on a series of 1-km LAM simulations over Colorado. For the same terrestrial datasets, the ~20-km geolocation discrepancy between spheroidal-versus-spherical Earth models over the domain leads to simulated differences in near-surface and midtropospheric air temperature, humidity, and wind speed that are larger and more widespread than those due to using different topography and land use datasets altogether but not changing the Earth model. Simulated differences are caused by the shift of static fields with respect to boundary conditions, and altered Coriolis forcing and topographic gradients. The sensitivity of high-resolution LAM simulations to Earth model assumptions emphasizes the importance for users to ensure terrestrial and meteorological input data are consistently mapped during preprocessing (i.e., datasets share a common geographic coordinate system before remapping to the LAM domain). Concurrently, the modeling community should update preprocessing systems to make sure input data are correctly mapped for all global and limited-area simulation domains.

Download Full-text