Soil NO emissions modelling using artificial neural network

Delon, Claire; Serça, D.; Boissard, Christophe; Düpont, R.; Dutot, A.; Laville, Patricia; Rosnay, Patricia de; delMas, Robert C.

doi:10.3402/tellusb.v59i3.17025

Cited by 18 publications

(30 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biogenic emissions from soils are derived from an artificial neural network (ANN) approach. The resulting algorithm provides on line biogenic NO emissions and has been developed in Delon et al (2007). Fluxes depend on surface water filled pore space (WFPS) and temperature, soil deep temperature (20-30 cm), pH, sand percentage, fertilization rate and wind speed.…”

Section: No Biogenic Emission From Soilsmentioning

confidence: 99%

Nitrogen emission and deposition budget in West and Central Africa

Galy‐Lacaux

Delon

2014

Environ. Res. Lett.

View full text Add to dashboard Cite

Atmospheric nitrogen depends on land surface exchanges of nitrogen compounds. In Sub Saharan Africa, deposition and emission fluxes of nitrogen compounds are poorly quantified, and are likely to increase in the near future due to land use change and anthropogenic pressure. This work proposes an estimate of atmospheric N compounds budget in West and Central Africa, along an ecosystem transect, from dry savanna to wet savanna and forest, for years 2000−2007.The budget may be considered as a one point in time budget, to be included in long term studies as one of the first reference point for Sub Saharan Africa. Gaseous dry deposition fluxes are estimated by considering N compounds concentrations measured in the frame of the IDAF network (IGAC/DEBITS/AFrica) at the monthly scale and modeling of deposition velocities at the IDAF sites, taking into account the bi directional exchange of ammonia. Particulate dry deposition fluxes are calculated using the same inferential method. Wet deposition fluxes are calculated from measurements of ammonium and nitrate chemical content in precipitations at the IDAF sites combined with the annual rainfall amount. In terms of emission, biogenic NO emissions are simulated at each IDAF site with a surface model coupled to an emission module elaborated from an artificial neural network equation. Ammonia emissions from volatilization are calculated from literature data on livestock quantity in each country and N content in manure. NO x and NH 3 emission from biomass burning and domestic fires are estimated from satellite data and emission factors. The total budget shows that emission sources of nitrogen compounds are in equilibrium with deposition fluxes in dry and wet savannas, with respectively 7.40 (±1.90) deposited and 9.01 (±3.44) kgN ha −1 yr −1 emitted in dry savanna, 8.38 (±2.04) kgN ha −1 yr −1 deposited and 9.60 (±0.69) kgN ha −1 yr −1 emitted in wet savanna. In forested ecosystems, the total budget is dominated by wet plus dry deposition processes (14.75 ± 2.36 kgN ha −1 yr −1 ), compared to emissions processes (8.54 ± 0.50 kgN ha −1 yr −1 ).

show abstract

Section: No Biogenic Emission From Soilsmentioning

confidence: 99%

Nitrogen emission and deposition budget in West and Central Africa

Galy‐Lacaux

Delon

2014

Environ. Res. Lett.

View full text Add to dashboard Cite

show abstract

“…With the accumulation of available flux measurements, there is an opportunity for using a datadriving ANN approach to estimate CH 4 emissions. The ANN approach has appeared as a great alternative to classical statistical models [Delon et al, 2007;Dupont et al, 2008], and it is particularly useful in quantifying the responses of nonlinear processes, like wetland CH 4 emissions. In this study, we first use the ANN approach to find the optimal nonlinear regression between CH 4 fluxes and key environmental controls.…”

Section: Introductionmentioning

confidence: 99%

Estimating wetland methane emissions from the northern high latitudes from 1990 to 2009 using artificial neural networks

Zhu

Zhuang

Qin

et al. 2013

Global Biogeochemical Cycles

View full text Add to dashboard Cite

[1] Methane (CH 4 ) emissions from wetland ecosystems in nothern high latitudes provide a potentially positive feedback to global climate warming. Large uncertainties still remain in estimating wetland CH 4 emisions at regional scales. Here we develop a statistical model of CH 4 emissions using an artificial neural network (ANN) approach and field observations of CH 4 fluxes. Six explanatory variables (air temperature, precipitation, water table depth, soil organic carbon, soil total porosity, and soil pH) are included in the development of ANN models, which are then extrapolated to the northern high latitudes to estimate monthly CH 4 emissions from 1990 to 2009. We estimate that the annual wetland CH 4 source from the northern high latitudes (north of 45 N) is 48.7 Tg CH 4 yr À1 (1 Tg = 10 12 g) with an uncertainty range of 44.0~53.7 Tg CH 4 yr À1 . The estimated wetland CH 4 emissions show a large spatial variability over the northern high latitudes, due to variations in hydrology, climate, and soil conditions. Significant interannual and seasonal variations of wetland CH 4 emissions exist in the past 2 decades, and the emissions in this period are most sensitive to variations in water table position. To improve future assessment of wetland CH 4 dynamics in this region, research priorities should be directed to better characterizing hydrological processes of wetlands, including temporal dynamics of water table position and spatial dynamics of wetland areas.Citation: Zhu, X., Q. Zhuang, Z. Qin, M. Glagolev, and L. Song (2013), Estimating wetland methane emissions from the northern high latitudes from 1990 to 2009 using artificial neural networks, Global Biogeochem. Cycles, 27, 592-604,

show abstract

“…(Hartley and Schlesinger, 2000;Martin and Asner, 2005;Martin et al, 2003a). These previous studies have either looked at the larger landscape scale (Aranibar et al, 2004;Brümmer et al, 2008;Davidson, 1991a;Delon et al, 2007;Hartley and Schlesinger, 2000;Jaegle et al, 2004;Martin et al, 2003b;Otter et al, 1999;Serca et al, 1998) or at the vegetation canopy scale (Barger et al, 2005;Hall and Asner, 2007;Hartley and Schlesinger, 2000;Holst et al, 2007;Le Roux and Abbadie, 1995;Levine et al, 1996;Martin et al, 1998;McCalley and Sparks, 2008;Meixner et al, 1997;Mosier et al, 2003;Smart et al, 1999); however there is a need to determine what occurs in the emission of NO between the plant canopy scale and the vegetation patch scale which has been examined in only very few studies (Kirkman et al, 2001;Martin and Asner, 2005;Van Dijk et al, 2002). The main points of consideration in this study are (1) to determine the effect of differing vegetation cover types on the emission of NO along a disturbance gradient and (2) attempt to up-scale point measurements of NO release to a regional emission estimate for NO flux from the soil.…”

Section: Interactive Discussionmentioning

confidence: 99%

Use of laboratory and remote sensing techniques to estimate vegetation patch scale emissions of nitric oxide from an arid Kalahari savanna

Feig

Mamtimin

Meixner

2008

Preprint

View full text Add to dashboard Cite

Abstract. The biogenic emission of nitric oxide (NO) from the soil has an important impact on a number of environmental issues, such as the production of tropospheric ozone, the cycle of the hydroxyl radical (OH) and the production of NO. In this study we collected soils from four differing vegetation patch types (Pan, Annual Grassland, Perennial Grassland and Bush Encroached) in an arid savanna ecosystem in the Kalahari (Botswana). A laboratory incubation technique was used to determine the net potential NO flux from the soils as a function of the soil moisture and the soil temperature. The net potential NO emissions were up-scaled for the year 2006 and a region (185 km×185 km) of the southern Kalahari. For that we used (a) the net potential NO emissions measured in the laboratory, (b) the vegetation patch distribution obtained from Landsat NDVI measurements, (c) estimated soil moisture contents obtained from ENVISAT ASAR measurements and (d) the soil surface temperature estimated using MODIS MOD11A2 8 day land surface temperature measurements. Differences in the net potential NO fluxes between vegetation patches occur and range from 0.27 ng m−2 s−1 in the Pan patches to 2.95 ng m−2 s−1 in the Perennial Grassland patches. Up-scaling the net potential NO fluxes with the satellite derived soil moisture and temperature data gave NO fluxes of up to 323 g ha−1 month−1, where the highest up-scaled NO fluxes occurred in the Perennial Grassland patches, and the lowest in the Pan patches. A marked seasonal pattern was observed where the highest fluxes occurred in the austral summer months (January and February) while the minimum fluxes occurred in the austral winter months (June and July), and were less than 1.8 g ha−1 month−1. Over the course of the year the mean NO emission for the up-scaled region was 0.54 kg ha−1 yr−1, which accounts for a loss of up to 7.4% of the nitrogen (N) input to the region through atmospheric deposition and biological N fixation. The biogenic emission of NO from the soil is therefore an important mechanism of N loss from this arid savanna ecosystem and has the potential to play an important role in the production of tropospheric ozone and the OH cycle.

show abstract

Soil NO emissions modelling using artificial neural network

Cited by 18 publications

References 29 publications

Nitrogen emission and deposition budget in West and Central Africa

Nitrogen emission and deposition budget in West and Central Africa

Estimating wetland methane emissions from the northern high latitudes from 1990 to 2009 using artificial neural networks

Use of laboratory and remote sensing techniques to estimate vegetation patch scale emissions of nitric oxide from an arid Kalahari savanna

Contact Info

Product

Resources

About