Soil NOx Emission Prediction via Recurrent Neural Networks

This paper presents designing sequence-to-sequence recurrent neural network(RNN)architectures for a novel study to predict soil NOx emissions,driven by the imperative of understanding and mitigating environmental impact.The study utilizes data collected by the Environmental Protection Agency(EPA)to develop two distinct RNN predictive models:one built upon the long-short term memory(LSTM)and the other utilizing the gated recurrent unit(GRU).These models are fed with a combination of historical and anticipated air temperature,air moisture,and NOx emissions as inputs to forecast future NOx emissions.Both LSTM and GRU models can capture the intricate pulse patterns inherent in soil NOx emissions.Notably,the GRU model emerges as the superior performer,surpassing the LSTM model in predictive accuracy while demonstrating efficiency by necessitating less training time.Intriguingly,the investigation into varying input features reveals that relying solely on past NOx emissions as input yields satisfactory performance,highlighting the dominant influence of this factor.The study also delves into the impact of altering input series lengths and training data sizes,yielding insights into optimal configurations for enhanced model performance.Importantly,the findings promise to advance our grasp of soil NOx emission dynamics,with implications for environmental management strategies.Looking ahead,the anticipated availability of additional measurements is poised to bolster machine-learning model efficacy.Furthermore,the future study will explore physical-based RNNs,a promising avenue for deeper insights into soil NOx emission prediction.

Soil mineral nitrogen and yield-scaled soil N2O emissions lowered by reducing nitrogen application and intercropping with soybean for sweet maize production in southern China

The increasing demand for fresh sweet maize （Zea mays L. saccharata） in southern China has prioritized the need to find solutions to the environmental pollution caused by its continuous production and high inputs of chemical nitrogen fertilizers. A promising method for improving crop production and environmental conditions is to intercrop sweet maize with legumes. Here, a three-year field experiment was conducted to assess the influence of four different cropping systems （sole sweet maize （SS）, sole soybean （SB）, two rows sweet maize-three rows soybean （S2B3） intercropping, and two rows sweet maize-four rows soybean （S2B4） intercropping）, together with two rates of N fertilizer application （300 and 360 kg N ha-1） on grain yield, residual soil mineral N, and soil N2O emissions in southern China. Results showed that in most case, inter- cropping achieved yield advantages （total land equivalent ratio （TLER=0.87-1.25） was above one）. Moreover, intercropping resulted in 39.8% less soil mineral N than SS at the time of crop harvest, averaged over six seasons （spring and autumn in each of the three years of the field experiment）. Generally, intercropping and reduced-N application （300 kg N ha-1） produced lower cumulative soil N20 and yield-scaled soil N20 emissions than SS and conventionaI-N application （360 kg N ha-l）, respectively. $2B4 intercropping with reduced-N rate （300 kg N ha-~） showed the lowest cumulative soil N20 （mean value=0.61 kg ha-1） and yield-scaled soil N20 （mean value=0.04 kg t-1） emissions. Overall, intercropping with reduced-N rate maintained sweet maize production, while also reducing environmental impacts. The system of S2B4 intercropping with reduced-N rate may be the most sustainable and environmentally friendly cropping system.

N_2O emissions from forest and grassland soils in northern China

Ｎ２ＯｅｍｉｓｉｏｎｓｆｒｏｍｆｏｒｅｓｔａｎｄｇｒａｓｌａｎｄｓｏｉｌｓｉｎｎｏｒｔｈｅｒｎＣｈｉｎａＬｉｕＹｅ，ＭｕＹｕｊｉｎｇ，ＹａｎｇＷｅｎｘｉａｎｇＲｅｓｅａｒｃｈＣｅｎｔｅｒｆｏｒＥｃｏＥｎｖｉｒｏｎｍｅｎｔａｌＳｃｉｅｎｃｅｓ，Ｃｈ...

Variation in Total Soil Organic Carbon Stocks in Relation to Some Land Use Systems in the Bamenda Highlands, Cameroon

Climate change and food security are among the pressing challenges facing humanity in the 21st century. Soil organic carbon (SOC) stocks, total nitrogen (TN), texture, and bulk density (BD) are important soil properties, which control climate change. Three land use systems (smallholder farmlands, grazing lands, and forest lands) that coexist in the Bamenda Highlands (BH) influence ecosystem services and induce soil degradation with the loss of SOC. The objective of this study was to evaluate the variation of SOC and some soil physicochemical properties as affected by the three land use systems (LUS). A total of 21 composite soil samples collected from 7 microclimatic zones of BH following “S” shape plots to the depth of 0 - 30 cm, were analysed for moisture content (MC), SOC, TN, BD, available phosphorus (Av.P), pH and texture. The results revealed that grazing land had the lowest mean sand content (40.79 ± 4.07). Mean MC, TN and SOC (%) content were significantly higher (p < 0.05) in forest land than those in the grazing land and smallholder farmlands. Conversely, BD and Av.P were significantly higher (p < 0.05) in smallholder farmlands than grazing and forest lands probably due to different litter accumulation and agricultural practices. Moisture content and TN revealed positive significant correlations (p < 0.05) with SOC, while BD and Av.P revealed negative significant correlations (p < 0.05). Mean SOC density in smallholder farmlands (132.91 ± 9.48 tC/ha) was the lowest among the three land use types. Losses in CO2 equivalence, as a result of land use change from forest lands to smallholder farmlands were 137.33 t/ha while that from grazing lands to smallholder farmlands were 109.13 t/ha. Total organic carbon (TOC) stocks differed significantly (p < 0.05) from smallholder farmlands (10.73 Mt) to forest lands (91.13 Mt). A sustainable farming technique that enhances SOC sequestration and minimizes soil CO2 emissions is therefore recommended to replace tillage ridges formation commonly practiced by smallholder farmers.

Unique genes carried by abundant species enhance CH_(4) emissions during the growing season at the Tibetan Plateau

CH_(4) emission rates followed an increased pattern during the growing season at Tibetan Plateau.•Unique genes carried by abundant species were positively correlated with CH_(4) emission rates.•Climate factors influenced CH_(4) emission rates by regulating microbial community and their genes.Microorganisms play pivotal roles in soil methane(CH_(4))emissions and their functional genes are origins of a key mechanism for soil CH4-cycling.However,understanding of the roles of specific genes(e.g.,unique or shared genes carried by species)underlying CH_(4)-cycling remains elusive.Here,we measured CH_(4) emission rates and investigated variations in microbial community and the abundance of genes carried by species during the growing season in alpine meadow on the Tibetan Plateau.We discovered that CH_(4) emission rates increased from 394.4,745.9,and 1092.7µg CH4 m−2 h−1,in April,June,and August,respectively,and had a positive correlation with unique genes carried by abundant species during the growing season.Moreover,we found that unique genes carried by abundant species involved in methanogenesis processes have a higher abundance than methanotrophic processes.Further analysis indicated that climate factors(i.e.,mean monthly temperature(MMT)and mean monthly precipitation(MMP))influenced microbial community and their functional genes,and therefore affected the CH_(4) emission rates.Overall,the present study provides a novel insight into the variation of soil CH4 emissions from a functional gene perspective,highlighting the important roles of unique genes carried by abundant species in CH4 emissions in the Tibetan Plateau under seasonal variation.

Predicting plant-soil N cycling and soil N_(2)O emissions in a Chinese old-growth temperate forest under global changes:uncertainty and implications

Soil-emitted N_(2)O contributes to two-thirds of global N_(2)O emissions,and is sensitive to global change.We used DayCent model to simulate major plant-soil N cycling processes under different global change scenarios in a typical temperate mixed forest in north-eastern China.Simulated scenarios included warming(T),elevated atmospheric CO_(2) concentration([CO_(2)])(C),increased N deposition(N)and precipitation(P),and their full factorial combinations.The responses of plant-soil nitrogen cycling processes including net N mineralization,plant N uptake,gross nitrification,denitrification and soil N_(2)O emission were examined.Concurrent increase of elevated[CO_(2)]and N deposition displayed most strong interactive effects on most fluxes.Using the results from experimental studies for evaluation,simulation uncertainty was highest under elevated[CO_(2)]and increased precipitation among the four global change factors.N deposition had a fundamental impact on soil N cycle and N_(2)O emission in our studied forest.Despite forest soil acting as a N sink for added N,scenarios which included increased N deposition showed higher cumulative soil N_(2)O emissions(summed up from 2001 to 2100).In particular,the scenario which included T,P,and N had the largest cumulative soil N_(2)O emission,which was a 24.4% increase over that under ambient conditions.Our study points to the importance of the interactive effects of global change factors on plant-soil N cycling and the necessity of multi-factor manipulation experiments.

MODEL STUDY OF THE EFFECT OF SOIL NO EMISSIONS ON SURFACE OZONE

The effect of soil NO emissions on surface ozone in autumn in East China has been studied by using TCTM(Troposphere Chemical Transport Model)with the input of meteorological variables from RAMS.The chemical mechanism for ozone variation caused by soil emissions has also been investigated.The model results reveal that soil NO emissions are important to regional ozone formation and distribution and the effect of soil NO emissions shows spatial inhomogeneity.Ozone over most areas in northern China decreases with maximum average decrement reaching 5 ppb while it increases over most areas of central and southern China with maximum average increment reaching 7 ppb caused by soil NO emissions.This situation of ozone variation is mainly determined by nonlinear photochemical mechanism.For the low NOx areas(≤3 ppb),ozone increases as NOx increases;for the high NOx areas(>3 ppb),ozone decreases as NOx increases.The effect of soil NO emissions on ozone depends on the transition value and NOx concentrations.

Volatile organic compound emissions from straw-amended agricultural soils and their relations to bacterial communities:A laboratory study

A laboratory study was conducted to investigate volatile organic compound（VOC） emissions from agricultural soil amended with wheat straw and their associations with bacterial communities for a period of 66 days under non-flooded and flooded conditions. The results indicated that ethene, propene, ethanol, i-propanol, 2-butanol, acetaldehyde, acetone,2-butanone, 2-pentanone and acetophenone were the 10 most abundant VOCs, making up over 90% of the total VOCs released under the two water conditions. The mean emission of total VOCs from the amended soils under the non-flooded condition（5924 ng C/（kg·hr）） was significantly higher than that under the flooded condition（2211 ng C/（kg·hr））. One ＂peak emission window＂ appeared at days 0–44 or 4–44, and over 95% of the VOC emissions occurred during the first month under the two water conditions. Bacterial community analysis using denaturing gradient gel electrophoresis（DGGE） showed that a relative increase of Actinobacteria, Bacteroidetes, Firmicutes and γ-Proteobacteria but a relative decrease of Acidobacteria with time were observed after straw amendments under the two water conditions. Cluster analysis revealed that the soil bacterial communities changed greatly with incubation time, which was in line with the variation of the VOC emissions over the experimental period. Most of the above top 10 VOCs correlated positively with the predominant bacterial species of Bacteroidetes, Firmicutes and Verrucomicrobia but correlated negatively with the dominant bacterial species of Actinobacteria under the two water conditions. These results suggested that bacterial communities might play an important role in VOC emissions from straw-amended agricultural soils.

Effects of nitrogen addition on carbonate-derived CO_(2) emission after biochar addition

●We studied the effect of nitrogen and biochar on CO_(2) emission from SOC and SIC.●Nitrogen increased SIC-derived CO_(2) by 41%but decreased SOC-derived CO_(2) by 20%.●Biochar reduced total soil-derived CO_(2) by neutralizing nitrogen-induced acidity.●We proposed a method for 3-or 4-source partitioning CO_(2) emission from calcareous soils.Biochar addition generally increases the alkalinity regeneration to resist soil acidification driven by nitrogen(N)fertilization.Calcareous soils contain soil organic carbon(SOC)and inorganic C(SIC).Owing to technical limitations in three-source partitioning CO_(2),how biochar addition affects SOC-and SIC-derived CO_(2) emission has not been clarified yet.Therefore,we conducted a 70-day incubation experiment of ammonium-N and maize-straw-derived biochar additions to investigate the N plus biochar impacts on SOC-and SIC-derived CO_(2) emission.Over the 70-day incubation,we found that the N-only addition increased the SIC-derived CO_(2) emission by approximately 41%compared with the control,but decreased the SOC-derived CO_(2) emission by approximately 20%.This suggests that the distinct responses of SIC-and SOC-derived CO_(2) emission to N-only addition come from N-induced acidification and preferential substrate(N)utilization of soil microorganisms,respectively.Compared with N-only addition,N plus biochar addition decreased the SIC-derived CO_(2) emission by 17%−20%during the first 20 days of incubation,but increased it by 54%during the next 50 days.This result suggested that biochar addition reduced the SIC-derived CO_(2) emission likely due to the alkalization capacity of biochar exceeding the acidification capacity of ammonium-N in the short term,but it may increase the SIC-derived CO_(2) emission induced by the weak acidity produced from biochar mineralization in the long term.This study is helpful to improve the quantification of CO_(2) emission from calcareous soils.

Larger floods reduce soil CO_(2)efflux during the post-flooding phase in seasonally flooded forests of Western Amazonia

Seasonally flooded várzea forests of Western Amazonia are one of the most productive and biodiverse wetland forests in the world.However,data on their soil CO_(2)emissions,soil organic matter decomposition rates,and soil C stocks are scarce.This is a concern because hydrological changes are predicted to lead to increases in the height,extent,and duration of seasonal floods,which are likely to have a significant effect on soil C stocks and fluxes.However,with no empirical data,the impact of altered flood regimes on várzea soil C cycles remains uncertain.This study quantified the effects of maximum annual flood height and soil moisture on soil CO_(2)efflux rate(R_(s))and soil organic matter decomposition rate(k)in the várzea forests of Pacaya Samiria National Reserve,Peru.The study was conducted between May and August 2017.The results showed that R_(s)(10.6–182.7 mg C m^(-2)h^(-1))and k(0.016–0.078)varied between and within sites,and were considerably lower than the values reported for other tropical forests.In addition,R_(s)was negatively affected by flood height(P<0.01)and soil moisture(P<0.001),and it decreased with decreasing river levels post flooding(P<0.001).In contrast,k was not affected by any of the above-mentioned factors.Soil moisture was the dominant factor influencing R_(s),and it was significantly affected by maximum flood height,even after the floods had subsided(P<0.001).Consequently,we concluded that larger floods will likely lead to reduced R_(s),whilst k could remain unchanged but with decomposition processes becoming more anaerobic.