Search for: All records

Spatio-temporal deep learning has drawn a lot of attention since many downstream real-world applications can benefit from accurate predictions. For example, accurate prediction of heavy rainfall events is essential for effective urban water usage, flooding warning, and mitigation. In this paper, we propose a strategy to leverage spatially connected real-world features to enhance prediction accuracy. Specifically, we leverage spatially connected real-world climate data to predict heavy rainfall risks in a broad range in our case study. We experimentally ascertain that our Trans-Graph Convolutional Network (TGCN) accurately predicts heavy rainfall risks and real estate trends, demonstrating the advantage of incorporating external spatially-connected real-world data to improve model performance, and it shows that this proposed study has a significant potential to enhance spatio-temporal prediction accuracy, aiding in efficient urban water usage, flooding risk warning, and fair housing in real estate. 

Abstract U.S. rice paddies, critical for food security, are increasingly contributing to non‐CO₂greenhouse gas (GHG) emissions like methane (CH₄) and nitrous oxide (N₂O). Yet, the full assessment of GHG balance, considering trade‐offs between soil organic carbon (SOC) change and non‐CO₂GHG emissions, is lacking. Integrating an improved agroecosystem model with a meta‐analysis of multiple field studies, we found that U.S. rice paddies were the rapidly growing net GHG emission sources, increased 138% from 3.7 ± 1.2 Tg CO₂eq yr⁻¹in the 1960s to 8.9 ± 2.7 Tg CO₂eq yr⁻¹in the 2010s. CH₄, as the primary contributor, accounted for 10.1 ± 2.3 Tg CO₂eq yr⁻¹in the 2010s, alongside a notable rise in N₂O emissions by 0.21 ± 0.03 Tg CO₂eq yr⁻¹. SOC change could offset 14.0% (1.45 ± 0.46 Tg CO₂eq yr⁻¹) of the climate‐warming effects of soil non‐CO₂GHG emissions in the 2010s. This escalation in net GHG emissions is linked to intensified land use, increased atmospheric CO₂, higher synthetic nitrogen fertilizer and manure application, and climate change. However, no/reduced tillage and non‐continuous irrigation could reduce net soil GHG emissions by approximately 10% and non‐CO₂GHG emissions by about 39%, respectively. Despite the rise in net GHG emissions, the cost of achieving higher rice yields has decreased over time, with an average of 0.84 ± 0.18 kg CO₂eq ha⁻¹emitted per kilogram of rice produced in the 2010s. The study suggests the potential for significant GHG emission reductions to achieve climate‐friendly rice production in the U.S. through optimizing the ratio of synthetic N to manure fertilizer, reducing tillage, and implementing intermittent irrigation. 

Abstract Effective nitrogen fertilizer management is crucial for reducing nitrous oxide (N₂O) emissions while ensuring food security within planetary boundaries. However, climate change might also interact with management practices to alter N₂O emission and emission factors (EFs), adding further uncertainties to estimating mitigation potentials. Here, we developed a new hybrid modeling framework that integrates a machine learning model with an ensemble of eight process‐based models to project EFs under different climate and nitrogen policy scenarios. Our findings reveal that EFs are dynamically modulated by environmental changes, including climate, soil properties, and nitrogen management practices. Under low‐ambition nitrogen regulation policies, EF would increase from 1.18%–1.22% in 2010 to 1.27%–1.34% by 2050, representing a relative increase of 4.4%–11.4% and exceeding the IPCC tier‐1 EF of 1%. This trend is particularly pronounced in tropical and subtropical regions with high nitrogen inputs, where EFs could increase by 0.14%–0.35% (relative increase of 11.9%–17%). In contrast, high‐ambition policies have the potential to mitigate the increases in EF caused by climate change, possibly leading to slight decreases in EFs. Furthermore, our results demonstrate that global EFs are expected to continue rising due to warming and regional drying–wetting cycles, even in the absence of changes in nitrogen management practices. This asymmetrical influence of nitrogen fertilizers on EFs, driven by climate change, underscores the urgent need for immediate N₂O emission reductions and further assessments of mitigation potentials. This hybrid modeling framework offers a computationally efficient approach to projecting future N₂O emissions across various climate, soil, and nitrogen management scenarios, facilitating socio‐economic assessments and policy‐making efforts. 

This dataset contains yearly projections of emission factors (EFs) for fertilizer-induced direct nitrous oxide (N2O) emissions across the global agricultural lands with a spatial resolution of 0.5° × 0.5° from 1990 to 2050. Emission factor (EF) is defined as the amount of N2O emitted per unit of nitrogen (N) fertilizer applied, expressed in percentage (%). They are developed from a hybrid modeling framework, Dym-EF (more details can be found in Li et al., 2024). The framework integrates machine learning approaches with an ensemble of eight process-based models from The Global N2O Model Intercomparison Project phase 2 (NMIP2) to learn the relationship between EF dynamics and multiple environmental factors, such as climate, soil properties, nitrogen fertilizer input, and other agricultural management practices. After the hybrid modeling framework was extensively validated, we applied it to develop EF projections under different nitrogen management policies and climate change scenarios, including future climate data from 37 Global Climate Models (GCMs). The annual median and standard deviation (SD) of EF under each scenario represent the projection median and variability derived from climate input data using the 37 GCMs.The dataset filenames follow the structure: 'Scenario'_'N regulation'_'Median/SD', where 'Scenario' corresponds to the different nitrogen management and climate scenarios (e.g., INMS1, INMS2, and INMS3), 'N regulation' corresponds to the different nitrogen management levels (e.g., BAU, LowNRegul, and MedNRegul), and 'Median/SD' indicates whether the file contains the median (Median) or standard deviation (SD) of the projections. All relevant data and further details can be found in the supplementary materials and the cited references.INMS1: Business-as-usual, Land use regulation: Medium, Diet: Meat & dairy-rich, Ambition level: LowINMS2: Low-nitrogen regulation, Land use regulation: Medium, Diet: Medium meat & dairy, Ambition level: LowINMS3: Medium-nitrogen regulation, Land use regulation: Medium, Diet: Medium meat & dairy, Ambition level: ModerateINMS4: High-nitrogen regulation, Land use regulation: Medium, Diet: Medium meat & dairy, Ambition level: HighINMS5: Best-case, Land use regulation: Strong, Diet: Low meat & dairy, Ambition level: HighINMS6: Best-case “Plus”, Land use regulation: Strong, Diet: Ambitious diet shift and food-loss/waste reductions, Ambition level: HighINMS7: Bioenergy, Land use regulation: Strong, Diet: Low meat & dairy, Ambition level: HighWe developed this data using the “ranger” package in R 4.1.1, which is accessible at https://cran.r-project.org/web/packages/ranger/. The optimization of the two hyperparameters (ntree and mtry) was performed using the ‘caret’ package, available at https://topepo.github.io/caret/.This database is developed by Li, L., C. Lu, W. Winiwarter, H. Tian, J. Canadell, A. Ito, A.K. Jain, S. Kou-Giesbrecht, S. Pan, N. Pan, H. Shi, Q. Sun, N. Vuichard, S. Ye., S. Zaehle, Q. Zhu. Enhanced nitrous oxide emission factors due to climate change increase the mitigation challenge in the agricultural sector Global Change Biology (In Press) 

Abstract Nitrous oxide (N₂O) is a greenhouse gas and stratospheric ozone‐depleting substance with large and growing anthropogenic emissions. Previous studies identified the influx of N₂O‐depleted air from the stratosphere to partly cause the seasonality in tropospheric N₂O (aN₂O), but other contributions remain unclear. Here, we combine surface fluxes from eight land and four ocean models from phase 2 of the Nitrogen/N₂O Model Intercomparison Project with tropospheric transport modeling to simulate aN₂O at eight remote air sampling sites for modern and pre‐industrial periods. Models show general agreement on the seasonal phasing of zonal‐average N₂O fluxes for most sites, but seasonal peak‐to‐peak amplitudes differ several‐fold across models. The modeled seasonal amplitude of surface aN₂O ranges from 0.25 to 0.80 ppb (interquartile ranges 21%–52% of median) for land, 0.14–0.25 ppb (17%–68%) for ocean, and 0.28–0.77 ppb (23%–52%) for combined flux contributions. The observed seasonal amplitude ranges from 0.34 to 1.08 ppb for these sites. The stratospheric contributions to aN₂O, inferred by the difference between the surface‐troposphere model and observations, show 16%–126% larger amplitudes and minima delayed by ∼1 month compared to Northern Hemisphere site observations. Land fluxes and their seasonal amplitude have increased since the pre‐industrial era and are projected to grow further under anthropogenic activities. Our results demonstrate the increasing importance of land fluxes for aN₂O seasonality. Considering the large model spread, in situ aN₂O observations and atmospheric transport‐chemistry models will provide opportunities for constraining terrestrial and oceanic biosphere models, critical for projecting carbon‐nitrogen cycles under ongoing global warming. 

Abstract. Excessive anthropogenic nitrogen (N) inputs to the biosphere have disruptedthe global nitrogen cycle. To better quantify the spatial and temporalpatterns of anthropogenic N inputs, assess their impacts on thebiogeochemical cycles of the planet and the living organisms, and improvenitrogen use efficiency (NUE) for sustainable development, we have developeda comprehensive and synthetic dataset for reconstructing the History ofanthropogenic Nitrogen inputs (HaNi) to the terrestrial biosphere. The HaNi datasettakes advantage of different data sources in a spatiotemporally consistentway to generate a set of high-resolution gridded N input products from thepreindustrial period to the present (1860–2019). The HaNi dataset includes annual ratesof synthetic N fertilizer, manure application/deposition, and atmospheric Ndeposition on cropland, pasture, and rangeland at a spatial resolution of5 arcmin × 5 arcmin. Specifically, the N inputs are categorized, according to the Nforms and land uses, into 10 types: (1) NH4+-N fertilizer applied to cropland,(2) NO3--N fertilizer applied to cropland, (3) NH4+-N fertilizer applied to pasture,(4) NO3--N fertilizer applied to pasture, (5) manure N application oncropland, (6) manure N application on pasture, (7) manure N deposition onpasture, (8) manure N deposition on rangeland, (9) NHx-N deposition, and(10) NOy-N deposition. The total anthropogenic N (TN) inputs to globalterrestrial ecosystems increased from 29.05 Tg N yr−1 in the 1860s to267.23 Tg N yr−1 in the 2010s, with the dominant N source changing fromatmospheric N deposition (before the 1900s) to manure N (in the 1910s–2000s)and then to synthetic fertilizer in the 2010s. The proportion of syntheticNH4+-N in fertilizer input increased from 64 %in the 1960s to 90 % in the 2010s, while synthetic NO3--N fertilizerdecreased from 36 % in the 1960s to 10 % in the 2010s. Hotspots of TNinputs shifted from Europe and North America to East and South Asia duringthe 1960s–2010s. Such spatial and temporal dynamics captured by the HaNidataset are expected to facilitate a comprehensive assessment of the coupledhuman–Earth system and address a variety of social welfare issues, such as theclimate–biosphere feedback, air pollution, water quality, and biodiversity. Thedata are available at https://doi.org/10.1594/PANGAEA.942069(Tian et al., 2022).