More Like this

1. Data from: Coupled machine learning-ecosystem ensemble models substantially improve predictions of nitrous oxide (N₂O) fluxes from US croplands

   https://doi.org/10.5061/dryad.pvmcvdnzx  

   Sharma, Prateek; Basso, Bruno; Manuraj, Aditya; Murillo, Michael S; Millar, Neville; Tadiello, Tommasso; Sharma, Mukta; Delandmeter, Mathieu; Robertson, G Philip (March 2026, Dryad)

   Nitrous oxide (N₂O) is a potent and persistent greenhouse gas, with rising atmospheric concentrations driven in part by inefficient use of synthetic nitrogen (N) fertilizers in agriculture. Predicting soil N₂O emissions is challenging due to high spatial and temporal variability arising from complex soil biogeochemical processes. Process-based ecosystem models and standalone machine learning (ML) approaches without extensive site-specific calibration often miss high emission episodes. Here, we show how an Ensemble Modeling System (EMS) based on outputs from an ensemble of ecosystem models coupled to an ensemble of ML models can improve predictions and understanding of N2O fluxes from US cropland. Trained and validated on approximately 12,000 N2O chamber measurements at 17 U.S. Midwest sites (six crops, 35 management practices), the EMS accurately predicted daily fluxes of N2O at both training (R² = 0.84, RMSE = 16.4 g N ha⁻¹ d⁻¹) and held-out testing sites (R² = 0.84, RMSE = 6.2 g N ha⁻¹ d⁻¹). Analyses identified six dominant N₂O drivers: soil organic carbon (SOC), NH₄⁺, NO₃⁻, water-filled pore space (WFPS), soil temperature, and biomass production. Wet, warm soils produced large N₂O peaks only with sufficient SOC and mineral N; in low-SOC soils, fluxes remained low. Incorporating these drivers into process-based models might significantly improve their predictive capacity. The EMS demonstrates a strong potential to predict N₂O fluxes at unseen sites, enabling more reliable regional inventories, improved gap-filling where measurements are sparse, and enhanced understanding of mechanisms to advance targeted mitigation strategies in food, feed, and bioenergy crops. # Data from: Coupled machine learning-ecosystem ensemble models substantially improve predictions of nitrous oxide (N~2~O) fluxes from US croplands Dataset DOI: [10.5061/dryad.pvmcvdnzx](10.5061/dryad.pvmcvdnzx) ## Description of the data and file structure We present here the data that were used for the analysis presented in: Coupled machine learning-ecosystem ensemble models substantially improve predictions of nitrous oxide (N~2~O) fluxes from US croplands. ### Files and variables Files: Dataset_S1.xlsx, Dataset_S2.csv, Dataset_S3.csv, #### **Description:**  **Description of data sheets** **Dataset S1A columns** * **Site_ID:** Numeric identifier for the experimental site. * **Treatment_ID:** Numeric code for the management treatment applied at that site * **DataUse:** To assign data to be used for model training (development) and testing (held-out evaluation) * **State/Province:** State acronym * **Latitude decimal deg:** Site location latitude * **Longitude decimal deg:** Site location longitude * **Start Data Year:** Starting year of data used * **End Data Year:** Ending year of data used * **Cover crop:** Type of cover crop used within the treatment * **Rotation Descriptor:** Describe the rotation of crops within the treatment * **Tillage Descriptor:** Describe tillage type within the treatment * **Residual Removal:** Describe residual management within the treatment * **Irrigation:** Describe if irrigation was applied or not within the treatment * **N Treatment Descriptor:** Describe nitrogen amendments within the treatment * **Reference:** Reference for the data **Dataset S1B**: This sheet contains the reference list for the data used **Dataset S2 columns** * **Date:** Gas sampling days * **Site_ID:** Numeric identifier for the experimental site. * **Treatment_ID:** Numeric code for the management treatment applied at that site * **DataUse:** To assign data to be used for model training (development) and testing (held-out evaluation) * **Observed N2O:** Daily average N2O flux measured (g N2O-N ha-1d-1) * **Predicted N2O:** Daily average N2O flux predicted by multimodel hybrid framework (g N2O-N ha-1d-1) * **NH4:** Process-based models simulated daily NH4-N content in the top 30-cm soil layer (kg ha-1) * **SOC:** Process-based models simulated daily soil organic carbon in the top 30-cm soil layer (kg ha-1) * **NO3:** Process-based models simulated daily NO3-N content in the top 30-cm soil layer (kg ha-1) * **ST:** Process-based models simulated daily average soil temperature in the top 30-cm soil layer (°C) * **WFPS:** Process-based models simulated daily water-filled pore space in the top 30-cm soil layer (fraction) * **ABG:** Process-based models simulated daily above-ground biomass (kg ha-1) * **BG:** Process-based models simulated daily below-ground biomass (kg ha-1) * **SRAD:** Average solar radiation for the last five days before gas sampling (Watt m-2) * **Tmax:** Average maximum air temperature for the last three days before gas sampling  (°C) * **APrecip:** Average precipitation in the last fifteen days before gas sampling (mm) * **Wspd:** Average wind in the last fifteen days before gas sampling (m s-1) * **LAI:** Process-based models simulated daily leaf area index (m2 m2) * **Nstress:** Process-based models simulated the daily nitrogen stress factor (fraction) * **Wstress:** Process-based models simulated the daily water stress factor (fraction) * **PET:** Process-based models simulated daily potential evapotranspiration (mm) * **SE:** Process-based models simulated daily soil evaporation (mm) * **SPrecip:** Cumulative precipitation in the last two days before gas sampling (mm) * **SH:** Average specific humidity in the last three days before gas sampling (g kg-1) * **RH:** Average relative humidity in the last fifteen days before gas sampling (%) **Dataset S3 columns** * **Date:** Gas sampling days * **Site_ID:** Numeric identifier for the experimental site. * **Treatment_ID:** Numeric code for the management treatment applied at that site * **DataUse:** To assign data to be used for model training (development) and testing (held-out evaluation) * **SD:** Monte Carlo standard deviation of the simulated daily N₂O flux distribution (g N2O-N ha-1d-1) * **CV**: Monte Carlo coefficient of variation of the simulated daily N₂O flux distribution (%) * **CI05:** 5th percentile (lower 90 % confidence bound) of the Monte Carlo flux distribution(g N2O-N ha-1d-1) * **CI95:** 95th percentile (upper 90 % confidence bound) of the Monte Carlo flux distribution(g N2O-N ha-1d-1) 

   more » « less
2. Management alternatives for climate‐smart agriculture at two long‐term agricultural research sites in the United States: A model ensemble case study

   https://doi.org/10.1002/agj2.70146  

   Maas, Ellen_D_v L; Sihi, Debjani (September 2025, Agronomy Journal)

   Abstract Greenhouse gas (GHG) emissions reduction efforts are underway to mitigate climate change worldwide. Climate‐smart agriculture (CSA) practices have been shown to both increase soil organic carbon (SOC) inputs and reduce net greenhouse gas emissions (GHGnet). We evaluated the GHGnet of several management practices with three biogeochemical models (APSIM, Daycent, and RothC) at two sites with contrasting soils, climates, and cropping systems. Additionally, two future climate scenarios (baseline and high‐emissions) provided alternative outcomes of SOC, N₂O, and CH₄by 2050. In Michigan, most biochar and residue retention with no‐till treatments increased SOC stocks; leguminous cover crops, no‐till, and reducing fertilizer input lowered N₂O emissions. The lowest biochar treatment lowered GHGnet in the baseline climate scenario, but all other management treatments increased GHGnet under both baseline and high emissions, and all management scenarios increased a mean of 8.0 Mg CO₂‐equivalent GHG (CO₂e) ha⁻¹from baseline to high emissions. Conversely, in Texas, most treatments increased SOC, and N₂O was relatively constant. Every no‐till treatment reversed GHGnet in both the baseline and high‐emissions climate scenarios but all management scenarios increased a mean of 0.6 Mg CO₂e ha⁻¹under high emissions. At both sites under high‐emissions climate change, cover crops and no‐till resulted in the lowest GHGnet overall. Overall, the study showed that no‐till, especially with residue retention, and cover crops are important CSA practices to lower the GHGnet of agriculture, but there remains much room to find even more effective solutions to adapt to climate change. 

   more » « less
3. Coupling Remote Sensing With a Process Model for the Simulation of Rangeland Carbon Dynamics

   https://doi.org/10.1029/2024MS004342  

   Xia, Yushu; Sanderman, Jonathan; Watts, Jennifer D; Machmuller, Megan B; Mullen, Andrew L; Rivard, Charlotte; Endsley, Arthur; Hernandez, Haydee; Kimball, John; Ewing, Stephanie A; et al (March 2025, Journal of Advances in Modeling Earth Systems)

   Abstract Rangelands provide significant environmental benefits through many ecosystem services, which may include soil organic carbon (SOC) sequestration. However, quantifying SOC stocks and monitoring carbon (C) fluxes in rangelands are challenging due to the considerable spatial and temporal variability tied to rangeland C dynamics as well as limited data availability. We developed the Rangeland Carbon Tracking and Management (RCTM) system to track long‐term changes in SOC and ecosystem C fluxes by leveraging remote sensing inputs and environmental variable data sets with algorithms representing terrestrial C‐cycle processes. Bayesian calibration was conducted using quality‐controlled C flux data sets obtained from 61 Ameriflux and NEON flux tower sites from Western and Midwestern US rangelands to parameterize the model according to dominant vegetation classes (perennial and/or annual grass, grass‐shrub mixture, and grass‐tree mixture). The resulting RCTM system produced higher model accuracy for estimating annual cumulative gross primary productivity (GPP) (R² > 0.6, RMSE <390 g C m⁻²) relative to net ecosystem exchange of CO₂(NEE) (R² > 0.4, RMSE <180 g C m⁻²). Model performance in estimating rangeland C fluxes varied by season and vegetation type. The RCTM captured the spatial variability of SOC stocks withR² = 0.6 when validated against SOC measurements across 13 NEON sites. Model simulations indicated slightly enhanced SOC stocks for the flux tower sites during the past decade, which is mainly driven by an increase in precipitation. Future efforts to refine the RCTM system will benefit from long‐term network‐based monitoring of vegetation biomass, C fluxes, and SOC stocks. 

   more » « less
4. Net greenhouse gas balance in U.S. croplands: How can soils be part of the climate solution?

   https://doi.org/10.1111/gcb.17109  

   You, Yongfa; Tian, Hanqin; Pan, Shufen; Shi, Hao; Lu, Chaoqun; Batchelor, William D; Cheng, Bo; Hui, Dafeng; Kicklighter, David; Liang, Xin‐Zhong; et al (January 2024, Global Change Biology)

   Abstract Agricultural soils play a dual role in regulating the Earth's climate by releasing or sequestering carbon dioxide (CO₂) in soil organic carbon (SOC) and emitting non‐CO₂greenhouse gases (GHGs) such as nitrous oxide (N₂O) and methane (CH₄). To understand how agricultural soils can play a role in climate solutions requires a comprehensive assessment of net soil GHG balance (i.e., sum of SOC‐sequestered CO₂and non‐CO₂GHG emissions) and the underlying controls. Herein, we used a model‐data integration approach to understand and quantify how natural and anthropogenic factors have affected the magnitude and spatiotemporal variations of the net soil GHG balance in U.S. croplands during 1960–2018. Specifically, we used the dynamic land ecosystem model for regional simulations and used field observations of SOC sequestration rates and N₂O and CH₄emissions to calibrate, validate, and corroborate model simulations. Results show that U.S. agricultural soils sequestered Tg CO₂‐C year⁻¹in SOC (at a depth of 3.5 m) during 1960–2018 and emitted Tg N₂O‐N year⁻¹and Tg CH₄‐C year⁻¹, respectively. Based on the GWP100 metric (global warming potential on a 100‐year time horizon), the estimated national net GHG emission rate from agricultural soils was Tg CO₂‐eq year⁻¹, with the largest contribution from N₂O emissions. The sequestered SOC offset ~28% of the climate‐warming effects resulting from non‐CO₂GHG emissions, and this offsetting effect increased over time. Increased nitrogen fertilizer use was the dominant factor contributing to the increase in net GHG emissions during 1960–2018, explaining ~47% of total changes. In contrast, reduced cropland area, the adoption of agricultural conservation practices (e.g., reduced tillage), and rising atmospheric CO₂levels attenuated net GHG emissions from U.S. croplands. Improving management practices to mitigate N₂O emissions represents the biggest opportunity for achieving net‐zero emissions in U.S. croplands. Our study highlights the importance of concurrently quantifying SOC‐sequestered CO₂and non‐CO₂GHG emissions for developing effective agricultural climate change mitigation measures. 

   more » « less
5. Balancing Non‐CO ₂ GHG Emissions and Soil Carbon Change in U.S. Rice Paddies: A Retrospective Meta‐Analysis and Agricultural Modeling Study

   https://doi.org/10.1029/2023AV001052  

   Zhang, Jingting; Tian, Hanqin; You, Yongfa; Liang, Xin‐Zhong; Ouyang, Zutao; Pan, Naiqing; Pan, Shufen (February 2024, AGU Advances)

   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. 

   more » « less