An official website of the United States government
Nitrous oxide (N2O) has a global warming potential that is 300 times that of carbon dioxide on a 100-y timescale, and is of major importance for stratospheric ozone depletion. The climate sensitivity of N2O emissions is poorly known, which makes it difficult to project how changing fertilizer use and climate will impact radiative forcing and the ozone layer. Analysis of 6 y of hourly N2O mixing ratios from a very tall tower within the US Corn Belt—one of the most intensive agricultural regions of the world—combined with inverse modeling, shows large interannual variability in N2O emissions (316 Gg N2O-N⋅y−1 to 585 Gg N2O-N⋅y−1). This implies that the regional emission factor is highly sensitive to climate. In the warmest year and spring (2012) of the observational period, the emission factor was 7.5%, nearly double that of previous reports. Indirect emissions associated with runoff and leaching dominated the interannual variability of total emissions. Under current trends in climate and anthropogenic N use, we project a strong positive feedback to warmer and wetter conditions and unabated growth of regional N2O emissions that will exceed 600 Gg N2O-N⋅y−1, on average, by 2050. This increasing emission trend in the US Corn Belt may represent a harbinger of intensifying N2O emissions from other agricultural regions. Such feedbacks will pose a major challenge to the Paris Agreement, which requires large N2O emission mitigation efforts to achieve its goals.
more »
« less
This content will become publicly available on August 1, 2026
Reinforcement Learning-Based Agricultural Fertilization and Irrigation Considering N2O Emissions and Uncertain Climate Variability
Nitrous oxide (N2O) emissions from agriculture are rising due to increased fertilizer use and intensive farming, posing a major challenge for climate mitigation. This study introduces a novel reinforcement learning (RL) framework to optimize farm management strategies that balance crop productivity with environmental impact, particularly N2O emissions. By modeling agricultural decision-making as a partially observable Markov decision process (POMDP), the framework accounts for uncertainties in environmental conditions and observational data. The approach integrates deep Q-learning with recurrent neural networks (RNNs) to train adaptive agents within a simulated farming environment. A Probabilistic Deep Learning (PDL) model was developed to estimate N2O emissions, achieving a high Prediction Interval Coverage Probability (PICP) of 0.937 within a 95% confidence interval on the available dataset. While the PDL model’s generalizability is currently constrained by the limited observational data, the RL framework itself is designed for broad applicability, capable of extending to diverse agricultural practices and environmental conditions. Results demonstrate that RL agents reduce N2O emissions without compromising yields, even under climatic variability. The framework’s flexibility allows for future integration of expanded datasets or alternative emission models, ensuring scalability as more field data becomes available. This work highlights the potential of artificial intelligence to advance climate-smart agriculture by simultaneously addressing productivity and sustainability goals in dynamic real-world settings.
more »
« less
- Award ID(s):
- 2226936
- PAR ID:
- 10646462
- Editor(s):
- na
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- AgriEngineering
- Volume:
- 7
- Issue:
- 8
- ISSN:
- 2624-7402
- Page Range / eLocation ID:
- 252
- Subject(s) / Keyword(s):
- agricultural management reinforcement learning partially observable environments soil N2O emission climate variability uncertainty
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Big Data empowers the farming community with the information needed to optimize resource usage, increase productivity, and enhance the sustainability of agricultural practices. The use of Big Data in farming requires the collection and analysis of data from various sources such as sensors, satellites, and farmer surveys. While Big Data can provide the farming community with valuable insights and improve efficiency, there is significant concern regarding the security of this data as well as the privacy of the participants. Privacy regulations, such as the European Union’s General Data Protection Regulation (GDPR), the EU Code of Conduct on agricultural data sharing by contractual agreement, and the proposed EU AI law, have been created to address the issue of data privacy and provide specific guidelines on when and how data can be shared between organizations. To make confidential agricultural data widely available for Big Data analysis without violating the privacy of the data subjects, we consider privacy-preserving methods of data sharing in agriculture. Synthetic data that retains the statistical properties of the original data but does not include actual individuals’ information provides a suitable alternative to sharing sensitive datasets. Deep learning-based synthetic data generation has been proposed for privacy-preserving data sharing. However, there is a lack of compliance with documented data privacy policies in such privacy-preserving efforts. In this study, we propose a novel framework for enforcing privacy policy rules in privacy-preserving data generation algorithms. We explore several available agricultural codes of conduct, extract knowledge related to the privacy constraints in data, and use the extracted knowledge to define privacy bounds in a privacy-preserving generative model. We use our framework to generate synthetic agricultural data and present experimental results that demonstrate the utility of the synthetic dataset in downstream tasks. We also show that our framework can evade potential threats, such as re-identification and linkage issues, and secure data based on applicable regulatory policy rules.more » « less
-
Agriculture will play a central role in meeting greenhouse gas (GHG) emission targets, as the sector currently contributes ∼22% of global emissions. Because emissions are directly tied to resources employed in farm production, such as land, fertilizer, and ruminant animals, the productivity of input use tends to be inversely related to emissions intensity. We review evidence on how productivity gains in agriculture have contributed to historical changes in emissions, how they affect land use emissions both locally and globally, and how investments in research and development (R&D) affect productivity and therefore emissions. The world average agricultural emissions intensity fell by more than half since 1990, with a strong correlation between a region's agricultural productivity growth and reduction in emissions intensity. Additional investment in agricultural R&D offers an opportunity for cost-effective (more » « less
-
Climate anomalies and changes have complex and critical impacts on agriculture. Given global warming, the scientific community has dramatically increased research on these impacts. During 1996–2022, over 3,000 peer-reviewed papers in the Web of Science Core Collection database have investigated the fields. This study conducted a bibliometric analysis of these papers for systematic mapping and inductive understanding to comprehensively review the research’s status, focus, network, and funding. After almost 30 years, the research is now centered in quantifying climate impacts on crop yields and agriculture productivity while seeking effective adaptation solutions. The hot keywords recently emerged include poverty, food security, water resource, climate service, climate-smart agriculture, sustainability, and policy. They suggest increasing concerns on global food and water shortage and pressing needs for action to adapt to climate change and sustain agricultural productivity. Given the uncertainty of climate change and the complexity of agriculture systems, most current studies are interdisciplinary research combining various agricultural fields with climate, environmental, and socioeconomic sciences. The United States, as the world’s leading food commodity producer, has the most diverse funding agencies and provides the largest number of awards to support the research. Future priority research should take the coupled earth system approach with the food-energy-water nexus principles to provide effective, actionable decision supports at local-regional scales to sustain national agricultural productivity and quantify climate-smart agricultural practices to mitigate global warming.more » « less
-
Machine learning (ML) methods already permeate environmental decision-making, from processing high-dimensional data on earth systems to monitoring compliance with environmental regulations. Of the ML techniques available to address pressing environmental problems (e.g., climate change, biodiversity loss), Reinforcement Learning (RL) may both hold the greatest promise and present the most pressing perils. This paper explores how RL-driven policy refracts existing power relations in the environmental domain while also creating unique challenges to ensuring equitable and accountable environmental decision processes. We leverage examples from RL applications to climate change mitigation and fisheries management to explore how RL technologies shift the distribution of power between resource users, governing bodies, and private industry.more » « less
