SEARCH · Engineering Papers

Results for “data-driven constraint”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2025

A Mass Conservation Relaxed (MCR) LSTM Model for Streamflow Simulation Across CONUS

The recent development of the physics-aware Mass-Conserving Long Short-Term Memory network (MC-LSTM) provides an alternative to other data-driven Deep Learning (DL) models in hydrology. Mass-Conserving Long Short-Term Memory incorporates mass conservation directly into the LSTM architecture. Despite the theoretical advancements, studies have reported a surprisingly limited performance of the MC-LSTM in streamflow simulation. We hypothesize that such a limitation is due to the unrealistic mass conservation scheme in MC-LSTM, which overlooks unobserved incoming water fluxes beyond precipitation. As an attempt to verify this hypothesis, we propose a Mass Conservation Relaxed LSTM (MCR-LSTM), which incorporates a bi-directional mass relaxation (MR) component to account for potential incoming water fluxes beyond precipitation. We train and test the proposed MCR-LSTM model across 531 watersheds in the contiguous United States (CONUS) against three baseline models: the Sacramento Soil Moisture Accounting, LSTM, and MC-LSTM. Our results show that MCR-LSTM outperforms MC-LSTM despite its underperformance compared to LSTM. Specifically, MCR-LSTM's advantage over MC-LSTM is mainly seen in the Plains and Western U.S., where the newly incorporated MR component better simulates water loss and suggests the likely existence of additional incoming water fluxes beyond precipitation, respectively. The novelty and contribution of this study are twofold: firstly, it introduces an alternative physics-aware DL tool (i.e., MCR-LSTM) in hydrology with higher accuracy in specific regions compared to MC-LSTM. Secondly, it provides a diagnosis of regions where strict, precipitation-based mass conservation constraints may be unrealistic in streamflow simulation.

deep learning↗

NASA NTRSDate not supplied

Comparison of Artemis 2 and Artemis 5 Model Outcomes Using the Impact Probabilistic Risk Assessment Tool

BACKGROUND The Artemis campaign is a Moon exploration program with a series of six planned missions, five of which will be crewed. These five crewed missions will contain a single mission segment (space flight), or multiple mission segments involving space flight (Orion), lunar landing (LTV) and/or space habitat (Gateway). Each crewed segment faces the risk of unique medical conditions, necessitating medical sets/kits tailored to those specificities. To support and enable a data-driven and evidence-based decision-making process through out a mission’s life cycle, a software tool called IMPACT was developed. Using probabilistic risk assessment (PRA) methodologies, IMPACT (Informing Mission Planning via Analysis of Complex Tradespaces) is a novel tool built for analyzing the possibility of encountering complex medical risks during space flight, and for identifying the medical resources and capabilities needed to treat those potential at-risk medical conditions. This presentation will seek to compare IMPACT’s computational results upon potential complex space medical conditions (e.g., sprain/strain back or sleep disturbance) using IMPACT’s risk metrics and the associated optimized medical sets/kits between two Artemis missions: single segment Artemis 2 and multi-segmented Artemis 5. OVERVIEW By identifying potential medical conditions in space using input criteria such as crew quantity and composition, certain crew physical characteristics, mission duration and mission activities, IMPACT can produce analyses on the type of medical resources and capabilities needed to produce an optimized medical set/kit to address those medical conditions. IMPACT achieves this by performing hundreds of thousands of Monte Carlo simulations of missions to build aggregate pictures of medical risk. IMPACT’s risk metrics include loss of crew life (LOCL) – a measure of crew mortality due to medical conditions in space, return to definitive care (RTDC) – the need to perform crew evacuation, and task time lost (TTL) – a measure of the inability to perform activities due to crew disability. These risk metrics are applied to every medical condition identified by IMPACT’s computation analyses for every segment of the mission. Medical sets/kits are optimized to address these medical conditions but must fit within the stated Artemis Design Reference Mission (DRM) request for mass and volume physical size constraints. ANTICIPATED ANALYSIS AND CONCLUSION Using two Artemis missions, Artemis 2 and Artemis 5, IMPACT will provide the analyses for comparison of medical set/kit contents based upon mass and/or volume requirements and identify the at-risk medical conditions within both missions. This paper serves as an initial exploration of probabilistic risk assessment (PRA) medical risk calculations between two crewed Artemis missions and is not intended to be deemed the official medical response for the Artemis campaign.

probabilistic risk assessment↗

DOE OSTI2025

Constrained or unconstrained? Neural-network-based equation discovery from data

Throughout many fields, practitioners often rely on differential equations to model systems. Yet, for many applications, the theoretical derivation of such equations and/or the accurate resolution of their solutions may be intractable. Instead, recently developed methods, including those based on parameter estimation, operator subset selection, and neural networks, allow for the data-driven discovery of both ordinary and partial differential equations (PDEs), on a spectrum of interpretability. The success of these strategies is often contingent upon the correct identification of representative equations from noisy observations of state variables and, as importantly and intertwined with that, the mathematical strategies utilized to enforce those equations. Specifically, the latter has been commonly addressed via unconstrained optimization strategies. Representing the PDE as a neural network, we propose to discover the PDE (or the associated operator) by solving a constrained optimization problem and using an intermediate state representation similar to a physics-informed neural network (PINN). The objective function of this constrained optimization problem promotes matching the data, while the constraints require that the discovered PDE is satisfied at a number of spatial collocation points. We present a penalty method and a widely used trust-region barrier method to solve this constrained optimization problem, and we compare these methods on numerical examples. Our results on several example problems demonstrate that the latter constrained method outperforms the penalty method, particularly for higher noise levels or fewer collocation points. This work motivates further exploration into using sophisticated constrained optimization methods in scientific machine learning, as opposed to their commonly used, penalty-method or unconstrained counterparts. For both of these methods, we solve these discovered neural network PDEs with classical methods, such as finite difference methods, as opposed to PINNs-type methods relying on automatic differentiation. Here, we briefly highlight how simultaneously fitting the data while discovering the PDE improves the robustness to noise and other small, yet crucial, implementation details.

Data-driven discovery↗

DOE OSTI2025

Operator learning for energy-efficient building ventilation control with computational fluid dynamics simulation of a real-world classroom

Energy-efficient ventilation control plays an important role in reducing building energy consumption while ensuring occupant health and comfort. While Computational Fluid Dynamics (CFD) simulations provide detailed and physically accurate representations of indoor airflow, their high computational cost limits their use in real-time building control. In this work, we present a neural operator learning framework that combines the physical accuracy of CFD with the computational efficiency of machine learning to enable building ventilation control with the high-fidelity fluid dynamics models. Our method jointly optimizes the airflow supply rates and vent angles to reduce energy use and adhere to air quality constraints. We train an ensemble of neural operator transformer models to learn the mapping from building control actions to airflow fields using high-resolution CFD data. This learned neural operator is then embedded in an optimization-based control framework for building ventilation control. Experimental results show that our approach achieves significant energy savings compared to maximum airflow rate control, rule-based control, as well as data-driven control methods using spatially averaged CO 2 prediction and deep learning–based reduced-order models, while consistently maintaining safe indoor air quality. These results highlight the practicality and scalability of our method in maintaining energy efficiency and indoor air quality in real-world buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗

DOE OSTI2025

Hyperplane decision trees as piecewise linear surrogate models for chemical process design

Recent trends in chemical engineering research point towards an increasing reliance on data-driven modeling approaches. Neural networks, for instance, have proven to be accurate when data is plentiful and high-dimensional, but in many cases, they require computationally-intensive training procedures. Here, in this work, we describe hyperplane decision trees (HT) as a highly expressive and low-compute machine learning model architecture. These models are locally linear and have linear decision boundaries, resulting in a piecewise linear model of the data. This property allows them to be converted into mixed-integer linear constraints which can be globally optimized. Our open-source PyTorch implementation of this method is a fast, flexible, and accessible way to build accurate piecewise linear models of data.

Decision trees↗

DOE OSTI2026

Hydropower potential derived from streamflow extremes for Alaska, USA

Alaska is an expansive region known for its abundant natural resources, including thousands of miles of streams and rivers. These rivers represent potential opportunities for future hydropower development that could provide reliable energy supply for local communities. There is limited long-term high temporal resolution streamflow data available for the region, making data-driven estimates of potential hydropower and its variability across the state challenging. This study provides a novel data-driven approach for hydropower capacity estimation across Alaska. We use supervised machine learning to develop a relationship between the daily and peak flow duration curves in order to augment the size of our dataset from 44 sites to 67 sites. We perform a stochastic hydropower estimation across the 67 sites and identify approximately 1000 MW of total potential hydropower capacity distributed across these sites. Our study provides the first step towards more comprehensive hydropower estimation for this critical region, highlighting the need for future work integrating high-resolution spatial data, community needs, and economic constraints in estimates of potential hydropower development in Alaska.

Hydropower↗

DOE OSTI2024

A portable application framework for energy management and information systems (EMIS) solutions using Brick semantic schema

This paper introduces a portable framework for developing, scaling and maintaining energy management and information systems (EMIS) applications using an ontology-based approach. Key contributions include an interoperable layer based on Brick schema, the formalization of application constraints pertaining metadata and data requirements, and a field demonstration. The framework allows for querying metadata models, fetching data, preprocessing, and analyzing data, thereby offering a modular and flexible workflow for application development. Its effectiveness is demonstrated through a case study involving the development and implementation of a data-driven anomaly detection tool for the photovoltaic systems installed at the Politecnico di Torino, Italy. During eight months of testing, the framework was used to tackle practical challenges including: (i) developing a machine learning-based anomaly detection pipeline, (ii) replacing data-driven models during operation, (iii) optimizing model deployment and retraining, (iv) handling critical changes in variable naming conventions and sensor availability (v) extending the pipeline from one system to additional ones.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2024

Power generation forecasting for solar plants based on Dynamic Bayesian networks by fusing multi-source information

A Dynamic Bayesian network (DBN) model for solar power generation forecasting in solar plants is proposed in this paper. The key idea is to fuse sensor data, operational indicators, meteorological data, lagged output power information, and model errors for more accurate short-term (e.g., hours) and mid-term (e.g., days to weeks) power generation forecasting. The proposed DBN augments automated data-driven structure learning with expert knowledge encoding using continuous and categorical data given constraints to represent causal relationships within a solar inverter system. Additionally, an error compensation mechanism is proposed to capture temporal fluctuation. The effectiveness of the DBN on solar power generation forecasting was evaluated by rolling window analysis with one-year testing data collected from a local solar plant. The proposed DBN is compared with four state-of-art methods including support-vector regression (SVR), k-nearest neighbors (kNN), artificial neural network (ANN), and long short-term memory (LSTM) models. The result show that the proposed DBN achieves better accuracy in general, and it is not as data-hungry as some neural network-based models. The proposed DBN is also shown to have robust and consistent forecasting power with different forecasting horizons. The accuracy is 92% - 95% from one hour to one week ahead forecasting.

14 SOLAR ENERGY↗

DOE OSTI2026

Towards a self-driving trigger at the LHC: adaptive response in real time

Real-time data filtering and selection—or trigger—systems at high-throughput scientific facilities such as the experiments at the Large Hadron Collider must process extremely high-rate data streams under stringent bandwidth, latency, and storage constraints. Yet these systems are typically designed as static, hand-tuned menus of selection criteria grounded in prior knowledge and simulation. In this work, we further explore the concept of a self-driving trigger, an autonomous data-filtering framework that reallocates resources and adjusts thresholds dynamically in real-time to optimize signal efficiency, rate stability, and computational cost as instrumentation and environmental conditions evolve. We introduce a benchmark ecosystem to emulate realistic collider scenarios and demonstrate real-time optimization of a menu including canonical energy sum triggers as well as modern anomaly-detection algorithms that target non-standard event topologies using machine learning. Using simulated data streams and publicly available collision data from the Compact Muon Solenoid experiment, we demonstrate the capability to dynamically and automatically optimize trigger performance under specific cost objectives without manual retuning. Our adaptive strategy shifts trigger design from static menus with heuristic tuning to intelligent, automated, data-driven control, unlocking greater flexibility and discovery potential in future high-energy physics analyses.

Emami, Shaghayegh [Michigan U.] (ORCID:00090007589↗

DOE OSTI2025

EMPDF : inferring the Milky Way mass with data-driven distribution function in phase space

We introduce the emPDF (empirical distribution function), a novel dynamical modelling method that infers the gravitational potential from kinematic tracers with optimal statistical efficiency under the minimal assumption of steady state. emPDF determines the best-fitting potential by maximizing the similarity between instantaneous kinematics and the time-averaged phase-space distribution function (DF), which is empirically constructed from observation upon the theoretical foundation of oPDF (Han et al. 2016). This approach eliminates the need for presumed functional forms of DFs or orbit libraries required by conventional DF- or orbit-based methods. emPDF stands out for its flexibility, efficiency, and capability in handling observational effects, making it preferable to the popular Jeans equation or other minimal assumption methods, especially for the Milky Way (MW) outer halo where tracers often have limited sample size and poor data quality. We apply emPDF to infer the MW mass profile using Gaia DR3 data of satellite galaxies and globular clusters, obtaining enclosed masses of M (,r) = 26±8, 46±8, 90±13⁠, and 149±40 x 10 10 M ⊙ at r = 30, 50, 100⁠, and 200 kpc, respectively. These are consistent with the updated constraints from simulation-informed DF fitting (Li et al. 2020). While the simulation-informed DF offers superior precision owing to the additional information extracted from simulations, emPDF is independent of such supplementary knowledge and applicable to general tracer populations. emPDF is currently implemented for tracers with complete 6D kinematics within spherical potentials, but it can potentially be extended to address more general problems.

Astrophysics of Galaxies (astro-ph.GA)↗

DOE OSTI2026

Dark Energy Survey Year 3 results: Simulation-based 𝑤CDM inference from weak lensing and galaxy clustering maps with deep learning: Analysis design

Data-driven approaches using deep learning are emerging as powerful techniques to extract non-Gaussian information from cosmological large-scale structure. Here, this work presents the first simulation-based inference (SBI) pipeline that combines weak lensing and galaxy clustering maps in a realistic Dark Energy Survey Year 3 (DES Y3) configuration and serves as preparation for a forthcoming analysis of the survey data. We develop a scalable forward model based on the CosmoGridV1 suite of N-body simulations to generate over one million self-consistent mock realizations of DES Y3 at the map level. Leveraging this large dataset, we train deep graph convolutional neural networks on the full survey footprint in spherical geometry to learn low-dimensional features that approximately maximize mutual information with target parameters. These learned compressions enable neural density estimation of the implicit likelihood via normalizing flows in a ten-dimensional parameter space spanning cosmological 𝑤CDM, intrinsic alignment, and linear galaxy bias parameters, while marginalizing over baryonic, photometric redshift, and shear bias nuisances. To ensure robustness, we extensively validate our inference pipeline using synthetic observations derived from both systematic contaminations in our forward model and independent Buzzard galaxy catalogs. Our forecasts yield significant improvements in cosmological parameter constraints, achieving 2−3× higher figures of merit in the 𝛺 𝑚 − 𝑆 8 plane relative to our implementation of baseline two-point statistics and effectively breaking parameter degeneracies through probe combination. These results demonstrate the potential of SBI analyses powered by deep learning for upcoming Stage-IV wide-field imaging surveys.

Thomsen, A. [Zurich, ETH] (ORCID:0000000203099021)↗

DOE OSTI2024

Constructing Data-Driven Predictions at the Far Detector for NOvA's Neutrino Oscillation Analysis.

NOvA, is a two-detector, long-baseline neutrino oscillation experiment located at Fermilab, Batavia, IL, USA. It is designed primarily to constrain neutrino oscillation parameters using $\nu_\mu \ (\bar{\nu}_\mu)$ disappearance and $\nu_e \ (\bar{\nu}_e)$ appearance data. The Neutrinos at Main Injector (NuMI) beamline at Fermilab provides a high purity 900 KW intense beam of neutrinos and anti-neutrinos to NOvA. The NOvA Near Detector, located 100m underground and 1km away from the beam source, observes the un-oscillated $\nu_\mu \ (\bar{\nu}_\mu)$ and beam $\nu_e \ (\bar{\nu}_e)$ event spectrum. The Far Detector, located in Ash River, MN, USA, is 809 km from the ND and records the oscillated $\nu_e \ (\bar{\nu}_e)$ and the un-oscillated $\nu_\mu \ (\bar{\nu}_\mu)$ event spectrum. NOvA uses a data-driven technique called extrapolation to predict the expected number of $\nu_\mu \ (\bar{\nu}_\mu)$ and $\nu_e \ (\bar{\nu}_e)$ events at the Far Detector using the Near Detector data. The use of data from a functionally equivalent Near Detector provides a powerful constraint on the systematic uncertainties in NOvA neutrino oscillation analyses. As NOvA continues to add data statistics, a robust constraint on systematics becomes more crucial for neutrino oscillation analysis. The details of the NOvA neutrino oscillation analysis framework and how it constrains dominant systematic uncertainties using the Near Detector data will be discussed in this poster.

43 PARTICLE ACCELERATORS↗

DOE OSTI2025

Probabilistic Deliverability Assessment of Distributed Energy Resources via Scenario-Based AC Optimal Power Flow

As electric grids decarbonize and distributed energy resources (DERs) become increasingly prevalent, interconnection assessments must evolve to reflect operational variability and control flexibility. This paper highlights key modeling limitations observed in practice and reviews approaches for modeling uncertainty. It then introduces a Probabilistic Deliverability Assessment (PDA) framework designed to complement and extend existing procedures. The framework integrates scenario-based AC optimal power flow (AC OPF), corrective dispatch, and optional multi-temporal constraints. Together, these form a structured methodology for quantifying DER utilization, deliverability, and reliability under uncertainty in load, generation, and topology. Outputs include interpretable metrics with confidence intervals that inform siting decisions and evaluate compliance with reliability thresholds across sampled operating conditions. A case study on Puerto Rico’s publicly available bulk power system model demonstrates the framework’s application using minimal input data, consistent with current interconnection practice. Across staged fossil generation retirements, the PDA identifies high-value DER sites and regions requiring additional reactive power support. Results are presented through mean dispatch signals, reliability metrics, and geospatial visualizations, demonstrating how the framework provides transparent, data-driven siting recommendations. The framework’s modular design supports incremental adoption within existing workflows, encouraging broader use of AC OPF in interconnection and planning contexts.

14 SOLAR ENERGY↗

NASA NTRS1994

Performance results of cooperating expert systems in a distributed real-time monitoring system

There are numerous definitions for real-time systems, the most stringent of which involve guaranteeing correct system response within a domain-dependent or situationally defined period of time. For applications such as diagnosis, in which the time required to produce a solution can be non-deterministic, this requirement poses a unique set of challenges in dynamic modification of solution strategy that conforms with maximum possible latencies. However, another definition of real time is relevant in the case of monitoring systems where failure to supply a response in the proper (and often infinitesimal) amount of time allowed does not make the solution less useful (or, in the extreme example of a monitoring system responsible for detecting and deflecting enemy missiles, completely irrelevant). This more casual definition involves responding to data at the same rate at which it is produced, and is more appropriate for monitoring applications with softer real-time constraints, such as interplanetary exploration, which results in massive quantities of data transmitted at the speed of light for a number of hours before it even reaches the monitoring system. The latter definition of real time has been applied to the MARVEL system for automated monitoring and diagnosis of spacecraft telemetry. An early version of this system has been in continuous operational use since it was first deployed in 1989 for the Voyager encounter with Neptune. This system remained under incremental development until 1991 and has been under routine maintenance in operations since then, while continuing to serve as an artificial intelligence (AI) testbed in the laboratory. The system architecture has been designed to facilitate concurrent and cooperative processing by multiple diagnostic expert systems in a hierarchical organization. The diagnostic modules adhere to concepts of data-driven reasoning, constrained but complete nonoverlapping domains, metaknowledge of global consequences of anomalous data, hierarchical reporting of problems that extend beyond a single domain, and shared responsibility for problems that overlap domains. The system enables efficient diagnosis of complex system failures in real-time environments with high data volumes and moderate failure rates, as indicated by extensive performance measurements.

Schwuttke, U. M.↗

NASA NTRS1999

SIRTF Science Operations System Design

SIRTF Science Operations System Design William B. Green Manager, SIRTF Science Center California Institute of Technology M/S 310-6 1200 E. California Blvd., Pasadena CA 91125 (626) 395 8572 Fax (626) 568 0673 bgreen@ipac.caltech.edu. The Space Infrared Telescope Facility (SIRTF) will be launched in December 2001, and perform an extended series of science observations at wavelengths ranging from 20 to 160 microns for five years or more. The California Institute of Technology has been selected as the home for the SIRTF Science Center (SSC). The SSC will be responsible for evaluating and selecting observation proposals, providing technical support to the science community, performing mission planning and science observation scheduling activities, instrument calibration during operations and instrument health monitoring, production of archival quality data products, and management of science research grants. The science payload consists of three instruments delivered by instrument Principal Investigators located at University of Arizona, Cornell, and Harvard Smithsonian Astrophysical Observatory. The SSC is responsible for design, development, and operation of the Science Operations System (SOS) which will support the functions assigned to the SSC by NASA. The SIRTF spacecraft, mission profile, and science instrument design have undergone almost ten years of refinement. SIRTF development and operations activities are highly cost constrained. The cost constraints have impacted the design of the SOS in several ways. The Science Operations System has been designed to incorporate a set of efficient, easy to use tools which will make it possible for scientists to propose observation sequences in a rapid and automated manner. The use of highly automated tools for requesting observations will simplify the long range observatory scheduling process, and the short term scheduling of science observations. Pipeline data processing will be highly automated and data-driven, utilizing a variety of tools developed at JPL, the instrument development teams, and Space Telescope Science Institute to automate processing. An incremental ground data system development approach has been adopted, featuring periodic deliveries that are validated with the flight hardware throughout the various phases of system level development and testing. This approach minimizes development time and decreases operations risk. This paper will describe the top level architecture of the SOS and the basic design concepts. A summary of the incremental development approach will be presented. Examples of the unique science user tools now under final development prior to the first proposal call scheduled for mid-2000 will be shown.

Green, William↗

NASA NTRS2017

Variability and Quasi-Decadal Changes in the Methane Budget over the Period 2000-2012

Following the recent Global Carbon Project (GCP) synthesis of the decadal methane (CH4) budget over 2000- 2012, we analyse here the same dataset with a focus on quasi-decadal and inter-annual variability in CH4 emissions. The GCP dataset integrates results from top-down studies (exploiting atmospheric observations within an atmospheric inverse-modelling framework) and bottom-up models (including process-based models for estimating land surface emissions and atmospheric chemistry), inventories of anthropogenic emissions, and data-driven approaches. The annual global methane emissions from top-down studies, which by construction match the observed methane growth rate within their uncertainties, all show an increase in total methane emissions over the period 2000-2012, but this increase is not linear over the 13 years. Despite differences between individual studies, the mean emission anomaly of the top-down ensemble shows no significant trend in total methane emissions over the period 2000-2006, during the plateau of atmospheric methane mole fractions, and also over the period 2008-2012, during the renewed atmospheric methane increase. However, the top-down ensemble mean produces an emission shift between 2006 and 2008, leading to 22 [16-32] Tg CH4 yr(exp -1) higher methane emissions over the period 2008-2012 compared to 2002-2006. This emission increase mostly originated from the tropics, with a smaller contribution from mid-latitudes and no significant change from boreal regions. The regional contributions remain uncertain in top-down studies. Tropical South America and South and East Asia seem to contribute the most to the emission increase in the tropics. However, these two regions have only limited atmospheric measurements and remain therefore poorly constrained. The sectorial partitioning of this emission increase between the periods 2002-2006 and 2008-2012 differs from one atmospheric inversion study to another. However, all top-down studies suggest smaller changes in fossil fuel emissions (from oil, gas, and coal industries) compared to the mean of the bottom-up inventories included in this study. This difference is partly driven by a smaller emission change in China from the top-down studies compared to the estimate in the Emission Database for Global Atmospheric Research (EDGARv4.2) inventory, which should be revised to smaller values in a near future. We apply isotopic signatures to the emission changes estimated for individual studies based on five emission sectors and find that for six individual top-down studies (out of eight) the average isotopic signature of the emission changes is not consistent with the observed change in atmospheric 13CH4. However, the partitioning in emission change derived from the ensemble mean is consistent with this isotopic constraint. At the global scale, the top-down ensemble mean suggests that the dominant contribution to the resumed atmospheric CH4 growth after 2006 comes from microbial sources (more from agriculture and waste sectors than from natural wetlands), with an uncertain but smaller contribution from fossil CH4 emissions. In addition, a decrease in biomass burning emissions (in agreement with the biomass burning emission databases) makes the balance of sources consistent with atmospheric 13CH4 observations. In most of the top-down studies included here, OH concentrations are considered constant over the years (seasonal variations but without any inter-annual variability). As a result, the methane loss (in particular through OH oxidation) varies mainly through the change in methane concentrations and not its oxidants. For these reasons, changes in the methane loss could not be properly investigated in this study, although it may play a significant role in the recent atmospheric methane changes as briefly discussed at the end of the paper.

Saunois, Marielle↗

DOE OSTI2023

Efficient Reinforcement Learning for Real-Time Hardware-Based Energy System Experiments: Preprint

In the context of urgent climate challenges and the pressing need for rapid technology development, Reinforcement Learning (RL) stands as a compelling data-driven method for controlling real-world physical systems. However, RL implementation often entails time-consuming and computationally intensive data collection and training processes, rendering them inefficient for real-time applications that lack non-real-time models. To address these limitations, real-time emulation techniques have emerged as valuable tools for the lab-scale rapid prototyping of intricate energy systems. While emulated systems offer a bridge between simulation and reality, they too face constraints, hindering comprehensive characterization, testing, and development. In this research, we construct a surrogate model using limited data from simulated systems, enabling an efficient and effective training process for a Double Deep Q-Network (DDQN) agent for future deployment. Our approach is illustrated through a hydropower application, demonstrating the practical impact of our approach on climate-related technology development.

deep Q-learning↗