Abstract The process of evapotranspiration transfers liquid water from vegetation and soil surfaces to the atmosphere, the so-called latent heat flux ( Q LE ), and modulates the Earth’s energy, water, and carbon cycle. Vegetation controls Q LE by regulating leaf stomata opening (surface resistance r s in the Big Leaf approach) and by altering surface roughness (aerodynamic resistance r a ). Estimating r s and r a across different vegetation types is a key challenge in predicting Q LE . We propose a hybrid approach that combines mechanistic modeling and machine learning for modeling Q LE . The hybrid model combines a feed-forward neural network which estimates the resistances from observations as intermediate variables and a mechanistic model in an end-to-end setting. In the hybrid modeling setup, we make use of the Penman–Monteith equation in conjunction with multi-year flux measurements across different forest and grassland sites from the FLUXNET database. This hybrid model setup is successful in predicting Q LE , however, this approach leads to equifinal solutions in terms of estimated physical parameters. We follow two different strategies to constrain the hybrid model and therefore control for the equifinality that arises when the two resistances are estimated simultaneously. One strategy is to impose an a priori constraint on r a based on mechanistic assumptions (theory-driven strategy), while the other strategy makes use of more observational data and adds a constraint in predicting r a through multi-task learning of both latent and sensible heat flux ( Q H ; data-driven strategy) together. Our results show that all hybrid models predict the target variables with a high degree of success, with R 2 = 0.82–0.89 for grasslands and R 2 = 0.70–0.80 for forest sites at the mean diurnal scale. The predicted r s and r a show strong physical consistency across the two regularized hybrid models, but are physically implausible in the under-constrained hybrid model. The hybrid models are robust in reproducing consistent results for energy fluxes and resistances across different scales (diurnal, seasonal, and interannual), reflecting their ability to learn the physical dependence of the target variables on the meteorological inputs. As a next step, we propose to test these heavily observation-informed parameterizations derived through hybrid modeling as a substitute for ad hoc formulations in Earth system models.
more »
« less
Machine learning predictions of irradiation embrittlement in reactor pressure vessel steels
Irradiation increases the yield stress and embrittles light water reactor (LWR) pressure vessel steels. In this study, we demonstrate some of the potential benefits and risks of using machine learning models to predict irradiation hardening extrapolated to low flux, high fluence, extended life conditions. The machine learning training data included the Irradiation Variable for lower flux irradiations up to an intermediate fluence, plus the Belgian Reactor 2 and Advanced Test Reactor 1 for very high flux irradiations, up to very high fluence. Notably, the machine learning model predictions for the high fluence, intermediate flux Advanced Test Reactor 2 irradiations are superior to extrapolations of existing hardening models. The successful extrapolations showed that machine learning models are capable of capturing key intermediate flux effects at high fluence. Similar approaches, applied to expanded databases, could be used to predict hardening in LWRs under life-extension conditions.
more » « less- NSF-PAR ID:
- 10366646
- Author(s) / Creator(s):
- ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more »
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- npj Computational Materials
- Volume:
- 8
- Issue:
- 1
- ISSN:
- 2057-3960
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Microstructural changes induced by helium implantation in materials lead to volumetric swelling and mechanical property changes. How these properties are linked and establishing direct relationships can be difficult due to the underlying material’s microstructure evolution. Some materials also experience a phase change due to irradiation damage making them even more complex to analyze. Here, single crystalline Si (100) was used to establish a relationship among these parameters. The swelling height as a function of implantation fluence can equally fit a linear relationship. Solely irradiation induced defects are observed at low fluence below 5.0 × 10 16 ions/cm 2 . An abrupt amorphous and crystalline mixed layer of ∼200 nm thick within a highly damaged polycrystalline matrix is observed when implantation fluence exceeds 5.0 × 10 16 ions/cm 2 , leading to the appearance of irradiation induced swelling and hardening behavior. As the fluence increases beyond 1.0 × 10 17 ions/cm 2 , the amorphous layer expands in size and the bubble size distribution takes the form of a Gaussian distribution with a maximum size of up to 6.4 nm, which causes a further increase in the height of swelling. Furthermore, irradiation induced softening appeared due to the enlarged bubble size and amorphization.more » « less
-
more » « less
Abstract Three-quarters of lifetime mental illness occurs by the age of 24, but relatively little is known about how to robustly identify youth at risk to target intervention efforts known to improve outcomes. Barriers to knowledge have included obtaining robust predictions while simultaneously analyzing large numbers of different types of candidate predictors. In a new, large, transdiagnostic youth sample and multidomain high-dimension data, we used 160 candidate predictors encompassing neural, prenatal, developmental, physiologic, sociocultural, environmental, emotional and cognitive features and leveraged three different machine learning algorithms optimized with a novel artificial intelligence meta-learning technique to predict individual cases of anxiety, depression, attention deficit, disruptive behaviors and post-traumatic stress. Our models tested well in unseen, held-out data (AUC ≥ 0.94). By utilizing a large-scale design and advanced computational approaches, we were able to compare the relative predictive ability of neural versus psychosocial features in a principled manner and found that psychosocial features consistently outperformed neural metrics in their relative ability to deliver robust predictions of individual cases. We found that deep learning with artificial neural networks and tree-based learning with XGBoost outperformed logistic regression with ElasticNet, supporting the conceptualization of mental illnesses as multifactorial disease processes with non-linear relationships among predictors that can be robustly modeled with computational psychiatry techniques. To our knowledge, this is the first study to test the relative predictive ability of these gold-standard algorithms from different classes across multiple mental health conditions in youth within the same study design in multidomain data utilizing >100 candidate predictors. Further research is suggested to explore these findings in longitudinal data and validate results in an external dataset.
-
Abstract Many short gamma-ray bursts (GRBs) originate from binary neutron star mergers, and there are several theories that predict the production of coherent, prompt radio signals either prior, during, or shortly following the merger, as well as persistent pulsar-like emission from the spin-down of a magnetar remnant. Here we present a low frequency (170–200 MHz) search for coherent radio emission associated with nine short GRBs detected by the Swift and/or Fermi satellites using the Murchison Widefield Array (MWA) rapid-response observing mode. The MWA began observing these events within 30–60 s of their high-energy detection, enabling us to capture any dispersion delayed signals emitted by short GRBs for a typical range of redshifts. We conducted transient searches at the GRB positions on timescales of 5 s, 30 s, and 2 min, resulting in the most constraining flux density limits on any associated transient of 0.42, 0.29, and 0.084 Jy, respectively. We also searched for dispersed signals at a temporal and spectral resolution of 0.5 s and 1.28 MHz, but none were detected. However, the fluence limit of 80–100 Jy ms derived for GRB 190627A is the most stringent to date for a short GRB. Assuming the formation of a stable magnetar for this GRB, we compared the fluence and persistent emission limits to short GRB coherent emission models, placing constraints on key parameters including the radio emission efficiency of the nearly merged neutron stars ( $\epsilon_r\lesssim10^{-4}$ ), the fraction of magnetic energy in the GRB jet ( $\epsilon_B\lesssim2\times10^{-4}$ ), and the radio emission efficiency of the magnetar remnant ( $\epsilon_r\lesssim10^{-3}$ ). Comparing the limits derived for our full GRB sample (along with those in the literature) to the same emission models, we demonstrate that our fluence limits only place weak constraints on the prompt emission predicted from the interaction between the relativistic GRB jet and the interstellar medium for a subset of magnetar parameters. However, the 30-min flux density limits were sensitive enough to theoretically detect the persistent radio emission from magnetar remnants up to a redshift of $z\sim0.6$ . Our non-detection of this emission could imply that some GRBs in the sample were not genuinely short or did not result from a binary neutron star merger, the GRBs were at high redshifts, these mergers formed atypical magnetars, the radiation beams of the magnetar remnants were pointing away from Earth, or the majority did not form magnetars but rather collapse directly into black holes.more » « less
-
more » « less
Abstract Solar energetic particle (SEP) events and their major subclass, solar proton events (SPEs), can have unfavorable consequences on numerous aspects of life and technology, making them one of the most harmful effects of solar activity. Garnering knowledge preceding such events by studying operational data flows is essential for their forecasting. Considering only solar cycle (SC) 24 in our previous study, we found that it may be sufficient to only utilize proton and soft X-ray (SXR) parameters for SPE forecasts. Here, we report a catalog recording ≥10 MeV ≥10 particle flux unit SPEs with their properties, spanning SCs 22–24, using NOAA’s Geostationary Operational Environmental Satellite flux data. We report an additional catalog of daily proton and SXR flux statistics for this period, employing it to test the application of machine learning (ML) on the prediction of SPEs using a support vector machine (SVM) and extreme gradient boosting (XGBoost). We explore the effects of training models with data from one
and two SCs, evaluating how transferable a model might be across different time periods. XGBoost proved to be more accurate than SVMs for almost every test considered, while also outperforming operational SWPC NOAA predictions and a persistence forecast. Interestingly, training done with SC 24 produces weaker true skill statistic and Heidke skill scores2, even when paired with SC 22 or SC 23, indicating transferability issues. This work contributes toward validating forecasts using long-spanning data—an understudied area in SEP research that should be considered to verify the cross cycle robustness of ML-driven forecasts.
