Search

Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming industry applications and generating new and improved capabilities for scientific discovery and model building. The adoption of DL in hydrology has so far been gradual, but the field is now ripe for breakthroughs. This paper suggests that DL-based methods can open up a complementary avenue toward knowledge discovery in hydrologic sciences. In the new avenue, machine-learning algorithms present competing hypotheses that are consistent with data. Interrogative methods are then invoked to interpret DL models for scientists to further evaluate. However, hydrology presents many challenges for DL methods, such as data limitations, heterogeneity and co-evolution, and the general inexperience of the hydrologic field with DL. The roadmap toward DL-powered scientific advances will require the coordinated effort from a large community involving scientists and citizens. Integrating process-based models with DL models will help alleviate data limitations. The sharing of data and baseline models will improve the efficiency of the community as a whole. Open competitions could serve as the organizing events to greatly propel growth and nurture data science education in hydrology, which demands a grassroots collaboration. The area of hydrologic DL presents numerous research opportunities that could, in turn, stimulate advances in machine learning as well.

Accurate prediction of snow water equivalent (SWE) can be valuable for water resource managers. Recently, deep learning methods such as long short-term memory (LSTM) have exhibited high accuracy in simulating hydrologic variables and can integrate lagged observations to improve prediction, but their benefits were not clear for SWE simulations. Here we tested an LSTM network with data integration (DI) for SWE in the western United States to integrate 30-day-lagged or 7-day-lagged observations of either SWE or satellite-observed snow cover fraction (SCF) to improve future predictions. SCF proved beneficial only for shallow-snow sites during snowmelt, while lagged SWE integration significantly improved prediction accuracy for both shallow- and deep-snow sites. The median Nash–Sutcliffe model efficiency coefficient (NSE) in temporal testing improved from 0.92 to 0.97 with 30-day-lagged SWE integration, and root-mean-square error (RMSE) and the difference between estimated and observed peak SWE values dmax were reduced by 41% and 57%, respectively. DI effectively mitigated accumulated model and forcing errors that would otherwise be persistent. Moreover, by applying DI to different observations (30-day-lagged, 7-day-lagged), we revealed the spatial distribution of errors with different persistent lengths. For example, integrating 30-day-lagged SWE was ineffective for ephemeral snow sites in the southwestern United States, but significantly reduced monthly-scale biases for regions with stable seasonal snowpack such as high-elevation sites in California. These biases are likely attributable to large interannual variability in snowfall or site-specific snow redistribution patterns that can accumulate to impactful levels over time for nonephemeral sites. These results set up benchmark levels and provide guidance for future model improvement strategies. [ABSTRACT FROM AUTHOR]

Machine learning methods can serve as highly efficient and more objective generators for data-consistent hypotheses that explain how hydrologic systems function. However, they alone cannot differentiate between causal and associative relationships. The hypotheses, however, can be further assessed by the physics and causal relationships encoded in process-based models in a data-centric Bayesian learning framework, as opposed to the typical model-centric one. As a demonstration case, we show how a classification tree algorithm generated competing hypotheses explaining the gradients in storage-streamflow correlation relationships found in basins in the eastern continental US. With the help of numerical experiments using a process-based model, we then rejected soil texture and terrain slope and validated large soil thickness as the factor that causes high correlations between streamflow and storage. Based on our work in soil moisture modeling with deep learning and a trans-disciplinary literature review, we then provide an outlook of how this framework could be migrated to deep-learning-based effort, opening up a new research avenue. [ABSTRACT FROM AUTHOR]

Abstract: Donor- and acceptor-cosubstituted BaTiO3 pellets with the composition of [((Ba,Sr)Pb x )0.98La0.02](Ti0.99Mg0.01)O3 are under investigation for the purpose of developing nonreducible dielectric layers for the applications of multilayered ceramic capacitors (MLCCs) with the base-metal electrodes. The added La and Mg in this composition behaved as donors and acceptors, respectively. The Pb addition changed the Curie temperature and grain size. The dielectric performance was dependent upon the Pb content and the re-oxidation treatment. These 1150°C-annealed pellets demonstrates a satisfying dielectric performance with a grain size of 0.8–1.5μm, dielectric constant of 48,500, loss tangent of 0.13, TCC of −12% at 85°C, and leakage current of 9×10−9 A at 5V (∼20V/cm). The 5% Pb-doped BaTiO3 pellets are most prospective. [Copyright &y& Elsevier]

In the present study, treatment of HEK-293 cells with the synthetic small molecule N-iodoacetyl-tryptophan (I-Trp) at submicromolar concentrations efficiently induced cell apoptosis as judged from the accumulation of sub-G(0) cells and intracellular DNA fragmentation. Activation of all intracellular caspases, except caspase-1, was detected in I-Trp-treated cells. Proteomic analysis revealed that beta-tubulin acted as a specific intracellular target of I-Trp. Protein fingerprinting analysis indicated that the Cys(354) residue in the peptide fragment TAVCDIPPR of beta-tubulin, which is located at the binding interface with chaperonin containing TCP1-beta (CCT-beta), was alkylated by I-Trp. Moreover, site-directed mutagenesis of Cys(354) (Cys-Ala) abolished the incorporation of I-Trp into beta-tubulin, suggesting Cys(354) is indeed the targeting site of I-Trp. Immunoprecipitation showed that the beta-tubulin/CCT-beta complex was constitutively formed but disrupted after treatment with I-Trp. Overexpression of the truncated beta-tubulin (T351-S364) or treatment with I-Trp or the synthetic peptide Myr-TAVCDIPPRG caused more severe cell apoptosis in multidrug-resistant MES-SA/Dx5 cancer cells due to higher levels of CCT-beta relative to wild-type MES-SA cancer cells. Silencing the expression of CCT-beta rendered MES-SA/Dx5 cells less sensitive to I-Trp-induced apoptotic cell death. These findings suggest that the beta-tubulin/CCT-beta complex may serve as an effective chemotherapeutic target for treating clinical tubulin-binding agent-resistant or CCT-beta-overexpressing tumors.