Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “RELEVANT”

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.

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

At least 91 records · Page 5

Organic peroxy radical chemistry in oxidation flow reactors and environmental chambers and their atmospheric relevance

Abstract. Oxidation flow reactors (OFRs) are a promising complement to environmental chambers for investigating atmospheric oxidation processes and secondary aerosol formation. However, questions have been raised about how representative the chemistry within OFRs is of that in the troposphere. We investigate the fates of organic peroxy radicals (RO 2 ), which play a central role in atmospheric organic chemistry, in OFRs and environmental chambers by chemical kinetic modeling and compare to a variety of ambient conditions to help define a range of atmospherically relevant OFR operating conditions. For most types of RO 2 , their bimolecular fates in OFRs are mainly RO 2 + HO 2 and RO 2 + NO, similar to chambers and atmospheric studies. For substituted primary RO 2 and acyl RO 2 , RO 2 + RO 2 can make a significant contribution to the fate of RO 2 in OFRs, chambers and the atmosphere, but RO 2 + RO 2 in OFRs is in general somewhat less important than in the atmosphere. At high NO, RO 2 + NO dominates RO 2 fate in OFRs, as in the atmosphere. At a high UV lamp setting in OFRs, RO 2 + OH can be a major RO 2 fate and RO 2 isomerization can be negligible for common multifunctional RO 2 , both of which deviate from common atmospheric conditions. In the OFR254 operation mode (for which OH is generated only from the photolysis of added O 3 ), we cannot identify any conditions that can simultaneously avoid significant organic photolysis at 254 nm and lead to RO 2 lifetimes long enough ( ∼ 10 s) to allow atmospherically relevant RO 2 isomerization. In the OFR185 mode (for which OH is generated from reactions initiated by 185 nm photons), high relative humidity, low UV intensity and low precursor concentrations are recommended for the atmospherically relevant gas-phase chemistry of both stable species and RO 2 . These conditions ensure minor or negligible RO 2 + OH and a relative importance of RO 2 isomerization in RO 2 fate in OFRs within ∼ × 2 of that in the atmosphere. Under these conditions, the photochemical age within OFR185 systems can reach a few equivalent days at most, encompassing the typical ages for maximum secondary organic aerosol (SOA) production. A small increase in OFR temperature may allow the relative importance of RO 2 isomerization to approach the ambient values. To study the heterogeneous oxidation of SOA formed under atmospherically relevant OFR conditions, a different UV source with higher intensity is needed after the SOA formation stage, which can be done with another reactor in series. Finally, we recommend evaluating the atmospheric relevance of RO 2 chemistry by always reporting measured and/or estimated OH, HO 2 , NO, NO 2 and OH reactivity (or at least precursor composition and concentration) in all chamber and flow reactor experiments. An easy-to-use RO 2 fate estimator program is included with this paper to facilitate the investigation of this topic in future studies.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Concept of Operations Evaluation for Mitigating Space Flight-Relevant Medical Issues in a Planetary Habitat

Introduction: Analogue environments assist the NASA Human Research Program (HRP) in developing capabilities to mitigate high risk issues to crew health and performance for space exploration. The Habitat Demonstration Unit (HDU) is an analogue habitat used to assess space-related products for planetary missions. The Exploration Medical Capability (ExMC) element at the NASA Johnson Space Center (JSC) was tasked with developing planetary-relevant medical scenarios to evaluate the concept of operations for mitigating medical issues in such an environment. Methods: Two medical scenarios were conducted within the simulated planetary habitat with the crew executing two space flight-relevant procedures: Eye Examination with a corneal injury and Skin Laceration. Remote guidance for the crew was provided by a flight surgeon (FS) stationed at a console outside of the habitat. Audio and video data were collected to capture the communication between the crew and the FS, as well as the movements of the crew executing the procedures. Questionnaire data regarding procedure content and remote guidance performance also were collected from the crew immediately after the sessions. Results: Preliminary review of the audio, video, and questionnaire data from the two scenarios conducted within the HDU indicate that remote guidance techniques from an FS on console can help crew members within a planetary habitat mitigate planetary-relevant medical issues. The content and format of the procedures were considered concise and intuitive, respectively. Discussion: Overall, the preliminary data from the evaluation suggest that use of remote guidance techniques by a FS can help HDU crew execute space exploration-relevant medical procedures within a habitat relevant to planetary missions, however further evaluations will be needed to implement this strategy into the complete concept of operations for conducting general space medicine within similar environments

Barsten, Kristina↗

Software Helps Retrieve Information Relevant to the User

The Adaptive Indexing and Retrieval Agent (ARNIE) is a code library, designed to be used by an application program, that assists human users in retrieving desired information in a hypertext setting. Using ARNIE, the program implements a computational model for interactively learning what information each human user considers relevant in context. The model, called a "relevance network," incrementally adapts retrieved information to users individual profiles on the basis of feedback from the users regarding specific queries. The model also generalizes such knowledge for subsequent derivation of relevant references for similar queries and profiles, thereby, assisting users in filtering information by relevance. ARNIE thus enables users to categorize and share information of interest in various contexts. ARNIE encodes the relevance and structure of information in a neural network dynamically configured with a genetic algorithm. ARNIE maintains an internal database, wherein it saves associations, and from which it returns associated items in response to a query. A C++ compiler for a platform on which ARNIE will be utilized is necessary for creating the ARNIE library but is not necessary for the execution of the software.

Mathe, Natalie↗

A Visual Designer of Layer-wise Relevance Propagation Models

Layer-wise Relevance Propagation (LRP) is an emerging and widely-used method for interpreting the prediction results of convolutional neural networks (CNN). LRP developers often select and employ different relevance backpropagation rules and parameters, to compute relevance scores on input images. However, there exists no obvious solution to define a "best" LRP model. A satisfied model is highly reliant on pertinent images and designers' goals. We develop a visual model designer, named as VisLRPDesigner, to overcome the challenges in the design and use of LRP models. Various LRP rules are unified into an integrated framework with an intuitive workflow of parameter setup. VisLRPDesigner thus allows users to interactively configure and compare LRP models. It also facilitates relevance-based visual analysis with two important functions: relevance-based pixel flipping and neuron ablation. Several use cases illustrate the benefits of VisLRPDesigner. The usability and limitation of the visual designer is evaluated by LRP users.

97 MATHEMATICS AND COMPUTING↗

Manufactured solutions for the three-dimensional Euler equations with relevance to Inertial Confinement Fusion

We present a set of manufactured solutions for the three-dimensional (3D) Euler equations. The purpose of these solutions is to allow for code verification against true 3D flows with physical relevance, as opposed to 3D simulations of lower-dimensional problems or manufactured solutions that lack physical relevance. Of particular interest are solutions with relevance to Inertial Confinement Fusion (ICF) capsules. While ICF capsules are designed for spherical symmetry, they are hypothesized to become highly 3D at late time due to phenomena such as Rayleigh–Taylor instability, drive asymmetry, and vortex decay. ICF capsules also involve highly nonlinear coupling between the fluid dynamics and other physics, such as radiation transport and thermonuclear fusion. The manufactured solutions we present are specifically designed to test the terms and couplings in the Euler equations that are relevant to these phenomena. Example numerical results generated with a 3D Finite Element hydrodynamics code are presented, including mesh convergence studies.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

An improved detailed chemical kinetic model for C3-C4 linear and iso-alcohols and their blends with gasoline at engine-relevant conditions

Propanol and butanol isomers have received significant research attention as promising fuel additives or neat biofuels. Robust chemical kinetic models are needed that can provide accurate and efficient predictions of combustion performance across a wide range of engine relevant conditions. Herein, this study seeks to improve the understanding of ignition and combustion behavior of pure C3-C4 linear and iso-alcohols, and their blends with gasoline at engine-relevant conditions. In this work, a kinetic model with improved thermochemistry and reaction kinetics was developed based on recent theoretical calculations of H-atom abstraction and peroxy radical reaction rates. Kinetic model validations are reported, and the current model reproduces the ignition delay times of the C3 and C4 alcohols well. Variations in reactivity over a wide range of temperatures and other operating conditions are also well predicted by the current model. Recent ignition delay time measurements from a rapid compression machine of neat iso-propanol and iso-butanol [Cheng et al., Proc. Combust Inst. (2020)] and blends with a research grade gasoline [Goldsborough et al., Proc. Combust Inst. (2020)] at elevated pressure (20–40 bar) and intermediate temperatures (780–950 K) were used to demonstrate the accuracy of the current kinetic model at conditions relevant to boosted spark-ignition engines. The effects of alcohol blending with gasoline on the autoignition behavior are discussed. The current model captures the suppression of reactivity in the low-temperature and negative-temperature-coefficient (NTC) region when either isopropanol and isobutanol are added to a research grade gasoline. Sensitivity and reaction flux analysis were performed to provide insights into the relevant fuel chemistry of the C3-C4 alcohols.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Development of a novel, physiologically relevant cytotoxicity model: Application to the study of chemotherapeutic damage to mesenchymal stromal cells

There is an increasing need for development of physiologically relevant in-vitro models for testing toxicity, however determining toxic effects of agents which undergo extensive hepatic metabolism can be particularly challenging. If a source of such metabolic enzymes is inadequate within a model system, toxicity from prodrugs may be grossly underestimated. Conversely, the vast majority of agents are detoxified by the liver, consequently toxicity from such agents may be overestimated. In this study we describe the development of a novel in-vitro model, which could be adapted for any toxicology setting. The model utilises HepG2 liver spheroids as a source of metabolic enzymes, which have been shown to more closely resemble human liver than traditional monolayer cultures. A co-culture model has been developed enabling the effect of any metabolised agent on another cell type to be assessed. This has been optimised to enable the study of damaging effects of chemotherapy on mesenchymal stem cells (MSC), the supportive stem cells of the bone marrow. Several optimisation steps were undertaken, including determining optimal culture conditions, confirmation of hepatic P450 enzyme activity and ensuring physiologically relevant doses of chemotherapeutic agents were appropriate for use within the model. The developed model was subsequently validated using several chemotherapeutic agents, both prodrugs and active drugs, with resulting MSC damage closely resembling effects seen in patients following chemotherapy. Minimal modifications would enable this novel co-culture model to be utilised as a general toxicity model, contributing to the drive to reduce animal safety testing and enabling physiologically relevant in-vitro study. -- Highlights: ► An in vitro model was developed for study of drugs requiring hepatic metabolism ► HepG2 spheroids were utilised as a physiologically relevant source of liver enzymes ► The model was optimised to enable study of chemotherapeutic damage to the bone marrow ► Minor modifications would enable application as a general toxicity model.

60 APPLIED LIFE SCIENCES↗

Naloxegol, an opioid antagonist with reduced CNS penetration: Mode-of-action and human relevance for rat testicular tumours

Naloxegol is an opioid antagonist which has been developed for the treatment of patients with opioid induced constipation. In the nonclinical safety program naloxegol was shown to have a very benign toxicity profile. In the rat, but not the mouse, 2-year carcinogenicity study a change in tumour pattern with an increase in testicular Leydig cell tumours (LCT) was observed after dosing at high (supra-pharmacological) concentrations. To establish the basis of the increase in LCT and to assess its potential relevance to humans, studies to exclude and potentially identify mode-of-action (MoA) were performed. A genotoxic mechanism was ruled out following negative results in the Ames, mouse lymphoma, and micronucleus assays. An effect on androgen metabolism was excluded since the treatment of rats with naloxegol for 14 days did not result in any induction of CYP protein levels. It was demonstrated that administration of centrally restricted opioid antagonists naloxegol or methylnaltrexone at high doses induced an increase in LH release with no clear increase in testosterone, in contrast to the centrally acting opioid antagonist naloxone, which showed marked increases in both LH and testosterone. LCT due to increased LH stimulation is common in rats but not documented in humans. Collectively, the lack of genotoxicity signal, the lack of androgen effect, the increase in LH secretion in rats, which is no considered to be relevant for LCT formation in humans, and high margins to clinical exposures, the observed increase in LCT in the rat is not expected to be clinically relevant. - Highlights: • Naloxegol elicited neuroendocrine responses in form of increased LH release. • In contrast to naloxone, naloxegol did not markedly increase testosterone. • Naloxegol treatment showed increases in rat testicular Leydig cell tumours. • A reduction in pituitary tumours was consistent with opioid antagonism. • Increase in LH mediated rat Leydig cell tumours is not relevant for patients.

60 APPLIED LIFE SCIENCES↗

Relevant energy scale of color confinement from lattice QCD

We propose a new lattice framework to extract the relevant gluonic energy scale of QCD phenomena which is based on a 'cut' on link variables in momentum space. This framework is expected to be broadly applicable to all lattice QCD calculations. Using this framework, we quantitatively determine the relevant energy scale of color confinement, through the analyses of the quark-antiquark potential and meson masses. The relevant energy scale of color confinement is found to be below 1.5 GeV in the Landau gauge. In fact, the string tension is almost unchanged even after cutting off the high-momentum gluon component above 1.5 GeV. When the relevant low-energy region is cut, the quark-antiquark potential is approximately reduced to a Coulomb-like potential, and each meson becomes a quasifree quark pair. As an analytical model calculation, we also investigate the dependence of the Richardson potential on the cut, and find the consistent behavior with the lattice result.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Discovering Conformational Sub-States Relevant to Protein Function

Background: Internal motions enable proteins to explore a range of conformations, even in the vicinity of native state. The role of conformational fluctuations in the designated function of a protein is widely debated. Emerging evidence suggests that sub-groups within the range of conformations (or sub-states) contain properties that may be functionally relevant. However, low populations in these sub-states and the transient nature of conformational transitions between these sub-states present significant challenges for their identification and characterization. Methods and Findings: To overcome these challenges we have developed a new computational technique, quasi-anharmonic analysis (QAA). QAA utilizes higher-order statistics of protein motions to identify sub-states in the conformational landscape. Further, the focus on anharmonicity allows identification of conformational fluctuations that enable transitions between sub-states. QAA applied to equilibrium simulations of human ubiquitin and T4 lysozyme reveals functionally relevant sub-states and protein motions involved in molecular recognition. In combination with a reaction pathway sampling method, QAA characterizes conformational sub-states associated with cis/trans peptidyl-prolyl isomerization catalyzed by the enzyme cyclophilin A. In these three proteins, QAA allows identification of conformational sub-states, with critical structural and dynamical features relevant to protein function. Conclusions: Overall, QAA provides a novel framework to intuitively understand the biophysical basis of conformational diversity and its relevance to protein function.

59 BASIC BIOLOGICAL SCIENCES↗

Relevant Additive Manufacturing Materials for Wind Industry

The purpose of this report is to equip wind industry professionals with the relevant material testing and properties of large format extrusion-based additive manufacturing processes. Discussion on the printability and processing of different classes of materials (i.e. low temperature, high temperature, thermoplastics, elastomeric, foam, etc.) is provided as well as relevant test standards and methods. Existing results for materials and properties are detailed. A companion document titled “Additive Manufacturing Design Guidelines for Wind Industry” covers the seven families of additive manufacturing, the relevance of each family to the wind industry, and design guidelines and considerations for the most relevant processes.

17 WIND ENERGY↗

Taming the Wild West: Assessing Impacts-Relevant Climate Data Products (Final Report)

Impacts-relevant Earth system data refers to observational and ESM data that are downscaled, debiased, validated, and provisioned for use by decision-makers. Impacts-relevant Earth system data is essential for mitigation and adaptation planning across a variety of regions and sectors. A vast number of these data products have emerged in recent years, which has led to confusion among stakeholders and scientists as to the best product to use. With no standard evaluation protocol available for these products, the decision on which product to use was sometimes made because it was pragmatic rather than the best product to use. This project sought to develop foundational capabilities around impacts-relevant data products that would support more informed selection and application of these products. This work has been immensely successful, driving several academic publications and supported the development of a community of practice around impacts-relevant data products.

54 ENVIRONMENTAL SCIENCES↗

Medical Scenarios Relevant to Spaceflight

The Medical Operational Support Team (MOST) was tasked by the JSC Space Medicine and Life Sciences Directorate (SLSD) to incorporate medical simulation into 1) medical training for astronaut-crew medical officers (CMO) and medical flight control teams and 2) evaluations of procedures and resources required for medical care aboard the International Space Station (ISS). Development of evidence-based medical scenarios that mimic the physiology observed during spaceflight will be needed for the MOST to complete these two tasks. The MOST used a human patient simulator, the ISS-like resources in the Medical Simulation Laboratory (MSL), and evidence from space operations, military operations and medical literature to develop space relevant medical scenarios. These scenarios include conditions concerning airway management, Advanced Cardiac Life Support (ACLS) and mitigating anaphylactic symptoms. The MOST has used these space relevant medical scenarios to develop a preliminary space medical training regimen for NASA flight surgeons, Biomedical Flight Controllers (Biomedical Engineers; BME) and CMO-analogs. This regimen is conducted by the MOST in the MSL. The MOST has the capability to develop evidence-based space-relevant medical scenarios that can help SLSD I) demonstrate the proficiency of medical flight control teams to mitigate space-relevant medical events and 2) validate nextgeneration medical equipment and procedures for space medicine applications.

Bacal, Kira↗

Corrosion on Mars: An Investigation of Corrosion Mechanisms Under Relevant Simulated Martian Environments

This one-year project was selected by NASA's Science Innovation Fund in FY17 to address Corrosion on Mars which is a problem that has not been addressed before. Corrosion resistance is one of the most important properties in selecting materials for landed spacecraft and structures that will support surface operations for the human exploration of Mars. Currently, the selection of materials is done by assuming that the corrosion behavior of a material on Mars will be the same as that on Earth. This is understandable given that there is no data regarding the corrosion resistance of materials in the Mars environment. However, given that corrosion is defined as the degradation of a metal that results from its chemical interaction with the environment, it cannot be assumed that corrosion is going to be the same in both environments since they are significantly different. The goal of this research is to develop a systematic approach to understand corrosion of spacecraft materials on Mars by conducting a literature search of available data, relevant to corrosion in the Mars environment, and by performing preliminary laboratory experiments under relevant simulated Martian conditions. This project was motivated by the newly found evidence for the presence of transient liquid brines on Mars that coincided with the suggestion, by a team of researchers, that some of the structural degradation observed on Curiosity's wheels may be caused by corrosive interactions with the brines, while the most significant damage was attributed to rock scratching. An extensive literature search on data relevant to Mars corrosion confirmed the need for further investigation of the interaction between materials used for spacecraft and structures designed to support long-term surface operations on Mars. Simple preliminary experiments, designed to look at the interaction between an aerospace aluminum alloy (AA7075-T73) and the gases present in the Mars atmosphere, at 20degC and a pressure of 700 Pa, showed that there is an interaction between the small amount of oxygen present in the Mars gas and the alloy when there is a scratch that removes the protective aluminum oxide film. Further studies are needed to consider many other important components of the Mars environment that can affect this interaction such as: the effect of oxidants, the effect of radiation on their oxidizing properties and the possible catalytic effects of the clays present in the Martian regolith. The results of this one-year project provide strong justification for further investigation of the corrosion mechanism of materials relevant to long-term surface operations in support of future human exploration missions on Mars.

Perchlorates↗

Evaluation of Technology Concepts for Traffic Data Management and Relevant Audio for Datalink in Commercial Airline Flight Decks

Datalink is currently operational for departure clearances and in oceanic environments and is currently being tested in high altitude domestic enroute airspace. Interaction with even simple datalink clearances may create more workload for flight crews than the voice system they replace if not carefully designed. Datalink may also introduce additional complexity for flight crews with hundreds of uplink messages now defined for use. Finally, flight crews may lose airspace awareness and operationally relevant information that they normally pickup from Air Traffic Control (ATC) voice communications with other aircraft (i.e., “party-line” transmissions). Once again, automation may be poised to increase workload on the flight deck for incremental benefit. Datalink implementation to support future air traffic management concepts needs to be carefully considered, understanding human communication norms and especially, the change from voice- to text-based communications modality and its effect on pilot workload and situation awareness. Increasingly autonomous systems, where autonomy is designed to support human-autonomy teaming, may be suited to solve these issues. NASA is conducting research and development of increasingly autonomous systems, utilizing machine-learning algorithms seamlessly integrated with humans whereby task performance of the combined system is significantly greater than the individual components. Increasingly autonomous systems offer the potential for significantly improved levels of performance and safety that are superior to either human or automation alone. Two increasingly autonomous systems concepts - a traffic data manager and a conversational co-pilot - were developed to intelligently address the datalink issues in a complex, future state environment with significant levels of traffic. The system was tested for suitability of datalink usage for terminal airspace. The traffic data manager allowed for automated declutter of the Automatic Dependent Surveillance-Broadcast (ADS-B) display. The system determined relevant traffic for display based on machine learning algorithms trained by experienced human pilot behaviors. The conversational co-pilot provided relevant audio air traffic control messages based on context and proximity to ownship. Both systems made use of the connected aircraft concepts to provide intelligent context to determine relevancy above and beyond proximity to ownship. A human-in-the-loop test was conducted in NASA Langley Research Center’s Integration Flight Deck B-737-800 simulator to evaluate the traffic data manager and the conversational co-pilot. Twelve airline crews flew various normal and non-normal procedures and their actions and performance were recorded in response to the procedural events. This paper details the flight crew performance and evaluation during the events.

Etherington, Timothy↗

Discovering conformational sub-states relevant to protein function

Internal motions enable proteins to explore a range of conformations, even in the vicinity of native state. The role of conformational fluctuations in the designated function of a protein is widely debated. Emerging evidence suggests that sub-groups within the range of conformations (or sub-states) contain properties that may be functionally relevant. However, low populations in these sub-states and the transient nature of conformational transitions between these sub-states present significant challenges for their identification and characterization. To overcome these challenges we have developed a new computational technique, quasi-anharmonic analysis (QAA). QAA utilizes higher-order statistics of protein motions to identify sub-states in the conformational landscape. Further, the focus on anharmonicity allows identification of conformational fluctuations that enable transitions between sub-states. QAA applied to equilibrium simulations of human ubiquitin and T4 lysozyme reveals functionally relevant sub-states and protein motions involved in molecular recognition. In combination with a reaction pathway sampling method, QAA characterizes conformational sub-states associated with cis/trans peptidyl-prolyl isomerization catalyzed by the enzyme cyclophilin A. In these three proteins, QAA allows identification of conformational sub-states, with critical structural and dynamical features relevant to protein function. Overall, QAA provides a novel framework to intuitively understand the biophysical basis of conformational diversity and its relevance to protein function.

59 BASIC BIOLOGICAL SCIENCES↗

Relevant multi-setting tight Bell inequalities for qubits and qutrits

In the celebrated paper [D. Collins, N. Gisin, J. Phys. A Math. Gen. 37 (2004) 1775], Collins and Gisin presented for the first time a three-setting Bell inequality (here we call it CG inequality for simplicity) which is relevant to the Clauser-Horne-Shimony-Holt (CHSH) inequality. Inspired by their brilliant ideas, we obtained some multi-setting tight Bell inequalities, which are relevant to the CHSH inequality and the CG inequality. Moreover, we generalized the method in the paper [J.L. Chen, D.L. Deng, Phys. Rev. A 79 (2009) 012115] to construct Bell inequality for qubits to higher dimensional system. Based on the generalized method, we present, for the first time, a three-setting tight Bell inequality for two qutrits, which is maximally violated by nonmaximally entangled states and relevant to the Collins-Gisin-Linden-Massar-Popescu inequality.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

Deep learning (DL), a new generation of artificial neural network research, has transformed industries, daily lives, and various scientific disciplines in recent years. DL represents significant progress in the ability of neural networks to automatically engineer problem-relevant features and capture highly complex data distributions. I argue that DL can help address several major new and old challenges facing research in water sciences such as interdisciplinarity, data discoverability, hydrologic scaling, equifinality, and needs for parameter regionalization. This review paper is intended to provide water resources scientists and hydrologists in particular with a simple technical overview, transdisciplinary progress update, and a source of inspiration about the relevance of DL to water. The review reveals that various physical and geoscientific disciplines have utilized DL to address data challenges, improve efficiency, and gain scientific insights. DL is especially suited for information extraction from image-like data and sequential data. Techniques and experiences presented in other disciplines are of high relevance to water research. Meanwhile, less noticed is that DL may also serve as a scientific exploratory tool. A new area termed AI neuroscience , where scientists interpret the decision process of deep networks and derive insights, has been born. This budding subdiscipline has demonstrated methods including correlation-based analysis, inversion of network-extracted features, reduced-order approximations by interpretable models, and attribution of network decisions to inputs. Moreover, DL can also use data to condition neurons that mimic problem-specific fundamental organizing units, thus revealing emergent behaviors of these units. Vast opportunities exist for DL to propel advances in water sciences.

54 ENVIRONMENTAL SCIENCES↗