Marie and BERT-A Knowledge Graph Embedding Based Question Answering System for Chemistry.

This paper presents a novel knowledge graph question answering (KGQA) system for chemistry, which is implemented on hybrid knowledge graph embeddings, aiming to provide fact-oriented information retrieval for chemistry-related research and industrial applications. Unlike other existing designs, the system operates on multiple embedding spaces, which use various embedding methods and queries the embedding spaces in parallel. With the answers returned from multiple embedding spaces, the system leverages a score alignment model to adjust the answer scores and rerank the answers. Further, the system implements an algorithm to derive implicit multihop relations to handle the complexities of deep ontologies and improve multihop question answering. The system also implements a BERT-based bidirectional entity-linking model to enhance the robustness and accuracy of the entity-linking module. The system uses a joint numerical embedding model to efficiently handle numerical filtering questions. Further, it can invoke semantic agents to perform dynamic calculations autonomously. Finally, the KGQA system handles numerous chemical reaction mechanisms using semantic parsing supported by a Linked Data Fragment server. This paper evaluates the accuracy of each module within the KGQA system with a chemistry question data set.

Blockchain Technology in the Chemical Industry.

This article presents a review of the application of blockchain and blockchain-based smart contracts in the chemical and related industries. We introduce the basic concepts of blockchain and smart contracts and explain how some of their features are enabled. We review several typical or novel applications of blockchain and smart contract technologies and their enabling concepts and underlying technologies. We classify the selected literature into five categories and discuss their motivations and technical designs. We recognize that the trend of decentralization creates a need to use blockchain and smart contracts to implement trust and distributed control mechanisms. We also speculate on future applications of blockchain and smart contracts. We believe that, in the future, blockchains with different consensus mechanisms will be studied and applied to achieve more efficient and practical decentralized systems. Also, blockchain-based smart contracts will be more widely applied to enhance autonomous distributed controls in decentralized systems.

On the Viability of Video Imaging in Leak Rate Quantification: A Theoretical Error Analysis.

Optical gas imaging through multispectral cameras is a promising technique for mitigation of methane emissions through localization and quantification of emissions sources. While more advanced cameras developed in recent years have led to lower uncertainties in measuring gas concentrations, a systematic analysis of the uncertainties associated with leak rate estimation have been overlooked. We present a systematic categorization of the involved uncertainties with a focus on a theoretical analysis of projection uncertainties that are inherent to this technique. The projection uncertainties are then quantified using Large Eddy Simulation experiments of a point source release into the atmosphere. Our results show that while projection uncertainties are typically about 5% of the emission rate, low acquisition times and observation of the gas plume at small distances from the emission source (<10 m) can amount to errors of about 20%. Further, we found that acquisition times on the order of tens of seconds are sufficient to significantly reduce (>50%) the projection uncertainties. These findings suggest robust procedures on how to reduce projection uncertainties, however, a balance between other sources of uncertainty due to operational conditions and the employed instrumentation are required to outline more practical guidelines.

Question Answering System for Chemistry.

This paper describes the implementation and evaluation of a proof-of-concept Question Answering (QA) system for accessing chemical data from knowledge graphs (KGs) which offer data from chemical kinetics to the chemical and physical properties of species. We trained the question classification and named the entity recognition models that specialize in interpreting chemistry questions. The system has a novel design which applies a topic model to identify the question-to-ontology affiliation to handle ontologies with different structures. The topic model also helps the system to provide answers with a higher quality. Moreover, a new method that automatically generates training questions from ontologies is also implemented. The question set generated for training contains 432,989 questions under 11 types. Such a training set has been proven to be effective for training both the question classification model and the named entity recognition model. We evaluated the system using other KGQA systems as baselines. The system outperforms the chosen KGQA system answering chemistry-related questions. The QA system is also compared to the Google search engine and the WolframAlpha engine. It shows that the QA system can answer certain types of questions better than the search engines.

Mobile Measurement System for the Rapid and Cost-Effective Surveillance of Methane and Volatile Organic Compound Emissions from Oil and Gas Production Sites.

In this study, a ground-based mobile measurement system was developed to provide rapid and cost-effective emission surveillance of both methane (CH4) and volatile organic compounds (VOCs) from oil and gas (O&G) production sites. After testing in several controlled release experiments, the system was deployed in a field campaign in the Eagle Ford basin, TX. We found fat-tail distributions for both methane and total VOC (C4-C12) emissions (e.g., the top 20% sites ranked according to methane and total VOC (C4-C12) emissions were responsible for ∼60 and ∼80% of total emissions, respectively) and a good correlation between them (Spearman's R = 0.74). This result suggests that emission controls targeting relatively large emitters may help significantly reduce both methane and VOCs in oil and wet gas basins, such as the Eagle Ford. A strong correlation (Spearman's R = 0.84) was found between total VOC (C4-C12) emissions estimated using SUMMA canisters and data reported from a local ambient air monitoring station. This finding suggests that this system has the potential for rapid emission surveillance targeting relatively large emitters, which can help achieve emission reductions for both greenhouse gas (GHG) and air toxics from O&G production well pads in a cost-effective way.

Multiscale Cross-Domain Thermochemical Knowledge-Graph.

In this paper, we develop a set of software agents which improve a knowledge-graph containing thermodynamic data of chemical species by means of quantum chemical calculations and error-canceling balanced reactions. The knowledge-graph represents species-associated information by making use of the principles of linked data, as employed in the Semantic Web, where concepts correspond to vertices and relationships between the concepts correspond to edges of the graph. We implement this representation by means of ontologies, which formalize the definition of concepts and their relationships, as a critical step to achieve interoperability between heterogeneous data formats and software. The agents, which conduct quantum chemical calculations and derive the estimates of standard enthalpies of formation, update the knowledge-graph with newly obtained results, improving data values, and adding nodes and connections between them. A key distinguishing feature of our approach is that it extends an existing, general-purpose knowledge-graph, called J-Park Simulator (http://theworldavatar.com), and its ecosystem of autonomous agents, thus enabling seamless cross-domain applications in wider contexts. To this end, we demonstrate how quantum calculations can directly affect the atmospheric dispersion of pollutants in an industrial emission use-case.

Knowledge Graph Approach to Combustion Chemistry and Interoperability.

In this paper, we demonstrate through examples how the concept of a Semantic Web based knowledge graph can be used to integrate combustion modeling into cross-disciplinary applications and in particular how inconsistency issues in chemical mechanisms can be addressed. We discuss the advantages of linked data that form the essence of a knowledge graph and how we implement this in a number of interconnected ontologies, specifically in the context of combustion chemistry. Central to this is OntoKin, an ontology we have developed for capturing both the content and the semantics of chemical kinetic reaction mechanisms. OntoKin is used to represent the example mechanisms from the literature in a knowledge graph, which itself is part of the existing, more general knowledge graph and ecosystem of autonomous software agents that are acting on it. We describe a web interface, which allows users to interact with the system, upload and compare the existing mechanisms, and query species and reactions across the knowledge graph. The utility of the knowledge-graph approach is demonstrated for two use-cases: querying across multiple mechanisms from the literature and modeling the atmospheric dispersion of pollutants emitted by ships. As part of the query use-case, our ontological tools are applied to identify variations in the rate of a hydrogen abstraction reaction from methane as represented by 10 different mechanisms.

A small, lightweight multipollutant sensor system for ground-mobile and aerial emission sampling from open area sources.

Characterizing highly dynamic, transient, and vertically lofted emissions from open area sources poses unique measurement challenges. This study developed and applied a multipollutant sensor and time-integrated sampler system for use on mobile applications such as vehicles, tethered balloons (aerostats) and unmanned aerial vehicles (UAVs) to determine emission factors. The system is particularly applicable to open area sources, such as forest fires, due to its light weight (3.5 kg), compact size (6.75 L), and internal power supply. The sensor system, termed "Kolibri", consists of sensors measuring CO2 and CO, and samplers for particulate matter (PM) and volatile organic compounds (VOCs). The Kolibri is controlled by a microcontroller which can record and transfer data in real time through a radio module. Selection of the sensors was based on laboratory testing for accuracy, response delay and recovery, cross-sensitivity, and precision. The Kolibri was compared against rack-mounted continuous emissions monitoring system (CEMs) and another mobile sampling instrument (the "Flyer") that has been used in over ten open area pollutant sampling events. Our results showed that the time series of CO, CO2, and PM2.5 concentrations measured by the Kolibri agreed well with those from the CEMs and the Flyer, with a laboratory- tested percentage error of 4.9%, 3%, and 5.8%, respectively. The VOC emission factors obtained using the Kolibri were consistent with existing literature values that relate concentration to combustion efficiency. The potential effect of rotor downwash on particle sampling was investigated in an indoor laboratory and the preliminary results suggested that its influence is minimal. Field application of the Kolibri sampling open detonation plumes indicated that the CO and CO2 sensors responded dynamically and their concentrations co-varied with emission transients. The Kolibri system can be applied to various challenging open area scenarios such as fires, lagoons, flares, and landfills.

A Mobile Sensing Approach for Regional Surveillance of Fugitive Methane Emissions in Oil and Gas Production.

This paper addresses the need for surveillance of fugitive methane emissions over broad geographical regions. Most existing techniques suffer from being either extensive (but qualitative) or quantitative (but intensive with poor scalability). A total of two novel advancements are made here. First, a recursive Bayesian method is presented for probabilistically characterizing fugitive point-sources from mobile sensor data. This approach is made possible by a new cross-plume integrated dispersion formulation that overcomes much of the need for time-averaging concentration data. The method is tested here against a limited data set of controlled methane release and shown to perform well. We then present an information-theoretic approach to plan the paths of the sensor-equipped vehicle, where the path is chosen so as to maximize expected reduction in integrated target source rate uncertainty in the region, subject to given starting and ending positions and prevailing meteorological conditions. The information-driven sensor path planning algorithm is tested and shown to provide robust results across a wide range of conditions. An overall system concept is presented for optionally piggybacking of these techniques onto normal industry maintenance operations using sensor-equipped work trucks.