Search for: All records

Metadata is a key data source for researchers seeking to apply machine learning (ML) to the vast collections of digitized biological specimens that can be found online. Unfortunately, the associated metadata is often sparse and, at times, erroneous. This paper extends previous research conducted with the Illinois Natural History Survey (INHS) collection (7244 specimen images) that uses computational approaches to analyze image quality, and then automatically generates 22 metadata properties representing the image quality and morphological features of the specimens. In the research reported here, we demonstrate the extension of our initial work to University of the Wisconsin Zoological Museum (UWZM) collection (4155 specimen images). Further, we enhance our computational methods in four ways: (1) augmenting the training set, (2) applying contrast enhancement, (3) upscaling small objects, and (4) refining our processing logic. Together these new methods improved our overall error rates from 4.6 to 1.1%. These enhancements also allowed us to compute an additional set of 17 image-based metadata properties. The new metadata properties provide supplemental features and information that may also be used to analyze and classify the fish specimens. Examples of these new features include convex area, eccentricity, perimeter, skew, etc. The newly refined process further outperforms humans in terms of time and labor cost, as well as accuracy, providing a novel solution for leveraging digitized specimens with ML. This research demonstrates the ability of computational methods to enhance the digital library services associated with the tens of thousands of digitized specimens stored in open-access repositories world-wide by generating accurate and valuable metadata for those repositories. 

ABSTRACT This paper reports on a demonstration of YAMZ (Yet Another Metadata Zoo) as a mechanism for building community consensus around metadata terms. The demonstration is motivated by the complexity of the metadata standards environment and the need for more user-friendly approaches for researchers to achieve vocabulary consensus. The paper reviews a series of metadata standardization challenges, explores crowdsourcing factors that offer possible solutions, and introduces the YAMZ system. A YAMZ demonstration is presented with members of the Toberer materials science laboratory at the Colorado School of Mines, where there is a need to confirm and maintain a shared understanding for the vocabulary supporting research documentation, data management, and their larger metadata infrastructure. The demonstration involves three key steps: 1) Sampling terms for the demonstration, 2) Engaging graduate student researchers in the demonstration, and 3) Reflecting on the demonstration. The results of these steps, including examples of the dialog provenance among lab members and voting, show the ease with YAMZ can facilitate building metadata vocabulary consensus. The conclusion discusses implications and highlights next steps. 

Building a knowledge graph is a time-consuming and costly process which often applies complex natural language processing (NLP) methods for extracting knowledge graph triples from text corpora. Pre-trained large Language Models (PLM) have emerged as a crucial type of approach that provides readily available knowledge for a range of AI applications. However, it is unclear whether it is feasible to construct domain-specific knowledge graphs from PLMs. Motivated by the capacity of knowledge graphs to accelerate data-driven materials discovery, we explored a set of state-of-the-art pre-trained general-purpose and domain-specific language models to extract knowledge triples for metal-organic frameworks (MOFs). We created a knowledge graph benchmark with 7 relations for 1248 published MOF synonyms. Our experimental results showed that domain-specific PLMs consistently outperformed the general-purpose PLMs for predicting MOF related triples. The overall benchmarking results, however, show that using the present PLMs to create domain-specific knowledge graphs is still far from being practical, motivating the need to develop more capable and knowledgeable pre-trained language models for particular applications in materials science. 

Sentence embedding methods offer a powerful approach for working with short textual constructs or sequences of words. By representing sentences as dense numerical vectors, many natural language processing (NLP) applications have improved their performance. However, relatively little is understood about the latent structure of sentence embeddings. Specifically, research has not addressed whether the length and structure of sentences impact the sentence embedding space and topology. This paper reports research on a set of comprehensive clustering and network analyses targeting sentence and sub-sentence embedding spaces. Results show that one method generates the most clusterable embeddings. In general, the embeddings of span sub-sentences have better clustering properties than the original sentences. The results have implications for future sentence embedding models and applications. 

Scientific literature presents a wellspring of cutting-edge knowledge for materials science, including valuable data (e.g., numerical data from experiment results, material properties and structure). These data are critical for accelerating materials discovery by data-driven machine learning (ML) methods. The challenge is, it is impossible for humans to manually extract and retain this knowledge due to the extensive and growing volume of publications.To this end, we explore a fine-tuned BERT model for extracting knowledge. Our preliminary results show that our fine-tuned Bert model reaches an f-score of 85% for the materials named entity recognition task. The paper covers background, related work, methodology including tuning parameters, and our overall performance evaluation. Our discussion offers insights into our results, and points to directions for next steps. 

Researchers across nearly every discipline seek to leverage ontologies for knowledge discovery and computational tasks; yet, the number of machine readable materials science ontologies is limited. The work presented in this paper explores the Processing, Structure, Properties and Performance (PSPP) framework for accelerating the development of materials science ontologies. We pursue a case study framed by the creation of an Aerogel ontology and a Battery Cathode ontology and demonstrate the Helping Interdisciplinary Vocabulary Engineer for Materials Science (HIVE4MAT) as a proof of concept showing PSPP relationships. The paper includes background context covering materials science, the PSPP framework, and faceted analysis for ontologies. We report our research objectives, methods, research procedures, and results. The findings indicate that the PSPP framework offers a rubric that may help guide and potentially accelerate ontology development. 

Researchers across nearly every discipline seek to leverage ontologies for knowledge discovery and computational tasks; yet, the number of machine readable materials science ontologies is limited. The work presented in this paper explores the Processing, Structure, Properties and Performance (PSPP) framework for accelerating the development of materials science ontologies. We pursue a case study framed by the creation of an Aerogel ontology and a Battery Cathode ontology and demonstrate the Helping Interdisciplinary Vocabulary Engineer for Materials Science (HIVE4MAT) as a proof of concept showing PSPP relationships. The paper includes background context covering materials science, the PSPP framework, and faceted analysis for ontologies. We report our research objectives, methods, research procedures, and results. The findings indicate that the PSPP framework offers a rubric that may help guide and potentially accelerate ontology development. 

In this position paper, we describe research on knowledge graph-empowered materials science prediction and discovery. The research consists of several key components including ontology mapping, materials data annotation, and information extraction from unstructured scholarly articles. We argue that although big data generated by simulations and experiments have motivated and accelerated the data-driven science, the distribution and heterogeneity of materials science-related big data hinders major advancements in the field. Knowledge graphs, as semantic hubs, integrate disparate data and provide a feasible solution to addressing this challenge. We design a knowledge-graph based approach for data discovery, extraction, and integration in materials science.