Creation of machine-usable, high-quality knowledge-bases is a critical prerequisite for many important applications that rely on availability of high-level of autonomous decision-making and reasoning capabilities. Manual construction of knowledge-bases for complex applications is a time-consuming and expensive process. In such application domains, however, a vast amount of knowledge is available in human-readable format, and it could be leveraged to build knowledge-bases automatically. Natural Language Processing (NLP)-based techniques provide an attractive option for this process. The field of NLP has made rapid strides in last several years and resulted in increased usage across a variety of consumer-facing applications. However, their usage for knowledge-base construction in the aviation industry remains rather limited to date. We present our assessment of using various NLP-based tools for the creation of aviation-focused, high-quality, machineprocessable, and human-legible knowledge bases (KBs) for various applications. We identify several gaps, both at the application and fundamental levels, and also identify potential directions for future research that could help overcome the challenges.
The CheMin instrument on the Mars Science Laboratory (MSL) rover Curiosity uses a Co tube source and a CCD detector to acquire mineralogy from diffracted primary X-rays and chemical information from fluoresced X-rays. CheMin has been operating at the MSL Gale Crater field site since August 5, 2012 and has provided the X-ray diffraction (XRD) analyses in situ on a body beyond Earth. Data from the sample collected, the Rocknest eolian soil, identify a basaltic mineral suite, predominantly plagioclase (approx.An50), forsteritic olivine (approx.Fo58), augite and pigeonite, consistent with expectation that detrital grains on Mars would reflect widespread basaltic sources. Minor phases (each <2 wt% of the crystalline component) include sanidine, magnetite, quartz, anhydrite, hematite and ilmenite. Significantly, about a third of the sample is amorphous or poorly ordered in XRD. This amorphous component is attested to by a broad rise in background centered at approx.27deg 2(theta) (Co K(alpha)) and may include volcanic glass, impact glass, and poorly crystalline phases including iron oxyhydroxides; a rise at lower 2(theta) may indicate allophane or hisingerite. Constraints from phase chemistry of the crystalline components, compared with a Rocknest bulk composition from the APXS instrument on Curiosity, indicate that in sum the amorphous or poorly crystalline components are relatively Si, Al, Mg-poor and enriched in Ti, Cr, Fe, K, P, S, and Cl. All of the identified crystalline phases are volatile-free; H2O, SO2 and CO2 volatile releases from a split of this sample analyzed by the SAM instrument on Curiosity are associated with the amorphous or poorly ordered materials. The Rocknest eolian soil may be a mixture of local detritus, mostly crystalline, with a regional or global set of dominantly amorphous or poorly ordered components. The Rocknest sample was targeted by MSL for first time analysis to demonstrate that a loose deposit could be scooped, sieved to <150 microns, and delivered to instruments in the body of the rover. A drilled sample of sediment in outcrop is anticipated. At the time of writing this abstract, promising outcrops are in range and this talk will provide an update on data collected with the CheMin instrument.
