This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 201368, “Automated Solids-Content Determination in Drilling and Completions Fluids,” by Sercan Gul, SPE, Ali Karimi Vajargah, and Eric van Oort, SPE, The University of Texas at Austin, et al., prepared for the 2020 SPE Annual Technical Conference and Exhibition, originally scheduled to be held in Denver, 5–7 October. The paper has not been peer reviewed. Monitoring of low- and high-gravity-solids (LGS and HGS) content and maintaining these at ideal levels is essential for optimal drilling fluid performance, efficient hole cleaning and equivalent-circulating-density management, and prevention of failures of surface and downhole equipment during drilling. LGS and HGS monitoring in the field is currently accomplished using the API retort-kit measurement, which has certain drawbacks and is difficult to automate. In the complete paper, two new approaches are investigated to automate the LGS and HGS content measurements of drilling fluids, which potentially can replace the retort test. Introduction The conventional way to characterize LGS and HGS in the field is by using a retort-kit measurement specified in API Recommended Practices 13B-1 and 13B-2. The longevity of these tests is testament to the effectiveness of the API standards and the tests themselves in providing useful and practical field guidance. Despite their evident success, however, various downsides exist in current solids-content-testing methods. Retort-kit measurements present the following issues: - Difficulty in obtaining accurate and repeatable test results - Safety issues associated with laboratory testing at elevated temperatures (over 930°F) - Interpretive bias issues associated with test results, including the potential for deliberate manipulation of these results - Difficulty in automating the retort test for improved efficiency and safety The authors’ opinion is that automating antiquated API test protocols is not a useful practice. They write that a clean-slate approach would be better, in which a determination is made whether solids-content information can be provided in a novel and meaningful way using methods that deviate from standard API recommended practices. In the complete paper, the authors investigate a machine-learning (ML) and data-analytics method for this purpose in combination with a novel inline X-ray fluorescence (XRF) measurement method.