Abstract: A technology is described for automating deployment of a machine learning model. An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric.

Abstract: A system remotely collects test data from a test platform using platform attached sensors. Identification chips, each having a unique identification code, are each paired with an associated sensor to form sensor/chip pairs. At least one patch panel having a plurality of connections is positioned approximate to the platform. Connections are communicatively linked to each of the sensor/chip pairs. A computer system is communicatively linked to additional patch panel connections. The identification of selected sensors is queried by a computer command to the patch panels, and a group of sensors for a given test is identified and selected. Test data from each of the selected sensors is transferred through the patch panels to the computer system for collation and generation of a test setup compatible with a data acquisition system. Test setup information is downloaded to the data acquisition system in preparation for the next test.

Abstract: A system remotely collects test data from a test platform using platform attached sensors. Identification chips, each having a unique identification code, are each paired with an associated sensor to form sensor/chip pairs. At least one patch panel having a plurality of connections is positioned approximate to the platform. Connections are communicatively linked to each of the sensor/chip pairs. A computer system is communicatively linked to additional patch panel connections. The identification of selected sensors is queried by a computer command to the patch panels, and a group of sensors for a given test is identified and selected. Test data from each of the selected sensors is transferred through the patch panels to the computer system for collation and generation of a test setup compatible with a data acquisition system. Test setup information is downloaded to the data acquisition system in preparation for the next test.

Abstract: A method for monitoring the movement of injected gas in an oil bearing formation behind the well casing is disclosed. A compensation neutron log is obtained from the well. The count rates are normalized to delineate water zones, gas zones and shale zones. Near and far count rates are rescaled and used to provide a qualitative determination of the distance from the point of injection to the top of the displaced gas in the formation by an analysis of the separation of the near and far count rate curves.

Abstract: The present disclosure relates to HIF-2? inhibitors and methods of making and using them for treating cancer. Certain compounds were potent in HIF-2? scintillation proximity assay, luciferase assay, and VEGF ELISA assay, and led to tumor size reduction and regression in 786-O xenograft bearing mice in vivo.