Abstract: The disclosure presents processes for evaluating a borehole design against one or more identified risks. The processes can determine borehole design concepts for the borehole design. Each borehole design concept can have multiple risks assigned, which can be selected from a library of risks, a risk matrix or template, a risk model, or user entered risks. The risks can be scored using one or more statistics-based algorithms, such as a sum, an average, a mean, or other algorithms. The risks can be grouped by a risk level, forming a sub-risk score for each risk level for each borehole design concept. A final risk score can be generated using the sub-risk scores for the borehole design. More than one borehole design can be evaluated using a risk tolerance parameter and the borehole design that satisfies the risk tolerance parameter can be selected as the recommended borehole design.

Abstract: An automated offset well analytics engine generates offset well rankings for a prospect well. The engine aggregates data for offset wells and the prospect wells is across multiple disparate data sources corresponding to a user-specified scope. The engine generates features comparing the offset wells to the prospect well are using a combination of machine-learning based models and risk analysis. Offset wells are ranked by feature and further ranked across features using a weighted feature ranking map. Feature weights are iteratively trained using a reinforcement learning model in a feedback loops with a well expert. A prospect well casing schema and bottom hole assembly is designed using automatically generated offset well rankings.