The Novi AI Roundup

EP 33 · Predicting Water Production in the Williston Basin using a Machine Learning Model

Can you accurately forecast water production before a well is drilled? In this episode of The Novi AI Roundup, we explore how machine learning is improving water production forecasting in the Williston Basin. Drawing from the technical paper “Predicting Water Production in the Williston Basin using a Machine Learning Model”, we examine how ML identifies the geological and operational drivers of water production, helping operators better plan infrastructure, manage disposal costs, and optimize field development. This podcast episode is based on the technical paper “Predicting Water Production in the Williston Basin using a Machine Learning Model”, authors: D. Niederhut, K. Crifasi, K. Darnell, K. Sathaye, T. Cross. Download the full paper here. [https://novilabs.com/resources/urtec-2020-predicting-water-production-in-the-williston-basin-using-a-machine-learning-model/]

EP 32 · The Impact of Interwell Spacing Over Time: A Machine Learning Approach

How does spacing impact well performance over time? In this episode of The Novi AI Roundup, we explore how machine learning helps quantify the long-term effects of interwell spacing in unconventional reservoirs. Drawing from the technical paper “The Impact of Interwell Spacing Over Time: A Machine Learning Approach”, we examine how spacing influences production decline, recovery, and well interference throughout a well’s life, and why short-term production gains can sometimes come at the expense of long-term value. This podcast episode is based on the technical paper “The Impact of Interwell Spacing Over Time: A Machine Learning Approach”, authors: D. Niederhut, J. Ramey, J. Reed, K. Darnell, K. Sathaye, T. Cross. Download the full paper here. [https://novilabs.com/resources/urtec-2020-the-impact-of-interwell-spacing-over-time-a-machine-learning-approach/]

EP 31 · Benchmarking Operator Performance in the Williston Basin using a Predictive Machine Learning Model

How do you separate operator skill from rock quality? In this episode of The Novi AI Roundup, we explore how predictive machine learning models are being used to benchmark operator performance in the Williston Basin. Drawing from the technical paper “Benchmarking Operator Performance in the Williston Basin using a Predictive Machine Learning Model”, we examine how ML normalizes for geology, spacing, and development conditions to uncover the true drivers of well performance, and why apples-to-apples benchmarking matters in mature unconventional plays.This podcast episode is based on the technical paper “Benchmarking Operator Performance in the Williston Basin using a Predictive Machine Learning Model”, authors: D. Niederhut, K. Crifasi, K. Darnell, K. Sathaye, T. Cross. Download the full paper here. [https://novilabs.com/resources/urtec-2020-benchmarking-operator-performance-in-the-williston-basin-using-a-predictive-machine-learning-model/]

EP 30 · Machine Learning Methods in the Williston: A Case Study in Productivity Decay and the Implications for Inventory Exhaustion

Is the Williston Basin running out of its best rock? In this episode of The Novi AI Roundup, we explore how machine learning is uncovering signs of productivity decay and what that means for future inventory. Drawing from the technical paper “Machine Learning Methods in the Williston: A Case Study in Productivity Decay and the Implications for Inventory Exhaustion”, we examine how well performance evolves as development expands, and how ML helps identify shifts in location quality that traditional analysis can miss.This podcast episode is based on the technical paper “Machine Learning Methods in the Williston: A Case Study in Productivity Decay and the Implications for Inventory Exhaustion”, authors: B. L. Myers, B. Davis, R. Duman, T. Cross. Download the full paper here. [https://novilabs.com/resources/urtec-2021-machine-learning-methods-in-the-williston/]

EP 29 · Quantifying the Diminishing Impact of Completions Over Time Across the Bakken, Eagle Ford, and Wolfcamp Using a Multi-Target Machine Learning Model and SHAP Values

How long does the impact of completions really last? In this episode of The Novi AI Roundup, we explore how machine learning and SHAP values are used to quantify the changing influence of completion design over the life of a well. Drawing from the technical paper “Quantifying the Diminishing Impact of Completions Over Time Across the Bakken, Eagle Ford, and Wolfcamp Using a Multi-Target Machine Learning Model and SHAP Values”, we examine how completion-driven uplift peaks early, fades over time, and gives way to geological and reservoir-driven performance across major U.S. plays.This podcast episode is based on the technical paper “Quantifying the Diminishing Impact of Completions Over Time Across the Bakken, Eagle Ford, and Wolfcamp Using a Multi-Target Machine Learning Model and SHAP Values”, authors: T. Cross, D. Niederhut, A. Cui, K. Sathaye, J. Chaplin. Download the full paper here. [https://novilabs.com/resources/urtec-2021-diminishing-completions-impact-over-time/]