While diagnostic fracture injection tests (DFIT) data is relatively rare, pressure and flow rate data are widely collected for hydraulic fracture treatment stages in multiple transverse-fracture horizontal wells, both during pumping and during pressure falloff after the end of pumping. Recent papers have shown value in applying analysis developed for DFIT data to hydraulic fracture treatment falloff (HFTF) data. As is often the case with routine processing of large volumes of data, the time required for analyzing HFTF datasets for each of the treatment stages in a long horizontal well may be overly expensive in time and human resources. To address this issue, this paper applies machine learning techniques to standard HFTF pressure data, to produce data-driven mathematical models that estimate wellbore and perforation friction loss, near-wellbore tortuosity friction loss, and the instantaneous shut-in pressure (ISIP). The models are trained based on a small subset of hydraulic fracture treatment stages, data from for which is processed manually, to provide targets for model outputs. Model structure is based on multivariate statistical methods, including principal component regression (PCR) and partial least squares regression (PLSR). Comparison between state-by-stage friction losses and ISIP values estimated manually and those quantified by machine learning reveals good agreement and underscores the value of the machine learning approach as a practical tool for field application tasks, including well and pad completion design decisions related to perforating strategies, and fracture and well spacing.

While diagnostic fracture injection tests (DFIT) data is relatively rare, most hydraulic fracture treatment stages in multiple transverse fracture horizontal wells (MTFHWs) follow pressure and rate data during pumping with several minutes of pressure falloff data after the end of pumping. Recent papers have shown value in applying analysis developed for DFIT data to hydraulic fracture treatment falloff (HFTF) data. As is often the case with routinely acquired operational data, the time required for analyzing HFTF datasets for each of the treatment stages in a long horizontal well may be prohibitive. This paper offers an automated analysis procedure that starts from standard treatment pressure and rate data and produces estimates for wellbore and perforation friction loss, near wellbore tortuosity friction loss, and the instantaneous shut in pressure (ISIP). Steps in the automated procedure include isolating the HFTF data from the rest of the hydraulic fracture treatment data (which is typically subject to hydraulic hammer), applying an optimized low-pass filter (LPF), and computing the friction and ISIP estimates by automating a previously published graphic procedure. We employ the automated analysis on field data that was previously analyzed by hand. Then we compare and contrast between the two analyses. The comparison between manual and automatically analyzed fracture treatment falloffs demonstrates that the automated procedure reproduces the previous analyses except in a few cases that pose special challenges to any analysis. The new field dataset results demonstrate the approach is practical for field application. Variations in friction loss and ISIP estimates along MTFHWs provide data useful for well and pad completion design decisions related to perforating strategies, and fracture and well spacing.