Field operations framework

Abstract

A method can include receiving downhole formation testing time series data acquired at a location along a borehole in a subsurface region during a formation testing operation performed by a downhole tool; processing the downhole formation testing time series data using a machine learning model to generate smoothed time series data; resampling the smoothed time series data; generating fluid and formation characteristics with respect to time based on the smoothed time series data; and outputting the fluid and formation characteristics with respect to time.

What is claimed is: 
     
         1 . A method comprising:
 receiving downhole formation testing time series data acquired at a location along a borehole in a subsurface region during a formation testing operation performed by a downhole tool;   processing the downhole formation testing time series data using a machine learning model to generate smoothed time series data;   resampling the smoothed time series data;   generating fluid and formation characteristics with respect to time based on the smoothed time series data; and   outputting the fluid and formation characteristics with respect to time.   
     
     
         2 . The method of  claim 1 , wherein the receiving comprises receiving the downhole formation testing time series data by a computational framework implemented in the downhole tool. 
     
     
         3 . The method of  claim 2 , wherein the outputting comprises transmitting the fluid and formation characteristics to surface equipment. 
     
     
         4 . The method of  claim 3 , wherein the transmitting comprises wireline transmission or acoustic transmission. 
     
     
         5 . The method of  claim 1 , wherein the machine learning model comprises a support vector machine. 
     
     
         6 . The method of  claim 1 , wherein the machine learning model comprises a tunable parameter for identification of one or more of noise and outliers. 
     
     
         7 . The method of  claim 6 , wherein the noise comprises spikes. 
     
     
         8 . The method of  claim 1 , wherein the downhole formation testing time series data comprise data indicative of a cleanup process and data indicative of a sampling process that acquires a fluid sample. 
     
     
         9 . The method of  claim 8 , wherein the fluid and formation characteristics comprise a fluid sample contamination characteristic. 
     
     
         10 . The method of  claim 9 , comprising controlling the formation testing operation based at least in part on the fluid sample contamination characteristic. 
     
     
         11 . The method of  claim 10 , wherein the controlling extends or shortens a cleanup time based at least in part on the fluid sample contamination characteristic. 
     
     
         12 . The method of  claim 9 , wherein the fluid sample contamination characteristic indicates a level of drilling fluid contamination in a fluid sample. 
     
     
         13 . The method of  claim 1 , wherein the processing processes the downhole formation testing time series data according to a first time interval and wherein the resampling resamples at a second time interval that is at least an order of magnitude greater than the first time interval. 
     
     
         14 . The method of  claim 1 , wherein the downhole formation testing time series data comprise one or more of viscosity data and density data. 
     
     
         15 . The method of  claim 1 , wherein the downhole formation testing time series data comprise gas-oil ratio data. 
     
     
         16 . The method of  claim 1 , wherein the downhole formation testing time series data comprise one or more of flow rate data and flowing pressure data. 
     
     
         17 . The method of  claim 1 , wherein the fluid and formation characteristics comprise one or more of mobility, fluid composition and level of contamination. 
     
     
         18 . The method of  claim 1 , comprising performing machine learning model training using the fluid and formation characteristics. 
     
     
         19 . A system comprising:
 one or more processors;   memory accessible to at least one of the one or more processors;   processor-executable instructions stored in the memory and executable to instruct the system to:
 receive downhole formation testing time series data acquired at a location along a borehole in a subsurface region during a formation testing operation performed by a downhole tool; 
 process the downhole formation testing time series data using a machine learning model to generate smoothed time series data; 
 resample the smoothed time series data; 
 generate fluid and formation characteristics with respect to time based on the smoothed time series data; and 
 output the fluid and formation characteristics with respect to time. 
   
     
     
         20 . One or more computer-readable storage media comprising processor-executable instructions to instruct a computing system to:
 receive downhole formation testing time series data acquired at a location along a borehole in a subsurface region during a formation testing operation performed by a downhole tool;   process the downhole formation testing time series data using a machine learning model to generate smoothed time series data;   resample the smoothed time series data;   generate fluid and formation characteristics with respect to time based on the smoothed time series data; and   output the fluid and formation characteristics with respect to time.