Estimating EM LWD measurement uncertainty using machine learning

A system, comprising:

• a processor and memory, the memory including instructions that cause the processor to:
• select a formation model and a configuration of an electromagnetic (EM) logging tool;
• compute synthetic EM voltages using a forward model, the selected formation model, and the selected configuration of the EM logging tool;
• apply noise to the synthetic EM voltages a plurality of times to obtain a set of noisy synthetic EM measurements;
• compute a standard deviation from the set of noisy synthetic EM measurements;
• repeat the selecting, the computing synthetic EM voltages, the applying, and the computing the standard deviation for a plurality of formation models to obtain a training data set including a set of modeled EM measurements and corresponding standard deviations;
• train a machine learning model with the training data set to obtain a trained machine learning model;
• collect, with the EM logging tool deployed downhole in a wellbore, field EM measurements;
• evaluate, downhole at the EM logging tool, the field EM measurements with the trained machine learning model deployed at the EM logging tool to estimate measurement uncertainties of the field EM measurements;
• and
• transmit the measurement uncertainties to a surface location.

A non-transitory computer readable medium including instructions that when executed by a processor, cause the processor to:

• select a formation model and a configuration of an electromagnetic (EM) logging tool;
• compute synthetic EM voltages using a forward model, the selected formation model, and the selected configuration of the EM logging tool;
• apply noise to the synthetic EM voltages a plurality of times to obtain a set of noisy synthetic EM measurements;
• compute a standard deviation from the set of noisy synthetic EM measurements;
• repeat the selecting, the computing synthetic EM voltages, the applying, and the computing the standard deviation for a plurality of formation models to obtain a training data set including a set of modeled EM measurements and corresponding standard deviations;
• train a machine learning model with the training data set to obtain a trained machine learning model, wherein the machine learning model includes a feed forward neural network having an input layer, a plurality of dense hidden layers, and an output layer, and wherein the synthetic EM measurements include at least 12 measurement channels, the input layer and output layer each include a single neuron for each of the at least 12 measurement channels, and each of the plurality of dense hidden layers includes two neurons for each of the at least 12 measurement channels;
• collect, with the EM logging tool deployed downhole in a wellbore, field EM measurements;
• and
• evaluate, downhole at the EM logging tool, the field EM measurements with the trained machine learning model deployed at the EM logging tool to estimate measurement uncertainties of the field EM measurements.