A method is proposed to calculate pore pressure at the bit while drilling using all data typically available in a modern drilling operation. This method utilizes a machine learning approach that can estimate pore pressures at the same or lesser range of uncertainty as traditional methods and can do so at the bit in real-time. Traditional pore pressure estimation while drilling utilizes a combination of data sources most of which are detected from logging while drilling (LWD) sensors placed 100's of feet behind the drill bit (where resistivity, sonic, density etc. tools are commonly placed). Furthermore, smoothing algorithms are often used to average the detection data thus increasing the offset from the drill bit to the estimated pore pressure calculation. The result of this is that the pore pressure calculation while drilling is only relevant to the formation that has already been penetrated and not being actively drilled. In hole sections where minor pore pressure changes can have significant impact on operational decisions this has obvious disadvantages. However, while drilling a well multiple sources of data from the drill bit itself are typically left unused in pore pressure calculation. Whereas traditional methods give an estimate of pore pressure after the well has already experienced a change in pressure, this method can calculate pore pressure at the bit, as the change is experienced. Another benefit of applying a machine learning model to pore pressure calculation while drilling is that the computational time is almost instantaneous.
