DataDRILL: Predicting Formation Pressure and Detecting Kicks in Drilling Rigs

Accurate real-time prediction of formation pressure and kick detection is crucial for drilling operations, as it significantly enhances decision-making and cost-effectiveness. Data-driven models are increasingly popular in automating drilling operations through precise prediction of formation pressure and effective detection of kicks. However, there is a notable absence of publicly available datasets in current literature, which hinders technological advancements in this domain. This repository introduces two comprehensive datasets, now publicly released under appropriate licensing, to support researchers in developing intelligent algorithms that enhance oil/gas well drilling research. These datasets, which include data samples for formation pressure prediction and kick detection, feature 28 drilling variables and contain over 2000 data samples each. Additionally, we provide simulation coding and detailed data analysis methodologies. Principal component regression is employed to predict formation pressure, while principal component analysis is utilized to identify kicks, ensuring the dataset’s technical validation.

If you use this dataset then please cite the following paper:

@misc{arifeen2024datadrillformationpressureprediction,
      title={DataDRILL: Formation Pressure Prediction and Kick Detection for Drilling Rigs}, 
      author={Murshedul Arifeen and Andrei Petrovski and Md Junayed Hasan and Igor Kotenko and Maksim Sletov and Phil       Hassard},
      year={2024},
      eprint={2409.19724},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2409.19724}, 
}

Description of the dataset: