Rate of penetration has been considered as an important factor in the entire drilling industry, which can largely determine the overall costs of drilling a well. This paper proposed a novel real-time prediction of rate of penetration by combining the Attention-based Bidirectional-Long Short-Term Memory and Long Short-Term Memory (Att-Bi-LSTM-LSTM). Eight parameters, which are total vertical depth, weight on bit, revolutions per minute, mud flow rate, density, viscosity, drill-bit outer-diameter, lithology, and rate of penetration, are adopted as datasets. The drilling speed of the well is trained and validated through the drilling data while a sliding window is introduced for the real-time update. In addition, the presented prediction model is compared with other traditional prediction methods. Finally, the prospect of field application and further study is discussed and suggested. The results indicate that the proposed model shows good accuracy and robustness. Moreover, compared with the traditional methods, the model exhibits good superiority with smaller absolute and relative errors. For field applications, the model proposed in this paper attempts to provide a solution to the prediction of real-time rate of penetration. The results are expected to provide guidance for the further study on the increase of drilling speed and reduction of well costs.

Recent efforts in quantum photonics emphasize on-chip generation, manipulation, and detection of single photons for quantum computing and quantum communication. In quantum photonic chips, single photons are often generated using parametric down-conversion and quantum dots. Quantum dots are particularly attractive due to their on-demand generation of high-purity single photons. Different photonic platforms are used to manipulate the states of the photons. Nevertheless, no single platform satisfies all the requirements of quantum photonics, as each platform has its merits and shortcomings. For example, the thin-film silicon nitride (SiN) platform provides ultra-low loss on the order of 0.1 dB m−1, but is incompatible with dense integration , requiring large bending radii. On the other hand, silicon on insulator offers a high refractive index contrast for dense integration but has a high absorption coefficient at the emission wavelengths (800–970 nm) of state-of-the-art QDs. Amorphous silicon carbide (a-SiC) has emerged as an alternative with a high refractive index (higher than SiN), an extended transparency window compared to Silicon, and a thermo-optic coefficient three times higher than that of SiN, which is crucial for tuning photonic devices on a chip. With the vision of realizing a quantum photonic integrated circuit, we explore the hybrid integration of SiN/a-SiC photonic platform with quantum dots and superconducting nanowire single-photon detectors. We validate our hybrid platform using a brief literature study, proof-of-principle experiments, and complementary simulations. As a proof-of-principle, we show a quantum dot embedded in nanowires (for deterministic micro-transfer and better integration) that emits single photons at 885 nm with a purity of 0.011 and a lifetime of 0.98 ns. Furthermore, we design and simulate an adiabatic coupler between two photonic platforms, a-SiC and SiN, by aiming to use the benefits of both platforms, i.e. dense integration and low losses, respectively. Our design couples the light from SiN waveguide to a-SiC waveguide with 96% efficiency at 885 nm wavelength. Our hybrid platform can be used to demonstrate on-chip quantum experiments such as Hong–Ou–Mandel, where we can design a large optical delay line in SiN and an interference circuit in a-SiC.