Pressure transient analysis is one of the most important tools used by reservoir engineers to understand how fluids move inside the subsurface. Even though the theory behind pressure analysis has existed for many decades, the way it is applied in practice still depends heavily on human judgement, manual plotting, and experience-based interpretation. With the rapid growth of digital pressure sensors and long-term monitoring systems, engineers are now faced with extremely large and complex pressure datasets that are difficult to analyse using traditional methods. In this work, a complete artificial intelligence–based framework is presented to automatically analyse pressure data in a way that still follows physical reservoir principles. The framework identifies pressure stability, builds pressure derivatives, classifies flow regimes, and generates clean datasets that can later be used for advanced modelling. All steps are implemented using open-source tools, and only publicly available pressure datasets are used. The results show that the system can reliably identify meaningful pressure behaviour while avoiding common interpretation mistakes. This work demonstrates that artificial intelligence, when guided by physics, can make pressure transient analysis easier, faster, and more consistent without removing engineering understanding.
It is found that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks, and performs competitively with the state-of-the-art on image, video, and speech recognition tasks.
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
F. Xia, Amir Zamir, Zhi-Yang He et al.· 2018 IEEE/CVF Conference on...· 1,069 citations· ⚡112
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.