LLMs enhance industrial ML data filtering, improving virtual flow meter accuracy

Researchers have developed a novel method for improving the quality of training data used in industrial machine learning applications, particularly for virtual flow meters. This text-informed approach utilizes large language models (LLMs) to integrate unstructured operational data, such as engineer comments and logs, with tabular sensor data. By performing contextual anomaly detection across both data modalities, the method generates a binary mask to filter the training dataset. Experiments on a synthetic oil and gas dataset demonstrated that this multimodal approach significantly improved the performance of a virtual flow meter model, reducing the Mean Absolute Percentage Error (MAPE) from 7.1% to 5.4% compared to traditional sensor-only filtering. AI

IMPACT This multimodal approach to data filtering can improve the accuracy of industrial machine learning models, potentially reducing manual data curation efforts.

RANK_REASON The cluster contains an academic paper detailing a new methodology for machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Hugging Face
• Kristoffer Hjelmen Nesland
• large language models

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →