Underground coal gasification (UCG) is pivotal for the clean and efficient in-situ utilization of deep and unminable coal seams. Its research demands high knowledge accuracy. However, general large language models (LLM) are limited in offering reliable knowledge services in UCG research and engineering due to insufficient specialized corpora, limited factual accuracy, and hallucination. This study therefore addresses the practical demand for multimodal knowledge services in underground coal gasification (UCG). We constructed a multi-source and multimodal dataset covering 8 categories of data throughout the full lifecycle of UCG, and established a domain-specific database through tokenization, standardization and quality evaluation. Precise representation of text modality was achieved through model fine-tuning and keyword enhancement. Textual conversion and semantic embedding were conducted for unified expression of numerical modality. Contrastive Language-Image Pre-training (CLIP) model was employed for feature extraction and cross-modal correlation of image modality, effectively eliminating the semantic gap between different modalities. We thus proposed a lightweight 3-layer UCG multimodal knowledge service framework featuring data representation, retrieval, storage and application based on the general Retrieval-Augmented Generation (RAG) architecture. A hybrid RAG process was designed by integrating sparse retrieval and dense vector retrieval. Ablation experiments show that the proposed hybrid RAG framework improved answer accuracy from 61.3% of the RAG-free baseline to 84.6%, increased factual consistency score from 3.1/5.0 to 4.2/5.0, and reduced hallucination rate from 38.7% to 16.1%. The proposed framework provides traceable knowledge services for UCG research.

China has rich reserves of deep coal resources, and underground coal gasification can transform coal into gas and transport it to the ground, which is an important way for in-situ fluidized mining of deep coal.This article introduces the development history and technical status of underground coal gasification technology (UCG), as well as typical cases of underground coal gasification in the middle and deep parts.Based on the modern underground coal gasification technology system, the key technologies and technical research directions of deep underground coal gasification was analyzed and the prospect of deep coal gasification mining with the goal of natural gas production was outlooked.The development trend of UCG is from the mine type to the drilling type, from shallow coal seams to deep coal seams, from single power generation to comprehensive utilization.The practice of UCG in the middle and deep coal seams has verified the technical feasibility.The key technologies of deep underground coal gasification mainly include geological evaluation and scientific site selection, gasifier construction, deep coal seam high-pressure ignition, controllable mobile injection and deep fire zone geophysical detection.Deep coal gasification to produce natural gas can not only realize the clean and efficient use of deep coal resources, but also solve the contradiction between supply and demand caused by the increase in natural gas consumption.