Coal is a cornerstone of China’s energy structure, and fluctuations in its price not only affect the upstream and downstream of the industrial chain but also bear on achieving the “dual-carbon” goals and safeguarding macroeconomic stability. To improve forecasting accuracy, this study develops an Informer-based multimodal cross-attention forecasting model, using the Bohai-Rim 5 500 K thermal coal price as the prediction target. We build a multimodal dataset that integrates key drivers including raw coal output, coal imports and tariffs, geopolitical uncertainty, coal enterprise inventories, total thermal power generation, and the consumer price index. The numerical modality is processed via linear mapping; the textual modality employs a RoBERTa encoder to extract semantic representations; and a cross-attention mechanism is introduced for cross-modal fusion between numerical sequences and textual information. Empirical results show that Informer performs better than multiple benchmark models on long-horizon forecasting; relative to simple concatenation, introducing cross-modal cross-attention significantly improves predictive accuracy; the model also passes robustness tests under noisy text conditions. The proposed Informer-based multimodal cross-attention model provides methodological support for scientific coal price forecasting and offers theoretical and practical value for energy-market research and related policy formulation.
为刻画不同模态之间的相互作用,本文构建了跨模态交叉注意力机制[37].考虑到数值序列能够直接反映煤炭价格的变化状态与结构性约束,在时序预测中承担对目标变量演化的主要解释作用,本文以数值模态作为查询( Q ),以文本模态作为键( K )与值( V ),在时间对齐的基础上,动态检索、按需提取与当前数值状态相关的文本语义证据,将外部信息注入统一的状态表征中.该设计使注意力权重以数值状态为条件进行自适应分配,实现对关键语义的筛选,并围绕预测目标所依赖的主要信息进行跨模态匹配[38‑39].具体公式为
YANZhipeng, YUZemin, GUXinlian. Research on conduction mechanism between carbon price and coal future price in China[J]. On Economic Problems, 2022(6): 67-74.
National Bureau of Statistics of China. Statistical Communiqué of the People’s Republic of China on the 2024 National Economic and Social Development[EB/OL].
ZHANGYunyi, SUTong, WANGSiquan, et al. Only by standing up can move forward: Assessing the operation characteristics and pricing policy of China’s coal market[J]. Journal of Management World, 2025, 41(2): 101-119.
DUKerui, LIMinyang, WANGSiquan, et al. The impact of coal price shocks and new energy business expansion on corporate financing constraints[J]. Economic Research Journal, 2024, 59(12): 4-20.
YUZuo, SHIJunrong, LUOTianyu. Partial ownership of competitive enterprises, de-capacity policy and distortional overcharge on coal in China[J]. China Economic Quarterly, 2024, 24(3): 861-877.
LIU Chang WANG Xuran. Influencing factors of coal price fluctuation in China: Based on SVAR model[J]. Journal of Xi’an Jiaotong University (Social Sciences), 2020, 40(3): 101-108.
[13]
GUOX P, SHIJ X, REND F. Coal price forecasting and structural analysis in China[J]. Discrete Dynamics in Nature and Society, 2016, 2016(1): 1256168.
[14]
WANGC, XUG, SUNC L, et al. Modeling and forecasting of coal price based on influencing factors and time series[J]. Journal of Cleaner Production, 2024, 467: 143030.
[15]
JINX, SONGA Y, HEM F. Short-term thermal coal price forecasting based on EL-CLSTM model[J]. IEEE Access, 2024, 12: 147364-147371.
[16]
DINGZ H, FENGC C, LIUZ H, et al. Coal price fluctuation mechanism in China based on system dynamics model[J]. Natural Hazards, 2017, 85(2): 1151-1167.
[17]
YANGS L, LIUQ H, DUANZ P. Study on the price elasticity problem of China's coal supply and demand[C]//IEEE. 2012 International Conference on Information Management, Innovation Management and Industrial Engineering. Sanya, 2012, 3: 275-277.
[18]
ZHUS Q, CHIY Y, GAOK Y, et al. Analysis of influencing factors of thermal coal price[J]. Energies, 2022, 15(15): 5652.
[19]
ZHAOZ Y, ZHUJ, XIAB. Multi-fractal fluctuation features of thermal power coal price in China[J]. Energy, 2016, 117: 10-18.
[20]
JIANGS M, YANGC, GUOJ T, et al. ARIMA forecasting of China’s coal consumption, price and investment by 2030[J]. Energy Sources, Part B: Economics, Planning, and Policy, 2018, 13(3): 190-195.
[21]
ZHANGB, MAJ H. Coal price index forecast by a new partial least-squares regression[J]. Procedia Engineering, 2011, 15: 5025-5029.
[22]
SHIR Y, WANGD, ZHAOY Y. The effect of international energy market shocks on coal price of China based on the fuzzy integrated vector auto regressive and error correction model[J]. Journal of Intelligent & Fuzzy Systems, 2021, 40(4): 8451-8461.
[23]
YUL, LAIK K, WANGS Y, et al. Oil price forecasting with an EMD-based multiscale neural network learning paradigm[C]// International Conference on Computational Science. Springer: Berlin, 2007: 925-932.
LIUShuo, HEYongxiu, TAOWeijun, et al. Coal price forecasting based on GABP neural network and risk resistance strategy[J]. Journal of North China Electric Power University, 2009, 36(6): 75-80.
[26]
KÖLMEKM A, NAVRUZİ. Forecasting the day-ahead price in electricity balancing and settlement market of Turkey by using artificial neural networks[J]. Turkish Journal of Electrical Engineering and Computer Sciences, 2015, 23(3): 841-852.
LIPenglin, LIANGLulu. Research on the influence factors and prediction of coal price based on BP neural network [J]. Mathematics in Practice and Theory, 2015, 17: 113-126.
YULean. Forecasting and decision optimization theory and methods based on artificial intelligence[J]. Journal of Management Science, 2022, 35(1): 60-66.
LIXingyi, LIZhongfei, LIQiqian, et al. A review of research on asset return prediction based on machine learning[J]. Chinese Journal of Management Science, 2025, 33(1): 311-322.
BIWenjie, FUChunjuan. Price estimation and determinants research of Airbnb with machine learning: Based on data from Beijing[J]. Operations Research and Management Science, 2022, 31(9): 217-224.
[36]
MANDALP, SRIVASTAVAA K, SENJYUT, et al. A new recursive neural network algorithm to forecast electricity price for PJM day-ahead market[J]. International Journal of Energy Research, 2010, 34(6): 507-522.
[37]
HOCHREITERS, SCHMIDHUBERJ. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[38]
ALAMEERZ, FATHALLAA, LIK, et al. Multistep-ahead forecasting of coal prices using a hybrid deep learning model[J]. Resources Policy, 2020, 65: 101588.
[39]
QIAOW B, YANGZ. Forecast the electricity price of US using a wavelet transform-based hybrid model[J]. Energy, 2020, 193: 116704.
[40]
HUANGW Y, GAOT X, HAOY, et al. Transformer-based forecasting for intraday trading in the Shanghai crude oil market: Analyzing open-high-low-close prices[J]. Energy Economics, 2023, 127: 107106.
[41]
FATALIYEVK, LIUW. MCASP: multi-modal cross attention network for stock market prediction[C]// Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association. 2023: 67-77.
[42]
ZHOUH Y, ZHANGS H, PENGJ Q, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[C]// Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(12): 11106-11115.
[43]
GONGM J, YANC C, XUW, et al. Short-term wind power forecasting model based on temporal convolutional network and Informer[J]. Energy, 2023, 283: 129171.
SHIJinwei, ZHANGCheng, YUANDongyun. Short-term wind power prediction based on data correction with probabilistic sparse self-attention[J]. Smart Power, 2023, 51(10): 54-61.
QINJin, HURan, MAOChenghui, et al. EMD-Informer method for prediction of daily passenger flow of high-speed railways[J]. Journal of the China Railway Society, 2024, 46(2): 1-11.
YANGXinsheng, YOUChao, ZHUChengyuan. Flight delay prediction based on Informer modeling[J]. Science Technology and Engineering, 2025, 25(19): 8282-8288.
[50]
ZHOUH Y, LIJ X, ZHANGS H, et al. Expanding the prediction capacity in long sequence time-series forecasting[J]. Artificial Intelligence, 2023, 318: 103886.
[51]
TSAIY H H, BAIS J, LIANGP P, et al. Multimodal transformer for unaligned multimodal language sequences[C]// Proceedings of the 57th conference of the Association for Computational Linguistics. Florence, 2019: 6558.
[52]
TANH, BANSALM. Lxmert: Learning cross-modality encoder representations from transformers[C]// 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hongkong, 2019: 5100-5111.
[53]
LUJ S, BATARD, PARIKHD, et al. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks[C]//Advances in Neural Information Processing Systems32 (NIPS 2019. Vancouver, 2019: 32.