基于AQI-Transformer的生态环境大气污染浓度预测研究
Prediction of Atmospheric Pollution Concentration in Ecological Environment Based on AQI-Transformer
DOI: 10.12677/airr.2025.144101, PDF,   
作者: 范 建, 胡兴元*, 刘 京, 武建双：中检集团天帷信息技术(安徽)股份有限公司，人工智能研究中心，安徽 合肥；何 君：滁州学院外国语学院，安徽 滁州
关键词: 生态环境；大数据；人工智能；AQI-Transformer；污染浓度预测；Ecological Environment； Big Data； Artificial Intelligence； AQI-Transformer；Pollution Concentration Prediction
摘要: 工业化和城市化的快速发展导致大气污染加剧，对公众健康及生态环境造成显著危害。本文主要介绍了人工智能与大数据技术在大气污染防治中的创新应用及效果分析。文章探讨了人工智能在构建空气质量预测模型以及优化决策策略等方面的作用，指出其能为决策者提供定量分析依据，提高污染防治的科学性和有效性。同时，还分析了数据分析与挖掘以及智慧环保建设等方面的融合创新，强调了人工智能与大数据、FaaS函数技术在提高监测效率、发现污染规律和支持政策制定等方面的重要作用以及对未来发展趋势的展望。通过实际数据集上的实验验证，本文提出的AQI-Transformer模型在短期(4小时)与中长期(24小时)的污染浓度预测任务中，均展现出了更低的均方根误差(RMSE)和平均绝对误差(MAE)，证明了其在提升大气污染防治效率与效果方面的潜力。
Abstract: The rapid development of industrialization and urbanization has led to the aggravation of air pollution, which has caused significant harm to public health and ecological environment. This paper mainly introduces the innovative application and effect analysis of artificial intelligence and big data technology in the prevention and control of air pollution. This paper discusses the role of artificial intelligence in building air quality prediction models and optimizing decision-making strategies, and points out that it can provide quantitative analysis basis for decision-makers and improve the scientificity and effectiveness of pollution prevention and control. At the same time, it also analyzes the integration and innovation of data analysis and mining and smart environmental protection construction, and emphasizes the important role of AI, big data and FAAS function technology in improving monitoring efficiency, discovering pollution laws and supporting policy-making, as well as the prospect of future development trends. Through the experimental verification on the actual data set, the AQI transformer model proposed in this paper shows lower root mean square error (RMSE) and mean absolute error (MAE) in the short-term (4 hours) and medium and long-term (24 hours) pollution concentration prediction tasks, which proves its potential in improving the efficiency and effect of air pollution prevention and control.
文章引用：范建, 胡兴元, 何君, 刘京, 武建双. 基于AQI-Transformer的生态环境大气污染浓度预测研究[J]. 人工智能与机器人研究, 2025, 14(4): 1064-1076. https://doi.org/10.12677/airr.2025.144101

参考文献

[1] 稳清, 姜琳琳, 朱元航, 等. 苏州市土地利用及生境质量变化预测[J]. 环境监测管理与技术, 2023, 35(6): 15-21.
[2] 孔冬艳, 陈会广, 吴孔森. 中国“三生空间”演变特征、生态环境效应及其影响因素[J]. 自然资源学报, 2021, 36(5): 10-30.
[3] 廖雨辰, 史雪威, 刘俊雁, 等. 九寨沟国家级自然保护区地震前后生态系统服务价值评估[J]. 生态学报, 2022, 42(6): 2063-2073.
[4] 杨光宗, 吕凯, 李峰. 基于格网尺度的南昌市土地利用变化及生态系统服务价值时空相关性分析[J]. 中国土地科学, 2022, 36(8): 121-130.
[5] 李姚旺, 张宁, 杜尔顺, 等. 基于碳排放流的电力系统低碳需求响应机制研究及效益分析[J]. 中国电机工程学报, 2022, 42(8): 2830-2842
[6] Hmiel, B., Petrenko, V.V., Dyonisius, M.N., Buizert, C., Smith, A.M., Place, P.F., et al. (2020) Preindustrial 14CH4 Indicates Greater Anthropogenic Fossil CH4 Emissions. Nature, 578, 409-412. [Google Scholar] [CrossRef] [PubMed]
[7] Hensen, A., Velzeboeri, Frumau, K.F.A., et al. (2019) Methane e-Mission Measurements of Offshore Oil and Gas Platforms: TNO Report R10895. TNO, 32-35.
[8] Denil, M., Shakibi, B., Dinh, L., et al. (2013) Predicting Parameters in Deep Learning. In: Proceedings of the 26th International Conference on Neural Information Processing Systems, Curran Associates Inc., 2148-2156.
[9] Girshick, R. (2015) Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 13-16 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[10] Ren, S., He, K., Girshick, R. and Sun, J. (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] [PubMed]
[11] Chen, Y., Huo, J., Liu, Y., Zeng, Z., Zhu, X., Chen, X., et al. (2020) Development of a Novel Flow Cytometry‐Based Approach for Reticulocytes Micronucleus Test in Rat Peripheral Blood. Journal of Applied Toxicology, 41, 595-606. [Google Scholar] [CrossRef] [PubMed]
[12] Saunois, M., Stavert, A.R., Poulter, B., et al. (2020) The Global Methane Budget 2000-2017. Earth System Science Data, 12, 1561-1623.
[13] Bai, J., et al. (2023) Qwen Technical Report.
[14] Glm, T., et al. (2024) ChatGLM: A Family of Large Language Models from GLM-130b to GLM-4 All Tools.
[15] Rajpurkar, P., Chen, E., Banerjee, O. and Topol, E.J. (2022) AI in Health and Medicine. Nature Medicine, 28, 31-38. [Google Scholar] [CrossRef] [PubMed]
[16] Mao, Y., et al. (2024) A Survey on Lora of Large Language Models.
[17] Yang, A., et al. (2023) Baichuan 2: Open Large-Scale Language Models.
[18] Devlin, J. (2018) Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding.
[19] Yao, H., Liu, H. and Zhang, P. (2018) A Novel Sentence Similarity Model with Word Embedding Based on Convolutional Neural Network. Concurrency and Computation: Practice and Experience, 30, 1-12. [Google Scholar] [CrossRef] 
[20] Tyner, D.R. and Johnson, M.R. (2021) Where the Methane Is—Insights from Novel Airborne LiDAR Measurements Combined with Ground Survey Data. Environmental Science & Technology, 55, 9773-9783. [Google Scholar] [CrossRef] [PubMed]
[21] Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., et al. (2021) Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 11106-11115. [Google Scholar] [CrossRef] 
[22] Wu, H.X., Xu, J.H., Wang, J.M., et al. (2021) Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting. Proceedings of the Annual Conference on Neural Information Processing Systems, 6-14 December 2021, 22419-22430.
[23] Souza, F., Nogueira, R. and Lotufo, R. (2020) BERTimbau: Pretrained BERT Models for Brazilian Portuguese. In: Cerri, R. and Prati, R.C., Eds., Intelligent Systems, Springer International Publishing, 403-417. [Google Scholar] [CrossRef] 
[24] Plant, G., Kort, E.A., Floerchinger, C., Gvakharia, A., Vimont, I. and Sweeney, C. (2019) Large Fugitive Methane Emissions from Urban Centers along the U.S. East Coast. Geophysical Research Letters, 46, 8500-8507. [Google Scholar] [CrossRef] [PubMed]
[25] Sapci, A.H. and Sapci, H.A. (2020) Artificial Intelligence Education and Tools for Medical and Health Informatics Students: Systematic Review. JMIR Medical Education, 6, e19285. [Google Scholar] [CrossRef] [PubMed]
[26] Tsourounis, D., Kastaniotis, D., Theoharatos, C., Kazantzidis, A. and Economou, G. (2022) SIFT-CNN: When Convolutional Neural Networks Meet Dense SIFT Descriptors for Image and Sequence Classification. Journal of Imaging, 8, 256-291. [Google Scholar] [CrossRef] [PubMed]
[27] Eyring, V., Collins, W.D., Gentine, P., Barnes, E.A., Barreiro, M., Beucler, T., et al. (2024) Pushing the Frontiers in Climate Modelling and Analysis with Machine Learning. Nature Climate Change, 14, 916-928. [Google Scholar] [CrossRef] 
[28] Zhang, H., Ren, R., Gao, X., Wang, H., Jiang, W., Jiang, X., et al. (2025) Synchronous Monitoring Agricultural Water Qualities and Greenhouse Gas Emissions Based on Low-Cost Internet of Things and Intelligent Algorithms. Water Research, 268, Article ID: 122663. [Google Scholar] [CrossRef] [PubMed]
[29] Chen, S., Huang, J., Wang, P., Tang, X. and Zhang, Z. (2024) A Coupled Model to Improve River Water Quality Prediction towards Addressing Non-Stationarity and Data Limitation. Water Research, 248, Article ID: 120895. [Google Scholar] [CrossRef] [PubMed]
[30] Liu, R., Zayed, T. and Xiao, R. (2024) Advanced Acoustic Leak Detection in Water Distribution Networks Using Integrated Generative Model. Water Research, 254, Article ID: 121434. [Google Scholar] [CrossRef] [PubMed]
[31] Hamedi, S.Z., Emami, H., Khayamzadeh, M., Rabiei, R., Aria, M., Akrami, M., et al. (2024) Application of Machine Learning in Breast Cancer Survival Prediction Using a Multimethod Approach. Scientific Reports, 14, Article No. 30147. [Google Scholar] [CrossRef] [PubMed]

为你推荐