设施农业具有高投入与高产出的特点，如何提高设施环境调控效益与降低能源消耗已成为其可持续发展的关键议题。构建精确的农业设施环境时序变化预测模型并据此开发设施环境智能调控算法，是实现农业低碳生产的可行途径。然而，现有预测模型未充分利用时序数据中存在的多变量、多周期性特征，导致多步预测精度提升受限，从而制约了设施环境的精准调控效果。本研究旨在实现对农业设施环境的高精度预测，研究对象为所采集的多变量时间序列数据。针对农业设施环境中各变量之间的关联性以及时间序列数据所体现的周期性特征，本文以Transformer网络为基础，并对其注意力机制模块进行改进，通过合理构建深度学习模型架构，实现对环境变化的精准预测。在此基础上，进一步融合模型预测控制的理念，以降低能源消耗、实现节能减排为目标，采用粒子群优化算法对农业设施的环境调控策略进行优化设计。主要研究思路如下：

（1）针对现有农业设施环境多变量预测模型未显式地考虑外源序列对目标序列的影响的问题，提出TwoStageformer模型。在Transformer模型的编解码器中加入两阶段注意力模块：跨时间注意力模块和跨变量注意力模块，分别捕获跨时间依赖性和跨变量依赖性，将自相关注意力范式改为更适合预测任务的预测型注意力范式。试验结果表明，当采用144步预测144步时，TwoStageformer模型在高邮鸭舍数据集的MAE和MSE分别是0.399℃、0.300℃。采用144步预测72步时，TwoStageformer模型在高邮鸭舍数据集的MAE和MSE分别是0.321℃、0.225℃。

（2）针对现有预测模型未充分利用时序数据中存在的多周期性特征，导致多步预测精度提升受限的问题，本研究在Transformer架构的基础上设计了农业设施环境预测模型TimesTransformer。采用傅里叶变换获取多个时序周期特征，将其进行二维转换，随后利用局部-全局 Transformer对二维数据实现基于时序依赖性的长期精准预测。试验结果表明，当采用144步预测144步时，TimesTransformer模型在溧水鸭舍数据集的R²、MAE和RMSE分别是0.918、0.501℃和0.621℃；采用144步预测72步时，TimesTransformer模型在溧水鸭舍数据集的R²、MAE和RMSE分别是0.934、0.456℃和0.516℃。

（3）针对农业生产中广泛采用的阈值控制方法存在过度依赖人工经验、调控精度不足等问题，本文提出一种基于模型预测控制理念的农业设施环境智能调控策略，以提升调控的科学性与精细化水平。首先基于已知环境参数，利用本研究提出的环境变化预测模型结合粒子群算法生成不同的调控方案，接着用预测模型对上述调控方案进行预测，然后以降低生产过程中的能耗为目标，对不同的调控方案进行评估，对上述过程进行多次迭代直至找到能耗最低并符合预期效果的最优环境调控方案。本研究提出的环境调控方案在一周内的能源消耗为341.4 kW·h^-1，相比阈值控制法的504.6 kW·h^-1，降低了约32.3%的能源消耗。

Facility agriculture has the characteristics of high input and high output. How to improve the environmental regulation efficiency of facilities and reduce energy consumption has become the key to its sustainable development. Constructing an accurate prediction model for the temporal changes in agricultural facility environment and developing intelligent regulation algorithms for facility environment based on it is a feasible way to achieve low-carbon agricultural production. However, existing prediction models have not fully utilized the multivariate and multi periodic features present in time-series data, which limits the improvement of multi-step prediction accuracy and thus restricts the precise control effect of facility environment. This research aims to achieve high-precision prediction of the agricultural facility environment, and the research object is the collected multivariate time series data. In view of the correlation between the variables in the agricultural facility environment and the periodic characteristics reflected by the time series data, this paper is based on the Transformer network and improves its attention mechanism module. By reasonably constructing a deep learning model architecture, it can achieve accurate prediction of environmental changes. On this basis, the concept of model predictive control is further integrated, with the goal of reducing energy consumption and achieving energy conservation and emission reduction, and the particle swarm optimization algorithm is used to optimize the design of the environmental control strategy of agricultural facilities. The main research ideas are as follows:

（1）To address the issue of existing multivariate prediction models for agricultural facility environments not explicitly considering the impact of external sequences on target sequences, a TwoStageformer model is proposed. Add two-stage attention modules to the encoder and decoder of the Transformer model, namely the cross-temporal attention module and the cross-variable attention module, which capture cross temporal and cross variable dependencies respectively, and change the autocorrelation attention mechanism to a more suitable predictive attention mechanism for prediction scenarios. The experimental results showed that when using 144 step prediction, the MAE and MSE of the TwoStageformer model on the Gaoyou duck shed dataset were 0.399℃ and 0.300℃, respectively. When using 144 step prediction for 72 steps, the MAE and MSE of the TwoStageformer model on the Gaoyou duck shed dataset were 0.321℃ and 0.225℃, respectively.

（2）To address the problem that existing prediction models do not utilize the multi-periodic characteristics of time series data, resulting in limited improvement in multi-step prediction accuracy, this study designed an agricultural facility environment prediction model TimesTransformer based on the Transformer architecture. Fourier transform is used to obtain multiple time-series periodic features, which are then transformed into two dimensions. Subsequently, a local global Transformer is used to achieve long-term accurate prediction based on temporal dependencies on the two-dimensional data. The experimental results show that when 144 steps are used to predict 144 steps, the R², MAE and RMSE of the TimesTransformer model on the Lishui duck house dataset are 0.918, 0.501℃ and 0.621℃ respectively. When using 144 steps to predict 72 steps, the R², MAE and RMSE of the TimesTransformer model on the Lishui duck house dataset are 0.934, 0.456℃ and 0.516℃ respectively.

（3）In view of the problems of over-reliance on manual experience and insufficient control precision in the threshold control method widely used in agricultural production, this paper proposes an intelligent control strategy for agricultural facility environment based on the concept of model predictive control to improve the scientificity and refinement of control. Firstly, based on known environmental parameters, the environmental change prediction model proposed in this study is combined with particle swarm optimization algorithm to generate different control schemes. Then, the prediction model is used to predict the above control schemes. With the goal of reducing energy consumption in the production process, different control schemes are evaluated. The above process is iterated multiple times until the optimal environmental control scheme with the lowest energy consumption and meeting the expected effect is found. The environmental regulation scheme proposed in this study has an energy consumption of 341.4 kW · h^-1 within one week, which is about 32.3% lower than the threshold control method of 504.6 kW · h^-1.

[1]蔡一鸣, 马力, 陆恒杨, 等. 基于全流程并行遗传算法的贝叶斯网络结构学习[J]. 系统工程与电子技术, 2024, 46(05): 1703-1711.

[2]封钰, 宋佑斌, 金晟, 等. 基于随机森林算法和粗糙集理论的改进型深度学习短期负荷预测模型[J]. 发电技术, 2023, 44(06): 889-895.

[3]康孟珍, 孙贺全, 王秀娟, 等. 系统农业: 结合农业社会经济属性的建模和控制[J]. 智能科学与技术学报, 2023, 5(01): 41-50.

[4]李锋, 樊玉和, 梁辉. 基于改进 BP 神经网络 PID 控制器温室温湿度控制研究[J]. 计算机与数字工程, 2021, 49(05): 908-913+986.

[5]梁超, 尹欢欢, 李保明, 等. 蛋鸡舍热湿环境参数全年逐时动态预测模型[J]. 农业工程学报, 2021, 37(08): 229-235.

[6]潘金伟, 王乙乔, 钟博, 等. 基于统计特征搜索的多元时间序列预测方法[J]. 电子与信息学报, 2024, 46(08): 3276-3284.

[7]庞维庆, 何宁, 李秀梅, 等. 室内环境的数据融合自适应调控方法研究[J]. 控制理论与应用, 2020, 37(03): 610-619.

[8]孙艺伟, 任妮, 郭婷, 等. 设施畜牧业关键技术研究态势分析[J]. 农业图书情报学报, 2021, 33(10): 87-97.

[9]滕光辉. 畜禽设施精细养殖中信息感知与环境调控综述[J]. 智慧农业, 2019, 1(03): 1-12.

[10]张芳, 方慧, 杨其长, 等. 基于 CFD 模型的大跨度温室自然通风热环境模拟[J]. 中国农业气象, 2017, 38(04): 221-229.

[11]邹秋滢. 温室小气候模型的建立及其控制策略研究[D]. 沈阳: 沈阳农业大学, 2010.

[12]邹宇航, 王明飞, 张馨, 等. 基于模型预测控制的工厂化菇房空调调控方法[J]. 中国农机化学报, 2024, 45(06): 98-105.

[13]Abou Houran M, Bukhari S M S, Zafar M H, et al. COA-CNN-LSTM: Coati optimization algorithm-based hybrid deep learning model for PV/wind power forecasting in smart grid applications[J]. Applied Energy, 2023, 349(21): 121638.

[14]Adesanya M A, Obasekore H, Rabiu A, et al. Deep reinforcement learning for PID parameter tuning in greenhouse HVAC system energy Optimization: A TRNSYS-Python cosimulation approach[J]. Expert Systems with Applications, 2024, 252(18): 124126.

[15]Ahmed S F, Alam M S B, Hassan M, et al. Deep learning modelling techniques: current progress, applications, advantages, and challenges[J]. Artificial Intelligence Review, 2023, 56(11): 13521-13617.

[16]Alabi T M, Aghimien E I, Agbajor F D, et al. A review on the integrated optimization techniques and machine learning approaches for modeling, prediction, and decision making on integrated energy systems[J]. Renewable Energy, 2022, 194(14): 822-849.

[17]Ali A, Hussain T, Tantashutikun N, et al. Application of smart techniques, internet of things and data mining for resource use efficient and sustainable crop production[J]. Agriculture, 2023, 13(02): 397-418.

[18]Boateng E Y, Otoo J, Abaye D A. Basic tenets of classification algorithms K-nearest-neighbor, support vector machine, random forest and neural network: A review[J]. Journal of Data Analysis and Information Processing, 2020, 8(04): 341-357.

[19]Bounoua I, Saidi Y, Yaagoubi R, et al. Deep learning approaches for water stress forecasting in arboriculture using time series of remote sensing images: Comparative study between convlstm and cnn-lstm models[J]. Technologies, 2024, 12(06): 77-99.

[20]Box G E, Pierce D A. Distribution of residual autocorrelations in autoregressive-integrated moving average time series models[J]. Journal of the American statistical Association, 1970, 65(332): 1509-1526.

[21]Cavus M, Allahham A. Enhanced microgrid control through genetic predictive control: integrating genetic algorithms with model predictive control for improved non-linearity and non-convexity handling[J]. Energies, 2024, 17(17): 4458-4477.

[22]Challa S K, Kumar A, Semwal V B. A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data[J]. The Visual Computer, 2022, 38(12): 4095-4109.

[23]Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE transactions on Neural Networks, 1999, 10(05): 1055-1064.

[24]Chen J, Zhu D, Ding S, et al. Government environmental concerns and corporate green innovation: Evidence from heavy‐polluting enterprises in China[J]. Business Strategy and the Environment, 2024, 33(03): 1920-1936.

[25]Chen S, Liu A, Tang F, et al. A Review of Environmental Control Strategies and Models for Modern Agricultural Greenhouses[J]. Sensors, 2025, 25(05): 1388-1410.

[26]Chen T-H, Lee M-H, Hsia I-W, et al. Develop a smart microclimate control system for greenhouses through system dynamics and machine learning techniques[J]. Water, 2022, 14(23): 3941-3959.

[27]Chen X, Jiang Z, Cheng H, et al. A novel global average temperature prediction model——based on GM-ARIMA combination model[J]. Earth Science Informatics, 2024, 17(01): 853-866.

[28]Chung J, Gulcehre C, Cho K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv preprint arXiv:14123555, 2014.

[29]D’Antonoli T A, Stanzione A, Bluethgen C, et al. Large language models in radiology: fundamentals, applications, ethical considerations, risks, and future directions[J]. Diagnostic and Interventional Radiology, 2024, 30(02): 80-90.

[30]Dargan S, Kumar M, Ayyagari M R, et al. A survey of deep learning and its applications: a new paradigm to machine learning[J]. Archives of computational methods in engineering, 2020, 27(04): 1071-1092.

[31]Dayıoğlu M A, Turker U. Digital transformation for sustainable future-agriculture 4.0: A review[J]. Journal of Agricultural Sciences, 2021, 27(04): 373-399.

[32]Driesen E, Van den Ende W, De Proft M, et al. Influence of environmental factors light, CO2, temperature, and relative humidity on stomatal opening and development: A review[J]. Agronomy, 2020, 10(12): 1975-2002.

[33]Du S, Li T, Yang Y, et al. Multivariate time series forecasting via attention-based encoder–decoder framework[J]. Neurocomputing, 2020, 388(18): 269-279.

[34]Fan G-F, Zhang L-Z, Yu M, et al. Applications of random forest in multivariable response surface for short-term load forecasting[J]. International Journal of Electrical Power & Energy Systems, 2022, 139(06): 108073.

[35]Fan G, Peng C, Wang X, et al. Optimal scheduling of integrated energy system considering renewable energy uncertainties based on distributionally robust adaptive MPC[J]. Renewable Energy, 2024, 226(07): 120457.

[36]Freitag D. Machine learning for information extraction in informal domains[J]. Machine learning, 2000, 39(2): 169-202.

[37]Goh Y S, Hum Y C, Lee Y L, et al. A meta-analysis: Food production and vegetable crop yields of hydroponics[J]. Scientia Horticulturae, 2023, 321(15): 112339.

[38]Gu D, Andreev K, Dupre M E. Major trends in population growth around the world[J]. China CDC weekly, 2021, 3(28): 604-613.

[39]Hamidi O, Tapak L, Abbasi H, et al. Application of random forest time series, support vector regression and multivariate adaptive regression splines models in prediction of snowfall (a case study of Alvand in the middle Zagros, Iran)[J]. Theoretical and Applied Climatology, 2018, 134(3): 769-776.

[40]Hassanin M, Anwar S, Radwan I, et al. Visual attention methods in deep learning: An in-depth survey[J]. Information Fusion, 2024, 108(8): 102417.

[41]Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.

[42]Iddio E, Wang L, Thomas Y, et al. Energy efficient operation and modeling for greenhouses: A literature review[J]. Renewable and Sustainable Energy Reviews, 2020, 117(01): 109480.

[43]Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]// International conference on machine learning. 2015: 448-456.

[44]Jiang J, Li Y, Zhu B. A study of stochastic evolutionary game prediction models based on SVM and random forests[C]// 2024 International Conference on Electronics and Devices, Computational Science (ICEDCS). 2024: 841-848.

[45]Kashyap R L. Optimal choice of AR and MA parts in autoregressive moving average models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1982, (2): 99-104.

[46]Khan M I H, Batuwatta-Gamage C P, Karim M, et al. Fundamental understanding of heat and mass transfer processes for physics-informed machine learning-based drying modelling[J]. Energies, 2022, 15(24): 9347-9373.

[47]Khudoyberdiev A, Ahmad S, Ullah I, et al. An optimization scheme based on fuzzy logic control for efficient energy consumption in hydroponics environment[J]. Energies, 2020, 13(2): 289-315.

[48]Lea C, Flynn M D, Vidal R, et al. Temporal convolutional networks for action segmentation and detection[C]// proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 156-165.

[49]LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

[50]Lemaire G, Franzluebbers A, de Faccio Carvalho P C, et al. Integrated crop–livestock systems: Strategies to achieve synergy between agricultural production and environmental quality[J]. Agriculture, Ecosystems & Environment, 2014, 190(09): 4-8.

[51]Liakos K G, Busato P, Moshou D, et al. Machine learning in agriculture: A review[J]. Sensors, 2018, 18(8): 2674-2702.

[52]Lindemann B, Müller T, Vietz H, et al. A survey on long short-term memory networks for time series prediction[J]. Procedia Cirp, 2021, 99(4): 650-655.

[53]Mao X, Ren N, Dai P, et al. A variable weight combination prediction model for climate in a greenhouse based on BiGRU-Attention and LightGBM[J]. Computers and Electronics in Agriculture, 2024, 219(04): 108818.

[54]Maraveas C, Karavas C-S, Loukatos D, et al. Agricultural greenhouses: Resource management technologies and perspectives for zero greenhouse gas emissions[J]. Agriculture, 2023, 13(7): 1464-1509.

[55]Menghani G. Efficient deep learning: A survey on making deep learning models smaller, faster, and better[J]. ACM Computing Surveys, 2023, 55(12): 1-37.

[56] Mienye I D, Sun Y. A survey of ensemble learning: Concepts, algorithms, applications, and prospects[J]. Ieee Access, 2022, 10(1): 99129-99149.

[57]Mienye I D, Swart T G, Obaido G. Recurrent neural networks: A comprehensive review of architectures, variants, and applications[J]. Information, 2024, 15(9): 517-550.

[58]Mittal A, Brajpuriya R, Gupta R. Solar steam generation using hybrid nanomaterials to address global environmental pollution and water shortage crisis[J]. Materials Today Sustainability, 2023, 21(1): 100319.

[59]Mohammadi B, Ranjbar S F, Ajabshirchi Y. Application of dynamic model to predict some inside environment variables in a semi-solar greenhouse[J]. Information processing in agriculture, 2018, 5(2): 279-288.

[60]Munappy A R, Bosch J, Olsson H H, et al. Data management for production quality deep learning models: Challenges and solutions[J]. Journal of Systems and Software, 2022, 191(08): 111359.

[61]Munarsih E, Saluza I. Comparison of exponential smoothing method and autoregressive integrated moving average (ARIMA) method in predicting dengue fever cases in the city of Palembang[C]// Journal of Physics: conference series. 2020: 032100-032106.

[62]Nandi A, De A, Mallick A, et al. Attention based long-term air temperature forecasting network: ALTF Net[J]. Knowledge-Based Systems, 2022, 252(18): 109442.

[63]Natarajan S K, Elavarasan E. A review on computational fluid dynamics analysis on greenhouse dryer[C]// IOP Conference Series: Earth and Environmental Science. 2019: 012033-012043.

[64]Nie Y, Nguyen N H, Sinthong P, et al. A time series is worth 64 words: Long-term forecasting with transformers[J]. arXiv preprint arXiv:221114730, 2022.

[65]Peng B, Guan K, Tang J, et al. Towards a multiscale crop modelling framework for climate change adaptation assessment[J]. Nature plants, 2020, 6(4): 338-348.

[66]Pervez A, Ali I. Robust regression analysis in analyzing financial performance of public sector banks: A case study of India[J]. Annals of Data Science, 2024, 11(2): 677-691.

[67]Rao A S, Radanovic M, Liu Y, et al. Real-time monitoring of construction sites: Sensors, methods, and applications[J]. Automation in Construction, 2022, 136(04): 104099.

[68]Selmy H A, Mohamed H K, Medhat W. A predictive analytics framework for sensor data using time series and deep learning techniques[J]. Neural Computing and Applications, 2024, 36(11): 6119-6132.

[69]Sethi V, Sumathy K, Lee C, et al. Thermal modeling aspects of solar greenhouse microclimate control: A review on heating technologies[J]. Solar energy, 2013, 96(10): 56-82.

[70]Singh R K, Berkvens R, Weyn M. AgriFusion: An architecture for IoT and emerging technologies based on a precision agriculture survey[J]. IEEE Access, 2021, 9(9): 136253-136283.

[71]Sohn G, Zhang N, Olukotun K. Implementing and optimizing the scaled dot-product attention on streaming dataflow[J]. arXiv preprint arXiv:240416629, 2024.

[72]Soltani A, Maleki M, Zeinali E. Optimal crop management can reduce energy use and greenhouse gases emissions in rainfed canola production[J]. International Journal of plant production, 2014, 8(4): 587-604.

[73]Sun F, Hao W, Zou A, et al. A survey on spatio-temporal series prediction with deep learning: taxonomy, applications, and future directions[J]. Neural Computing and Applications, 2024, 36(17): 9919-9943.

[74]Sun N, Fan B, Ding Y, et al. Analysis of the development status and prospect of china’s agricultural sensor market under smart agriculture[J]. Sensors, 2023, 23(6): 3307-3321.

[75]Tao P, Hao X, Cheng J, et al. Predicting time series by data-driven spatiotemporal information transformation[J]. Information Sciences, 2023, 622(04): 859-872.

[76]Tong G, Ge Z, Peng D. RSMformer: an efficient multiscale transformer-based framework for long sequence time-series forecasting[J]. Applied Intelligence, 2024, 54(2): 1275-1296.

[77]Vandana G, Sejian V, Lees A, et al. Heat stress and poultry production: impact and amelioration[J]. International Journal of Biometeorology, 2021, 65(02): 163-179.

[78]Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]// Advances in neural information processing systems. 2017: 5998-6008.

[79]Verdonck T, Baesens B, Óskarsdóttir M, et al. Special issue on feature engineering editorial[J]. Machine learning, 2024, 113(7): 3917-3928.

[80]Wan R, Mei S, Wang J, et al. Multivariate temporal convolutional network: A deep neural networks approach for multivariate time series forecasting[J]. Electronics, 2019, 8(8): 876-893.

[81]Waqas M, Humphries U W. A critical review of RNN and LSTM variants in hydrological time series predictions[J]. MethodsX, 2024, 13(2): 102946.

[82]Wu H, Xu J, Wang J, et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting[C]// Advances in neural information processing systems. 2021: 22419-22430.

[83]Xu H, Shen M. The control of lithium‐ion batteries and supercapacitors in hybrid energy storage systems for electric vehicles: A review[J]. International Journal of Energy Research, 2021, 45(15): 20524-20544.

[84]Yang Y, Gao P, Sun Z, et al. Multistep ahead prediction of temperature and humidity in solar greenhouse based on FAM-LSTM model[J]. Computers and Electronics in Agriculture, 2023, 213(10): 108261.

[85]Yao Y, Yang M, Wang J, et al. Multivariate time-series prediction in industrial processes via a deep hybrid network under data uncertainty[J]. IEEE Transactions on Industrial Informatics, 2022, 19(2): 1977-1987.

[86]Yule G U. On a method of investigating periodicities in disturbed series with special reference to Wolfer’s sunspot numbers[J]. Statistical Papers of George Udny Yule, 1971, 226(1): 267-298.

[87]Zarzycki K, Ławryńczuk M. LSTM and GRU neural networks as models of dynamical processes used in predictive control: A comparison of models developed for two chemical reactors[J]. Sensors, 2021, 21(16): 5625-5651.

[88]Zeng P, Hu G, Zhou X, et al. Muformer: A long sequence time-series forecasting model based on modified multi-head attention[J]. Knowledge-Based Systems, 2022, 254(22): 109584.

[89]Zhang F, Liu Q, Liu Y, et al. Novel fault location method for power systems based on attention mechanism and double structure GRU neural network[J]. IEEE Access, 2020, 8(1): 75237-75248.

[90]Zhang K, Qiang S, Liang Z, et al. A greenhouse temperature prediction framework based on transformer neural network[C]// 2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI). 2021: 232-236.

[91]Zhang X, Fu X, Xue Y, et al. A review on basic theory and technology of agricultural energy internet[J]. IET Renewable Power Generation, 2024, 18(7): 1318-1331.

[92]Zhang Y, Xu L, Zhu X, et al. Thermal environment model construction of Chinese solar greenhouse based on temperature–wave interaction theory[J]. Energy and Buildings, 2023, 279(02): 112648.

[93]Zhang Z, Wang C, Zhao W, et al. Ego vehicle trajectory prediction based on time-feature encoding and physics-intention decoding[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(7): 6527-6542.

[94]Zhao W X, Zhou K, Li J, et al. A survey of large language models[J]. arXiv preprint arXiv:230318223, 2023, 1(2).

[95]Zhao X, Wang L, Zhang Y, et al. A review of convolutional neural networks in computer vision[J]. Artificial Intelligence Review, 2024, 57(4): 99-141.

[96]Zhou H, Zhang S, Peng J, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[C]// Proceedings of the AAAI conference on artificial intelligence. 2021: 11106-11115.