The active response to the climate change is one of the goals of sustainable development. This paper presents a temperature prediction model based on the graph attention mechanism. The attention mechanism on the topology of the temperature sites is used to selectively aggregate the temperature feature of the surrounding area. Then the neural network is used to fit the complex temperature change pattern and forecast the future temperatures. In the experiments, the temperature data of Beijing-Tianjin-Hebei region from 2000 to 2010 are used. A large number of experiments show that with this method more accurate predictions can be made with a small amount of historical temperature data. The model can provide the decision support for the climate prediction and the climate disaster prevention, with an important scientific and practical significance.
[1] Sakr G E, Elhajj I H, Mitri G, et al. Artificial intelligence for forest fire prediction[C]//2010 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Piscataway, NJ:IEEE, 2010:1311-1316.
[2] Cheng T, Wang J. Integrated spatio-temporal data mining for forest fire prediction[J]. Transactions in GIS, 2008, 12(5):591-611.
[3] Pinson P, Kariniotakis G. Conditional prediction intervals of wind power generation[J]. IEEE Transactions on Power Systems, 2010, 25(4):1845-1856.
[4] Zhao X, Gang W, Zhao K K, et al. On-line least squares support vector machine algorithm in gas prediction[J]. Mining Science and Technology (China), 2009, 19(2):194-198.
[5] 崔书岳, 黄晓辉, 陈云亮, 等. 基于HMM的缝洞型油藏产量预测算法[J]. 西南大学学报:自然科学版, 2020, 42(2):137-144.
[6] 李雪超. 兰州市气温变化趋势及预测[D]. 兰州:兰州财经大学统计学院, 2019.
[7] 陈广仁. 气候变化关乎人类未来[J]. 科技导报, 2011, 29(34):8.
[8] Boko M, Niang I, Nyong A, et al. Africa Climate Change 2007:Impacts, Adaptation and Vulnerability:Contribution of working group ii to the fourth assessment report of the intergovernmental panel on climate change[R]. Cambridge UK:IPCC, 2018.
[9] 王灏晨, 路凤, 武继磊, 等. 中国气候变化对人口健康影响研究评述[J]. 科技导报, 2014, 32(28/29):109-116.
[10] Xue M, Wang D, Gao J, et al. The Advanced Regional Prediction System (ARPS), storm-scale numerical weather prediction and data assimilation[J]. Meteorology & Atmospheric Physics, 2003, 82(1):139-170.
[11] 杨成荫, 赵苏璇, 程立国, 等. 短期区域气候预测系统及回报试验[J]. 解放军理工大学学报:自然科学版, 2016, 17(3):289-295.
[12] Smith M. Vehicle-centric weather prediction system and method:US, Patent 6,603,405[P]. 2003-08-05.
[13] 彭京备, 布和朝鲁, 郑飞, 等. 2017年夏季全国气候趋势展望[J]. 中国科学院院刊, 2017, 32(4):413-417.
[14] Abuella M, Chowdhury B. Solar power probabilistic forecasting by using multiple linear regression analysis[C]//SoutheastCon 2015, Fort Lauderdale, USA:IEEE, 2015:1-5.
[15] 王丹, 王建鹏, 白庆梅, 等. 递减平均法与一元线性回归法对ECMWF温度预报订正能力对比[J]. 气象, 2019, 45(9):1310-1321.
[16] 金秀良, 宋燕, 吴洪, 等. 应用北半球大气环流系统预测中国降水量和气温[J]. 气象科技, 2014, 42(6):1028-1038.
[17] 倪淑娜, 唐波, 蔡家辉. 基于GM-ARMA组合模型的全球年平均气温预测[J]. 中国新技术新产品, 2008(12):9-10.
[18] 陈百硕, 李守伟, 何建敏, 等. 天气衍生品中时变均值回复的气温预测模型研究[J]. 管理工程学报, 2014, 28(2):145-150.
[19] Huang C Y, Liu Y W, Tzeng W C, et al. Short term wind speed predictions by using the grey prediction model based forecast method[C]//2011 IEEE Green Technologies Conference (IEEE-Green). Baton Rouge, USA:IEEE, 2011:1-5.
[20] 牛志娟, 胡红萍. 基于主成分分析的BP神经网络和RBF神经网络月平均气温预测模型[J]. 高师理科学刊, 2015, 35(11):6-8.
[21] 林耿, 郑紫微. 基于灰色-BP神经网络的福州市年平均气温预测模型[J]. 河南工程学院学报:自然科学版, 2018, 30(4):71-75.
[22] 陶晔, 杜景林. 基于随机森林的长短期记忆网络气温预测[J]. 计算机工程与设计, 2019, 40(3):737-743.
[23] Miguez-Macho G, Stenchikov G L, Robock A. Regional climate simulations over North America:Interaction of local processes with improved large-scale flow[J]. Journal of Climate, 2005, 18(8):1227-1246.
[24] 刘鸿波, 张大林, 王斌. 区域气候模拟研究及其应用进展[J]. 气候与环境研究, 2006(5):649-668.
[25] Hornik K. Approximation capabilities of multilayer feedforward networks[J]. Neural Networks, 1991, 4(2):251-257.
[26] Bianchini M, Maggini M, Sarti L, et al. Recursive neural networks for processing graphs with labelled edges:Theory and applications[J]. Neural Networks, 2005, 18(8):1040-1050.
[27] Scarselli F, Gori M, Tsoi A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1):61-80.
[28] Velič ković P, Cucurull G, Casanova A, et al. Graph Attention Networks[C]//International Conference on Learning Representations. Vancouver, Canada:International Conference on Learning Representations. 2018:1-12
[29] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in neural information processing systems. Long Beach, CA:Curran Associates, 2017:5998-6008.
[30] Clevert D A, Unterthiner T, Hochreiter S. Fast and accurate deep network learning by exponential linear units (elus)[C]//International Conference on Learning Representations. San Juan, Puerto Rico:International Conference onLearning Representations, 2016:1-14.
