Forecasting model of pollen concentration based on particle swarm optimization and support vector machine
ZHAO Wenfang1,2, WANG Jingli1, SHANG Min3, LIU Yanan2
1. Institute of Urban Meteorology, China Meteorological Administration, Beijing 100089, China; 2. Beijing Meteorological Information Center, Beijing 100089, China; 3. College of Geography and Land Engineering, Yuxi Normal University, Yuxi Yunnan 653100, China
Abstract：To improve the accuracy of pollen concentration forecast and resolve low accuracy of current pollen concentration forecast model, a model for daily pollen concentration forecasting based on Particle Swarm Optimization (PSO) algorithm and Support Vector Machine (SVM) was proposed. Firstly, the feature vector extraction was carried out by using correlation analysis technique to select meteorological data with strong correlation with pollen concentration, such as temperature, daily temperature difference, relative humidity, precipitation, wind, sunshine hours. Secondly, an SVM prediction model based on this vector and pollen concentration observation data was established. The PSO algorithm was designed to optimize the parameters in SVM algorithm, and then the optimal parameters were used to construct daily pollen concentration prediction model. Finally, the forecast of pollen concentration in 24 hours in advance was made by using the optimized SVM model. The comparison among the accuracy of the optimized SVM model, Multiple Linear Regression (MLR) model and Back Propagation Neural Network (BPNN) model was performed to evaluate their performances. In addition, the optimized model was also applied for the forecast of pollen concentration in 24 hours in advance at Nanjiao and Miyun meteorological observation stations. The experimental results show that the proposed method performs better than MLR and BPNN methods. Meanwhile, it also provides promising results for forecast of pollen concentration in 24 hours in advance and also has good generalization ability.
赵文芳, 王京丽, 尚敏, 刘亚楠. 基于粒子群优化和支持向量机的花粉浓度预测模型[J]. 计算机应用, 2019, 39(1): 98-104.
ZHAO Wenfang, WANG Jingli, SHANG Min, LIU Yanan. Forecasting model of pollen concentration based on particle swarm optimization and support vector machine. Journal of Computer Applications, 2019, 39(1): 98-104.
[1] 吴振玲,刘爱霞,白玉荣,等.花粉预报服务社会经济效益估算分析[J].气象,2011,37(5):626-632.(WU Z L, LIU A X, BAI Y R, et al. Study on evaluation of economic benefits from pollen forecast and service in Tianjin[J]. Meteorological Monthly, 2011, 37(5):626-632.) [2] 白玉荣,刘彬贤,刘艳,等.花粉浓度预报[J].气象,2002,28(6):56-57.(BAI Y R, LIU B X, LIU Y, et al. Pollen concentration forecast[J]. Meteorological Monthly, 2002, 28(6):56-58.) [3] 刘彬贤,白玉荣.花粉浓度预报方法的初步探究[J].气象科学,2007,27(b12):95-99.(LIU B X, BAI Y R. Primary research method on forecasting the pollen concentration[J]. Scientia Meteorologica Sinica, 2007,27(b12):95-99.) [4] 段丽瑶,白玉荣,吴振铃.天津地区气象要素与花粉浓度的关系[J].城市环境与城市生态,2008,21(4):37-40.(DUAN L Y, BAI Y R, WU Z L. Relationship between pollen concentration and meteorological elements in Tianjin area[J]. Urban Environment & Urban Ecology, 2008, 21(4):37-40.) [5] 吴振玲,宛公展,白玉荣,等.天津气传花粉预测模型研究[J].气象科技,2007,35(6):832-838.(WU Z L, YUAN G Z, BAI Y R, et al. Study of airborne pollen prediction model[J]. Meteorological Science and Technology, 2007, 35(6):832-838.) [6] 张德山,海玉龙,冯涛,等.北京地区1~4天花粉浓度预报的应用研究[J].气象,2010,36(5):128-132.(ZHANG D S, HAI Y L, FENG T, et al. Applied research on the 1-4 day pollen concentration forecast in Beijing area[J]. Meteorological Monthly, 2010, 36(5):128-132.) [7] 张德山,徐景先,张姝丽,等.北京地区花粉通量演变曲线的预报模式初探[J].气象科学,2010,30(6):822-826.(ZHANG D S, XU J X, ZHANG Z L, et al. Preliminary study on predicting model of airborne pollen flux in Beijing[J]. Meteorological Science, 2010, 30(6):822-826.) [8] 张姝丽,张德山,何海娟.北京城市花粉数量天气条件分析法研究[J].气象科技,2003,31(6):406-408.(ZHANG Z L, ZHANG D S, HE H J. Study on the weather conditions of pollen concentration in Beijing city[J]. Meteorological Science and Technology, 2003, 31(6):406-408.) [9] 张姝丽,张德山,何海娟.北京城区8月日花粉总量和致敏花粉数量短期预报[J].气象科技,2006,34(6):724-727.(ZHANG Z L, ZHANG D S, HE H J. Daily total pollen and allergic pollen forecasting in August in Beijing[J]. Meteorological Science and Technology, 2006, 34(6):724-728.) [10] 李龙,马磊,贺建峰,等.基于特征向量的最小二乘支持向量机PM2.5浓度预测模型[J].计算机应用,2014,34(8):2212-2216.(LI L, MA L, HE J F, et al. PM2.5 concentration prediction model of least squares support vector machine based on feature vector[J]. Journal of Computer Applications, 2014,34(8):2212-2216.) [11] 刘杰,杨鹏,吕文生,等.模糊时序与支持向量机建模相结合的PM2.5质量浓度预测[J].北京科技大学学报,2014,36(12):1694-1703.(LIU J, YANG P, LYU W S, et al. Prediction model of PM2.5 mass concentrations based on fuzzy time series and support vector machine[J]. Journal of University of Science and Technology Beijing, 2014, 36(12):1694-1703.) [12] 岳鹏程,张林梁,马阅军.基于模糊时序和支持向量机的高速公路SO2浓度预测算法[J].计算机系统应用,2017,26(6):1-8.(YUE P C, ZHANG L L, MA Y J. Prediction for SO2 concentration based on the fuzzy time series and Support Vector Machine (SVM) on expressway[J]. Journal of Computer System Applications, 2017, 26(6):1-8.) [13] 陈柳,吴冬梅,陈俏.小波分析及支持向量机应用于大气污染预测[J].西安科技大学学报,2010,30(6):726-730.(CHEN L, WU D M, CHEN Q. Prediction of air pollution based on wavelet analysis and support vector machine[J]. Journal of Xi'an University of Science and Technology,2010, 30(6):726-730.) [14] 刘春波,王群芳,潘丰.基于蚁群优化算法的支持向量机参数选择及仿真[J].中南大学学报(自然科学版),2008,39(6):1309-1314.(LIU C B, WANG Q F, PAN F. Parameters selection and stimulation of support vector machines based on ant colony optimization algorithm[J]. Journal of Central South University (Science and Technology), 2008, 39(6):1309-1314.) [15] RAKOTOMAMONJY A, LE RICHE R, GUALANDRIS D, et al. A comparison of statistical learning approaches for engine torque estimation[J]. Control Engineering Practice, 2008, 16(1):43-45. [16] 陈然,孙冬野,秦大同,等.发动机支持向量机建模及精度影响因素[J].中南大学学报(自然科学版),2010,41(4):1391-1396.(CHEN R, SUN D Y, QIN D T, et al. A novel engine identification model based on support vector machine and analysis of precision-influencing factors[J]. Journal of Central South University (Science and Technology), 2010, 41(4):1391-1396.) [17] YOU Z Y, CHEN W R, HE G J. Adaptive weight particle swarm optimization algorithm with constriction factor[C]//Proceedings of the 2010 International Conference of Information Science and Management Engineering. Washington, DC:IEEE Computer Society, 2010:245-248.
2019, Vol. 39 
