导师介绍

李连发

    男,博士,中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室研究员。主要从事时空大数据挖掘及知识发现、深度学习及空间统计等研究,近3年主要创新性成果:1) 创建时空分异及地学知识引导的地理图网络过程建模方法,通过时空动态模拟,减少分异混杂,降低估计偏差,显著提高泛化性,是对传统纯数据驱动插值及时空建模方法重要突破;2) 提出全残差时空深度建模方法,结合空间分异性分析,该方法解决了深度回归网络学习不稳定性,在高分遥感数据插补及地表参数反演取得重要进展;3) 研建非线性时空混合效应模型及空间限制性知识优化,该系列方法可利用稀疏样本可实现研究区全覆盖趋势模拟。发表论文60余篇,第一或通讯作者SCI论文30余篇,其中包括遥感、环境及机器学习领域的国际专业顶刊(1区论文)发表论文8篇。出版专著4部,包括《深度学习原理及遥感地学分析》、《地理空间数据挖掘》及《空间分析》等。


主要招生领域:时空大数据建模、遥感地学分析、空间统计

   

代表性论文:  

1)       Lianfa Li, Ying Fang, Jinfeng Wang, Jun Wu, Ge Yong, 2020, Encoder-Decoder Full Residual Deep Networks for Robust Regression and Spatiotemporal Estimation, IEEE Transactions on Neural Network and Learning System, https://doi.org/10.1109/TNNLS.2020.3017200  

2)       Li, L., Franklin, M., Girguis, M., Lurmann, F., Wu, J., Pavlovic, N., Breton, C., Gilliland, F. & Habre, R., 2020, Spatiotemporal imputation of MAIAC AOD using deep learning with downscaling, Remote Sensing of Environment, 237, 111584.   

3)       Li, L., 2020, A robust deep learning approach for spatiotemporal estimation of satellite AOD and PM2.5, Remote Sensing, 12(2), 264.  

4)       Li, L., 2020, Optimal inversion of conversion parameters from satellite AOD to ground aerosol extinction coefficient using automatic differentiation, Remote Sensing, 12(3), 492.   

5)       Li, L., 2020, Deep residual autoencoder with multiscaling for semantic segmentation of land-use images, Remote Sensing, 2019, 11(18): 0-2142.   

6)       Li, L., 2019, Geographically weighted machine learning and downscaling for high-resolution spatiotemporal estimations of wind speed, Remote Sensing, 11(11), 1378.  

7)       Li, L., Girguis, M., Lurmann, F., Wu, J., Urman, R., Rappaport, E., Ritz, B., Franklin, M., Breton, C., Gilliland, F., Habre, R., 2019, Cluster-based bagging of constrained mixed-effects models for high spatiotemporal resolution nitrogen oxides prediction over large regions , Environment International, 2019, 128: 310-323.   

8)       Girguis, M., Li, L., Lurmann, F., 2019, Exposure measurement error in air pollution studies: A framework for assessing shared, multiplicative measurement error in ensemble learning estimates of nitrogen oxides, Environment International,125, 97-106.  

9)       方颖,李连发(通讯作者),2019,基于机器学习的高精度高分辨率气象因子时空估计,地球信息科学,21799-813  

10)    Li, L., Zhang, J., Meng, X., Fang, Y., Ge, Y., Wang, C., Wu, J., Kan, H., 2018, Estimation of PM2.5 concentrations at a high spatiotemporal resolution using constrained mixed-effect bagging models with MAIAC aerosol optical depth, Remote Sensing of Environment, 217.   

11)    Li, L., W. Qiu, C. Xu, J. Wang, 2018, A Spatiotemporal Mixed Models to Assessthe Influence of Environmental and Socioeconomic Factors on the Incidence of Hand, Foot and Mouth Disease, BMC Public Health, 18, 274.   

12)    Masri, S., L. Li, A. Dang, et al. 2018, Source characterization and exposure modeling of gas-phase polycyclic aromatic hydrocarbon (PAH) concentrations in Southern California, Atmos Environ, 177, 175-186.  

13)    Younan, D., Li, L., Tuvblad, C. et al., 2018, Long-term ambient temperature and externalizing behaviors in adolescents, American Journal of Epidemiology (2018) 187(9) 1931-1941. 

14)    Younan. D., Tuvblad, C., Franklin M.,  Lurmann, F., Li, L., et al., 2018, Longitudinal Analysis of Particulate Air Pollutants and Adolescent Delinquent Behavior in Southern California, Journal of Abnormal Child Psychology (2018) 46(6) 1283-1293   

15)    Li, L., Lurmann, F., Habre, R., Urman, R., Rappaport, E., Ritz, B., Chen, J., Gilliland, F., Wu, J., 2017, Constrained Mixed-Effect Models with Ensemble Learning for Prediction of Nitrogen Oxides Concentrations at High Spatiotemporal Resolution, Environmental Science and Technology, 51(17): 9920-9929.   

16)    Li, L., A. Wu, I. Cheng, et al., 2017, Spatiotemporal estimation of historical PM2.5 concentrations using PM10, meteorological variables, and spatial effect, Atmos Environ, 166, 182-191. 

17)    Li, L., J. Zhang & W. Qiu, et al. 2017, An ensemble spatiotemporal model for predicting PM2.5 concentrations, Int. J Environ Res Public Health, 14, 549.  

18)    Li, L., O. Laurent, & J. Wu, 2016, Spatial variability of the effect of air pollution on term birth weight: evaluating influential factors using Bayesian Hierarchical Models, Environ Health, 15: 14.  

19)    Laurent, O., Hu, J., Li, L., et al., 2016, A statewide nested case–Control study of preterm birth and air pollution by source and composition: California, 2001–2008, Environmental Health Perspectives, 124(9) 1479-1486  

20)    Younan, D., Tuvblad, C., Li, L. 2016, Environmental Determinants of Aggression in Adolescents: Role of Urban Neighborhood Greenspace, Journal of the American Academy of Child and Adolescent Psychiatry (2016) 55(7) 591-601.  

21)    Laurent, O., Hu, L., Li, L., 2016, Low birth weight and air pollution in California: Which sources and components drive the risk? Environment International (2016) 92-93 471-477.  

22)    Yang, X., Li, L., Wang, J., 2015, Cardiovascular mortality associated with low and high temperatures: determinants of inter-region vulnerability in China, Int J Environ Res Public Health. 2015, 12(6):5918-33.  

23)    Li, X., Xie, X., Li, L., Li, J., Zhao, H., Wang, H., Zhao, H., Wang, J., 2015, Using robust Bayesian network to estimate the residuals of fluoroquinolone antibiotic in soil. Environ Sci Pol Res. 22(22):17540-9.  

24)    杨勋凤、李连发、王劲峰、黄季夏 ,安徽省温度与心脑血管疾病死亡关系的广义叠加模型分析 ,地球信息科学学报,11 ,  pp 1388-1394, 2015/11 EI.  

25)    Laurent, O., Hu, J. & Li, L. et al., 2014, Sources and contents of air pollution affecting term low birth weight in Los Angeles County, California, 2001-2008, Environmental Research (2014) 134 488-495.   

26)    王劲峰, 葛咏, 李连发, 孟斌, 武继磊, 柏延臣, 杜世宏, 廖一兰, 胡茂桂, 徐成东. 2014. 地理学时空数据分析方法. 地理学报 69(9): 1326-1345.  

27)    Li, L., J. Wu, J.K. Ghosh & B. Ritz, 2013, Estimating spatiotemporal variability of ambient air pollutant concentrations with a hierarchical model, Atmos Environ, 71, 54-63.  

28)    Li, L., J. Wu, N. Hudda, C. Sioutas, S.A. Fruin & R.J. Delfino, 2013, Modelling the concentrations of on-road air pollutants in southern California, Environmental Science & Technology, 47(16), 9291-9299.  

29)    Laurent, O., Wu, J. & Li, L. et al, 2013, Green spaces and pregnancy outcomes in Southern California, Health and Place, 24, 190-195.  

30)    Laurent, O., Wu, J. & Li, L. et al, 2013, Investigating the association between birth weight and complementary air pollution metrics: a cohort study, Environmental Health: A Global Access Science Source, 12(1).  

31)    Haining, T. Liu, L. Li & C. Jiang, 2013, Design-based spatial sampling: theory and implementation, Environ modell Softw 40, 280-288.  

32)    王阳、李连发 ,空间贝叶斯分类器并行化,地理与地理信息科学, 29(4), pp 47-51, 2013/04/01 04.   

33)    Li, L., J. Wu, M. Wilhelm & B. Ritz, 2012, Use of generalized additive models and cokriging of spatial residuals to improve land-use regression estimates of nitrogen oxides in southern California, Atmospheric Environment, 55, 220-228.  

34)    Li, L., J. Wang, H. Leung & S. Zhao, 2012, A Bayesian method to mine spatial data sets to evaluate the vulnerability of human beings to catastrophic risk, Risk Analysis, 32(6), 1072-1092.  

35)    Li, L., Wang, J. & Wu, J., 2012, A spatial model to predict the incidence of neural tube defects, BMC Public Health (2012) 12(1).  

36)    Li, L. & Leung, H., 2011, Mining static code metrics for a robust prediction of software defect-proneness, International Symposium on Empirical Software Engineering and Measurement (2011) 207-214.   

37)    Li, L., J. Wang & H. Leung, 2010, An unsupervised similarity classifier to stratify samples to improve estimation precision, Int J of Remote Sensing, 30(5): 1207-1234.  

38)    Li, L., & H. Leung, 2011, Mining static code metrics for a robust prediction of software defect-proneness, ACM /IEEE 2011 International Symposium on Empirical Software Engineering and Measurement (http://dl.acm.org/citation.cfm?id=2083427).  

39)    Lianfa Li, Jinfeng Wang & Hareton Leung, 2010, Assessment of Catastrophic Risk Using Bayesian Network Constructed from Domain Knowledge and Spatial Data , Risk Analysis, 2010, 30(7):1157-75.   

40)    Lianfa Li, Jinfeng Wang & Hareton Leung, 2010, Using spatial analysis and Bayesian network to model the vulnerability and make insurance pricing of catastrophic risk, International Journal of Geographical Information Science, 24(12): 1759–1784.  

41)    Lianfa Li, Jinfeng Wang & Chengyi Wang, Typhoon insurance pricing with spatial decision-making support tools, International Journal of Geographical Information Science, 19(3): 363-384  

42)    Lianfa Li & Jinfeng Wang, 2006, A prototype auto-human support system for spatial analysis, Progress in Natural Science, 16(9): 954-966  

43)    Lianfa Li, Jinfeng Wang & Jiyuan Liu, 2005, Optimal decision-making model of spatial sampling for survey of China’s land with remotely sensed data, Science in China – Series D, 48(6): 752-764  

44)    Lianfa Li & Jinfeng Wang, 2004, Integrated spatial sampling modeling of geospatial data, Science in China – Series D, 47(3): 201-208  

45)    Jinfeng Wang, Lianfa Li & George Christakos, 2009, Sampling and Kriging Spatial Means: Efficiency and Conditions, Sensor, 9(7), 5224-5240  

46)    Jinfeng Wang & Lianfa Li, Improving tsunami warning systems with remote sensing and geographical information system input, 2008, Risk Analysis, 2008, 28(6): 1653-1668  

47)    Jinfeng Wang, Jiyuan Liu, Dafang Zhuang, Lianfa Li & Yong Ge, Spatial sampling design for monitoring the area of cultivated land, International Journal of Remote Sensing, 2002, 23(3): 263-284   

48)    Lianfa Li & Hareton Leung, 2009, Using the number of faults to improve fault-proneness prediction of the probability models, 2009, World Congress on Computer Science and Information Engineering, March 31 - April 2, Los Angeles/Anaheim, USA (IEEE Xplore收录)  

49)    Lianfa Li, Jinfeng Wang, Zhidong Cao, et al., 2006, An information-fusion method to regionalize spatial heterogeneity for improving the accuracy of spatial sampling estimation, 53rd Annual North American Meetings of the Regional Science Association International, Toronto, Canada  (会议论文)  

50)    Jinfeng Wang, Lianfa Li, Zhidong Cao, et al., 2006, A systematic analysis for an intelligent induced spatial sampling (IISS) 53rd Annual North American Meetings of the Regional Science Association International, Toronto, Canada  (会议论文 

51)    王劲峰、武继磊、孙英君、李连发、孟 斌,2005,空间信息分析技术, 地理研究,243: 464-472 (中文核心) 

52)    李连发、王劲峰、刘纪远,2004,国土遥感调查的空间抽样优化决策, 中国科学 D辑,3410):975~982(中文核心) 

53)    李连发、王劲峰,2002,地理数据空间抽样模型, 自然科学进展, 12(5), 545-548(中文核心) 

54)    王劲峰、李连发、葛咏等,2000,地理信息空间分析的理论体系探讨, 地理学报, 551: 92-105(中文核心) 

  利:  

1)       于图卷积的全残差深度网络的模型建立方法及应用, 202110021814.3,发明人:李连发等  

2)       基于非监督限制性优化的空气污染时空趋势预测方法, 202110080462.9,发明人:李连发等  

3)       一种基于深度双模态的气象参数精细尺度转化方法, 202110148282.X,发明人:李连发等 

4)       一种多源时空大数据深度融合的空气污染预测方法, 202110144010.2,发明人:李连发等  

5)       一种半监督深度图卷积的遥感土地利用语义分割方法, 202110174829.3,发明人:李连发等  

6)       一种基于无人机的地物高光谱仪遥感土地利用样本采集仪, 20205863395,发明人:李连发等  

7)       一种移动式空气质量样本自动采集仪, 202020461380.X,发明人:李连发等 

8)       一种基于大数据的时空混淆暴露度评估系统及方法   发明人:李连发等,已公示(公布号:CN107798425A 

9)       一种提高海量空间数据处理效率的方法 发明人:李连发等,2015授权(CN103235974B.  

10)    2009.2 一种基于栅格的空间异质模式识别方法及分层方法 200810116559.5),负责人:李连发    

11)    2008.10 一种精细尺度下的动态风险及易损性预测方法 200810222052.8),负责人:李连发  

  著:  

1)       李连发、王劲峰, 2014. 空间数据挖掘, 科学出版社(http://www.sciencep.com/m_single.php?id=34844) 

2)       王劲峰、姜成晟、李连发、胡茂桂著,2009,《空间抽样与统计推断》,科学出版社,20095月出版  

3)       王劲峰 等著,2006,《空间分析》,科学出版社,20069月出版,本人负责第一章、第九章、第二十八章及名词解释与索引的编写  

软件包:  

1)       李连发、王阳、赵斯思、王劲峰 ,空间统计及贝叶斯模型并行计算系统软件(计算机软件版权号:2014SR077131 ,中国, 2014/6/12   

2)       2008.1-现在:空间数据挖掘及决策支持工具包 (负责人) 

3)       2007.1-2008.10:三明治空间抽样及与统计推断软件包 0.9版本 (主要参与人员) 

4)       SIMPLE空间分析 系列软件包  已获软件著作权(2005SR05091)(第二著作权人)   

招生专业:地球信息科学、时空数据挖掘   

联系电话:010-64888362  

E-mail: lilf@lreis.ac.cnlilf@igsnrr.ac.cn 

更新日期:2022年5月31日