地理空间大数据与人工智能在城市登革热驱动因素识别与风险预测中的应用

doi:10.11853/j.issn.1003.8280.2022.03.001

摘要/Abstract

摘要： 登革热是蚊媒病毒性传染病，广泛分布于全球热带、亚热带、甚至暖温带的城市化和半城市化区域，对全球100多个国家造成人群健康威胁。全球气候变化、城镇化和人口增长为登革病毒的扩散创造了有利条件。目前，由于缺乏可广泛接种的疫苗，媒介伊蚊控制是预防控制登革热的主要措施，而准确、及时的登革热风险预测可为登革热精准防控和决策制定提供重要依据。近年来，地理空间大数据的发展促进不同时空尺度下登革热驱动因素的识别。人工智能算法的进步，尤其是多种深度学习网络的出现，为登革热的风险预测提供了新技术。该文综合考虑登革热多种类型的驱动因素及其作用机制、地理空间大数据与人工智能技术，阐述如何应用地理空间大数据识别登革热的城市土地利用、气候环境和人口流动3方面的驱动因素，阐述人工智能算法在登革热传播风险预测中的应用现状。并基于现状提出未来研究应该加强在不同时空尺度上构建时空一体的风险预测模型，提议从预测值与真实值的差异、疫情时空聚集格局和防疫实际需求等方面评估模型性能。

关键词: 登革热, 驱动因素, 风险预测, 地理空间大数据, 人工智能

Abstract: Dengue fever is a mosquito-borne viral infectious disease that is widely distributed in urban or peri-urban areas in the tropical, subtropical, and warm temperate zones worldwide and threatens the health of populations in more than 100 countries and regions. Global climate change, urbanization, and urban population growth have created favorable conditions for the spread of dengue fever virus. At present, due to a lack of vaccines applicable for mass vaccination, Aedes vector control is the main measure for the prevention and control of dengue fever, and accurate and timely risk prediction for dengue fever can provide an important basis for precise prevention and control, and decision-making. In recent years, the development of geospatial big data promotes the identification of the driving factors for dengue fever at different spatial and temporal scales, and the advances in artificial intelligence, especially the emergence of various deep learning networks, provide new techniques for the risk prediction of dengue fever. Through a comprehensive analysis of the various types of driving factors for dengue fever and their mechanism of action, geospatial big data, and artificial intelligence techniques, this article elaborates on the application of geospatial big data in identifying the driving factors for dengue fever from the aspects of urban land use, climate and environment conditions, and population movement, as well as the current status of the application of artificial intelligence algorithms in predicting the risk of dengue fever transmission. Based on the current research status of geospatial big data and artificial intelligence, it is proposed that future research should develop spatiotemporal risk predictive models at different spatial and temporal scales and the performance of such models should be evaluated in terms of the difference between predicted and true values, the spatiotemporal aggregation patterns of dengue fever, and the actual needs of dengue fever prevention and control.

Key words: Dengue fever, Driving factor, Risk prediction, Geospatial big data, Artificial intelligence

中图分类号:

R373.3⁺3

李之超, 董金玮, 刘起勇. 地理空间大数据与人工智能在城市登革热驱动因素识别与风险预测中的应用[J]. 中国媒介生物学及控制杂志, 2022, 33(3): 321-325.

LI Zhi-chao, DONG Jin-wei, LIU Qi-yong. Application of geospatial big data and artificial intelligence in driving factor identification and risk prediction for urban dengue fever[J]. Chinese Journal of Vector Biology and Control, 2022, 33(3): 321-325.

参考文献

[1] Bhatt S, Gething PW, Brady OJ, et al. The global distribution and burden of dengue[J]. Nature, 2013, 496(7446):504-507. DOI:10.1038/nature12060.
[2] 赵春春, 周欣欣, 李文玉, 等. 2020年中国13省份登革热媒介白纹伊蚊抗药性监测及分析研究[J]. 中国媒介生物学及控制杂志, 2022, 3(1):30-37. DOI:10.11853/j.issn.1003.8280. 2022.01.006. Zhao CC, Zhou XX, Li WY, et al. Insecticide resistance surveillance and characteristic analysis of dengue vector Aedes albopictus in 13 provinces of China in 2020[J]. J Vector Biol Control, 2022, 3(1):30-37.DOI:10.11853/j.issn.1003.8280. 2022.01.006.(in Chinese)
[3] Ryan SJ, Carlson CJ, Mordecai EA, et al. Global expansion and redistribution of Aedes-borne virus transmission risk with climate change[J]. PLoS Negl Trop Dis, 2019, 13(3):e0007213. DOI:10.1371/journal.pntd.0007213.
[4] Brady OJ, Hay SI. The global expansion of dengue:How Aedes aegypti mosquitoes enabled the first pandemic arbovirus[J]. Ann Rev Entomol, 2020, 65:191-208. DOI:10.1146/annurev-ento-011019-024918.
[5] 刘起勇. 我国登革热流行新趋势、防控挑战及策略分析[J]. 中国媒介生物学及控制杂志, 2020, 31(1):1-6. DOI:10.11853/j.issn.1003.8280.2020.01.001. Liu QY. Dengue fever in China:New epidemical trend, challenges and strategies for prevention and control[J]. J Vector Biol Control, 2020, 31(1):1-6. DOI:10.11853/j.issn.1003. 8280.2020.01.001.(in Chinese)
[6] Louis VR, Phalkey R, Horstick O, et al. Modeling tools for dengue risk mapping:A systematic review[J]. Int J Health Geogr, 2014, 13:50. DOI:10.1186/1476-072X-13-50.
[7] Sylvestre E, Joachim C, Cécilia-Joseph E, et al. Data-driven methods for dengue prediction and surveillance using real-world and Big Data:A systematic review[J]. PLoS Negl Trop Dis, 2022, 16(1):e0010056. DOI:10.1371/journal.pntd.0010056.
[8] Mussumeci E, Coelho FC. Large-scale multivariate forecasting models for dengue-LSTM versus random forest regression[J]. Spat Spatio:Temporal Epidemiol, 2020, 35:100372. DOI:10. 1016/j.sste.2020.100372.
[9] Campbell LP, Luther C, Moo-Llanes D, et al. Climate change influences on global distributions of dengue and chikungunya virus vectors[J]. Philos Trans R Soc Lond B Biol Sci, 2015, 370(1665):20140135. DOI:10.1098/rstb.2014.0135.
[10] Franklinos LHV, Jones KE, Redding DW, et al. The effect of global change on mosquito-borne disease[J]. Lancet Infect Dis, 2019, 19(9):e302-e312. DOI:10.1016/S1473-3099(19)30161-6.
[11] Marti R, Li ZC, Catry T, et al. A mapping review on urban landscape factors of dengue retrieved from earth observation data, GIS techniques, and survey questionnaires[J]. Remote Sens, 2020, 12(6):932. DOI:10.3390/rs12060932.
[12] Polwiang S. The time series seasonal patterns of dengue fever and associated weather variables in Bangkok (2003-2017)[J]. BMC Infect Dis, 2020, 20:208. DOI:10.1186/s12879-020-4902-6.
[13] Jain R, Sontisirikit S, Iamsirithaworn S, et al. Prediction of dengue outbreaks based on disease surveillance, meteorological and socio-economic data[J]. BMC Infect Dis, 2019, 19(1):272. DOI:10.1186/s12879-019-3874-x.
[14] Wesolowski A, Qureshi T, Boni MF, et al. Impact of human mobility on the emergence of dengue epidemics in Pakistan[J]. Proc Natl Acad Sci USA, 2015, 112(38):11887-11892. DOI:10.1073/pnas.1504964112.
[15] Bomfim R, Pei S, Shaman J, et al. Predicting dengue outbreaks at neighbourhood level using human mobility in urban areas[J]. J R Soc Interface, 2020, 17(171):20200691. DOI:10.1098/rsif. 2020.0691.
[16] Li QX, Cao W, Ren HY, et al. Spatiotemporal responses of dengue fever transmission to the road network in an urban area[J]. Acta Trop, 2018, 183:8-13. DOI:10.1016/j.actatropica. 2018.03.026.
[17] Pan SJ, Yang Q. A survey on transfer learning[J]. IEEE Trans Knowl Data Eng, 2010, 22(10):1345-1359. DOI:10.1109/TKDE.2009.191.
[18] Ren PZ, Xiao Y, Chang XJ, et al. A survey of deep active learning[J]. ACM Comput Surv, 2022, 54(9):1-40. DOI:10.1145/3472291.
[19] 曹元晖, 刘纪平, 王勇, 等. 基于POI数据的城市建筑功能分类方法研究[J]. 地球信息科学学报, 2020, 22(6):1339-1348. DOI:10.12082/dqxxkx.2020.190608. Cao YH, Liu JP, Wang Y, et al. A study on the method for functional classification of urban buildings by using POI data[J]. J Geo-Inf Sci, 2020, 22(6):1339-1348. DOI:10.12082/dqxxkx. 2020.190608.(in Chinese)
[20] Lin AQ, Sun XM, Wu H, et al. Identifying urban building function by integrating remote sensing imagery and POI data[J]. IEEE J Sel Top Appl Earth Obs Remote Sens, 2021, 14:8864-8875. DOI:10.1109/JSTARS.2021.3107543.
[21] Li ZC, Gurgel H, Xu L, et al. Improving dengue forecasts by using geospatial big data analysis in google earth engine and the historical dengue information-aided long short term memory modeling[J]. Biology (Basel), 2022, 11(2):169. DOI:10.3390/biology11020169.
[22] Chabot-Couture G, Nigmatulina K, Eckhoff P. An environmental data set for vector-borne disease modeling and epidemiology[J]. PLoS One, 2014, 9(4):e94741. DOI:10.1371/journal.pone. 0094741.
[23] Siraj AS, Rodriguez-Barraquer I, Barker CM, et al. Spatiotemporal incidence of Zika and associated environmental drivers for the 2015-2016 epidemic in Colombia[J]. Sci Data, 2018, 5(1):180073. DOI:10.1038/sdata.2018.73.
[24] Tamiminia H, Salehi B, Mahdianpari M, et al. Google earth engine for geo-big data applications:A meta-analysis and systematic review[J]. ISPRS J Photog Remote Sens, 2020, 164:152-170. DOI:10.1016/j.isprsjprs.2020.04.001.
[25] 付东杰, 肖寒, 苏奋振, 等. 遥感云计算平台发展及地球科学应用[J]. 遥感学报, 2021, 25(1):220-230. DOI:10.11834/jrs.20210447. Fu DJ, Xiao H, Su FZ, et al. Remote sensing cloud computing platform development and Earth science application[J]. Nat Remote Sens Bull, 2021, 25(1):220-230. DOI:10.11834/jrs. 20210447.(in Chinese)
[26] Frake AN, Peter BG, Walker ED, et al. Leveraging big data for public health:Mapping malaria vector suitability in Malawi with Google Earth Engine[J]. PLoS One, 2020, 15(8):e0235697. DOI:10.1371/journal.pone.0235697.
[27] Ramadona AL, Tozan Y, Lazuardi L, et al. A combination of incidence data and mobility proxies from social media predicts the intra-urban spread of dengue in Yogyakarta, Indonesia[J]. PLoS Negl Trop Dis, 2019, 13(4):e0007298. DOI:10.1371/journal.pntd.0007298.
[28] Zhang Y, Riera J, Ostrow K, et al. Modeling the relative role of human mobility, land-use and climate factors on dengue outbreak emergence in Sri Lanka[J]. BMC Infect Dis, 2020, 20(1):649. DOI:10.1186/s12879-020-05369-w.
[29] Appice A, Gel YR, Iliev I, et al. A Multi-stage machine learning approach to predict dengue incidence:A case study in Mexico[J]. IEEE Access, 2020, 8:52713-52725. DOI:10.1109/ACCESS.2020.2980634.
[30] Xu JC, Xu KQ, Li ZC, et al. Forecast of dengue cases in 20 Chinese cities based on the deep learning method[J]. Int J Environ Res Public Health, 2020, 17(2):453. DOI:10.3390/ijerph17020453.
[31] Zhao NZ, Charland K, Carabali M, et al. Machine learning and dengue forecasting:Comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia[J]. PLoS Negl Trop Dis, 2020, 14(9):e0008056. DOI:10.1371/journal.pntd.0008056.
[32] Amin S, Uddin MI, Hassan S, et al. Recurrent neural networks with TF-IDF embedding technique for detection and classification in tweets of dengue disease[J]. IEEE Access, 2020, 8:131522-131533. DOI:10.1109/ACCESS.2020.3009058.
[33] Amin S, Uddin MI, Zeb MA, et al. Detecting dengue/Flu infections based on tweets using LSTM and word embedding[J]. IEEE Access, 2020, 8:189054-189068. DOI:10.1109/ACCESS. 2020.3031174.
[34] Hoyos W, Aguilar J, Toro M. Dengue models based on machine learning techniques:A systematic literature review[J]. Artif Intellig Med, 2021, 119:102157. DOI:10.1016/j.artmed.2021. 102157.
[35] Rehman NA, Saif U, Chunara R. Deep landscape features for improving vector-borne disease prediction[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Long Beach:IEEE, 2019:44-51.
[36] Liu K, Zhang M, Xi GK, et al. Enhancing fine-grained intra-urban dengue forecasting by integrating spatial interactions of human movements between urban regions[J]. PLoS Negl Trop Dis, 2020, 14(12):e0008924. DOI:10.1371/JOURNAL.PNTD.0008924.