Nội dung được dịch bởi AI, chỉ mang tính chất tham khảo
Phương pháp học máy có thể giải thích để phân tích tác động của các yếu tố cảnh quan và khí tượng đến sự xuất hiện của muỗi ở Seoul, Hàn Quốc
Tóm tắt
Muỗi là nguyên nhân chính gây ra nhiều vấn đề về sức khỏe cộng đồng và kinh tế. Trong nghiên cứu này, các mẫu xuất hiện của muỗi đã được phân tích dựa trên các yếu tố cảnh quan và khí tượng ở thành phố đô thị Seoul. Chúng tôi đã đánh giá ảnh hưởng của các yếu tố môi trường đối với sự xuất hiện của muỗi thông qua việc giải thích các mô hình dự đoán bằng thuật toán học máy. Thông qua phân tích phân cụm theo cấp bậc, các khu vực nghiên cứu đã được phân loại thành khu vực bên bờ nước và khu vực không bên bờ nước, dựa trên các mẫu hình cảnh quan. Sự xuất hiện của muỗi cao hơn trong khu vực bên bờ nước, và độ phong phú của muỗi bị ảnh hưởng tiêu cực bởi lượng mưa tại khu vực này. Sự xuất hiện của muỗi đã được dự đoán trong mỗi khu vực cụm dựa trên các biến cảnh quan và khí tượng tích lũy, sử dụng thuật toán rừng ngẫu nhiên. Cả hai mô hình đều cho thấy hiệu suất tốt (cả độ chính xác và AUROC > 0.8) trong việc dự đoán mức độ xuất hiện của muỗi. Mối quan hệ ẩn chứa giữa sự xuất hiện của muỗi và các yếu tố môi trường trong các mô hình đã được giải thích bằng phương pháp giải thích cộng thêm Shapley. Theo mức độ quan trọng của biến và các biểu đồ phụ thuộc phần cho mỗi mô hình, khu vực bên bờ nước bị ảnh hưởng nhiều hơn bởi các biến khí tượng và độ che phủ đất so với khu vực không bên bờ nước. Do đó, các chiến lược kiểm soát muỗi nên xem xét các tác động của điều kiện cảnh quan và khí tượng, bao gồm nhiệt độ, lượng mưa và tính không đồng nhất của cảnh quan. Những phát hiện hiện tại có thể đóng góp vào việc phát triển các hệ thống dự đoán muỗi tại các thành phố đô thị nhằm nâng cao sức khỏe cộng đồng.
Từ khóa
#muỗi #sức khỏe cộng đồng #học máy #dự đoán sự xuất hiện #cảnh quan #khí tượng #Seoul #Hàn QuốcTài liệu tham khảo
Abdollahi A, Pradhan B (2021) Urban vegetation mapping from aerial imagery using Explainable AI (XAI). Sensors 21:4738
Arrieta AB, Díaz-Rodríguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, García S, Gil-López S, Molina D, Benjamins R (2020) Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion 58:82–115
Asigau S, Parker PG (2018) The influence of ecological factors on mosquito abundance and occurrence in Galápagos. J Vector Ecol 43:125–137
Beck-Johnson LM, Nelson WA, Paaijmans KP, Read AF, Thomas MB, Bjørnstad ON (2017) The importance of temperature fluctuations in understanding mosquito population dynamics and malaria risk. Soc Open Sci 4:160969
Benedum CM, Seidahmed OM, Eltahir EA, Markuzon N (2018) Statistical modeling of the effect of rainfall flushing on dengue transmission in Singapore. PLoS Negl Trop Dis 12:e0006935
Cha Y, Shin J, Go B, Lee D-S, Kim Y, Kim T, Park Y-S (2021) An interpretable machine learning method for supporting ecosystem management: Application to species distribution models of freshwater macroinvertebrates. J Environ Manage 291:112719
Chae SM, Kim DJ, Yoon SJ, Shin HS (2014) The impact of temperature rise and regional factors on malaria risk. Health Soc Welfare Rev 34(1):436–455
Chaves LF, Hamer GL, Walker ED, Brown WM, Ruiz MO, Kitron UD (2011) Climatic variability and landscape heterogeneity impact urban mosquito diversity and vector abundance and infection. Ecosphere 2:art70
Chuang T-W, Hildreth MB, Vanroekel DL, Wimberly MC (2011) Weather and land cover influences on mosquito populations in Sioux Falls, South Dakota. J Med Entomol 48:669–679
Cleckner HL, Allen TR, Bellows AS (2011) Remote sensing and modeling of mosquito abundance and habitats in coastal Virginia, USA. Remote Sens 3:2663–2681
Colón-González FJ, Soares Bastos L, Hofmann B, Hopkin A, Harpham Q, Crocker T, Amato R, Ferrario I, Moschini F, James S (2021) Probabilistic seasonal dengue forecasting in Vietnam: a modelling study using superensembles. PLoS Med 18:e1003542
Cuéllar AC, Kjær LJ, Baum A, Stockmarr A, Skovgard H, Nielsen SA, Andersson MG, Lindström A, Chirico J, Lühken R (2020) Modelling the monthly abundance of Culicoides biting midges in nine European countries using Random Forests machine learning. Parasit Vectors 13:1–18
Cutler DR, Edwards TC Jr, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88:2783–2792
Das A, Rad P (2020) Opportunities and challenges in explainable artificial intelligence (xai): A survey. arXiv preprint arXiv:2006.11371
Dinno A (2017) dunn.test: Dunnʼs test of multiple comparisons using rank sums. R package version 1.3.5. https://CRAN.R-project.org/package=dunn.test. Accessed 21 July 2021
Dosland O, Subramanyam B, Sheppard K, Mahroof R (2006) Temperature modification for insect control. In: JW Heaps (ed), Insect Management for Food Storage and Processing. AACC International, St. Paul, pp 89–103
Epstein PR (2002) Climate change and infectious disease: Stormy weather ahead? Epidemiology 13:373–375
Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann Stat 29(1189–1232):44
Früh L, Kampen H, Kerkow A, Schaub GA, Walther D, Wieland R (2018) Modelling the potential distribution of an invasive mosquito species: Comparative evaluation of four machine learning methods and their combinations. Ecol Model 388:136–144
Gong H, DeGaetano AT, Harrington LC (2011) Climate-based models for West Nile Culex mosquito vectors in the Northeastern US. Int J Biometeorol 55:435–446
Grandini M, Bagli E, Visani G (2020) Metrics for multi-class classification: an overview. arXiv preprint arXiv:2008.05756
Greenwell BM, Boehmke BC, McCarthy AJ (2018) A simple and effective model-based variable importance measure. ArXiv abs/1805.04755
Greiner M, Pfeiffer D, Smith R (2000) Principles and practical application of the receiver-operating characteristic analysis for diagnostic tests. Prev Vet Med 45(1–2):23–41
Gubler DJ, Reiter P, Ebi KL, Yap W, Nasci R, Patz JA (2001) Climate variability and change in the United States: Potential impacts on vector-and rodent-borne diseases. Environ Health Perspect 109(Suppl 2):223–233
Hales S, De Wet N, Maindonald J, Woodward A (2002) Potential effect of population and climate changes on global distribution of dengue fever: An empirical model. The Lancet 360:830–834
Hand DJ, Till RJ (2001) A simple generalisation of the area under the ROC curve for multiple class classification problems. Mach Learn 45:171–186
Hay SI, Cox J, Rogers DJ, Randolph SE, Stern DI, Shanks GD, Myers MF, Snow RW (2002) Climate change and the resurgence of malaria in the East African highlands. Nature 415:905–909
Higley LG, Haskell NH (2001) Insect development and forensic entomology. In: Byrd JH, Castner JL (Eds) Forensic Entomology: The Utility of Arthropods in Legal Investigations. CRC Press, New York, USA, pp 287–302
Hunter MD, Price PW (1998) Cycles in insect populations: Delayed density dependence or exogenous driving variables? Ecol Entomol 23:216–222
Jeong YS, Lee DK (2003) Prevalence and seasonal abundance of the dominant mosquito species in a large marsh near coast of Ulsan. Korean J Appl Entomol 42(2):125–132
Joshi A, Miller C (2021): Review of machine learning techniques for mosquito control in urban environments. Ecol Inform, 101241
Kearney M, Porter WP, Williams C, Ritchie S, Hoffmann AA (2009) Integrating biophysical models and evolutionary theory to predict climatic impacts on speciesʼ ranges: the dengue mosquito Aedes aegypti in Australia. Funct Ecol 23:528–538
Kim JH, Park SY (2013) The impact of land use structure and vector habitat conditions on the incidence of malaria : A case study in high-incidence areas. J Korean Assoc Geogr Inform Stud 16(3):12–24
Kindhauser MK, Allen T, Frank V, Santhana RS, Dye C (2016) Zika: the origin and spread of a mosquito-borne virus. Bull World Health Organ 94(9):675-686C
Korea Centers for Disease Control and Prevention (2019) Infectious Diseases Surveillance Yearbook 2019. Korea Centers for Disease Control and Prevention, Cheongju
Kottek M, Grieser J, Beck C, Rudolf B, Rubel F (2006) World map of the Köppen-Geiger climate classification updated. Meteorologische Zeitschrift 15(3):259–263
Kwon YS, Bae MJ, Chung N, Lee YR, Hwang S, Kim SA, Choi YJ, Park YS (2015) Modeling occurrence of urban mosquitos based on land use types and meteorological factors in Korea. Int J Environ Res Public Health 12:13131–13147
Laureano-Rosario AE, Duncan AP, Mendez-Lazaro PA, Garcia-Rejon JE, Gomez-Carro S, Farfan-Ale J, Savic DA, Muller-Karger FE (2018) Application of artificial neural networks for dengue fever outbreak predictions in the northwest coast of Yucatan, Mexico and San Juan, Puerto Rico. Trop Med Infect Dis 3:5
Lebl K, Brugger K, Rubel F (2013) Predicting Culex pipiens/restuans population dynamics by interval lagged weather data. Parasit Vectors 6:129
Lee CM, Lee D-S, Kwon T-S, Athar M, Park Y-S (2021a) Predicting the global distribution of Solenopsis geminata (Hymenoptera: Formicidae) under climate change using the MaxEnt model. Insects 12:229
Lee D-S, Bae Y-S, Byun B-K, Lee S, Park JK, Park Y-S (2019) Occurrence prediction of the citrus flatid planthopper (Metcalfa pruinosa (Say, 1830)) in South Korea using a random forest model. Forest 10:585
Lee D-S, Choi WI, Nam Y, Park Y-S (2021b) Predicting potential occurrence of pine wilt disease based on environmental factors in South Korea using machine learning algorithms. Eco Inform 64:101378
Lee J-W, Lee S-W, Hwang S-J, Jang M-H, Won D-H, An K-J, Park H-J, Lee J (2020) Establishing diagnosis systems for impaired stream ecosystem using stream/river ecosystem survey and health Assessment. Korean J Ecol Environ 53:1–10
Lee JS, Hong HK (1995) Seasonal prevalence and behaviour of Aedes togoi. Korean J Parasitol 33:19–26
Lee KY, Chung N, Hwang S (2016) Application of an artificial neural network (ANN) model for predicting mosquito abundances in urban areas. Eco Inform 36:172–180
Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2:18–22
Linardatos P, Papastefanopoulos V, Kotsiantis S (2021) Explainable AI: A review of machine learning interpretability methods. Entropy 23:18
Lindblade KA, Walker ED, Onapa AW, Katungu J, Wilson ML (2000) Land use change alters malaria transmission parameters by modifying temperature in a highland area of Uganda. Trop Med Int Health 5:263–274
Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions, Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, pp 4768–4777
Maguire M, Skelly C, Weinstein P, Moloney J (1999) Simulation modelling of Aedes aegypti prevalence, an environmental hazard surveillance tool for the control of dengue epidemics. Int J Environ Health Res 9:253–259
Maksymiuk S, Gosiewska A, Biecek P (2020) shapper: Wrapper of Python Library ‘shapʼ R package version 0.1.3.
Molnar C (2022) Interpretable Machine Learning: A Guide for Making Black Box Models Explainable (2nd edn). https://christophm.github.io/interpretable-ml-book/
Montagner FRG, Silva OSd, Jahnke SM (2017) Mosquito species occurrence in association with landscape composition in green urban areas. Braz J Biol 78:233–239
Oksanen J, Blanchet FG, Friendly M, Kindt R, Legendre P, McGlinn D, Minchin PR, O’Hara RB, Simpson GL, Solymos P, Stevens MHH, Szoecs E, Wagner H (2020) vegan: Community Ecology Package. (R package version 2.5–7.)
Olden JD, Lawler JJ, Poff NL (2008) Machine learning methods without tears: A primer for ecologists. Q Rev Biol 83:171–193
Park JS, Im YM (2018) Metropolitan Meteorological Administration predicts occurrence of mosquitoes like weather. Kor Dias Prev Assoc J 20(4):17–23
Park Y-S, Kwon TS, Park JK, Kim C, Kim JD (2003) Effect of temperatures on the development of the stick insect, Baculum elongatus (Phasmida: Phasmidae) and the life cycle. J Korean For Soc 92(1):62–70
QGIS.org (2021) QGIS Geographic Information System. QGIS Association. http://www.qgis.org. Accessed 21 Jan 2022
R Core Team (2021) R: A Language and environment for statistical computing. Foundation for Statistical Computing, Vienna, Austria
Ray P, Manach YL, Riou B, Houle TT, Warner DS (2010) Statistical evaluation of a biomarker. J Am Soc Anesthesiologists 112:1023–1040
Razavi S, Jakeman A, Saltelli A, Prieur C, Iooss B, Borgonovo E, Plischke E, Lo Piano S, Iwanaga T, Becker W, Tarantola S, Guillaume JHA, Jakeman J, Gupta H, Melillo N, Rabitti G, Chabridon V, Duan Q, Sun X, Smith S, Sheikholeslami R, Hosseini N, Asadzadeh M, Puy A, Kucherenko K, Maier HR (2021) The future of sensitivity analysis: an essential discipline for systems modeling and policy support. Environ Model Softw 137:104954
Reiter P (2001) Climate change and mosquito-borne disease. Environ Health Perspect 109:141–161
Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez J-C, Müller M (2011) pROC: an open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinformatics 12:1–8
Ruiz MO, Chaves LF, Hamer GL, Sun T, Brown WM, Walker ED, Haramis L, Goldberg TL, Kitron UD (2010) Local impact of temperature and precipitation on West Nile virus infection in Culex species mosquitoes in northeast Illinois, USA. Parasit Vectors 3:19–19
Shin HS (2011) Malaria prevalence rate and weather factors in Korea. Health Soc Welfare Rev 31(1):217–237
Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manage 45:427–437
Sutherst RW (2004) Global change and human vulnerability to vector-borne diseases. Clin Microbiol Rev 17:136–173
Valdez LD, Sibona GJ, Diaz LA, Contigiani M, Condat C (2017) Effects of rainfall on Culex mosquito population dynamics. J Theor Biol 421:28–38
Vandyk JK, Rowley WA (1995) Response of Iowa mosquito populations to unusual precipitation patterns as measured by New Jersey light trap collections. J Am Mosq Control Assoc 11:200–205
Verdonschot PFM, Besse-Lototskaya AA (2014) Flight distance of mosquitoes (Culicidae): A metadata analysis to support the management of barrier zones around rewetted and newly constructed wetlands. Limnologica 45:69–79
Webb C, Doggett S, Russell R (2016) A Guide to Mosquitoes of Australia. CSIRO Publishing, Clayton
Wieland R, Kerkow A, Früh L, Kampen H, Walther D (2017) Automated feature selection for a machine learning approach toward modeling a mosquito distribution. Ecol Model 352:108–112
Wieland R, Kuhls K, Lentz HH, Conraths F, Kampen H, Werner D (2021) Combined climate and regional mosquito habitat model based on machine learning. Ecol Model 452:109594
Wilke ABB, Medeiros-Sousa AR, Ceretti-Junior W, Marrelli MT (2017) Mosquito populations dynamics associated with climate variations. Acta Trop 166:343–350
World Health Organization (2018) Mosquito-Borne Diseases. Available online: http://www.who.int/neglected_diseases/vector_ecology/mosquito-borne-diseases/en/. Accessed 21 July 2021
Yang G-J, Brook BW, Whelan PI, Cleland S, Bradshaw CJA (2008) Endogenous and exogenous factors controlling temporal abundance patterns of tropical mosquitoes. Ecol Appl 18:2028–2040
Yi H, Devkota BR, Yu J-s, Oh K-C, Kim J, Kim H-J (2014) Effects of global warming on mosquitoes & mosquito-borne diseases and the new strategies for mosquito control. Entomol Res 44:215–235