請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58172完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張斐章(Fi-John Chang) | |
| dc.contributor.author | Pu-Yun Kow | en |
| dc.contributor.author | 邱普運 | zh_TW |
| dc.date.accessioned | 2021-06-16T08:07:27Z | - |
| dc.date.available | 2020-08-21 | |
| dc.date.copyright | 2020-08-21 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-07-16 | |
| dc.identifier.citation | Ausati, S., Amanollahi, J. (2016). Assessing the accuracy of ANFIS, EEMD-GRNN, PCR, and MLR models in predicting PM2. 5. Atmospheric environment, 142, 465-474. https://doi.org/10.1016/j.atmosenv.2016.08.007 Bai, Y., Zeng, B., Li, C., Zhang, J. (2019). An ensemble long short-term memory neural network for hourly PM2. 5 concentration forecasting. Chemosphere, 222, 286-294. https://doi.org/10.1016/j.chemosphere.2019.01.121 Borovykh, A., Bohte, S., Oosterlee, C. W. (2017). Conditional time series forecasting with convolutional neural networks. arXiv preprint arXiv:1703.04691. Chan, C. C., Chuang, K. J., Chien, L. C., Chen, W. J., Chang, W. T. (2006). Urban air pollution and emergency admissions for cerebrovascular diseases in Taipei, Taiwan. European heart journal, 27(10), 1238-1244. https://doi.org/10.1093/eurheartj/ehi835 Chang, F. J., Chen, P. A., Lu, Y. R., Huang, E., Chang, K. Y. (2014). Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control. Journal of Hydrology, 517, 836-846. https://doi.org/10.1016/j.jhydrol.2014.06.013 Chang, F. J., Chang, L. C., Kang, C. C., Wang, Y. S., Huang, A. (2020). Explore spatio-temporal PM2. 5 features in northern Taiwan using machine learning techniques. Science of The Total Environment, 139656. https://doi.org/10.1016/j.scitotenv.2020.139656 Chang, F.J., Kao, L.S., Kuo, Y.M., Liu, C.W., 2010, “Artificial Neural Networks for Estimating Regional Arsenic Concentrations in a Blackfoot Disease Area in Taiwan”, Journal of Hydrology, 388: 65-76. https://doi.org/10.1016/j.jhydrol.2010.04.029 Chen, X., Kopsaftopoulos, F., Wu, Q., Ren, H., Chang, F. K. (2019). A Self-Adaptive 1D Convolutional Neural Network for Flight-State Identification. Sensors, 19(2), 275. https://doi.org/10.3390/s19020275 Cheng, Y., Zhang, H., Liu, Z., Chen, L., Wang, P. (2019). Hybrid algorithm for short-term forecasting of PM2. 5 in China. Atmospheric environment, 200, 264-279. https://doi.org/10.1016/j.atmosenv.2018.12.025 Djalalova, I., Delle Monache, L., Wilczak, J. (2015). PM2. 5 analog forecast and Kalman filter post-processing for the Community Multiscale Air Quality (CMAQ) model. . Atmospheric Environment, 108, 76-87. https://doi.org/10.1016/j.atmosenv.2015.02.021 Du, S., Li, T., Yang, Y., Horng, S. J. (2018). Deep Air Quality Forecasting Using Hybrid Deep Learning Framework. arXiv preprint arXiv:1812.04783. Du, X., Kong, Q., Ge, W., Zhang, S., Fu, L. (2010). Characterization of personal exposure concentration of fine particles for adults and children exposed to high ambient concentrations in Beijing, China. Journal of Environmental Sciences, 22(11), 1757-1764. https://doi.org/10.1016/S1001-0742(09)60316-8 Elbayoumi, M., Ramli, N. A., Yusof, N. F. (2015). Development and comparison of regression models and feedforward backpropagation neural network models to predict seasonal indoor PM2. 5-10 and PM2. 5 concentrations in naturally ventilated schools. Atmospheric Pollution Research, 6(6), 1013-1023. https://doi.org/10.1016/j.apr.2015.09.001 EPA. (2019) Open dataset platform. Available at: https://taqm.epa.gov.tw/taqm/en/b0101.aspx EPA. (2019) PM_2.5 indicator and activity recommendation table. Available at: https://www.hpa.gov.tw/Pages/ashx/File.ashx?FilePath=~/File/Attach/3007/File_3697.pdf) EPM. (2015) EPA-Environmental Policy Monthly. Available at: https://www.epa.gov.tw/DisplayFile.aspx?FileID=9BBCE15769A6EF24 P=8905d3c6-79af-49fd-b608-6ec92bcdf740 Feng, R., Zheng, H. J., Gao, H., Zhang, A. R., Huang, C., Zhang, J. X., Fan, J. R. (2019). Recurrent Neural Network and random forest for analysis and accurate forecast of atmospheric pollutants: A case study in Hangzhou, China. Journal of Cleaner Production. https://doi.org/10.1016/j.jclepro.2019.05.319 Feng, R. Zheng, H., Zhang, A., Huang, C., Gao, H., Ma, Y. (2019). Unveiling tropospheric ozone by the traditional atmospheric model and machine learning, and their comparison: A case study in hangzhou, China. Environmental Pollution, 252, Part A, 366-378. Feng, X., Li, Q., Zhu, Y., Hou, J., Jin, L., Wang, J. (2015). Artificial neural networks forecasting of PM2. 5 pollution using air mass trajectory based geographic model and wavelet transformation. Atmospheric Environment, 107, 118-128. https://doi.org/10.1016/j.atmosenv.2015.02.030 Fernando, H. J., Mammarella, M. C., Grandoni, G., Fedele, P., Di Marco, R., Dimitrova, R., Hyde, P. (2012). Forecasting PM10 in metropolitan areas: Efficacy of neural networks. Environmental pollution, 163, 62-67. https://doi.org/10.1016/j.envpol.2011.12.018 Gao, M., Yin, L., Ning, J. (2018). Artificial neural network model for ozone concentration estimation and Monte Carlo analysis. Atmospheric Environment, 184, 129-139. https://doi.org/10.1016/j.atmosenv.2018.03.027 Glorot, X., Bordes, A., Bengio, Y. (2011, June). Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics(pp. 315-323). Hao, Y., Liu, Y. M. (2016). The influential factors of urban PM2. 5 concentrations in China: a spatial econometric analysis. Journal of cleaner production, 112, 1443-1453. https://doi.org/10.1016/j.jclepro.2015.05.005 Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network. In Neural networks for perception (pp. 65-93). https://doi.org/10.1109/IJCNN.1989.118638 Hernandez, G., Berry, T. A., Wallis, S., Poyner, D. (2017). Temperature and humidity effects on particulate matter concentrations in a sub-tropical climate during winter. International Proceedings of Chemical, Biological and Environmental Engineering, V01, 102. Hien, P. D., Bac, V. T., Tham, H. C., Nhan, D. D., Vinh, L. D. (2002). Influence of meteorological conditions on PM2. 5 and PM2. 5− 10 concentrations during the monsoon season in Hanoi, Vietnam. Atmospheric Environment, 36(21), 3473-3484. https://doi.org/10.1016/S1352-2310(02)00295-9 Ho, T. K. (1995). Random Decision Forests (PDF). Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, 14–16 August 1995. pp. 278–282. Archived from the original (PDF) on 17 April 2016. Retrieved 5 June 2016. https://doi.org/10.1109/ICDAR.1995.598994 Hsiao, T. C., Chen, W. N., Ye, W. C., Lin, N. H., Tsay, S. C., Lin, T. H., Wang, S. H. (2017). Aerosol optical properties at the Lulin Atmospheric Background Station in Taiwan and the influences of long-range transport of air pollutants. Atmospheric Environment, 150, 366-378. https://doi.org/10.1016/j.atmosenv.2016.11.031 Hsu, C. Y., Chiang, H. C., Lin, S. L., Chen, M. J., Lin, T. Y., Chen, Y. C. (2016). Elemental characterization and source apportionment of PM10 and PM2. 5 in the western coastal area of central Taiwan. Science of the Total Environment, 541, 1139-1150. https://doi.org/10.1016/j.scitotenv.2015.09.122 Hsu, S. C., Liu, S. C., Jeng, W. L., Chou, C. C., Hsu, R. T., Huang, Y. T., Chen, Y. W. (2006). Lead isotope ratios in ambient aerosols from Taipei, Taiwan: Identifying long-range transport of airborne Pb from the Yangtze Delta. Atmospheric Environment, 40(28), 5393-5404. https://doi.org/10.1016/j.atmosenv.2006.05.003 Huang, C. J., Kuo, P. H. (2018). A deep cnn-lstm model for particulate matter (Pm2. 5) forecasting in smart cities. Sensors, 18(7), 2220. https://doi.org/10.3390/s18072220 Jiang, P., Dong, Q., Li, P. (2017). A novel hybrid strategy for PM2. 5 concentration analysis and prediction. Journal of environmental management, 196, 443-457. https://doi.org/ 10.1016/j.jenvman.2017.03.046 Jin, J., Dundar, A., Culurciello, E. (2014). Flattened convolutional neural networks for feedforward acceleration. arXiv preprint arXiv:1412.5474. Kamińska, J. (2018). Probabilistic Forecasting of Nitrogen Dioxide Concentrations at an Urban Road Intersection. Sustainability, 10(11), 4213. https://doi.org/10.3390/su10114213 Kamińska, J. A. (2018). The use of random forests in modelling short-term air pollution effects based on traffic and meteorological conditions: a case study in Wrocław. Journal of Environmental Management, 217, 164-174. https://doi.org/10.1016/j.jenvman.2018.03.094 Kao, I. F., Zhou, Y., Chang, L. C., Chang, F. J. (2020). Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting. Journal of Hydrology, 124631. https://doi.org/10.1016/j.jhydrol.2020.124631 Karambelas, A., Holloway, T., Kiesewetter, G., Heyes, C. (2018). Constraining the uncertainty in emissions over India with a regional air quality model evaluation. Atmospheric Environment, 174, 194-203. https://doi.org/10.1016/j.atmosenv.2017.11.052 Karginova, N., Byttner, S., Svensson, M. (2012). Data-driven methods for classification of driving styles in buses. SAE Technical Paper, No. 2012-01-0744. Kumar, D. (2018). Evolving Differential evolution method with random forest for prediction of Air Pollution. Procedia Computer Science, 132, 824-833. https://doi.org/10.1016/j.procs.2018.05.094 Kong, L., Xin, J., Liu, Z., Zhang, K., Tang, G., Zhang, W., Wang, Y. (2017). The PM2. 5 threshold for aerosol extinction in the Beijing megacity. Atmospheric environment, 167, 458-465. https://doi.org/10.1016/j.atmosenv.2017.08.047 Lai, H. C., Ma, H. W., Chen, C. R., Hsiao, M. C., Pan, B. H. (2019). Design and application of a hybrid assessment of air quality models for the source apportionment of PM2. 5. Atmospheric Environment, 212, 116-127. https://doi.org/10.1016/j.atmosenv.2019.05.038 Li, L., Lei, Y., Wu, S., Chen, J., Yan, D. (2017). The health economic loss of fine particulate matter (PM2. 5) in Beijing. Journal of cleaner production, 161, 1153-1161. https://doi.org/10.1016/j.jclepro.2017.05.029 Li, R., Mei, X., Wei, L., Han, X., Zhang, M., Jing, Y. (2019). Study on the contribution of transport to PM2. 5 in typical regions of China using the regional air quality model RAMS-CMAQ. Atmospheric Environment, 214, 116856. https://doi.org/10.1016/j.atmosenv.2019.116856 Li, X., Feng, Y. J., Liang, H. Y. (2017, July). The impact of meteorological factors on PM2. 5 variations in Hong Kong. In IOP Conference Series: Earth and Environmental Science (Vol. 78, No. 1, p. 012003). IOP Publishing. https://doi.org/10.1088/1755-1315/78/1/012003 Li, Y., Yu, R., Shahabi, C., Liu, Y. (2017). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926. Liaw, A., Wiener, M. (2002). Classification and regression by random forest. R news, 2(3), 18-22. Liu, Y., Cao, G., Zhao, N., Mulligan, K., Ye, X. (2018). Improve ground-level PM2. 5 concentration mapping using a random forests-based geostatistical approach. Environmental pollution, 235, 272-282. https://doi.org/10.1016/j.envpol.2017.12.070 Lou, C., Liu, H., Li, Y., Peng, Y., Wang, J., Dai, L. (2017). Relationships of relative humidity with PM 2.5 and PM 10 in the Yangtze River Delta, China. Environmental Mmonitoring and Assessment, 189(11), 582. https://doi.org/10.1007/s10661-017-6281-z Loy-Benitez, J., Vilela, P., Li, Q., Yoo, C. (2019). Sequential prediction of quantitative health risk assessment for the fine particulate matter in an underground facility using deep recurrent neural networks. Ecotoxicology and Environmental Safety, 169, 316-324. https://doi.org/10.1016/j.ecoenv.2018.11.024 Ma, J., Ding, Y., Cheng, J. C., Jiang, F., Wan, Z. (2019). A temporal-spatial interpolation and extrapolation method based on geographic Long Short-Term Memory neural network for PM2. 5. Journal of Cleaner Production, 237, 117729. https://doi.org/10.1016/j.jclepro.2019.117729 Ma, J., Ding, Y., Cheng, J. C., Jiang, F., Tan, Y., Gan, V. J., Wan, Z. (2020). Identification of high impact factors of air quality on a national scale using big data and machine learning techniques. Journal of Cleaner Production, 244, 118955. https://doi.org/10.1016/j.jclepro.2019.118955 Mahajan, S., Liu, H. M., Tsai, T. C., Chen, L. J. (2018). Improving the accuracy and efficiency of PM2. 5 forecast service using cluster-based hybrid neural network model. IEEE Access, 6, 19193-19204.https://doi.org/ 10.1109/ACCESS.2018.2820164 Mihăiţă, A. S., Dupont, L., Chery, O., Camargo, M., Cai, C. (2019). Evaluating air quality by combining stationary, smart mobile pollution monitoring and data-driven modelling. Journal of Cleaner Production, 221, 398-418. https://doi.org/10.1016/j.jclepro.2019.02.179 Mishra, D., Goyal, P., Upadhyay, A. (2015). Artificial intelligence based approach to forecast PM2. 5 during haze episodes: A case study of Delhi, India. Atmospheric Environment, 102, 239-248. https://doi.org/10.1016/j.atmosenv.2014.11.050 Moisan, S., Herrera, R., Clements, A. (2018). A dynamic multiple equation approach for forecasting PM2. 5 pollution in Santiago, Chile. International Journal of Forecasting, 34(4), 566-581. https://doi.org/10.1016/j.ijforecast.2018.03.007 Niu, M., Wang, Y., Sun, S., Li, Y. (2016). A novel hybrid decomposition-and-ensemble model based on CEEMD and GWO for short-term PM2. 5 concentration forecasting. Atmospheric environment, 134, 168-180. https://doi.org/10.1016/j.atmosenv.2016.03.056 Nurkiewicz, T. R., Porter, D. W., Hubbs, A. F., Stone, S., Moseley, A. M., Cumpston, J. L., . . . Frisbee, J. C. (2011). Pulmonary particulate matter and systemic microvascular dysfunction. Research report (Health Effects Institute), (164), 3-48. Prechelt, L. (1998). Early Stopping-but when? In Lecture Notes in Computer Science; Springer: Berlin/Heidelberg, Germany, 1998; pp. 55–69, ISBN 978-3-642-35288-1, 978-3-642-35289-8. https://doi.org/10.1007/978-3-642-35289-8_5 Pucer, J. F., Pirš, G., Štrumbelj, E. (2018). A Bayesian approach to forecasting daily air-pollutant levels. . Knowledge and Information Systems, 57(3), 635-654. https://doi.org/10.1007/s10115-018-1177-y Qiu, H., Yu, I. T., Wang, X., Tian, L., Tse, L. A., Wong, T. W. (2013). Differential effects of fine and coarse particles on daily emergency cardiovascular hospitalizations in Hong Kong. Atmospheric environment, 64, 296-302. https://doi.org/10.1016/j.atmosenv.2012.09.060 Romero, A., Ballas, N., Kahou, S. E., Chassang, A., Gatta, C., Bengio, Y. (2015). Imagenet classification with deep convolutional neural networks. In International Conference on Learning Representations. https://doi.org/10.1145/3065386 Stafoggia, M., Bellander, T., Bucci, S., Davoli, M., de Hoogh, K., De'Donato, F., . . . Scortichini, M. (2019). Estimation of daily PM10 and PM2. 5 concentrations in Italy, 2013–2015, using a spatiotemporal land-use random-forest model. Environment international, 124, 170-179. https://doi.org/10.1016/j.envint.2019.01.016 Tai, A. P., Mickley, L. J., Jacob, D. J. (2010). Correlations between fine particulate matter (PM2. 5) and meteorological variables in the United States: Implications for the sensitivity of PM2. 5 to climate change. Atmospheric Environment, 44(32), 3976-3984. https://doi.org/10.1016/j.atmosenv.2010.06.060 Tang, G., Zhao, P., Wang, Y., Gao, W., Cheng, M., Xin, J., ... Wang, Y. (2017). Mortality and air pollution in Beijing: The long-term elationship. Atmospheric environment, 150, 238-243. https://doi.org/10.1016/j.atmosenv.2016.11.045 Tsai, Y. I., Kuo, S. C. (2005). PM2. 5 aerosol water content and chemical composition in a metropolitan and a coastal area in southern Taiwan. Atmospheric Environment, 39(27), 4827-4839. https://doi.org/10.1016/j.atmosenv.2005.04.024 Wang, H. W., Li, X. B., Wang, D., Zhao, J., Peng, Z. R. (2020). Regional prediction of ground-level ozone using a hybrid sequence-to-sequence deep learning approach. Journal of Cleaner Production, 253, 119841. https://doi.org/10.1016/j.jclepro.2019.119841 Wallace, J., Kanaroglou, P. (2009). The effect of temperature inversions on ground-level nitrogen dioxide (NO2) and fine particulate matter (PM2. 5) using temperature profiles from the Atmospheric Infrared Sounder (AIRS). Science of the Total Environment, 407(18), 5085-5095. https://doi.org/10.1016/j.scitotenv.2009.05.050 Widiana, D. R., You, S. J., Yang, H. H., Wang, L. C., Tsai, J. H., Chen, H. M. (2019). Air Pollution Profiles and Health Risk Assessment of Ambient Volatile Organic Compounds above a Municipal Wastewater Treatment Plant, Taiwan. Aerosol and Air Quality Research, 19(2), 375-382. https://doi.org/10.4209/aaqr.2018.11.0408 Yang, G., Huang, J., Li, X. (2018). Mining sequential patterns of PM2. 5 pollution in three zones in China. Journal of cleaner production, 170, 388-398. https://doi.org/10.1016/j.jclepro.2017.09.162 Yuan, C. S., Sau, C. C., Chen, M. C. (2004). Influence of Asian dusts on the physicochemical properties of atmospheric aerosols in Taiwan district—Using the Penghu Islands as an example. China Particuology, 2(4), 144-152. https://doi.org/10.1016/S1672-2515(07)60045-1 Yang, S. N., Ku, Y. Y., Kuo, C. L., Wang, Y. F., Lin, C. Y., Chang, F. J., Chang, L. C. (2019). Develop AI Early flood warning systems for smart cities flood defense with IoT flood sensors. AGUFM, 2019, H33L-2116. Zhang, L., Lin, J., Qiu, R., Hu, X., Zhang, H., Chen, Q., . . . Wang, J. (2018). Trend analysis and forecast of PM2. 5 in Fuzhou, China using the ARIMA model. Ecological indicators, 95, 702-710. https://doi.org/10.1016/j.ecolind.2018.08.032 Zhao, J., Deng, F., Cai, Y., Chen, J. (2019). Long short-term memory-Fully connected (LSTM-FC) neural network for PM2. 5 concentration prediction. Chemosphere, 220, 486-492. https://doi.org/10.1016/j.chemosphere.2018.12.128 Zhou, L., Chen, X., Tian, X. (2018). The impact of fine particulate matter (PM2. 5) on China's agricultural production from 2001 to 2010. Journal of Cleaner Production, 178, 133-141. https://doi.org/10.1016/j.jclepro.2017.12.204 Zhou, Y., Chang, F. J., Chang, L. C., Kao, I. F., Wang, Y. S., Kang, C. C. (2019). Multi-output support vector machine for regional multi-step-ahead PM2. 5 forecasting. Science of the Total Environment, 651, 230-240. https://doi.org/10.1016/j.scitotenv.2018.09.111 Zhou, Y., Chang, F.J., Chang, L. C., Kao, I. F., Wang, Y. S. (2019). Explore a deep learning multi-output neural network for regional multi-step-ahead air quality forecasts. Journal of Cleaner Production, 209, 134-145. https://doi.org/10.1016/j.jclepro.2018.10.243 Zhou, Y., Guo, S., Chang, F. J. (2019). Explore an evolutionary recurrent ANFIS for modelling multi-step-ahead flood forecasts. Journal of Hydrology, 570, 343-355. https://doi.org/10.1016/j.jhydrol.2018.12.040 Zhou, Y., Chang, L. C., Chang, F. J. (2020). Explore a Multivariate Bayesian Uncertainty Processor driven by artificial neural networks for probabilistic PM2. 5 forecasting. Science of The Total Environment, 711, 134792. https://doi.org/10.1016/j.scitotenv.2019.134792 Zhou, Y., Chang, F. J., Chen, H., Li, H. (2020). Exploring copula-based Bayesian Model Averaging with multiple ANNs for PM2. 5 ensemble forecasts. Journal of Cleaner Production, 121528. https://doi.org/10.1016/j.jclepro.2020.121528 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/58172 | - |
| dc.description.abstract | 近來隨著人們越來越關心健康惡化的問題，細懸浮微粒(PM2.5)越發的得到社會上的關注。建立精準的PM2.5預測模式仍面臨著巨大的挑戰因爲對於它動態的化學反應且排放數據及預測的不確定性。本研究將會建立一個混合模型 (CNN-BP) ，它是使用卷積神經網絡（CNN）和倒傳播神經網絡（BPNN）來同時對多個測站進行準確的長時距PM2.5預測。此研究用了2017年的73個空品測站的資料，并且用了六個空污因子以及兩個氣象因子為輸入模式輸入。總共有639,480筆資料并切分成訓練(409,238,64%)， 驗證(102,346, 16%)以及測試 (127,896, 20%) 階段。PM2.5的預測被視爲是以空污因子及七項因子為參數之函數。此研究提出的CNN-BP模式有效地學習到輸入數據的主要特徵，並同時預測了區域性之PM2.5長時距預測 (73個測站；t+1-t+10)。 本研究結果反映出區域性長時距的預測，利用混合式CNN-BP可獲得比BPNN, 隨機森林(random forest)及長短期記憶體類神經網路(LSTM)要高的準確率及卓越的表現。此外，CNN-BP模式不但可藉由高維度異質性的長延滯輸入資料來應對因維度被降低而導致重要資訊遺失的問題；也因此有著探索全臺灣五個區域(R1-R5)不同機制(本地排放和遠距離跨界傳播)的能力。此研究證明多個測站(區域性) 之長時距預測問題是可以用一個模式(CNN-BP)來完成這個目的，達到一個新的里程碑。因此，CNN-BP可以促進即時的PM2.5預報服務，并且可以在綫公開提供預報。 | zh_TW |
| dc.description.abstract | It is well known that some diseases are caused by fine particulate matters such as PM2.5. Therefore, the forecast of such particles gains an increasing public concern. Due to the uncertainty of the dynamic formulation process of the tiny particles (emission data and their projections), modelling PM2.5 concentrations remains a challenging task. Since PM2.5 forecasting is a complex non-linear problem, artificial neural networks (ANNs) are often used in previous studies. The hybrid model (CNN-BP), which is a fusion of the Convolutional Neural Network (CNN) and a Back Propagation Neural Network (BPNN), is proposed in this study to make accurate PM2.5 forecasts for multiple stations at multiple horizons simultaneously through effectively learning the dominant features of input data. The datasets used for the PM2.5 forecasting in this study are related to six air quality and two meteorological factors (hourly) collected from 73 air quality monitoring stations in Taiwan during 2017. The hourly monitoring datasets (639,480) were allocated into training (409,238, 64%), validation (102,346, 16%), and testing (127,896, 20%) stages. The results demonstrate this proposed CNN-BP model can produce more accurate regional multi-step-ahead PM2.5 forecasts (73 stations; t+1−t+10), as compared to the widely used ANNs like BPNN, random forest and long short term memory neural network. With the ability to handle the heterogeneous inputs (with relatively large time-lags) adequately, the CNN-BP can mitigate the loss caused by dimension reduction. In addition, this hybrid model can explore the differences in PM2.5 mechanisms (local emission and transboundary transmission) for the 5 regions (R1-R5) and the whole Taiwan. In this study, exactly one model (i.e. the proposed CNN-BP model) is used to make multi-site (regional) and multi-horizon forecasting, which is a novel achievement. Consequently, this work suggests a real-time PM2.5 forecast service for the public. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T08:07:27Z (GMT). No. of bitstreams: 1 U0001-1407202016471900.pdf: 4788884 bytes, checksum: 501e8601c8c19121e8a16a337e6267fb (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 謝誌 I 摘要 III Abstract IV Chapter 1 Introduction 1 1.1 Research background 1 1.2 Research Motivation 3 1.3 Literature Review 4 1.3.1 The impact of air pollution and aerosols on human health 4 1.3.2 Current studies that applied the machine learning method to air pollution forecasting 5 1.4 Research goal 7 Chapter 2 Case Study 9 2.1 Study area 9 2.2 Data collection and statistical analysis 10 Chapter 3 Methodology 15 3.1 Problems and motivations 15 3.2 Convolutional neural network (CNN) 18 3.3 Back propagation neural network (BPNN) 21 3.4 Hybrid of CNN and BPNN (CNN-BP) 23 3.5 Random forest (RF) 25 3.6 Long Short Term Memory Neural Network (LSTM) 27 3.7 Techniques to prevent overfitting 28 3.8 Evaluation indicators 29 3.9 Kriging method 30 Chapter 4 Results and discussion 32 4.1 Data preprocessing 32 4.2 Model construction 32 4.3 Comparison of ANN models for PM2.5 forecasts 44 Chapter 5 Conclusion 59 Reference 62 Appendix 77 A. Air quality factors monitored by the Taiwan EPA at air quality monitoring stations 77 B. Geographic information of air quality monitoring stations 78 C. Performance (R2) of two BPNN forecast models of PM2.5 concentrations at horizons t+2 up to t+9 in the testing stages for the central and southern regions of Taiwan in winter. 80 D. Performance (R2) of one BPNN forecast model of PM2.5 concentrations at horizon t+2 to t+9 in the testing stage for the central and southern regions of Taiwan in winter. 81 E. Absolute errors of forecast models for the Nanzi station at horizon t+6. (i) Convolutional-backpropagation neural network. (ii) Backpropagation neural network. (iii) Random forest. 83 F. Absolute errors of forecast models for the Nanzi station at horizon t+10. (i) Convolutional-backpropagation neural network. (ii) Backpropagation neural network. (iii) Random forest. 85 謝誌 I 摘要 III Abstract IV Chapter 1 Introduction 1 1.1 Research background 1 1.2 Research Motivation 3 1.3 Literature Review 4 1.3.1 The impact of air pollution and aerosols on human health 4 1.3.2 Current studies that applied the machine learning method to air pollution forecasting 5 1.4 Research goal 7 Chapter 2 Case Study 9 2.1 Study area 9 2.2 Data collection and statistical analysis 10 Chapter 3 Methodology 15 3.1 Problems and motivations 15 3.2 Convolutional neural network (CNN) 18 3.3 Back propagation neural network (BPNN) 21 3.4 Hybrid of CNN and BPNN (CNN-BP) 23 3.5 Random forest (RF) 25 3.6 Long Short Term Memory Neural Network (LSTM) 27 3.7 Techniques to prevent overfitting 28 3.8 Evaluation indicators 29 3.9 Kriging method 30 Chapter 4 Results and discussion 32 4.1 Data preprocessing 32 4.2 Model construction 32 4.3 Comparison of ANN models for PM2.5 forecasts 44 Chapter 5 Conclusion 59 Reference 62 Appendix 77 A. Air quality factors monitored by the Taiwan EPA at air quality monitoring stations 77 B. Geographic information of air quality monitoring stations 78 C. Performance (R2) of two BPNN forecast models of PM2.5 concentrations at horizons t+2 up to t+9 in the testing stages for the central and southern regions of Taiwan in winter. 80 D. Performance (R2) of one BPNN forecast model of PM2.5 concentrations at horizon t+2 to t+9 in the testing stage for the central and southern regions of Taiwan in winter. 81 E. Absolute errors of forecast models for the Nanzi station at horizon t+6. (i) Convolutional-backpropagation neural network. (ii) Backpropagation neural network. (iii) Random forest. 83 F. Absolute errors of forecast models for the Nanzi station at horizon t+10. (i) Convolutional-backpropagation neural network. (ii) Backpropagation neural network. (iii) Random forest. 85 List of Tables Table 1 Statistical analysis results of air quality and meteorological data (1/1/2017−31/12/2017). 14 Table 2 Parameter setting of each machine learning model in this study. 33 Table 3 Training performance of the forecast model with 6 input factors. (i). R2 (ii) RMSE. 39 Table 4 Testing performance of the forecast model with 6 input factors. (i). R2 (ii) RMSE. 40 Table 5 Training performance of the forecast model with 8 input factors. (i) R2 (ii) RMSE. 41 Table 6 Testing performance of the forecast model with 8 input factors. (i) R2 (ii) RMSE. 42 Table 7 Performance of the CNN-BP model in training/validation and testing stage for the whole of Taiwan.. 44 Table 8 MAE values between observed and forecasted PM2.5 concentrations at the Nantzu Station for three ANN models at horizon t+10. 51 Table 9 Training performance of the multi-step-ahead forecast models constructed by inputs of 12 time steps and 24 time steps separately for multiple pollutants. (i) R2. (ii) RMSE. 57 Table 10 Testing performance of the multi-step-ahead forecast model constructed by inputs of 12 time steps and 24 time steps separately for multiple pollutants. (i) R2. (ii) RMSE. 58 | |
| dc.language.iso | en | |
| dc.title | 卷積層與倒傳遞混合式類神經網路針對大區域之PM2.5進行長時距預測 | zh_TW |
| dc.title | Hybrid convolutional and back-propagation neural networks for regional multi-step-ahead PM_2.5 forecasting | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.advisor-orcid | 張斐章(0000-0002-1655-8573) | |
| dc.contributor.oralexamcommittee | 黃文政(Wen-Cheng Huang),張麗秋(Li-Chiu Chang),李奇旺(Chi-Wang Li),王怡心(Yi-Shin Wang) | |
| dc.subject.keyword | PM2.5預測,深度學習,卷積層類神經網路,倒傳遞類神經網路,長時距之預測,臺灣, | zh_TW |
| dc.subject.keyword | PM2.5 forecast,Deep learning,Convolutional neural network,Multistep ahead forecasts,Artificial neural networks, | en |
| dc.relation.page | 84 | |
| dc.identifier.doi | 10.6342/NTU202001518 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-07-17 | |
| dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
| dc.contributor.author-dept | 生物環境系統工程學研究所 | zh_TW |
| 顯示於系所單位： | 生物環境系統工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1407202016471900.pdf 目前未授權公開取用 | 4.68 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。