臺灣博碩士論文加值系統

　　目前濕地研究多集中於高緯度的泥炭地(peatlands)，低緯度濕地的研究相對較少，然而低緯度濕地面積占全球濕地面積之70%，若以泥炭地之研究結果進行全球濕地碳通量的推估，可能會與實際情形產生誤差。在碳收支的研究中，渦度相關法(eddy-covariance method)被認為是最直接而準確地量測生態系統通量的方式，但受限於此法對量測環境的要求，故無通量塔處之碳通量變化趨勢須以推估的方式進行。在眾多推估方式中，類神經網路(artificial neural network)在各種不同生態系統的推估研究中，已證實具有良好的模擬能力，能夠精確掌握氣象資料與碳通量資料之間的關聯性。
　　本研究使用類神經網路作為推估工具，採用關渡塔一(GDP-T1)、關渡塔二(GDP-T2)、佛羅里達站(US-Esm)三個低緯度濕地測站資料(包括氣象及二氧化碳通量)作為輸入及輸出參數，配合倒傳遞演算法(back propagation algorithm)進行模式建立與推估。模型訓練完成後，計算相關係數(Correlation coefficient)、均方根誤差(RMSE)、平均絕對百分比誤差(MAPE)等指標，以討論推估結果與觀測結果之間的誤差情形，以及模型推估二氧化碳通量變化模式之能力。GDP-T1及GDP-T2站最佳結果出現在日間模型(R=0.89及R=0.87)，US-Esm站點最佳結果出現在夜間模型(R=0.62)。跨站模擬最佳情況可高達R=0.73，此結果顯示未來以類神經網路應用於大範圍推估為可行的。
　　本研究所建立之模型可應用於濕地生態系統進行二氧化碳通量數據的推估，提高全球濕地碳收支推估精確程度，並進一步研究無通量塔處之二氧化碳通量變化特徵，分析相似生態系統二氧化碳通量的變異模式，如季節或年際變異等，克服通量塔設置之空間限制及節省儀器架設成本。在面對氣候變遷時，此模型的推估能力也可增加對於未知風險的了解，作為評估未來變化趨勢的依據之一。

　　In wetland studies, few attentions have been given to low-latitude wetland ecosystem presently, but it accounts for about 70% of the global wetland area. Therefore, it’s very important to consider the contribution of this significant portion on global carbon (C) budget. In the past decades, eddy-covariance method has been widely applied in many C budget studies at the ecosystem scale, but there are still several limitations affecting the performance of EC methods. In order to overcome the abovementioned limitations, many linear or non-linear statistical techniques are applied to fill the measurement gap. Among various methods, the Artificial Neural Network (ANN) method is considered to be an excellent means to identify the complex non-linear relationship between the CO2 flux and meteorological variables.

　　In this study, a back-propagation ANN model was applied to quantify CO2 flux at three low-latitude wetland sites (Guandu Nature Park Tower One (GDP-T1), Guandu Nature Park Tower Two (GDP-T1), and Florida Everglades short hydroperiod marsh (US-Esm)) in East Asia and the US. Meteorological variables were used as the input parameters to train the ANN to predict the CO2 exchange. The best results of the GDP-T1 (R=0.89) and GDP-T2 (R=0.87) occurred in the simulation of the daytime (DT) model, and that of the US-Esm (R=0.62) in the nighttime (NT) models. The cross-site simulation was feasible, the best result could up to 0.73 in terms of R. This model provided a quick, efficient, and highly accurate estimation, and could be conducted to estimate the dynamics of CO2 flux where there is no direct in-situ flux measurement. The simulation capability is helpful to characterize the spatial/temporal variations in low-latitude wetland ecosystems, and improve the quantification of global C budget.

Acknowledgement i
摘要 ii
Abstract iii
Contents iv
List of figures vi
List of tables vii
1. Introdution 1
1.1. Wetland ecosystems 1
1.2. Eddy covariance method 3
1.3. Estimation of C flux 5
1.4. The application of ANN models on C budget 6
1.5. The relationship of environmental factors and NEE 11
1.6. Objectives 12
2. Methods 14
2.1. Site descriptions 14
2.1.1. Guandu Nature Park Tower One (GDP-T1) 14
2.1.2. Guandu Nature Park Tower Two (GDP-T2) 15
2.1.3. Florida Everglades short hydroperiod marsh (US-Esm) 16
2.1.4. Brief summary 16
2.2. Study design 18
2.3. Artificial Neural Network (ANN) 19
2.4. Input and output variables 23
2.5. Data pre-processing 24
2.6. Model comparison indices 26
3. Results 29
3.1. The model performance in each site 29
3.2. The data distribution at each site 31
3.2.1. All data 34
3.2.2. Daytime data 35
3.2.3. Nighttime data 36
3.3. The capability of cross-site prediction 40
3.4. The comparison of data distribution between different site 41
4. Discussion 44
4.1. The data period in each site 44
4.2. The advantage of the meteorological variables as the input data 44
4.3. The comparison of MAPE in different site 45
4.4. The results of data division 45
5. Conclusions and Future Works 47
Reference 49
Appendix I: The maximum (max) and the minimum (min) of input parameters used in the normalization process at each site. 55
Appendix II: The RMSE curve of three groups in the training phase. 56
Appendix III: The simulation results in each site. 61
Appendix IV: The cross-site simulation results. 72
Appendix V: The code used in the training phase. 81
Appendix VI: The code used in the simulation phase. 85

Amundson, R., Stern, L., Baisden, T., and Wang, Y. (1998). The isotopic composition of soil and soil-respired CO 2. Geoderma, 82(1), 83-114.
Armentano, T. V., and Menges, E. S. (1986). Patterns of change in the C balance of organic soil-wetlands of the temperate zone. The Journal of Ecology, 755-774.
Baldocchi, D. (2014). Measuring fluxes of trace gases and energy between ecosystems and the atmosphere–the state and future of the eddy covariance method. Global change biology, 20(12): 3600-3609.
Baldocchi, D., Falge, E., Gu, L., Olson, R., Hollinger, D., Running, S., Anthoni, P., Bernhofer, C., Davis, K., Evans, R., Fuentes, J., Goldstein, A., Katul, G., Law, B., Lee, X., Malhi, Y., Meyers, T., Munger, W., Oechel, W., Paw U, K. T., Pilegaard, K., Schmid, H. P., Valentini, R., Verma, S., Vesala, T., Wilson, K., Wofsy, S. (2001). Fluxnet: A new tool to study the temporal and spatial variability of ecosystem-scale C dioxide, water vapor, and energy flux densities. Bulletin of the American Meteorological Society, 82(11): 2415-2434.
Bernal, B., and Mitsch, W. J. (2008). A comparison of soil carbon pools and profiles in wetlands in Costa Rica and Ohio. Ecological Engineering, 34(4), 311-323.
Bernal, B., and Mitsch, W. J. (2012). Comparing C sequestration in temperate freshwater wetland communities. Global Change Biology, 18(5), 1636-1647.
Bonneville, M. C., Strachan, I. B., Humphreys, E. R., and Roulet, N. T. (2008). Net ecosystem CO 2 exchange in a temperate cattail marsh in relation to biophysical properties. Agricultural and Forest Meteorology, 148(1), 69-81.
Bousquet, P., Peylin, P., Ciais, P., Le Quéré, C., Friedlingstein, P., and Tans, P. P. (2000). Regional changes in C dioxide fluxes of land and oceans since 1980. Science, 290(5495), 1342-1346.
Brix, H., Sorrell, B. K., and Lorenzen, B. (2001). Are Phragmites-dominated wetlands a net source or net sink of greenhouse gases? Aquatic Botany, 69(2): 313-324.
Bubier, J. L., Crill, P. M., Moore, T. R., Savage, K., and Varner, R. K. (1998). Seasonal patterns and controls on net ecosystem CO2 exchange in a boreal peatland complex. Global Biogeochemical Cycles, 12(4), 703-714.
Carrara, A., Kowalski, A. S., Neirynck, J., Janssens, I. A., Yuste, J. C., & Ceulemans, R. (2003). Net ecosystem CO 2 exchange of mixed forest in Belgium over 5 years. Agricultural and Forest Meteorology, 119(3), 209-227.
Chang, F. J., and Chang, L. C. (2015). Artificial neural network: Theory and application (2nd edition). Tsang Hai Publishing: Taipei.
Chmura, G. L., Anisfeld, S. C., Cahoon, D. R., Lynch, J. C. (2003). Global C sequestration in tidal, saline wetland soils. Global biogeochemical cycles, 17(4). doi:10.1029/2002GB001917.
Clevering, O. A., and Lissner, J. (1999). Taxonomy, chromosome numbers, clonal diversity and population dynamics of Phragmites australis. Aquatic Botany, 64(3), 185-208.
Dragomir, C. M., Klaassen, W., Voiculescu, M., Georgescu, L. P., van der Laan, S. (2012). Estimating annual CO2 flux for Lutjewad station using three different gap-filling techniques. The Scientific World Journal, 2012. doi:10.1100/2012/842893.
Duever, M. J., Meeder, J. F., Meeder, L. C., and McCollom, J. M. (1994). The climate of south Florida and its role in shaping the Everglades ecosystem. In: Everglades: The Ecosystem and its Restoration, ed. S. M. Davis, and J. C. Ogden, 225-248. Delray Beach: St. Lucie Press.
Falge, E., Baldocchi, D., Olson, R., Anthoni, P., Aubinet, M., Bernhofer, C., Burba, G., Ceulemans, R., Clement, R., Dolman, H., Granier, A., Gross, P., Grünwald, T., Hollinger, D., Jensen, N.-O., Katul, G., Keronen, P., Kowalski, A., Lai, C. T., Law, B. L., Meyers, T., Moncrieff, J., Moors, E., Munger, J. W., Pilegaard, K., Rannik, Ü., Rebmann, C., Suyker, A., Tenhunen, J., Tu, K., Verma, S., Vesala, T., Wilson, K., Wofsy, S. (2001). Gap filling strategies for defensible annual sums of net ecosystem exchange. Agricultural and forest meteorology, 107(1), 43-69.
Falge, E., Baldocchi, D., Olson, R., Anthoni, P., Aubinet, M., Bernhofer, C., Burba, G., Ceulemans, R., Clement, R., Dolman, H., Granier, A., Gross, P., Grünwald, T., Hollinger, D., Jensen, N.-O., Katul, G., Keronen, P., Kowalski, A., Lai, C. T., Law, B. E., Meyers, T., Moncrieff, J. Moors, E., Munger, J. W., Pilegaard, K., Rannik, Ü., Rebmann, C., Suyker, A., Tenhunen, J., Tu, K., Verma, S., Vesala, T., Wilson, K., Wofsy, S. (2001). Gap filling strategies for defensible annual sums of net ecosystem exchange. Agricultural and forest meteorology, 107(1), 43-69.
Fennessy, M. S. (2014). Wetland ecosystems and global change, in Bill Freedman (ed.), Global Environmental Change, Netherlands: Springer, 255-261.
FLUXNET (2015) Historical Site Status. http://fluxnet.ornl.gov/site_status (last accessed 30 December 2015).
Gorham, E. (1995). The biogeochemistry of northern peatlands and its possible response to global warming. Biotic Feedback in the Global Climatic System, GM Woodwell and FT Mackenzie (eds.), Oxford University Press, New York, 169-187.
Gower, S. T., Kucharik, C. J., and Norman, J. M. (1999). Direct and indirect estimation of leaf area index, f APAR, and net primary production of terrestrial ecosystems. Remote sensing of environment, 70(1), 29-51.
Han, G., Chu, X., Xing, Q., Li, D., Yu, J., Luo, Y., Wang, G., Mao, P., and Rafique, R. (2015). Effects of episodic flooding on the net ecosystem CO2 exchange of a supratidal wetland in the Yellow River Delta. Journal of Geophysical Research: Biogeosciences, 120(8), 1506-1520.
Hollinger, D. Y., Aber, J., Dail, B., Davidson, E. A., Goltz, S. M., Hughes, H., Leclerc, M. Y., Lee, J. T., Richardson, A. D., Rodrigues, C., Scott, N. A., Achuatavarier, D., Walsh, J. (2004). Spatial and temporal variability in forest–atmosphere CO2 exchange. Global Change Biology, 10(10), 1689-1706.
Inglett, K. S., Inglett, P. W., Reddy, K. R., Osborne, T. Z. (2012). Temperature sensitivity of greenhouse gas production in wetland soils of different vegetation. Biogeochemistry, 108(1-3): 77-90.
Jimenez, K. L., Starr, G., Staudhammer, C. L., Schedlbauer, J. L., Loescher, H. W., Malone, S. L., and Oberbauer, S. F. (2012). Carbon dioxide exchange rates from short‐and long‐hydroperiod Everglades freshwater marsh. Journal of Geophysical Research: Biogeosciences, 117(G4).
Jung, M., M. Reichstein, Margolis, H. A., Cescatti, A., Richardson, A. D., Arain, M. A., Arneth, A., Bernhofer, C., Bonal, D., Chen, J., Gianelle, D., Gobron, N., Kiely, G., Kutsch, W., Lasslop, G., Law, B. E., Lindroth, A., Merbold, L., Montagnani, L., Moors, E. J., Papale, D., Sottocornola, M., Vaccari, F., Williams, C. (2011). Global patterns of land‐atmosphere fluxes of C dioxide, latent heat, and sensible heat derived from eddy covariance, satellite, and meteorological observations. Journal of Geophysical Research: Biogeosciences (2005–2012), 116(G3).
Kaimal, J. C. and J. J. Finnigan. 1994. Atmospheric boundary layer flows: Their structure and measurement. Oxford university press, New York.
Knorr, W., and Kattge, J. (2005). Inversion of terrestrial ecosystem model parameter values against eddy covariance measurements by Monte Carlo sampling. Global Change Biology, 11(8), 1333-1351.
Kwok, T. Y., and Yeung, D. Y. (1997). Constructive algorithms for structure learning in feedforward neural network for regression problems. IEEE Transactions on Neural Network, 8(3), 630-645.
Lal, R. (2008). C sequestration. Philosophical Transactions of the Royal Society B: Biological Sciences, 363(1492), 815-830.
Lee, S. C., Fan, C. J., Wu, Z. Y., and Juang, J. Y. (2015). Investigating effect of environmental controls on dynamics of CO2 budget in a subtropical estuarial marsh wetland ecosystem. Environmental Research Letters, 10(2), 025005.
Leuning, R., Cleugh, H. A., Zegelin, S. J., and Hughes, D. (2005). C and water fluxes over a temperate Eucalyptus forest and a tropical wet/dry savanna in Australia: measurements and comparison with MODIS remote sensing estimates. Agricultural and Forest Meteorology, 129(3), 151-173.
Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting. London: Butterworth Scientific.
Melesse, A. M. and Hanley, R. S. (2005). Artificial neural network application for multi-ecosystem C flux simulation. Ecological Modelling, 189(3): 305-314.
Mitsch, W. J., and Gosselink, J. G. 2007. Wetlands, 4th ed. John Wiley & Sons, New York
Mitsch, W. j., Bernal, B., Nahlik, A. M., Mander, Ü., Zhang, L., Anderson, C. J., Jørgensen, S. E., Brix, H. (2013). Wetlands, C, and climate change. Landscape Ecology, 28(4): 583-597.
Moffat, A. M., Papale, D., Reichstein, M., Hollinger, D. Y., Richardson, A. D., Barr, A. G.,Beckstein, C., Braswell, B. H., Churkina, G., Desai, A. R., Falge, E., Gove, J. H., Heimann, M., Hui, D., Jarvis, A. J., Kattge, J., Noormets, A., Stauch, V. J. (2007) Comprehensive comparison of gap-filling techniques for eddy covariance net C fluxes. Agricultural and Forest Meteorology, 147(3): 209-232.
Mogami, J., Hirata, R., Hirano, T., Miura, M., Fujinuma,Y., Inukai, K. (2003). Comparison of gap-filling methods for the data sets of net ecosystem exchange and energy fluxes in a larch forest. J. Agric. Meteorol. (Hokkaido), 55: 9-16.
Morin, T. H., Bohrer, G., Frasson, R. D. M., Naor‐Azreli, L., Mesi, S., Stefanik, K. C., and Schäfer, K. V. R. (2014). Environmental drivers of methane fluxes from an urban temperate wetland park. Journal of Geophysical Research: Biogeosciences, 119(11), 2188-2208.
National Climatic Data Center (NCDC). 2015. Climate at a Glance: U.S. Time Series. http://www.ncdc.noaa.gov/cag/ (last accessed 2017.02.24).
Neue, H. U., Gaunt, J. L., Wang, Z. P., Becker-Heidmann, P., and Quijano, C. (1997). C in tropical wetlands. Geoderma, 79(1), 163-185.
O’Connell, M. J. (2003). Detecting, measuring and reversing changes to wetlands. Wetland Ecology and Management, 11: 397-401.
Ooba, M., Hirano, T., Mogami, J. I., Hirata, R., Fujinuma, Y. (2006). Comparisons of gap-filling methods for C flux dataset: a combination of a genetic algorithm and an artificial neural network. Ecological modelling, 198(3): 473-486.
Papale, D., and Valentini, R. (2003). A new assessment of European forests C exchanges by eddy fluxes and artificial neural network spatialization. Global Change Biology, 9(4), 525-535.
Papale, D., and Valentini, R. (2003). A new assessment of European forests C exchanges by eddy fluxes and artificial neural network spatialization. Global Change Biology, 9(4), 525-535.
Park, J., Hong, M. G., & Kim, J. G. (2013). Relationship between early development of plant community and environmental condition in abandoned paddy terraces at mountainous valleys in Korea. Journal of Ecology and Environment, 36(2), 131-140.
Ramsar. (2015). Wetlands of International Importance (Ramsar Sites). http://www.ramsar.org/about/wetlands-of-international-importance-ramsar-sites (last accessed 30 December 2015).
Rayner, P. J., Law, R. M., Allison, C. E., Francey, R. J., Trudinger, C. M., and Pickett‐Heaps, C. (2008). Interannual variability of the global C cycle (1992–2005) inferred by inversion of atmospheric CO2 and δ13CO2 measurements. Global Biogeochemical Cycles, 22(3).
Rowbottom, C. G., Webb, S., and Oldham, M. (1999). Beam-orientation customization using an artificial neural network. Physics in medicine and biology, 44(9), 2251.
Running, S. W., Baldocchi, D. D., Turner, D. P., Gower, S. T., Bakwin, P. S., and Hibbard, K. A. (1999). A global terrestrial monitoring network integrating tower fluxes, flask sampling, ecosystem modeling and EOS satellite data. Remote Sensing of Environment, 70(1), 108-127.
Schedlbauer, J. L., Oberbauer, S. F., Starr, G., and Jimenez, K. L. (2010). Seasonal differences in the CO 2 exchange of a short-hydroperiod Florida Everglades marsh. Agricultural and Forest Meteorology, 150(7), 994-1006.
Schedlbauer, J. L., Munyon, J. W., Oberbauer, S. F., Gaiser, E. E., and Starr, G. (2012). Controls on ecosystem C dioxide exchange in short-and long-hydroperiod Florida Everglades freshwater marshes. Wetlands, 32(5), 801-812.
Stoy,P. C., Richardson, A. D., Baldocchi, D. D., Katul, G. G., Stanovick, J., Mahecha, M. D., Reichstein, M., Detto,M., Law, B. E., Wohlfahrt, G., Arriga, N., Campos, J., McCaughey, J. H.,Montagnani, L.,Paw U, K. T., Sevanto, S., Williams, M. (2009). Biosphere-atmosphere exchange of CO2 in relation to climate: a cross-biome analysis across multiple time scales. Biogeosciences, 6(10): 2297-2312.
Turetsky, M. R., Wieder, R. K., Vitt, D. H., Evans, R. J., and Scott, K. D. (2007). The disappearance of relict permafrost in boreal north America: Effects on peatland carbon storage and fluxes. Global Change Biology, 13(9), 1922-1934.
Van Wijk, M. T., and Bouten, W. (1999). Water and C fluxes above European coniferous forests modelled with artificial neural network. Ecological Modelling, 120(2), 181-197.
Van Wijk, M. T., Bouten, W., Verstraten, J. M. (2002). Comparison of different modelling strategies for simulating gas exchange of a Douglas-fir forest. Ecological Modelling, 158(1): 63-81.
Vymazal, J. (2013). Emergent plants used in free water surface constructed wetlands: a review. Ecological engineering, 61, 582-592.
Waddington, J. M., and Roulet, N. T. (2000). C balance of a boreal patterned peatland. Global Change Biology, 6(1), 87-97.
Watanabe, T., Yokozawa, M., Emori, S., Takata, K., Sumida, A., and Hara, T. (2004). Developing a multilayered integrated numerical model of surface physics–growing plants interaction (MINoSGI). Global Change Biology, 10(6), 963-982.
Zhang, Q., Sun, R., Jiang, G., Xu, Z., and Liu, S. (2016). C and energy flux from a Phragmites australis wetland in Zhangye oasis-desert area, China. Agricultural and Forest Meteorology, 230, 45-57.
Zhou, L., Zhou, G., Jia, Q. (2009). Annual cycle of CO2 exchange over a reed(Phragmites australis)wetland in Northeast China. Aquatic Botany, 91(2): 91-98.