Recursive Partitioning application in the assessment of the climatic conditions impact of non- CO2 GHGs on agricultural emissions

• Autorzy: Kolasa-Więcek A.

Warianty tytułu

PL

Zastosowanie metody Recursive Partitioning w ocenie wpływu warunków klimatycznych na rolnicze emisje gazów cieplarnianych innych niż CO2

• Języki publikacji: EN

Abstrakty

EN

Agricultural practices contribute to emissions of the greenhouse gases (GHGs) such a methan (CH4) and nitrous oxide (N2O). Their estimated share from agricultural sources is assessed at around 50% of CH4 and 60% of N2O emissions. The efforts made by the agricultural sector aim to limit and reduce emissions. Due to their significant share, all the complementary knowledge information concerning their reduction are highly precious. The paper proposes the use of neural modeling techniques and the summary of results by modeling based on a decision tree (Recursive Partitioning) to estimate the levels of methane and nitrous oxide emissions from agriculture under varying weather conditions in Poland. The obtained results support the hypothesis that neural model describing the effect of meteorological conditions on the CH4and N2O emissions is an appropriate tool for the assessment of the projected emission level.

PL

Praktyki rolnicze przyczyniają się do emisji gazów cieplarnianych (GGC), takich jak metan (CH4) i podtlenku azotu (N2O). Ich szacunkowy udział ze źródeł rolniczych oceniany jest na około 50% emisji CH4 i 60% emisji N2O. Wysiłki podejmowane przez sektor rolny mają na celu ograniczenie i redukcję ich emisji. Ze względu na ich znaczący udział, wszelkie informacje dopełniające wiedzę na temat możliwości ich redukcji są niezwykle cenne. W pracy zaproponowano wykorzystanie technik neuronowego modelowania oraz posumowania wyników z wykorzystaniem modelowania w oparciu o drzewo decyzyjne (Recursive Partitioning) do estymacji poziomu metanu i podtlenku azotu emitowanych z rolnictwa przy zmiennych warunkach meteorologicznych w Polsce. Uzyskane wyniki badań potwierdzają hipotezę, że model neuronowy, opisujący wpływ warunków meteorologicznych na emisję CH4 i N2O, jest właściwym instrumentem dla dokonania oceny prognozowania poziomu tej emisji.

Słowa kluczowe

EN

greenhouse gases; CH4; N2O; modeling; neural networks; decision tree; meteorological conditions

PL

gazy cieplarniane; CH4; N2O; modelowanie; sieci neuronowe; drzewo decyzyjne; warunki meteorologiczne

• Wydawca: Sieć Badawcza Łukasiewicz - Poznański Instytut Technologiczny
• Czasopismo: Journal of Research and Applications in Agricultural Engineering
• Rocznik: 2013
• Tom: Vol. 58, nr 1
• Strony: 96--101
• Opis fizyczny: Bibliogr. 31 poz., rys., tab.

Twórcy

autor

Kolasa-Więcek A.

• Opole University of Technology, Department of Economics and Regional Research, Faculty of Economy and Management Waryńskiego 4, 45-047 Opole

Bibliografia

• [1] Ball B.C., Scott A., Parker J.P.: Field N2O, CO2 and CH4 fluxes in relation to tillage. Compaction and soil quality in Scotland. Soil & Tillage Research, 53: 29-39, 1999.
• [2] Buntine W.L., Weingend A.S.: Bayesian back-propogation. Complex system, 5, 6: 603-643, 1991.
• [3] Caldeira K., Morgan M.G., Baldocci D., Brewer P.G., Chen C.T.A., Nabuurs G.J., Nakicenovic N., Robertson G.P.: A portfolio of carbon management options. In: The Global Carbon Cycle: Integrating Humans, Climate, and the Natural World, Eds. Field, C.B., Raupach M.R. Island Press, Washington, DC, 103-129, 2004.
• [4] Dose V., Menzel A.: Bayesian analysis of climate change impacts in phenology. Global Change Biology, 10, 2: 259-272, 2004.
• [5] Ellison A.M.. Bayesian inference in ecology. Ecology Latters, 7, 6: 509-2520, 2004.
• [6] Food and Agricultural Organization, 2003: World Agriculture: Towards 2015/2030. An FAO Perspective, FAO, Rome 2003.
• [7] Furrer R., Sain S.R., Nychka D., Meehl G.A:. Multivariate Bayesian Analysis in atmosphere – ocean general circulation models. Environmental and Ecological Statistics, 14, 3: 249-266, 2007.
• [8] Heping Z., Burton H.S.: Recursive Partitioning and Applications, Springer-Verlag Gmbh. 2010.
• [9] Heping Z.: Recursive Partitioning and Tree-based Methods. Springer Handbooks of Computational Statistics, 853-882, 2012.
• [10] IPCC. Radiative Forcing of Climate Change. The 1996 Report of the Scientific Assessment Working Group of IPCC Summary for Policy Makers. World Meteorology Organization. UN Environment Program, Geneva, Switzerland, 1996.
• [11] IPCC. Climate change 2001. The scientific basis–contribution of work group I to the third assessment report of IPCC. Cambridge University Press, Cambridge, 2001.
• [12] Lampinen J., Vehtari A.: Bayesian approach for neural networks-review and case studies, Neural Networks, 14: 257-274, 2001.
• [13] Mosier A., Kroeze C.: Potential impact on the global atmospheric N2O budget of the increased nitrogen input required to meet future global food demands. Chemosphere-Global Change Science, 2: 465-473, 2000.
• [14] Nazir N., Mir A.H., A.A. Khan A.A: Bayesian analysis of mixed effect models and its applications in agriculture, Electronic Journal of Applied Statistical Analysis, 4, 2: 164 – 171, 2011.
• [15] Neal R.: Bayesian Learning for Neural Networks, Springer – Verlag GnbH, 1996. A. Kolasa-Więcek „Journal of Research and Applications in Agricultural 101 Engineering” 2013, Vol. 58(1)
• [16] Neal R.: Flexible Bayesian Models on Neural Networks, Gaussian Processes and Mixtures v. 2004-11-10, University of Toronto, 2004.
• [17] Nelson L.M., Bloch D.A., Longstreth W.T. Jr., Shi H.: Recursive partitioning for the identification of disease risk subgroups: a case-control study of subarachnoid hemorrhage, Journal of Clinical Epidemiology, 51, 3: 199-209, 1998.
• [18] Pasyniuk P.: Reducing greenhouse gas emissions by replacing diesel by vegetable oils. Problems of Agricultural Engineering, 4: 79-89, 2010.
• [19] Sadoddin A., Shahabi M.: Agricultural drought management using a Bayesian decision model for rainfed wheat farmlands in east of Golestan Province, Iran, Workshop on metrics and methodologies of estimation of extreme climate event, UNESCO, Paris, 2010.
• [20] Smith P., Martino D., Cai Z., Gwary D., Janzen H., Kumar P., McCarl B., Ogle S., O’Mara F., Rice C., Scholes B., Sirotenko O.: Agriculture. In Climate Change 2007: Mitigation. Contribution of Working Group III to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change. Eds. B. Metz, O.R. Davidson, P.R. Bosch, R. Dave, L.A. Meyer, Cambridge University Press, Cambridge, United Kingdom and New York, NY, USA, 2007.
• [21] Song C.C., Zhang L.H., Wang Y.Y., Zhao Z.C.: Annual dynamics of CO2, CH4, N2O emissions from freshwater marshes and affected by nitrogen fertilization, Huan Jing Ke Xue, 27, 12: 2369-2375, 2006.
• [22] Strobl C., Malley J., Tutz G.: An introduction to recursive partitioning: rationale. Application. and characteristics of classification and regression trees. Bagging. and random forests. Psychological Methods, 14, 4: 323-48. 2009.
• [23] Su X., Tsai Ch., Wang H., Nickerson D.M., Li B.: Subgroup Analysis via Recursive Partitioning. Journal of Machine Learning Research, 10: 141-158, 2009.
• [24] Tukiendorf A.: Selected aspects of contemporary spatial epidemiology of cancer example in Opole province, Institute of Occupational Medicine named prof named J. Nofera, 2004, [in polish].
• [25] Tukiendorf M.: Neural Modeling of mixing of heterogeneous granular systems. Dissertations of Agricultural University in Lublin, 272, 2003, [in polish].
• [26] Ullah S., Frasier R., King L., Picotte-Anderson N., Moore T.R.: Potential fluxes of N2O and CH4 from soils of three forest types in Eastern Canada. Soil Biology and Biochemistry, 40, 986–994, 2008.
• [27] Unsitalo L.: Advantages and challenges of Bayesian networks in environmental modelling. Ecological Modelling, 203, 3-4: 2312-318, 2007.
• [28] United States Environmental Protection Agency (USEPA): Global Anthropogenic Non-CO2 Greenhouse Gas Emissions: 1990- 2020. EPA, 2006. Washington, http://www.epa.gov/nonco2/econinv/downloads/GlobalAnthroEmissionsReport.pdf [Accessed: 3.02.2013].
• [29] Whithers S.D.: Quantitative methods: Bayesian inference, Bayesian thinking, Progress in Human Geography, 26, 4: 553-566, 2002.
• [30] Zeileis A., Hothorn T., Hornik K.: Model-Based Recursive Partitioning. Journal of Computational and Graphical Statistics, 17, 2: 492-514. 2008.
• [31] United Nations Framework Convention on Climate Change: http://unfccc.int/di/DetailedByGas/Event.do?event=go [Accessed: 10.12.2012]