|
|
Sharif, B., Olesen, J. E., & Schelde, K. (2014). Statistical learning approach for modelling the effects of climate change on oilseed rape yield. FACCE MACSUR Mid-term Scientific Conference, 3(S) Sassari, Italy.
Abstract: Statistical learning is a fairly new term referring to a set of supervised and unsupervised modelling and prediction techniques. It is based on traditional statistics but has been highly enhanced inspired by developments in machine learning and data mining. The main focus of statistical learning is to estimate the functions that quantify relations between several parameters and observed responses. These functions are further used for prediction, inference or a combination of both. For a particular case of quantitative responses, regularization techniques in regression are developed to overcome the weaknesses of ordinary least square (OLS) regression in prediction. These new shrinkage methods outperform OLS for prediction, especially in large datasets. In this study, a large dataset of field experiments on winter oilseed rape in Denmark for 22 years (1992 to 2013) was collected. Biweekly climatic data along with sowing date, harvest date, soil type and previous crop are considered as the explanatory variables. Yield of winter oilseed rape is considered as response variable. LASSO and Elastic Nets are the regularization techniques used to estimate the functions. Hold-one-out cross validation method for testing the prediction power reveals that these techniques are much useful in both prediction and inference. Since these techniques are included in recent versions of some software packages (e.g. R), they can be easily implemented by users at any level. The estimated function (model) is further used to predict the oilseed rape yield responses to climate change for several scenarios using representative weather data produced by a weather generator.
|
|
|
|
Olesen, J. E., Porter, J. R., & Christensen, J. H. (2014). Centre for Regional change in the Earth System. FACCE MACSUR Mid-term Scientific Conference, 3(S) Sassari, Italy.
Abstract: Centre for Regionalchange in the Earth System (CRES, cres-centre.net) is funded by the DanishStrategic Research Council for the period 2009-2014 and is coordinated by theDanish Meteorological Institute. CRES has established a coordinated researcheffort aiming to improve societal preparedness for climate change, inparticular for Denmark. The overall objective of CRES is to extend knowledge ofand reduce the uncertainties surrounding regional climate change and itsimpacts and thereby support future climate change adaptation and mitigationpolicies. Some of the objectives that also have large synergies with theeffects in the CropM theme of MACSUR are a) to reduce uncertainty surroundingregional climate change and its impacts for the period 2020-2050 by improvingmodel formulation and process understanding; b) identify key changes andtipping points in the regional hydrological system, agriculture, freshwater andestuarine ecosystems caused by changes in seasonality, dynamics and extremeevents of precipitation, droughts, heat waves and sea level rise; c) quantifyconfidence and uncertainties in predictions of future regional climate and itsimpacts, by improving the statistical methodology and substance and byintegrating interdisciplinary risk analyses; d) interpret these results inrelation to risk management approaches for climate change adaptation andmitigation. Studies in CRES of particular interest to MACSUR include a)Estimation on generic crop model uncertainties in projection of climate changeimpacts on wheat year, b) Assessment of uncertainties in projected effects onwater balance, crop productivity and nitrate leaching of changes in land use,climate and assessment models.
|
|
|
|
Ewert, F., Rötter, R. P., Bindi, M., Webber, H., Trnka, M., Kersebaum, K., et al. (2015). Crop modelling for integrated assessment of risk to food production from climate change (Vol. 6).
Abstract: The complexity of risks posed by climate change and possible adaptations for crop production has called for integrated assessment and modelling (IAM) approaches linking biophysical and economic models. This paper attempts to provide an overview of the present state of crop modelling to assess climate change risks to food production and to which extent crop models comply with IAM demands. Considerable progress has been made in modelling effects of climate variables, where crop models best satisfy IAM demands. Demands are partly satisfied for simulating commonly required assessment variables. However, progress on the number of simulated crops, uncertainty propagation related to model parameters and structure, adaptations and scaling are less advanced and lagging behind IAM demands. The limitations are considered substantial and apply to a different extent to all crop models. Overcoming these limitations will require joint efforts, and consideration of novel modelling approaches. No Label
|
|
|
|
Trnka, M., Kersebaum, K., Christian,, & Olesen, J. E. (2015). Description of the compiled experimental data available in the MACSUR CropM database (Vol. 6).
Abstract: The input data necessary for crop model simulations and data for their calibration/validation (and thus requirements for observations and measurements in suitable experiments) have been collected through out the project together with data for additional analysis of abiotic factors influencing yields. A list of possible dataset was collated in the first year of project however very few of the existing datasets were found usable for the crop model simulation as they fell short of the requirements defined in the part 2.3. However database has been populated as planned with the results of the ongoing MACSUR studies and will serve in the same way for the MACSUR 2 duration. No Label
|
|
|
|
Rötter, R. P., Asseng, S., Ewert, F., Rosenzweig, C., Jones, J. W., Hatfield, J. L., et al. (2013). Quantifying Uncertainties in Modeling Crop Water Use under Climate Change..
|
|
