Environmental Data Analysis
Coursework 2021-2022 [50% of the module’s mark]
环境数据分析代写 In the excel files Data_GEAR.xlsx and Data_ERA5.xlsx you are given precipitation time series at the daily time scale for 20 locations in the
In the excel files Data_GEAR.xlsx and Data_ERA5.xlsx you are given precipitation time series at the daily time scale for 20 locations in the United Kingdom. The sites’ coordinates can be found in the file Sites.xlsx. The origin of the time series products is (i) the GEAR data set from the Centre of ecology and hydrology and (ii) the precipitation data set of the reanalysis product ERA5-Land.
Using the data, you will perform the following tasks: 环境数据分析代写
1.For all sites, compute descriptive statistics for both data sets and report them in a tabular format.
2.Fit the lognormal and gamma distribution to all time series, neglecting zero values, using all methods described in the lecture notes, and report the fit parameters.
3.For Site #1, plot the normalized histogram of non-zero precipitation and the associated pdfs of the fitted gamma and lognormal distributions.
4.For Site #1, create a q-q plot between the CEH-GEAR data and the ERA5-Land data.
5.For Site #1, create a scatter plot between the CEH-GEAR data and the ERA5-Land data.
6.For all sites aggregate the time series at the annual scale.
7.For Site #1, use the ordinary least squares method to fit a linear model between the CEH-GEAR annual precipitation data and the ERA5-Land annual precipitation data.
8.For all sites, assuming that at the annual scale rainfall is normally distributed, test if the mean values of both products are the same.
9.Perform LASSO and ridge regression using MATLAB’s built-in functionalities (functions lasso, ridge) considering as the independent variable the annual precipitation from the CEH-GEAR data from station #1 and predictors the annual rainfall from all other sites from the CEH-GEAR data. 环境数据分析代写
10.Perform a 1-way ANOVA for the annual precipitation values for the ERA5-Land product, for all sites located east of 2oW and south of 52oN and report the ANOVA table. Write your own code and compare it with the built-in function anova1.
11.For the CEH GEAR product perform a PCA and create the biplot and scree plot. Write your own code and compare it with the built-in MATLAB function pca.
Provide all your MATLAB .m files in a zipped directory. Accompany your code with a short report in a .pdf format where you report all tables and figures. Do not use .mlx files.
Marking criteria 环境数据分析代写
- Code correctness [50/100]
- Code clarity [10/100]
- Code organization [10/100]
- Code efficiency [10/100]
- Quality of figures [10/100]
- Report quality [10/100]
