我有一个海洋表面温度时间序列，我想计算热带地区(30.0N到30S)节点之间的(Pearson)相关系数。在时间序列中，土地信息被掩盖。我不知道在相关性计算中如何处理蒙面数据。请帮助。我在这里使用的数据是在这个链接https://drive.google.com/file/d/1SVKQ4uBDEZOuN7_ftd5tqpF9_NGKY3pZ/view?usp=sharing

我尝试了以下代码，这没有工作:

 temp5 = 'sst.day.mean.1983。fh5 =数据集(temp5, mode = 'r') sst5 = fh5。变量['sst'][:365] time = fh5。变量['time'][:] lat = fh5。变量['lat'][210:510][::35] #热带纬度lon = fh5。变量['lon'][::45] mar_05=[] for I in range(len(lat)): for j in range(len(lon)): for m in range(len(lat)): for n in range(len(lon)): mar_05.append(np。corrcoef (sst5 [59:90, i, j], sst5 [59:90, m, n] [0,1])) df = pd。DataFrame(data = mar_05) 

参考这张图片…:

…from 这条最近的推文，我想知道地中海地区在多大程度上受到其南部大沙漠地区的影响?

“受影响”，这里的意思是撒哈拉和马耳他(例如)之间的温度测量之间的相关性高于马耳他和冰岛。我认为测量值是相关的，但这种相关性随着距离到某个较低值(但不是零)的距离而减小。这里的问题是，这种相关性多快会趋向于其较低的值，撒哈拉沙漠的“质心”(?)与地中海各点之间的距离是否足够短，以至于可以被认为是一种“影响”?< / p >

From my yearly flow, I have to generate monthly streamflows. In the end, instead of 50 streamflow realizations, each one representing an annual flow; I'll have 600 streamflow realizations, each representing a monthly stream flow.

Now, to get from annual to monthly stream flow, I will need a correlation matrix.

I could simply estimate the monthly correlation from January to December by calculating the correlation among monthly streamflows from a set of historical streamflow.

One could say that the physical aspects involving the (auto)correlation are implicit in the data itself. However, the data I have for this gauge station - as for any other - is only one realization of the stochastic process from which the observed streamflows were generated.

How, then, could I enrich this monthly (auto)correlation with physical concepts stemming from the river where the gauge station is located? I should add that my question also applies to cross-correlation between two different time-series. How, in that case, could I enrich the cross-correlation matrix employing physical aspects between 2 observed time-series?

However, we know that correlation does not necessarily imply causation, mainly for two factors: there may be external factors acting on both series or spurious coincidences may also happen.

What are possible and comprehensible ways, that have been used and are possible to reproduce in the Earth Sciences (Meteorology, Oceanography, Clmatology...), to go further and make a point to show that correlation does imply causation in some situations?

EDIT to make it more specific:

Imagine correlation is found between sea surface temperature (SST) in some region and rainfall in another. How to test if the variability of the two series are not being externally forced by a third party?

Thank you.

Is it enough with a simple correlation analysis or is there's another approach to make the analysis more robust?

thanks a lot in advance for your answers!

On the European side, two orogenies are recognised: the Caledonian and Variscan (or Hercynian). On the American side the Appalachians are also recognised to be made up of multiple orogenies, eg. the Taconic and Allegheny.

A parallel could be drawn with the present day Tethyan Belt - especially the Mediterranean length. Here we don't see one big mountain building episode but many as each sub-continent or large island is accreted onto Europe. Similarly, Pangaea was not formed in one big orogeny but multiple as sub-continents such as Avalonia were accreted on to what is now North America.

Can each orogenic episode on the European side be correlated with an orogenic episode on the North American side? I.e. having two names for the same orogeny?

Are correlations possible at a finer scale? For example the Caledonides in Scotland are marked by some very prominent ancient faults (Great Glen, Moine, and Highland Boundary Faults). The Appalachians also have some large fault systems. Can any of these be correlated across the Atlantic? Can specific sedimentary sequences be correlated? (I realise that big picture sequences in the late Palaeozoic are broadly similar, e.g. Permian Aeolian Sandstones, Carboniferous Deltaics & Coal, etc)

One way to bring down costs a lot, is to combine on the same grid, regions where the wind over a period of weeks to years, are negatively correlated: that is to say, it helps if we can easily identify pairs of regions where low winds in one region tend to happen at the same time as high winds in the other.

At a scale of days, sufficiently distant regions are uncorrelated. At a scale of weeks to years, a set of correlations of reanalysis data (e.g. ECMWF or CFSR) suggests that there are pairs of regions which do exhibit negatively correlated wind, either seasonally or annually.

Is there a reliable way to identify such combinations of regions?