Multiple time series network training with LSTM

Hi there,

I would like to ask several questions.

How Can I input several time series dataset to train LSTM network? I would like to make the network storonger with many samples.

For example, I have 4 defferent time series water balance data from Apr to Sep, 2015, 2016, 2017, 2018 and corresponded dataset as well.

but, I do not know how I express those data in cell matrix together.

Thank you.