# Using LSTM model to train spatial inputs

I have an $$x$$-$$y$$ plane, inside that plane I have 9 paths $$(p_1, p_2, \dots, p_3)$$. Each path is classified into one of the three classes $$(c_1, c_2, c_3)$$. Each path has 100 coordinates points i.e $$((x_1, y_1),(x_2, y_2), \dots, (x_n, y_n))$$. Totally I have 1800 input coordinate points. Now I am interested in training the LSTM model in such a way that if I feed some test path $$p_{10}$$, the model should be supposed to predict which class it belongs to. This is my problem definition. Regarding this, I have some questions

1. First of all, is it necessary to use LSTM models to obtain a solution?
2. Are there any other simple models to attain a solution to this problem?
3. I did some literature surveys for this kind of problem using LSTM, they are having time has one of the parameters along with $$(x_1, y_1, t_1)$$.

The paper I have read is "A Single-Shot Approach Using an LSTM for Moving Object Path Prediction".

I am a beginner to sequence model neural networks. A link or examples to similar works is very much beneficial.