I am working with simulated univariate sequential data and the goal is to forecast that data. I was wondering which model CNN-LSTM or LSTM is better for predicting univariate time series data. Both models are used for time series forecasting, but I can't find information about how well CNN-LSTM actually is for forecasting univariate data. I mainly find information about multivariate forecasting, for example in this paper.
LSTM models are for sure options to model univariate time series like they mention in this post:
LSTMs can be used to model univariate time series forecasting problems. These are problems comprised of a single series of observations and a model is required to learn from the series of past observations to predict the next value in the sequence.
Also, like in this post they mention that LSTM is a good option for univariate data analysis because of the feedback connections:
Unlike any feedforward neural network, LSTM has feedback connections. Therefore, it can predict values for point data and can predict sequential data like weather, stock market data, or work with audio or video data, which is considered sequential data.
In this post (Is it a good idea to use CNN to classify 1D signal?) they mention that CNN is a possible approach for 1D signals:
I guess that by 1D signal you mean time-series data, where you assume temporal dependence between the values. In such cases convolutional neural networks (CNN) are one of the possible approaches.
But I was wondering, is CNN-LSTM or just LSTM better for forecasting univariate time series data, or are they both good options?
