Deep learning time series forecasting: use LSTM algorithm to build a time series univariate model to predict temperature & code implementation

Deep learning time series forecasting: use LSTM algorithm to build a time series univariate model to predict temperature & code implementation

As people's demand for weather is getting higher and higher, the accuracy of weather forecast has become the focus of people's concern. Traditional weather prediction methods often need to analyze and calculate based on a large amount of historical data, and then make predictions through corresponding models. The deep learning algorithm can directly predict future values ​​by learning historical data, which has great advantages.

This article will introduce how to use the LSTM algorithm to build a time series univariate model and use the model to predict the temperature. Here is the code to implement the process:

import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, LSTM
from sklearn.preprocessing import MinMaxScaler