Gas concentration prediction by LSTM network combined with wavelet thresholding denoising and phase space reconstruction.

The Long Short-Term Memory neural network is a specialized architecture designed for handling time series data, extensively applied in the field of predicting gas concentrations. In the harsh conditions prevalent in coal mines, the time series data of gas concentrations collected by sensors are susceptible to noise interference. Directly inputting such noisy data into a neural network for training would significantly reduce predictive accuracy and lead to deviations from the actual values.

Improved Combination Weighted Prediction Model of Aquifer Water Abundance Based on a Cloud Model.

The sandstone aquifer is an important underground water storage space, and the study of its water abundance is of great significance to ensure the safety of underground engineering and to explore the occurrence mechanism of groundwater sources. Based on the correlation between geological characteristics and aquifer water abundance, this paper proposed an aquifer water abundance prediction model based on a cloud model that improved combination weighting. The model took the roof sandstone aquifer of the Qingshuiying Coalfield as an example and selected five basic geological indicators that are closely related to the water-rich influence degree of the aquifer as evaluation indicators.