Machine Learning Models Improve The Prediction Of Groundwater Depth In The Ningxia Area Of China

A study conducted by Professor Sun Bo and colleagues found that two hybrid machine learning models, MH-CNN-LSTM and MH-CNN-GRU, have great potential in predicting groundwater depth in the Ningxia area. The models were compared to a traditional statistical model and were further enhanced with the use of the dung beetle optimization algorithm. The results showed that the hybrid models outperformed the traditional model and the use of the improved DBO algorithm further improved the accuracy of the predictions.