Pan Evaporation Prediction Using LSTM Models Based on PCA Factor Reduction and Firefly Optimization Algorithm

Evaporation is an important part of the moisture exchange between earth and air. Understanding trend pan evaporation can help to reveal status in actual evaporation, which very useful for allocation regional water resources. However, LSTM has become a mainstream algorithm predicting there are two issues worth considering. One issue how automatically find optimal hyperparameters, other eliminate correlation prediction factors improve performance. To address issues, paper proposes models based on PCA factor reduction firefly optimization algorithm. In proposed model, factors. Xiangjiang River Basin, Basin China’s resource management, selected as study area, experimental results evaluated by root mean square error (RMSE) coefficient determination (R2). The show that successfully predict daily area.