Research on Settlement Prediction of Small Water Conservancy Project based on ELM Model Optimized by Genetic Algorithm

To find suitable for small water conservancy engineering standard method prediction of subsidence. This paper based on the genetic algorithm GA optimization extreme learning machine, three different ELM model activation function. From this, six computational models are obtained. According to input groundwater dynamic changes, precipitation, temperature and soil four indicators two kinds combinations, a total 12 input. It’s concluded that optimal settlement model, results showed that: Ga-ELM sin shows high accuracy, can improve calculation accuracy model. Groundwater dynamics is main factor affecting settlement.