Applying a BP Neural Network Approach to the Evolution Stage Classification of China Rift Lakes

Abstract

Abstract-The evolution stage classification which contains adolescence, adulthood, and old age of China rift lakes was constructed by using BP neural network model. In this paper, the model was applied to eleven lakes from Yunnan Plateau Lakes region and the middle and lower reaches of the Yangtze River plain. Through the selection of training samples, test samples and optimal number of hidden layer nodes to determine, the precision of BP neural network classification is supposed suitable for evolution stage classification of rift lakes. According to the classification results, dianchi lake is an old age lake, erhai lake, chenghai lake, xingyun lake, yilong lake, qilu lake, yangzong lake and chaohu lake are all in adulthood, and fuxian lake, lugu lake and poyang lake are in adolescence.

GNSS-R Soil Moisture Retrieval Model Based on Elman Neural Network

“…Artificial intelligence algorithms such as machine learning are becoming increasingly popular for remote sensing applications. They can build nonlinear relationships between data inputs and outputs and build complex regression models [17][18][19]. The Elman neural network is a representative dynamic recurrent neural network, which adds a takeover layer based on the feed-forward neural network.…”