{"id":317,"date":"2021-12-10T11:35:01","date_gmt":"2021-12-10T11:35:01","guid":{"rendered":"https:\/\/els-journal.net\/wp\/about\/"},"modified":"2022-02-02T20:02:18","modified_gmt":"2022-02-02T20:02:18","slug":"25202-prediction-model-of-soil-electrical-conductivity-based-on-elm-optimized-by-bald-eagle-search-algorithm","status":"publish","type":"page","link":"https:\/\/els-journal.net\/wp\/?page_id=317","title":{"rendered":"25202 Prediction Model of Soil Electrical Conductivity Based on ELM Optimized by Bald Eagle Search Algorithm"},"content":{"rendered":"\n\n\n

Vol. 25, No. 2 – December 2021<\/h3>\n

Prediction Model of Soil Electrical Conductivity\nBased on ELM Optimized by Bald Eagle\nSearch Algorithm<\/h3>\n

https:\/\/doi.org\/10.53314\/ELS2125050H<\/h5>\n
Ying Huang, Hao Jiang, Weixing Wang and Daozong Sun<\/h5>\n
Abstract<\/b><\/h5>\n
Soil electrical conductivity is one of the indispens-\nable and important parameters in fine agriculture management,\nand a suitable soil electrical conductivity can promote good plant\ngrowth. Prediction model of soil electrical conductivity is con-\nstructed to effectively obtain the conductivity values of soil, which\ncan provide a reference basis for irrigation and fertilization man-\nagement and prediction evaluation in fine agriculture. Prediction\nmodel of soil electrical conductivity based on extreme learning\nmachine (ELM) optimized by bald eagle search (BES) algorithm is\nproposed in this paper. In the prediction model, the input weights\nand bias values of the ELM network were optimized using the BES\nalgorithm, and the performance of the model was evaluated with\nparameters such as mean square error (MSE), coefficient of de-\ntermination (R 2 ). Also, the correlations of parameters such as soil\ntemperature, moisture content, pH, and water potential in the soil\nconductivity prediction model were determined using the explor-\natory data analysis (EDA) and HeatMap heat map tools. Finally,\nthe proposed model was compared with back propagation neural\nnetwork (BP), radial basis function networks (RBF), support vec-\ntor machine (SVM), gated recurrent neural network (GRNN), long\nshort-term memory (LSTM), particle swarm algorithm (PSO) op-\ntimization ELM, genetic algorithm (GA) optimized ELM predic-\ntion model. The experimental results showed that MSE, R 2 of the\nproposed model are 4.09 and 0.941, which are better than the other\nmodels. Also the results verified the effectiveness of the proposed\nmethod, which is a feasible prediction method to guide the irriga-\ntion and fertilization management in fine agriculture, because of\nits good prediction effect on soil conductivity.<\/h5>\n
Full text: <\/a><\/h5>\n\n\n\n\n\"cited<\/a>\n\n\n\n\nGoogle Scholar Citations <\/a>\n\n\n\n\n
<\/span> <\/center>