Prediction of Leachate Generation in a Landfill Using Artificial Neural Networks

作     者：Samin Tohru Furuichi Kiasei Ishhi Enri Damanhuri Suprihanto Notodarmodjo Kuntjoro Adji Sidarta 

作者机构：Department of Civil Engineering University of Muhammadiyah Malang East Java 062-65144 Indonesia School of Engineering Hokkaido University Sapporo 060-8628 Japan Study Program of Environmental Engineering lnstitut Teknologi Bandung West Java 062-40116 Indonesia Study Program of Mathematic Institut Teknologi Bandung West Java 062-40116 Indonesia 

出 版 物：《Journal of Environmental Science and Engineering(B)》 (环境科学与工程（B）)

年 卷 期：2012年第1卷第11期

页      面：1233-1238页

学科分类：12[管理学] 083002[工学-环境工程] 0830[工学-环境科学与工程（可授工学、理学、农学学位）] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Artificial neural network back-propagation leachate neurons landfills. 

摘      要：One of the problems encountered in the operation of a leachate treatment in a landfill is the quantity of the fluctuating leachate. Therefore, information on the precise prediction about the quantity of leachate produced in a landfill is required. This information can be obtained by using an ANN （artificial neural networks） model. In this study, a prediction on a leachate generation for a period of 15 days was made. The input for the ANN model consists of data such as rainfall, temperature, humidity, duration of solar radiation, and the landfill characteristics, while the output is the leachate landfills production in Minamiashigara, Japan. The ANN algorithm uses a BP （back propagation） with LM （Levenberg-Marquadrt） training type. By using the input-output data pairs, the training of ANN model was conducted in order to obtain the values of the weights that describe the relationship between the input-output data. Furthermore, with the trained ANN model, the prediction of leachate generation for a period of 15 days was made. The study result shows that the prediction accuracy ofleachate generation of ANN-C model, with a correlation coefficient （r） of 0.924, is quite good. Thus, the prediction of leachate generation using artificial neural network model can be recommended for predicting leachate generation in the future. In this study, a prediction on a leachate generation for a period of 15 days was made. The quantity of leachate generation in a landfill can be obtained by using ANN for future periods. By entering data for future periods （t ＋1） in ANN models, the leachate generation for the period （t ＋1） can be predicted.