Nonlinear regression in environmental sciences using extreme learning machines: A comparative evaluation |
| |
| Affiliation: | 1. Department of Earth, Ocean and Atmospheric Sciences, University of British Columbia, Vancouver, BC, Canada;2. Pacific Climate Impacts Consortium, University of Victoria, Victoria, BC, Canada;1. Chair of Forest Inventory and Remote Sensing, Georg-August-Universität Göttingen, D-37077 Göttingen, Germany;2. Selviculture and Forest Management Department, CIFOR-INIA, E-28040 Madrid, Spain;1. Dept. of Computer Architecture, University of Granada, Spain;2. Water Research Institute, University of Granada, Spain;3. Dept. of Civil Engineering, University of Granada, Spain;4. Research Center for Information and Communications Technologies, University of Granada (CITIC), Spain;1. USDA Agricultural Research Service, Grazinglands Research Laboratory, El Reno, OK, 73036, USA;2. USDA Agricultural Research Service, Conservation and Production Research Laboratory, Bushland, TX, 79012, USA;3. USDA Agricultural Research Service, Grassland Soil and Water Research Laboratory, Temple, TX, 76502, USA;4. Texas A&M, Agriculture and Life Sciences, Spatial Science Laboratory, College Station, TX, 77843, USA;1. School of Civil and Environmental Engineering, Cornell University, Ithaca, NY, USA;2. Department of Civil Engineering, Indian Institute of Technology Hyderabad, Yeddumailaram, India;3. Department of Geosciences, The Pennsylvania State University, University Park, PA, USA;4. Department of Engineering and Public Policy, Carnegie Mellon University, Pittsburgh, PA, USA;5. Earth and Environmental Systems Institute, The Pennsylvania State University, University Park, PA, USA |
| |
| Abstract: | The extreme learning machine (ELM), a single-hidden layer feedforward neural network algorithm, was tested on nine environmental regression problems. The prediction accuracy and computational speed of the ensemble ELM were evaluated against multiple linear regression (MLR) and three nonlinear machine learning (ML) techniques – artificial neural network (ANN), support vector regression and random forest (RF). Simple automated algorithms were used to estimate the parameters (e.g. number of hidden neurons) needed for model training. Scaling the range of the random weights in ELM improved its performance. Excluding large datasets (with large number of cases and predictors), ELM tended to be the fastest among the nonlinear models. For large datasets, RF tended to be the fastest. ANN and ELM had similar skills, but ELM was much faster than ANN except for large datasets. Generally, the tested ML techniques outperformed MLR, but no single method was best for all the nine datasets. |
| |
| Keywords: | Extreme learning machines Support vector machine Artificial neural network Regression Environmental science Machine learning |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
