Mapping Tillage Practices Using Extreme Learning Machine and Remote Sensing Images

Overview

Conservational tillage practices can increase crop yields while reducing the negative impact of agriculture to the environment. Implementation of this technique requires efficient mapping method so that the fields can be monitored. An improved classifier based on extreme learning machine (ELM) is proposed here to map agricultural tillage practices from airborne hyperspectral remote sensing imagery. The kernel version, called kernel ELM (KELM), is implemented due to its powerfulness. To utilize spatial information of an image, a spatial convolution filter is adopted to generate spatial-spectral features of a hyperspectral pixel by incorporating its surrounding pixels, which are the actual inputs to the KELM. The KELM can be adaptively modified when new training samples are added without completely re-training the model. Experimental results using airborne hyperspectral images demonstrate that the KELM can outperform other classic methods, such as support vector machine and random forest with lower computational cost, a larger window size such as 7×7 can be used for large homogeneous agricultural fields, and the adaptive KELM can further improve its efficiency.

Competition history

• AJAS 2020 Category not listed

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• AJAS None projects
• Every AJAS 2020 project