Multilayer Perceptron Neural Network for Surface Water Extraction in Landsat 8 OLI Satellite Images

Huichan Liu,Yan Peng,Wei Jiang,Guojin He,Kenan Lv,Guizhou Wang,Tengfei Long,Yuan Ni

doi:10.3390/rs10050755

Abstract

Surface water mapping is essential for monitoring climate change, water resources, ecosystem services and the hydrological cycle. In this study, we adopt a multilayer perceptron (MLP) neural network to identify surface water in Landsat 8 satellite images. To evaluate the performance of the proposed method when extracting surface water, eight images of typical regions are collected, and a water index and support vector machine are employed for comparison. Through visual inspection and a quantitative index, the performance of the proposed algorithm in terms of the entire scene classification, various surface water types and noise suppression is comprehensively compared with those of the water index and support vector machine. Moreover, band optimization, image preprocessing and a training sample for the proposed algorithm are analyzed and discussed. We find that (1) based on the quantitative evaluation, the performance of the surface water extraction for the entire scene when using the MLP is better than that when using the water index or support vector machine. The overall accuracy of the MLP ranges from 98.25–100%, and the kappa coefficients of the MLP range from 0.965–1. (2) The MLP can precisely extract various surface water types and effectively suppress noise caused by shadows and ice/snow. (3) The 1–7-band composite provides a better band optimization strategy for the proposed algorithm, and image preprocessing and high-quality training samples can benefit from the accuracy of the classification. In future studies, the automation and universality of the proposed algorithm can be further enhanced with the generation of training samples based on newly-released global surface water products. Therefore, this method has the potential to map surface water based on Landsat series images or other high-resolution images and can be implemented for global surface water mapping, which will help us better understand our changing planet.

Highlights

Water is the foundation that supports the survival of various biological activities in nature and is the basis for the production, life and development of social civilization [1,2]
The water index method is a popular method for highlighting surface water by establishing a water index, such as the normalized difference water index (NDWI) [20], the modified normalized difference water index (MNDWI) [21] and the automated water extraction index (AWEI) [22]
Many detailed surface water bodies are not identified with the water index and the support vector machine in Region c and Region e

Summary

Introduction

Water is the foundation that supports the survival of various biological activities in nature and is the basis for the production, life and development of social civilization [1,2]. The machine learning method is used to select tremendous amounts of training samples to identify surface water using different intelligent classifiers, including maximum likelihoods (MLs) [25], support vector machines (SVMs) [30], decision trees (DTs) [31], neural networks (NNs) [32] and constraint energy minimizations (CEMs) [33]. These methods are automatic, efficient and require less manual labor [15]. The machine learning method promotes global surface water mapping, there are still challenges regarding algorithm complexity and high-quality training samples [15]

Objectives

Methods

Results

Discussion

Conclusion