Integration of Sentinel-1 and Sentinel-2 Data with the G-SMOTE Technique for Boosting Land Cover Classification Accuracy

Hamid Ebrahimy,Omid Ghorbanzadeh,Bakhtiar Feizizadeh,Amin Naboureh,Jagannath Aryal

doi:10.3390/app112110309

Abstract

The importance of Land Cover (LC) classification is recognized by an increasing number of scholars who employ LC information in various applications (i.e., address global climate change and achieve sustainable development). However, studying the roles of balancing data, image integration, and performance of different machine learning algorithms in various landscapes has not received as much attention from scientists. Therefore, the present study investigates the performance of three frequently used Machine Learning (ML) algorithms, including Extreme Learning Machines (ELM), Support Vector Machines (SVM), and Random Forest (RF) in LC mapping at six different landscapes. Moreover, the Geometric Synthetic Minority Over-sampling Technique (G-SMOTE) was adopted to deal with the class imbalance problem. In this work, the time-series of Sentinel-1 and Sentinel-2 data were integrated to improve LC mapping accuracy, taking advantage of both data. Moreover, Support Vector Machine-Recursive Feature Elimination (SVM-RFE) was implemented to distinguish the most informative features. Based on the results, the RF integrated with G-SMOTE showed the best result for four landscapes (coastal, cropland, desert, and semi-arid). SVM integrated with G-SMOTE had the highest accuracy in the remaining two landscapes (plain and mountain). Applied ML algorithms showed good performances in various landscapes, ranging Overall Accuracy (OA) from 85% to 93% for RF, 83% to 94% for SVM, and 84% to 92% for ELM. The outcomes exhibit that although applying G-SMOTE may slightly decrease OA values, it generally boosts the results of LC classification accuracies in various landscapes, particularly for minority classes.

Highlights

This article is an open access articleLand cover (LC) data has great importance for different disciplines, such as biodiversity patterns [1], natural hazards studies, and CO2 emissions [4]
After analyzing the results of Support Vector Machines (SVM)-RFE to choose the most critical feature for each landscape, it was revealed that Normalized Difference Vegetation Index (NDVI), VV, and B12 bands were selected as prominent features in all six landscapes, which could confirm their importance in Land Cover (LC) classification
After analyzing the results of Support Vector Machine-Recursive Feature Elimination (SVM-RFE) to choose the most critical feature for each landscape, it was revealed that NDVI, VV, and B12 bands were selected as prominent features in all six landscapes, which could confirm their importance in LC classification [16]

Summary

Introduction

This article is an open access articleLand cover (LC) data has great importance for different disciplines, such as biodiversity patterns [1], natural hazards studies (i.e., landslides [2] and wildfire [3]), and CO2 emissions [4]. Toward providing data with better temporal and spatial resolutions have motivated scholars and scientists to study LC mapping widely. The tremendous attempts exerted in LC mapping, examining the roles of balancing data, image integration, and performance of different machine learning algorithms in various landscapes has not yet received much attention from scholars. The advent of Sentinel-1 and Sentinel-2, providing images with high spatial resolution, global coverage, and their free access, brings excellent opportunities for LC mapping. Abdi [6] integrated these images for LC mapping complex boreal landscapes. In another study, those images were integrated for LC mapping in Colombia [7]. It has been reported that incorporating time-series of these images can lead to more accurate and reliable LC maps compared to using them individually [10]

Methods

Results

Discussion

Conclusion