Improvement in the Accuracy of the Postclassification of Land Use and Land Cover Using Landsat 8 Data Based on the Majority of Segment-Based Filtering Approach

Abstract

Improvement in the accuracy of the postclassification of land use and land cover (LULC) is important to fulfil the need for the rapid mapping of LULC that can describe the changing conditions of phenomena resulting from interactions between humans and the environment. This study proposes the majority of segment-based filtering (MaSegFil) as an approach that can be used for spatial filters of supervised digital classification results. Three digital classification approaches, namely, maximum likelihood (ML), random forest (RF), and the support vector machine (SVM), were applied to test the improvement in the accuracy of LULC postclassification using the MaSegFil approach, based on annual cloud-free Landsat 8 satellite imagery data from 2019. The results of the accuracy assessment for the ML, RF, and SVM classifications before implementing the MaSegFil approach were 73.6%, 77.7%, and 77.5%, respectively. In addition, after using this approach, which was able to reduce pixel noise from the results of the ML, RF, and SVM classifications, there were increases in the accuracy of 81.7%, 85.2%, and 84.3%, respectively. Furthermore, the method that has the best accuracy RF classifier was applied to several national priority watershed locations in Indonesia. The results show that the use of the MaSegFil approach implemented on these watersheds to classify LULC had a variation in overall accuracy ranging from 83.28% to 89.76% and an accuracy improvement of 6.41% to 15.83%.

Monitoring land cover change and its estimated carbon loss in the Nusantara capital city Indonesia on high-resolution planet satellite imagery

“…To counter the errors arising from the salt and pepper phenomenon, we employ Majority of Segment-Based Filtering (MaSegFil). Demonstrating its efficacy, MaSegFil enhances the accuracy of land use classification results, notably in the Citarum, Ciliwung, and Cisadane river basin areas 46 . Operating by infusing the class attribute within each segment's clustering outcome with the majority class derived from the classification results within that segment, MaSegFil effectively refines the data.…”

Perbandingan algoritma classification and regression tree (cart) dan random forest (rf) untuk klasifikasi penggunaan lahan pada google earth engine

“…Terdapat beberapa metode klasifikasi yang menggunakan algoritma pohon keputusan diantaranya adalah Classification and Regression Tree (CART) dan Random Forest (RF) classifier. Perbedaan metode klasifikasi yang digunakan dalam mengidentifikasi penggunaan lahan memungkinkan terjadinya perbedaan akurasi dari klasifikasi yang dihasilkan (Aldiansyah & Saputra, 2022;Yulianto, Nugroho, & Suwarsono, 2021). Sementara itu, perbedaan data spasial juga berpengaruh terhadap akurasi hasil klasifikasi yang ditunjukkan dengan nilai Overall Accuracy (OA) dan Kappa Coefficient (Basheer et al, 2022).…”

The use of texture analysis and band transformation on multispectral imagery to map open-pit mines using machine learning

“…Each tree's decision is made by referring to the provided training samples. This algorithm offers reasonable accuracy for land cover classification [11,[22][23][24][25].…”