Performance Evaluation of Sentinel-2 and Landsat 8 OLI Data for Land Cover/Use Classification Using a Comparison between Machine Learning Algorithms

Abstract

With the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating and managing changes in land cover as created by changes to ecosystem and land use. The main objective of our study is to evaluate the performance of Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), Minimum Distance (MD), and Mahalanobis (MH) algorithms and compare them in order to generate a LULC map using data from Sentinel 2 and Landsat 8 satellites. Further, we also investigate the effect of a penalty parameter on SVM results. Our study uses different kernel functions and hidden layers for SVM and ANN algorithms, respectively. We generated the training and validation datasets from Google Earth images and GPS data prior to pre-processing satellite data. In the next phase, we classified the images using training data and algorithms. Ultimately, to evaluate outcomes, we used the validation data to generate a confusion matrix of the classified images. Our results showed that with optimal tuning parameters, the SVM classifier yielded the highest overall accuracy (OA) of 94%, performing better for both satellite data compared to other methods. In addition, for our scenes, Sentinel 2 date was slightly more accurate compared to Landsat 8. The parametric algorithms MD and MLC provided the lowest accuracy of 80.85% and 74.68% for the data from Sentinel 2 and Landsat 8. In contrast, our evaluation using the SVM tuning parameters showed that the linear kernel with the penalty parameter 150 for Sentinel 2 and the penalty parameter 200 for Landsat 8 yielded the highest accuracies. Further, ANN classification showed that increasing the hidden layers drastically reduces classification accuracy for both datasets, reducing zero for three hidden layers.

Galactic component mapping of galaxy UGC 2885 by machine learning classification

“…The combined power of several types of information is optimal for galaxy component classification within digital imagery. The success of the SVM and RF models and relatively poor performance of MLC is expected and agrees with results from other recent studies comparing machine learning algorithms in both remote sensing and astronomy (Ghayour et al, 2021;Wang et al, 2021).…”

Methodology for Precision Land Use Mapping towards Sustainable Urbanized Land Development

“…The study demonstrated that high-precision maps could be generated based exclusively on free multi-temporal satellite images. Machine learning algorithms promote the generation of land-use/land cover data based on satellite images [ 24 , 25 , 26 , 27 , 28 ]. Cloud computing platforms such as Google Earth Engine enable semi-automatic analyses of urban land-based on remote sensing data acquired from Sentinel-2 and Landsat satellites [ 29 ].…”

“…The results of land-use studies are highly influenced by the quality of data from various sources. Advanced remote sensing techniques and the growing availability of satellite images that facilitate land-use/land-cover mapping play an important role in land-use planning and land management [ 24 , 35 , 36 ]. Data from public registers, surveys, geo-surveys (social participation projects), points-of-interest (POI), social media, geotagged images and mobile data are used in addition to remote sensing data [ 21 , 22 , 37 , 38 , 39 , 40 ].…”

Land Resource Use Classification Using Deep Learning in Ecological Remote Sensing Images

“…The improvement of most classification algorithms can improve the accuracy of land resources classification, but still, there are problems such as too large processing scale, complex calculation, and easy to fall into the minimum. In particular, it is difficult to meet the needs of current applications in classification efficiency and speed and cannot well solve many problems of high spectral remote sensing images for land resources [ 19 ]. Therefore, this study proposes a land resource use classification method using deep learning in ecological remote sensing images.…”