Evaluation of tree-base data mining algorithms in land used/land cover mapping in a semi-arid environment through Landsat 8 OLI image; Shiraz, Iran

Abstract

Land Use Land Cover (LULC) mapping has been used in different environmental applications including disaster management, risk analysis, heat island mapping, and the effects of urbanization on environmental changes such as floods and droughts in the recent decade. The earth's natural surface coverage including urban infrastructure, surface vegetation, bare soil can be identified with LULC maps. Besides, LULC is one of the most important tasks in natural hazards, planning activities, resource management, and global monitoring studies. The present study aimed to improve the level of land used and land cover change mapping in a semi-arid environment using Landsat 8 Operational Land Imager (OLI) image. In this research, several tree-based algorithms for LULC mapping are used and compared. These algorithms are used in a combination model implementation of WEKA 3.8 and R programming language to provide a method of a fit-for-purpose algorithms for LULC mapping. It is found that Reduced Error Pruning Tree (REP Tree) is the best approach according to the training and test datasets which are four classes including the build-up, soil, roads, and vegetation region pixels in a semi-arid environment. For the training dataset, the best values of Overall Accuracy (OA), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) is determined, 99.7313, 0.002 and 0.0354 as well as for the test dataset are 99.7313, 0.002 and 0.0354, respectively. Finally, trained models of the implemented data mining algorithms are used for the classification of a different dataset without using any training data where the Logical Analysis of Data Tree (LAD Tree) algorithm shows the best performance in terms of OA, MAE, and RMSE with values of 99.2815, 0.0057, and 0.0557 respectively.

Evaluation of predicted loss of different land use and land cover (LULC) due to coastal erosion in Bangladesh

“…Land loss prediction performance was evaluated by averaging the ranking of each metric. We followed a similar ranking approach to Moayedi et al (2020) who evaluated the performance of different image classification algorithms. First, we ranked individual metrics (e.g., recall, precision, F1) based on the prediction performance.…”

Comparison Of K-nearest Neighbor (KNN) And Linear Discriminant Analysis (LDA) Algorithms For Mature Ajwa Date Fruit Classification

“…Despite being a standard machine learning method, some image classification studies still use this algorithm, such as in critical land prediction in agricultural production zones, where it achieves an accuracy value of 92.47% [22], in the cultural heritage image classification, with an accuracy score of 76% [23], and in the land cover mapping in a semi-arid environment classification, with an average accuracy value of 99.24% [24].…”

Geospatial Analysis of Urban Expansion Using Remote Sensing Methods and Data: A Case Study of Yangtze River Delta, China

“…Since the 1970s, the United States began to use long time series remote sensing data from Landsat to investigate the patterns and driving forces of urban land cover expansion and landscape metrics to predict future urban development trends [6,7]. Other countries are also currently focusing on monitoring and predicting the rapid urbanization of cities by using Landsat ematic Mapper (TM) or Operational Land Imager (OLI) [8][9][10][11].…”