Modeling land cover change dynamic using a hybrid model approach in Qeshm Island, Southern Iran

LULC change detection using support vector machines and cellular automata-based ANN models in Guna Tana watershed of Abay basin, Ethiopia

Recurrent changes recorded in LULC in Guna Tana watershed are a long-standing problem due to the increase in urbanization and agricultural lands. This research aims at identifying and predicting frequent changes observed using support vector machines (SVM) for supervised classification and cellular automata-based artificial neural network (CA-ANN) models for prediction in the quantum geographic information systems (QGIS) plugin MOLUSCE. Multi-temporal spatial Landsat 5 Thematic Mapper (TM) imageries, Enhanced Thematic Mapper plus 7 (ETM+), and Landsat 8 Operational Land Imager (OLI) images were used to find the acute problem the watershed is facing. Accuracy was assessed using the confusion matrix in ArcGIS 10.4 produced from ground truth data and Google Earth Pro. The results acquired from kappa statistics for 1991, 2007, and 2021 were 0.78, 0.83, and 0.88 respectively. The change detection trend indicates that urban land cover has an increasing trend throughout the entire period. In the future trend, agriculture land may shoot up to 86.79% and 86.78% of land use class in 2035 and 2049. Grassland may attenuate by 0.03% but the forest land will substantially diminish by 0.01% from 2035 to 2049. The increase of land specifically was observed in agriculture from 3128.4 to 3130 km2. Judicious planning and proper execution may resolve the water management issues incurred in the basin to secure the watershed.

Evaluation of comparing urban area land use change with Urban Atlas and CORINE data

Urban Atlas (UA) data covering the large urban areas have been produced by the European Environment Agency for a variety of European countries including Turkey since 2006. The use of the UA data for the determination of spatiotemporal land use and density changes in urban areas. UA data of Eskisehir, Turkey, were used in order to detect the spatiotemporal changes between 2012 and 2018. CORINE data-based change detection and NDVI analysis were also made and compared with the results obtained from the UA data. The results based on the UA data revealed that the artificial surfaces in the study area increased by 17.65% and there was a 18.32% increase in the total amount of agricultural lands, natural lands, forests, and vegetation. Although CORINE data-based analyses showed a similar trend in land use/land cover changes, the amount of changes between 2012 and 2018 in CORINE and UA data-based analyses were found to be 4.99% and 17.55%, respectively. A 9.30% mismatch between the UA changes and NDVI difference data was also calculated. Research findings revealed that the utilization of the UA data in the urban territories would be advantageous especially in planning processes to detect and compare the changes in the artificial and non-artificial surfaces and NDVI analysis would be very supportive to control and compare the results. It is also concluded that this study may be a useful model to monitor the cities in accordance with the 2030 and 2050 policies of European Council on Land Use, Land Use Change and Forestry.

A Novel Technique for Modeling Ecosystem Health Condition: A Case Study in Saudi Arabia

The present paper proposes a novel fuzzy-VORS (vigor, organization, resilience, ecosystem services) model by integrating fuzzy logic and a VORS model to predict ecosystem health conditions in Abha city of Saudi Arabia from the past to the future. In this study, a support vector machine (SVM) classifier was utilized to classify the land use land cover (LULC) maps for 1990, 2000, and 2018. The LULCs dynamics in 1990–2000, 2000–2018, and 1990–2018 were computed using delta (Δ) change and Markovian transitional probability matrix. The future LULC map for 2028 was predicted using the artificial neural network-cellular automata model (ANN-CA). The machine learning algorithms, such as random forest (RF), classification and regression tree (CART), and probability distribution function (PDF) were utilized to perform sensitivity analysis. Pearson’s correlation technique was used to explore the correlation between the predicted models and their driving variables. The ecosystem health conditions for 1990–2028 were predicted by integrating the fuzzy inference system with the VORS model. The results of LULC maps showed that urban areas increased by 334.4% between 1990 and 2018. Except for dense vegetation, all the natural resources and generated ecosystem services have been decreased significantly due to the rapid and continuous urbanization process. A future LULC map (2028) showed that the built-up area would be 343.72 km2. The new urban area in 2028 would be 169 km2. All techniques for sensitivity analysis showed that proximity to urban areas, vegetation, and scrubland are highly sensitive to land suitability models to simulate and predict LULC maps of 2018 and 2028. Global sensitivity analysis showed that fragmentation or organization was the most sensitive parameter for ecosystem health conditions.