Applied Geomatics最新文献

The geological hazards caused by natural and manmade activities pose serious property damage, loss of life, and changes in the earth’s features. In this work, GIS-based landslide susceptibility mapping was carried out using the Analytical Hierarchy Process (AHP) and Frequency Ratio (FR) methods for the Chemoga River Sub-Basin (CRSB), in the Aba Libanos area in Northwestern Ethiopia. To produce a susceptibility map, eight influencing factors were selected. They are elevation, slope, aspect, Lithology, land use land cover, curvature, distance to drainage, and distance lineaments. All those influencing factors were statistically analyzed to decide their relationship to past landslides. The relationships between the observed landslide areas and these eight related factors were identified using GIS-based statistical models including AHP and FR. Detailed fieldwork (lithological description and mapping, geological structural measurements, and taking considerations for the impact of each influencing factor on the occurrence of landslides in the area) was conducted to interpret and produce the various maps of the study area. The AHP modeling susceptibility map of the study area was 9.6%, 15.4%, 29.7%, 27.8%, and 17.5% very low, low, moderate, high, and very high respectively. Similarly, based on the value of FR, the study area was classified into five susceptibility zones, 20.7%, 14.6%, 13.0%, 18.6%, and 33.0% very low, low, moderate, high, and very high respectively. Both results showed that steep side slopes and lineaments are very high landslide susceptibility zones. Lastly, the landslide susceptibility maps produced from the two models were validated with detailed fieldwork measurements and observation. Prediction accuracy of these maps that the landslide inventory map was overlaid on the AHP and FR maps. Both susceptibility maps show almost similar results and mainly, introduced some parts of the study areas of the Chemoga river sub-basin (CRSB) as landslide-prone areas.

Abstract

Metropolitan and town planners in Ethiopia are dealing with high racial tensions concerned about the high rate of urban expansion which is posing a challenge to get efficient urban planning. Therefore, this study aimed to evaluate urban land use and land cover (LULC) changes in Shambu Town over the past three decades and to forecast the futurity of urban expansion. The LULC classification was performed by using supervised classification with maximum likelihood from Landsat images of 1990, 2000, 2010, and 2020. The rapid rise of the urban population is a source of urban expansion. According to the study, every LULC type in the study area has been transformed from one LULC to another types. The result shows that agriculture, forest, and grassland land cover declined by 217.2 ha, 39 ha, and 54.8 ha, respectively, in the study area from 1990 to 2020. However, the built-up area increased by 311 ha within the past three decades. However, over the study period, agriculture and grassland both decreased by 474.7 ha and 66.3 ha, respectively. From LULC types of the study area, built-up area and forest land will be expanded by an area of 1064.3 ha and 170.5 ha respectively, in the coming 2050. Based on the finding of this study, we suggested that urban planners, land administration and management offices, environmental protection offices, and other stakeholders can investigate the impacts of LULC change and urban expansion on natural resources and ecological service systems, as well as the impact on people’s livelihoods in the future for natural and land resource management.

Numerous uses of the hyperspectral remote sensing technology exist for identifying land cover and tracking its evolution. The classification of hyperspectral images must now take into account both spectral and spatial information due to recent advancements and the production of images with high spatial resolution. Convolutional neural networks (CNNs) have much employed in recent years to enhance the classification precision of hyperspectral images. The simultaneous use of spatial feature extraction methods in CNNs has not received significant attention in prior studies. In this study, a novel CNN architecture has been developed for classifying hyperspectral images. The weighted genetic (WG) algorithm is used in the proposed technique to minimize the hyperspectral image’s dimensions. The WG algorithm keeps every band in the image and gives each one weight between zero and one based on how much information it contains. Following the expectation maximization (EM) method to the collected features, the segmented objects are then categorized using the CNN algorithm. Three benchmark hyperspectral images, Pavia, DC Mall, and Indiana Pine, were used to assess the proposed approach. The trials’ findings demonstrate the proposed approach’s superiority over the multilayer perceptron (MLP) algorithm in the Pavia, DC Mall, and Indiana Pine images by 14, 16, and 8% in the overall accuracy parameter, respectively.

Woody canopy cover (CC) is important for characterising terrestrial ecosystems and understanding vegetation dynamics. The lack of accurate calibration and validation datasets for reliable modelling of CC in the indigenous forests in South Africa contributes to uncertainties in carbon stock estimates and limits our understanding of how they might influence long-term climate change. The aim of this study was to develop a method for monitoring CC in the Dukuduku indigenous forest in South Africa. Advanced Land Observing Satellite (ALOS) Phased Arrayed L-band Synthetic Aperture Radar (PALSAR) global mosaics of 2008, 2015, and 2018, polarimetric features, and Grey Level Co-occurrence Matrix (GLCMs) were used. Machine learning models Random Forest (RF) vs Support Vector Machines (SVM) were developed and calibrated using Collect Earth Online (CEO) data, a free and open-access land monitoring tool developed by the Food and Agriculture Organisation (FAO). The addition of GLCMs produced the highest accuracy in 2008, R² (RMSE) = 0.39 (36.04%), and in 2015, R² (RMSE) = 0.51 (27.82%), and in 2018, only SAR variables gave the highest accuracy R² (RMSE) = 0.55 (29.50). The best-performing models for 2008, 2015, and 2018 were based on RF. During the ten-year study period, shrubland and wooded grassland had the highest transition, at 6% and 13%, respectively. The observed changes in the different canopies provide valuable insights into the vegetation dynamics of the Dukuduku indigenous forest. The modelling results suggest that the CEO calibration data can be improved by integrating airborne LiDAR data.