Egyptian Journal of Remote Sensing and Space Sciences最新文献

The dual use of wind and solar energy holds great promise for low-cost and high-performance green infrastructure. However, for such hybrid systems to operate successfully, comprehensive and simultaneous dimensional planning is required, a goal that single-perspective assessment approaches fail to attain. This paper proposes a novel SpatioTemporal Decision-Making (STDM) model based on Geospatial Artificial Intelligence (GeoAI) for the optimal allocation of onshore wind-solar hybrid plants, with application on a national scale in Iraq. To this end, a wide range of 21 evaluative and restrictive spatial criteria were covered. The temporal synergy factor between renewable resources was considered for the first time in this type of study. Unique global weightings for decision factors were derived using Random Forest (RF) and SHapley Additive exPlanations (SHAP) algorithms supported by sample inventories of wind and solar plants worldwide. Finally, weighted linear combination (WLC) and fuzzy overlay techniques were harnessed in a GIS environment for spatiotemporal suitability mapping of energy systems. According to the RF-SHAP model, the techno-economic criteria demonstrated substantial contributions to the placement of wind and solar systems compared with the socio-environmental criteria. The spatiotemporal suitability map identified three promising opportunities for Iraq at South Dhi-Qar, East Wasit, and West Diyala, with total areas of 780, 2166, and 649 km², respectively. We anticipate that our findings will encourage government agencies, decision-makers, and stakeholders to increase funding for clean energy transition initiatives.

The manual extraction of land disturbances associated with oil exploration, which normally includes resource roads, mining facilities, and well pads, presents significant challenges in terms of cost and time. Accurate monitoring and mapping of land disturbances resulting from oil exploration plays a crucial role in conducting comprehensive environmental assessments and facilitating effective land reclamation initiatives. However, prevailing deep learning methodologies in the realm of oil and gas exploration primarily focus on oil spill detection, neglecting the critical aspect of land disturbances resulting from oil exploration, thus overlooking the impact on land. Furthermore, given that the well sites are scattered and relatively diminutive compared to other land covers, their detection poses substantial difficulties. This paper proposes an automatic error-correcting (AEC) algorithm to address deficiencies in ground truth data quality. This AEC method was integrated into the deep-learning framework for land disturbance extraction, specifically tailored for land disturbances analysis associated with oil exploration. The efficacy of our method was validated on a dataset collected in Alberta covering an area of oil sand mining sites. The application of the AEC algorithm significantly enhanced the accuracy of land disturbance analysis, thereby contributing to a more effective hydrocarbon exploration impact analysis and facilitating the timely planning by the Alberta government. The results demonstrate notable improvements in both average pixel accuracy (AA) and mean intersection over union (mIoU), ranging from 8.3% to 15.4% and 0.5% to 5.8%, respectively. These enhancements, which have profound implications for the precision of land disturbance detection, prove that the proposed AEC algorithm can serve a dual purpose: correcting errors in the dataset and efficiently detecting land disturbance features in the oil exploration area.

This study aims to map the non-sulphide Zinc (Zn)-bearing gossans at the Gujer Zn deposit area, Central Iran, using Landsat 8 Operational Land Imager (OLI) and GeoEye-1 satellites. The colour composites, Principal Component Analysis (PCA), and Support Vector Machine (SVM) were adopted for image analysis. Zn-bearing gossans contain Fe-oxyhydroxide minerals displaying spectral characteristics in visible and infrared (IR) wavelengths. The application of colour composites using GeoEye-1 images resulted in the delineation of gossans (real target) and ferruginous sandstones (false targets) having the same colour tone in the study area. IR spectroscopy of ore samples showed that hemimorphite exhibits low absorption in shortwave infrared (SWIR) wavelengths. Consequently, the Crosta-PC analysis was conducted using bands 4, 5, SWIR-1, and SWIR-2 of Landsat OLI to enhance only ore gossans. Five target zones were specified using the Crosta technique. The SVM method was performed to increase the accuracy of image analysis using the Radial Basis Function (RBF) kernel. The SVM-RBF method accomplished enhancing ore gossans by defining a new target zone. According to the results, the application of the Crosta technique using bands 4, 5, SWIR-1, and SWIR-2 of Landsat OLI can specify ore gossans and eliminate the interfering effect of ferruginous sandstones in similar geological settings. The SVM-RBF can improve the results of image processing using PC entry of Landsat OLI bands. GeoEye-1 images are useful for the initial assessment of geological units in the region and for delineating the accurate boundary of ore gossans derived from Landsat 8 OLI data.

The technological advancements in spectroscopy give rise to acquiring data about different materials on earth's surface which can be utilized in a variety of potential applications. But, the hundreds of spectral bands are generally equipped with highly correlated information with limited training samples. This will degrade the Hyperspectral Image (HSI) classification accuracy. So Dimensionality Reduction (DR) has become inevitable and necessary step need to incorporate before HSI classification. The main contribution of this work lies in comparative study and review on dimensionality reduction techniques for Hyperspectral remote sensing image classification. The related challenges and research directions are also discussed. This study will help the researchers in the Hyperspectral remote sensing community to choose the appropriate DR technique for classification which can be useful in various real time applications.

Ocean-Atmosphere interactions have been gradually recognized to play a significant role in hydrological cycle and climate change. It is essential to understand ocean-circulation behaviour, including the Sea Surface Salinity (SSS) which is a root cause of variations in sea water density in both coastal system and open ocean. The study has evaluated the performance of SSS obtained from the Soil Moisture and Ocean Salinity (SMOS) satellite data. Daily Barcelona Expert Center (BEC), SMOS, SSS data from 2012 to 2016 are compared with the salinity observations from Argo floats within the Exclusive Economic Zone (EEZ) of Pakistan. Statistics between a daily reporting Argo float and daily SMOS SSS resulted in a spatial correlation, a bias, a standard deviation, and a variance has been examined to determine the monthly, annual and seasonal variations of SSS. Bias analysis showed the underestimation between −0.52 and −0.008 psu while variance has been observed to be between 0.02 and 0.19 psu. The monthly, seasonal and yearly comparison suggests both SMOS and Argo are are found to be in concurrence. Finally, it has been revealed that SSS retrieval algorithm by BEC SMOS provides good estimation along the EEZ of Pakistan.

Landslides, even shallow ones, can displace and destroy the fragile archaeological record. Therefore, it is essential to develop a comprehensive risk assessment and predict the sites at risk before a disaster, which this study aims to provide for 508 archaeological sites associated with Indus civilization and regional Chalcolithic cultures in Gujarat, India. As a hazard inventory for the study area is not available, this study integrates multi-criteria decision-making (MCDM), satellite remote sensing, and Geographic Information Systems (GIS) first to generate a landslide susceptibility map and then to use it for assessing the landslide risk of archaeological sites. Fifteen parameters, viz., elevation, slope, aspect, curvature, average rainfall, drainage density, Topographic Wetness Index (TWI), Stream Power Index (SPI), lithology, soil type, geomorphology, distance from lineaments, Normalized Difference Vegetation Index (NDVI), Land Use Land Cover (LULC), and distance from roads were selected to determine susceptibility. The weights of each parameter were derived using the Analytical Hierarchy Process (AHP). The novelty of this study lies in the spatial overlay of the area of the sites and landslide susceptibility to measure the value loss of the archaeological sites. The results revealed that three of the 508 sites studied are at high risk, and 214 are at medium risk of landslides. With this proposed methodology, this study generates a new dataset on landslide susceptibility for the study area. In addition, it attempts to provide an integrated risk assessment framework for the archaeological sites in India that aids in identifying and mitigating risks.

Land Use/Land Cover (LULC) classification using hyperspectral images in remote sensing is a leading technology. However, LULC classification using hyperspectral images is a difficult task and time-consuming process because it has fewer training samples. To overcome these issues, we proposed a deep-Long Short-Term Memory (deep-LSTM) to classify the LULC. Before classifying the LULC, extracting valuable features from an image is needed, and after extracting the features, selecting the bands which are helpful for classification should be done. In this work, we have proposed an auto-encoder model for feature extraction, a ranking-based band selection model to select the bands, and deep-LSTM for classification. We have used three publicly available benchmark datasets; they are Pavia University (PU), Kennedy Space Centre (KSC), and Indian Pines (IP). Average Accuracy (AA), Overall Accuracy (OA), and Kappa Coefficient (KC) are used to measure the classification accuracy. The suggested technique has provided the top outcomes compared to the other state-of-the-art methods.

This study introduces an innovative approach for analyzing bending deformation and strength in textile-reinforced laminated composites, which is crucial for CubeSat structures. Our research develops a dual-scale modelling framework: a microscale model capturing the detailed viscoelastic-viscoplastic behaviour of fibres and matrices and a mesoscale model that integrates this with textile geometry, advanced shear deformation theories, and distributed damage effects. Extensive laboratory experiments validate our model, confirming its accuracy in predicting the composite behaviour under varied conditions. This work notably enhances the understanding and prediction of textile-reinforced composites, offering significant implications for CubeSat structural design and performance.

Space debris is a growing problem for low earth orbit (LEO) and geosynchronous orbit (GEO). The risk of space debris currently affects human activities in Space and is controlled by the collision avoidance alert. However, the risk is growing, which increases future space mission costs to avoid or shield against space debris impact.

The project has evolved over four years, culminating in Meng/BEng graduation projects. At the heart of our innovation is utilising the naturally high temperatures in the exosphere and stratosphere, which can soar to 1200 °C. This environment is ideal for initiating a chemical reaction within a pressurised chamber containing a mix of H2-O2 gases, generating heat sufficient to ablate common space debris materials such as titanium, aluminium, and composites. We have crafted an initial satellite design and performed Multiphysics simulations using COMSOL to validate our concept. The project now seeks investment to enhance four critical areas: the satellite's mechanical design to ensure safe operation within a debris field, the development of a dynamic control system for debris collection and satellite navigation, the management of H2 and O2 tank refilling, and the creation of a mechanism for the safe release of ablated materials back into Space.

Extraction of color and texture features of buildings from high-resolution remote sensing images often encounters the problems of interference of background information and varying target scales. In addition, most of the current attention mechanisms focus on building key feature selection for building extraction optimization, but ignore the influence of the complex background. Hence, we propose incorporating a novel reverse attention module into the network. The innovative module enables the model to selectively extract crucial building features while suppressing the impact of intricate background noise. It mitigates the influence of uniform spectral and structurally similar heterogeneous background targets on building segmentation and extraction. As a result, the overall generalizability of the model is improved. The reverse attention can also emphasize and amplify the specific details pertaining to the boundaries of the target. Furthermore, we couple a new multi-branch convolution block into the encoder, integrating dilated convolutions with multiple dilation rates. Compared to other methods that use only one multi-scale module to extract multi-scale information from high-level features, we use different receptive field convolutions to simultaneously capture multi-scale targets from multi-level features, effectively improving the ability of the model to extract multi-scale building features. The experimental findings demonstrate that our proposed multi-branch reverse attention semantic segmentation network achieves IoU of 90.59% and 81.79% on the well-known WHU building and Inria aerial image datasets, respectively.