Egyptian Journal of Remote Sensing and Space Sciences最新文献

Climate changes have exposed many countries to the risks of heavy rains and floods that may lead to the loss of lives and damage to properties. The trend in prioritizing the establishment of stormwater drainage systems in urban areas in Egypt came after the provision and completion of drinking water. This necessitated the implementation of permanent solutions to absorb the unprecedented amounts of rainwater and torrential rain, which were not taken into account when designing the existing sewage networks. Furthermore, there is a lack of water resources and the existing water resources are less than the demand. Therefore, this research study aimed to take advantage of the stormwater that falls on residential neighborhoods by making underground reservoirs or retention ponds to protect these areas from the damage caused by the rains and reusing it in irrigating local green area inside these regions, to achieve sustainable water resources solutions for these areas. Satellite imagery, DEM & ArcGIS are used. A hydrological calculation for 24 different storms, with 4 different return periods for New Cairo City. However, it is the basin of interest that includes public green spaces for rain harvesting and storage for irrigation. For avoiding the risks of heavy rains in a city that hasn’t stormwater networks, and get a sustainable solution by using the water from rainfall for irrigation through using sub-areas of some public green spaces such as retention ponds or ground reservoirs, using the runoff volume shall save approximately 6 days of irrigation per storm.

The agricultural sector in Egypt is adversely affected by factors such as inadequate soil fertility and environmental hazards such as pestilence and diseases. The implementation of early pest prediction techniques has the potential to enhance agricultural yield. Bactrocera zonata and Ceratitis capitata, known as peach fruit fly and Mediterranean fruit fly, respectively, are the predominant pests that cause significant damage to fruits on a global scale. The present study proposes a deep learning-based approach for the detection and quantification of pests. The proposed approach entails the retrieval of data pertaining to the adhesive trap condition, followed by its examination and presentation through a mobile application. The YOLOV5 model has been implemented for the purpose of pest classification, localization, and quantification. In order to address the issue of a restricted dataset, a hybrid technique of transfer learning and data augmentation (copy and paste) was employed. The proposed approach offers an intelligent real time pest detection, thereby facilitating the prediction of treatment options. An application for smartphones has been developed to aid farmers and agricultural professionals in the management and treatment of pests. The proposed approach has the potential to aid farmers in identifying the existence of pests, thereby diminishing the duration and resources needed for farm inspection. As per the results of the conducted experiments, the proposed approach demonstrates a noteworthy increase in performance. The weighted average accuracy reaches 84%, while precision (P), mean average precision (mAP), and F1-score show enhancements of up to 15%, 18%, and 7% respectively.

The unsustainable expansion of cities is generating urban heat islands (UHIs) by exchanging (trading) vegetation cover (green) for built impervious surfaces which is associated with heat-related health risks, globally. This phenomenon is exacerbated by climate change and anthropogenic activities like urban population growth, particularly in African cities. This study explores the spatio-temporal trends of land surface temperature (LST), land use land cover (LULC) and their economic and health risks in the Greater Accra Metropolitan Area (GAMA) of Ghana, from 1991 to 2021. We extracted LST/LULC information from Landsat datasets to perform change analysis, alongside an online survey across 56 communities on how LST relates to economic and human health risks perceptions of residents. The results show urbanization of GAMA is trading greens for heated surfaces, impacting communities’ health risks. While the built environment grew (8.6%), the vegetation cover declined (2.5%) and the mean LST rose (0.8⁰C) in 25 years. A 30⁰C LST corresponds to the point of inflexion of exchanging green vegetative cover for heated built surfaces. The forest community of Kisseman, the populous community of Dansoman and the harbour city of Tema corresponded to the first, fourth and fifth LST quintiles, changing at −0.05⁰C, 0.06⁰C and 0.164⁰C per year. The common health risks include discomfort from heavy sweating, headaches, dehydration, thirst and skin rashes. These results call for climate action and green spatial planning through urban forestry and environmentalism in GAMA. For urban resilience and sustainable cities, we advocate green-cooling multi-purpose housing, roads, and industrial infrastructure.

In recent decades, severe climate change, decreased precipitation, temperature rise, and increased evapotranspiration (ET) have significantly reduced waterbodies. Furthermore, governments have prioritized the study of water level fluctuations of lakes to protect them from degradation nationally and regionally. The present study investigated the physical changes in lakes Bakhtegan and Tashk due to climatic parameters. To this end, Landsat satellite imagery and the NDWI were employed to calculate the area of the waterbodies from 1986 to 2018. The results showed that the area had decreased during the study period-- since 2009, Lake Bakhtegan had dried up completely. In 2008 and 2010, the lowest precipitation was 127.82 and 107.7 mm, respectively. During the study period (1986 to 2018), the average temperature was 19.44 °C, with an increase of 0.6 °C. Among the climatic parameters, precipitation, with a correlation coefficient of 0.55, and potential evapotranspiration (PET), with a correlation coefficient of about −0.68, were more strongly correlated with changes in the area of the waterbodies. To predict temperature and precipitation in the study area in the coming decades (2020–2050), the HadCM2 model of the CORDEX Project -WAS (South Asia) was used under two scenarios: RCP4.5 and RCP8.5. These scenarios revealed the decrease in precipitation and increase in temperature trends. As a result, the waterbodies’ areas were estimated using the projected precipitation and PET for the period 2050–2020, indicating a decrease in the areas of the waterbodies.

Recently, hyperspectral image (HSI) classification methods based on deep-learning have attracted widespread attention. Convolutional neural networks, as a crucial deep-learning technique, have exhibited outstanding performance in HSI classification. However, there are still some challenges, such as limited labeled samples, and feature extraction of complex land cover objects. To address these challenges, in this paper, we propose a multiscale cross-fusion network for HSI classification. It consists of three components: a spectral signatures extraction network, a spatial features extraction network and a classification network, which are utilized to extract spectral signatures, extract spatial contextual information and generate classification results, respectively. Specifically, the cross-branch multiscale convolutional block and the channel global contextual attention are integrated to extract spectral signatures, and the cross-hierarchy multiscale convolutional blocks and the spatial global contextual attention are combined to extract spatial features. Furthermore, special fusion strategies are proposed in these blocks to promote the interaction between features and achieve better feature connectivity. A series of experiments are conducted on three public HCI datasets, and the results show that the overall accuracy of the proposed network is 0.57%, 0.61%, and 0.3% higher than that of the state-of-the-art method on the PU, SV, and HH datasets, respectively.

The Gulf of Suez region accommodates diverse activities, including oil exploration and production, recreational activities, and export and import ports. The Gulf region is exposed to pollution risks due to these interactions, with few research studies documenting these pollution cases. This research aimed to use Synthetic Aperture Radar (SAR) satellite data to detect and map all the oil pollution incidents within the geographical extent of the Gulf of Suez that occurred from 2017 to 2021, locating the most affected regions and possible sources of pollution. It enabled the detection and mapping of nearly 150 oil spill incidents that occurred over 67 dates during the study period and covered 851 km² of the sea surface. The year 2018 recorded the greatest pollution area over the study period, with 201 km². Along the Gulf coast, Suez, Ain Sokhna, and Ras Ghareb cities recorded the highest number of marine pollution incidents. The research also located seven sources of pollution that frequently discharge into the Gulf water without regulations. This research recommends implementing a real-time monitoring system for oil pollution to robustly detect any future oil incidents in these high-risk areas as quickly as possible and minimize their environmental impact.

Remote sensing and GIS technologies help in decision-making processes to reduce pollution and treatment time. In this study, we aim to investigate using remote sensing data in predicting water quality parameters of the Tigris River. Our approach involves the development of mathematical and statistical models that leverage satellite imagery to predict relevant water parameters. Over 2018 and 2019, fourteen different locations along the Tigris River were surveyed. Measurements for eight parameters were collected simultaneously with satellite images at each location. These parameters included temperature (Temp), electrical conductivity, total dissolved solids (TDS), pH, turbidity, chlorophyll A, blue-green algae, and dissolved oxygen. The spectral bands from Landsat 8 images and spectral indices of soil, vegetation, and water were adjusted as a preprocessing step. Spectral bands and indices were then implemented in the least absolute shrinkage and selection operator (LASSO) to predict the eight water parameters. The evaluation of the prediction model showed that the LASSO model has a determination coefficient (R²) of more than 0.8 for pH and Temp, and the minimum R² of 0.52 was for TDS. It was found that incorporating spectral indices, as additional features in the prediction models, has significantly improved the models' performance, as demonstrated by an average R² of 0.7 compared to 0.42 when using spectral bands only. The predictive model for each parameter provided cost-effective alternatives to frequent monitoring of Tigris water quality using field data. The predicted parameters were then utilized to calculate the water quality index (WQI) to indicate water quality along the river. The WQI showed that the river had poor water quality during the year except for April and June, which was very poor. This information will be beneficial in enforcing standards and controlling pollution activities in the study region.

Taking advantage of the 250 m resolution and daily observation of dual thermal infrared channels data of the Medium Resolution Spectral Imager (MERSI) onboard the Fengyun 3D (FY-3D) satellite, a refined thermal infrared island surface temperature (ILST) inversion model is established through radiation transmission simulation. And the Tonga ILST change maps before and after the volcanic eruption are produced and analyzed based on ILST time series dataset. The results show that the ILST decreases by 2 K –3 K within the five days after the eruption due to the amount of volcanic ash deposition, but increases significantly by 2 K –6 K within the fifth to tenth days after the eruption. The trend of time-limited cooling, warming, and then gradual recovery after volcanic eruption is very obvious. Through the manual cleaning and the scouring by seawater or rainwater to the volcanic ash covered ground, more parts of the island surface restored its original state. Hence, the Tonga ILST also increased gradually within a week thereafter. However, in regions with local vegetation, the recovery time of ILST would be longer. The temporal and spatial resolution of FY-3D MERSI meets the need for monitoring the changes of the island surface states before and after the volcanic eruption.

Mediterranean Fruit Fly, Ceratitis capitata (Diptera: Tephritidae) is regarded as an important pest of orange (Citrus). Early detection of pest infestations enables the optimal application of preventative and control measures. This study was carried out under laboratory conditions, in order to predict and monitor orange pest infestations. Consequently, the scope was to find a remote sensing application that can help in the prediction of Mediterranean Fruit Fly infestation in oranges with the least loss in production. Spectroscopic and thermal imaging techniques were investigated, as effective tools in determination of pest infestation and damage in orange fruits. According to the findings, the optimum spectral zones that can be used to discriminate and differentiate between healthy (non-infected) orange fruit and infected ones were red and near infrared bands. Six vegetation indices were calculated to analyze the Field Spectral measurements. By calculating the NPCI (Normalized Pigment Chlorophyll Index), it was found that NPCI values for infected orange fruits were higher in comparison to healthy ones. Thermal imaging showed that the infected orange fruit temperatures were on average 0.8 °C higher than that of healthy fruits. As the maximum temperature differential (MTD) between healthy and infected fruits were 23.7–24.5 °C, respectively. These spectral reflectance curves were useful for researchers working on Site-specific crop management, as they can use remote sensing to detect individual fruit infections. Also, this technique should be used as a powerful and non-destructive method for assistance in agriculture.