Search Results (247)

Floods are considered to be among the most dangerous and destructive geohazards, leading to human victims and severe economic outcomes. Yearly, many regions around the world suffer from devasting floods. The estimation of flood aftermaths is one of the high priorities for the global community. One such flood took place in northern Libya in September 2023. The presented study is aimed at evaluating the flood aftermath for Derna city, Libya, using high resolution GEOEYE-1 and Sentinel-2 satellite imagery in Google Earth Engine environment. The primary task is obtaining and analyzing data that provide high accuracy and detail for the study region. The main objective of study is to explore the capabilities of different algorithms and remote sensing datasets for quantitative change estimation after the flood. Different supervised classification methods were examined, including random forest, support vector machine, naïve-Bayes, and classification and regression tree (CART). The various sets of hyperparameters for classification were considered. The high-resolution GEOEYE-1 images were used for precise change detection using image differencing (pixel-to-pixel comparison and geographic object-based image analysis (GEOBIA) for extracting building), whereas Sentinel-2 data were employed for the classification and further change detection by classified images. Object based image analysis (OBIA) was also performed for the extraction of building footprints using very high resolution GEOEYE images for the quantification of buildings that collapsed due to the flood. The first stage of the study was the development of a workflow for data analysis. This workflow includes three parallel processes of data analysis. High-resolution GEOEYE-1 images of Derna city were investigated for change detection algorithms. In addition, different indices (normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), transformed NDVI (TNDVI), and normalized difference moisture index (NDMI)) were calculated to facilitate the recognition of damaged regions. In the final stage, the analysis results were fused to obtain the damage estimation for the studied region. As the main output, the area changes for the primary classes and the maps that portray these changes were obtained. The recommendations for data usage and further processing in Google Earth Engine were developed. Full article

Sulfur dioxide (SO₂) is sourced by degassing magma in the shallow crust; hence its monitoring provides information on the rates of magma ascent in the feeding conduit and the style and intensity of eruption, ultimately contributing to volcano monitoring and hazard assessment. Here, we present a new algorithm to extract SO₂ data from the TROPOMI imaging spectrometer aboard the Sentinel-5 Precursor satellite, which delivers atmospheric column measurements of sulfur dioxide and other gases with an unprecedented spatial resolution and daily revisit time. Specifically, we automatically extract the volcanic clouds by introducing a two-step approach. Firstly, we used the Simple Non-Iterative Clustering segmentation method, which is an object-based image analysis approach; secondly, the K-means unsupervised machine learning technique is applied to the segmented images, allowing a further and better clustering to distinguish the SO₂. We implemented this algorithm in the open-source Google Earth Engine computing platform, which provides TROPOMI imagery collection adjusted in terms of quality parameters. As case studies, we chose three volcanoes: Mount Etna (Italy), Taal (Philippines) and Sangay (Ecuador); we calculated sulfur dioxide mass values from 2018 to date, focusing on a few paroxysmal events. Our results are compared with data available in the literature and with Level 2 TROPOMI imagery, where a mask is provided to identify SO₂, finding an optimal agreement. This work paves the way to the release of SO₂ flux time series with reduced delay and improved calculation time, hence contributing to a rapid response to volcanic unrest/eruption at volcanoes worldwide. Full article

Cropland is fundamental to food security, and monitoring cropland non-agriculturalization through satellite enforcement can effectively manage and protect cropland. However, existing research primarily focuses on optical imagery, and there are problems such as low data processing efficiency and long updating cycles, which make it difficult to meet the needs of large-scale rapid monitoring. To comprehensively and accurately obtain cropland change information, this paper proposes a method based on the Google Earth Engine (GEE) cloud platform, combining optical imagery and synthetic aperture radar (SAR) data for quick and accurate detection of cropland non-agriculturalization. The method uses existing land-use/land cover (LULC) products to quickly update cropland mapping, employs change vector analysis (CVA) for detecting non-agricultural changes in cropland, and introduces vegetation indices to remove pseudo-changes. Using Shanwei City, Guangdong Province, as a case study, the results show that (1) the cropland map generated in this study aligns well with the actual distribution of cropland, achieving an accuracy of 90.8%; (2) compared to using optical imagery alone, the combined optical and SAR data improves monitoring accuracy by 22.7%, with an overall accuracy of 73.65%; (3) in the past five years, cropland changes in Shanwei followed a pattern of an initial increase followed by a decrease. The research in this paper can provide technical reference for the rapid monitoring of cropland non-agriculturalization on a large scale, so as to promote cropland protection and rational utilization of cropland. Full article

This study explores the dynamics of urban green spaces in five major Indonesian cities—Central Jakarta, Bandung, Yogyakarta, Surabaya, and Semarang—using Sentinel-2 satellite imagery and vegetation indices, such as NDVI and EVI. As major urban areas expand and become more densely populated, development activities have significantly altered urban green spaces, necessitating comprehensive mapping through remote sensing technologies. The findings reveal significant variability in green space coverage among the cities over three periods (2019–2020, 2021–2022, 2023–2024), ensuring that the findings are comprehensive and up to date. This study demonstrates the utility of remote sensing for detailed urban analysis, emphasizing its effectiveness in identifying, quantifying, and monitoring changes in green spaces. Integrating advanced techniques, such as NDVI and EVI, offers a nuanced understanding of urban vegetation dynamics and their implications for sustainable urban planning. Utilizing Sentinel-2 data within the Google Earth Engine (GEE) framework represents a contemporary and innovative approach to urban studies, particularly in rapidly urbanizing environments. The novelty of this research lies in its method of preserving and enhancing green infrastructure while supporting the development of effective strategies for sustainable urban growth. Full article

Land cover mapping is essential to understanding global land-use patterns and studying biodiversity composition and the functioning of eco-systems. The introduction of remote sensing technologies and artificial intelligence models made it possible to base land cover mapping on satellite imagery in order to monitor changes, assess ecosystem health, support conservation efforts, and reduce monitoring time. However, significant challenges remain in managing large, complex satellite imagery datasets, acquiring specialized datasets due to high costs and labor intensity, including a lack of comparative studies for the selection of optimal deep learning models. No less important is the scarcity of aerial datasets specifically tailored for agricultural areas. This study addresses these gaps by presenting a methodology for semantic segmentation of land covers in agricultural areas using satellite images and deep learning models with pre-trained backbones. We introduce an efficient methodology for preparing semantic segmentation datasets and contribute the “Land Cover Aerial Imagery” (LICAI) dataset for semantic segmentation. The study focuses on the Franciacorta area, Lombardy Region, leveraging the rich diversity of the dataset to effectively train and evaluate the models. We conducted a comparative study, using cutting-edge deep-learning-based segmentation models (U-Net, SegNet, DeepLabV3) with various pre-trained backbones (ResNet, Inception, DenseNet, EfficientNet) on our dataset acquired from Google Earth Pro. Through meticulous data acquisition, preprocessing, model selection, and evaluation, we demonstrate the effectiveness of these techniques in accurately identifying land cover classes. Integrating pre-trained feature extraction networks significantly improves performance across various metrics. Additionally, addressing challenges such as data availability, computational resources, and model interpretability is essential for advancing the field of remote sensing, in support of biodiversity conservation and the provision of ecosystem services and sustainable agriculture. Full article

An effective satellite observation system is developed to retrieve the diatom concentration in freshwater ecosystems that could be utilized for understanding aquatic biogeochemical cycles. Although the singular value decomposition-based retrieval model can reflect the complicated diatom dynamics, the spatial distribution and temporal trend in diatom concentration on a large scale, as well as its driving mechanism, remain prevalently elusive. Based on the Google Earth Engine platform, this study uses Sentinel-2 MultiSpectral Instrument imagery to track the comprehensive diatom dynamics in a large reservoir, i.e., the Three Gorges Reservoir, in China during the years 2019–2023. The results indicate that a synchronous diatom distribution is found between the upstream and downstream artificial lakes along the primary tributary in the Three Gorges Reservoir, and the causal relationships between the declining diatom trend and hydrological/meteorological drivers on the monthly and yearly scales are highlighted. Moreover, the Sentinel-derived diatom concentration can be used to ascertain whether the dominant algae are harmful during bloom periods and aid in distinguishing algal blooms from ship oil spills. This study is a significant step forward in tracking the diatom dynamics in a large-scale freshwater ecosystem involving complex coupling drivers. Full article

Land use and land cover (LULC) changes are significantly impacting the natural environment. Human activities and population growth are negatively impacting the natural environment. This negative impact directly relates to climate change, sustainable agriculture, inflation, and food security at local and global levels. Remote sensing and GIS tools can provide valuable information about change detection. This study examines the correlation between population growth rate and LULC dynamics in three districts of South Punjab, Pakistan—Multan, Bahawalpur, and Dera Ghazi Khan—over a 30-year period from 2003 to 2033. Landsat 7, Landsat 8, and Sentinel-2 satellite imagery within the Google Earth Engine (GEE) cloud platform was utilized to create 2003, 2013, and 2023 LULC maps via supervised classification with a random forest (RF) classifier, which is a subset of artificial intelligence (AI). This study achieved over 90% overall accuracy and a kappa value of 0.9 for the classified LULC maps. LULC was classified into built-up, vegetation, water, and barren classes in Multan and Bahawalpur, with an additional “rock” class included for Dera Ghazi Khan due to its unique topography. LULC maps (2003, 2013, and 2023) were prepared and validated using Google Earth Engine. Future predictions for 2033 were generated using the MOLUSCE model in QGIS. The results for Multan indicated substantial urban expansion as built-up areas increased from 8.36% in 2003 to 25.56% in 2033, with vegetation and barren areas displaying decreasing trends from 82.96% to 70% and 7.95% to 3.5%, respectively. Moreover, areas containing water fluctuated and ultimately changed from 0.73% in 2003 to 0.9% in 2033. In Bahawalpur, built-up areas grew from 1.33% in 2003 to 5.80% in 2033, while barren areas decreased from 79.13% to 74.31%. Dera Ghazi Khan expressed significant increases in built-up and vegetation areas from 2003 to 2033 as 2.29% to 12.21% and 22.53% to 44.72%, respectively, alongside reductions in barren and rock areas from 32.82% to 10.83% and 41.23% to 31.2%, respectively. Population projections using a compound growth model for each district emphasize the demographic impact on LULC changes. These results and findings focus on the need for policies to manage unplanned urban sprawl and focus on environmentally sustainable practices. This study provides critical awareness to policy makers and urban planners aiming to balance urban growth with environmental sustainability. Full article

Anthropogenic activity leads to changes in sediment dynamics, creating imbalances in sediment distributions across the landscape. These imbalances can be variable within a littoral system, with adjacent areas experiencing sediment starvation and excess sediment. Historically, sediments were viewed as an inconvenient biproduct destined for disposal; however, beneficial use of dredge material (BUDM) is a practice that has grown as a preferred methodology for utilizing sediment as a resource to help alleviate the sediment imbalances within a system. BUDM enables organizations to adopt a more innovative and sustainable sediment management approach that also provides ecological, economic, and social co-benefits. Although location data are available on BUDM sites, especially in the US, there is limited understanding on how these sites evolve within the larger landscape, which is necessary for quantifying the co-benefits. To move towards BUDM more broadly, new tools need to be developed to allow researchers and managers to understand the effects and benefits of this practice. The National Exposed Sediment Search and Inventory (NESSI) was built to show the capability of using machine learning techniques to identify dredged sediments. A combination of satellite imagery data obtained and processed using Google Earth Engine and machine learning algorithms were applied at known dredged material placement sites to develop a time series of dredged material placement events and subsequent site recovery. These disturbance-to-recovery time series are then used in a landscape analysis application to better understand site evolution within the context of the surrounding areas. Full article

In September 2024, following two rare storms, Lake Iriqui in southern Morocco experienced a remarkable revival after five decades of desiccation. Historically, the lake played an important role as one of the largest water bodies before the Sahara Desert, serving as a critical stopover in migratory routes for various bird species. Two field missions documented this event: the first confirmed the lake’s reappearance, while the second recorded the resurgence of the ecosystem and the return of migratory birds, last observed in the lake in 1968. The lake’s surface water extent, which had been completely dry, expanded dramatically, reaching over 80 km² after the first storm and subsequently increasing to approximately 146 km² following the second. This event has drawn considerable attention from international and national media. The revival was monitored using satellite imagery from Landsat 8 and 9 and Sentinel-2A, processed through Google Earth Engine (GEE), with the Normalized Difference Water Index (NDWI) applied to detect water presence. A time-series analysis revealed significant changes in the lake’s surface water extent following the rainfall. This study emphasizes the need for proactive support to preserve Lake Iriqui, aligning with sustainable development goals: SDG 15 (Life on Land) and SDG 8 (Decent Work and Economic Growth). These goals highlight the importance of sustainable water resource management, biodiversity conservation, and eco-tourism initiatives to benefit local communities. Full article

The rapid detection of landslide phenomena that may be triggered by extreme rainfall events is a critical point concerning timely response and the implementation of mitigation measures. The main goal of the present study is to identify susceptible areas by estimating changes in the Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), Bare Soil Index (BSI), and Synthetic Aperture Radar (SAR) amplitude ratio before and after extreme rainfall events. The developed methodology was utilized in a case study of Storm Daniel, which struck central Greece in September 2023, with a focus on the Mount Pelion region on the Pelion Peninsula. Using Google Earth Engine, we processed satellite imagery to calculate these indices, enabling the assessment of vegetation health, soil moisture, and exposed soil areas, which are key indicators of landslide activity. The methodology integrates these indices with a Weight of Evidence (WofE) model, previously developed to identify regions of high and very high landslide susceptibility based on morphological parameters like slope, aspect, plan and profile curvature, and stream power index. Pre- and post-event imagery was analyzed to detect changes in the indices, and the results were then masked to focus only on high and very high susceptibility areas characterized by the WofE model. The outcomes of the study indicate significant changes in NDVI, NDMI, BSI values, and SAR amplitude ratio within the masked areas, suggesting locations where landslides were likely to have occurred due to the extreme rainfall event. This rapid detection technique provides essential data for emergency services and disaster management teams, enabling them to prioritize areas for immediate response and recovery efforts. Full article

The generation of cloud-free satellite mosaics is essential for a range of remote sensing applications, including land use mapping, ecosystem monitoring, and resource management. This study focuses on remote sensing across the climatic diversity of Hawai’i Island, which encompasses ten Köppen climate zones from tropical to Arctic: periglacial. This diversity presents unique challenges for cloud-free image generation. We conducted a comparative analysis of three cloud-masking methods: two Google Earth Engine algorithms (CloudScore+ and s2cloudless) and a new proprietary deep learning-based algorithm (L3) applied to Sentinel-2 imagery. These methods were evaluated against the best monthly composite selected from high-frequency Planet imagery, which acquires daily images. All Sentinel-2 bands were enhanced to a 10 m resolution, and an advanced weather mask was applied to generate monthly mosaics from 2019 to 2023. We stratified the analysis by cloud cover frequency (low, moderate, high, and very high), applying one-way and two-way ANOVAs to assess cloud-free pixel success rates. Results indicate that CloudScore+ achieved the highest success rate at 89.4% cloud-free pixels, followed by L3 and s2cloudless at 79.3% and 80.8%, respectively. Cloud removal effectiveness decreased as cloud cover increased, with clear pixel success rates ranging from 94.6% under low cloud cover to 79.3% under very high cloud cover. Additionally, seasonality effects showed higher cloud removal rates in the wet season (88.6%), while no significant year-to-year differences were observed from 2019 to 2023. This study advances current methodologies for generating reliable cloud-free mosaics in tropical and subtropical regions, with potential applications for remote sensing in other cloud-dense environments. Full article

The eastern segment of the Sunan-Qilian Fault (ES-SQF) is located within the seismic gap between the 1927 M8.0 Gulang earthquake and the 1932 M7.6 Changma earthquake in China. It also aligns with the extension direction of the largest surface rupture zone associated with the 2022 Mw6.7 Menyuan earthquake. Understanding the activity parameters of this fault is essential for interpreting strain distribution patterns in the central–western segment of the Qilian–Haiyuan fault zone, located along the northeastern margin of the Tibetan Plateau, and for evaluating the seismic hazards in the region. High-resolution Google Earth satellite imagery and UAV (Unmanned Aerial Vehicle)-based photogrammetry provide favorable conditions for detailed mapping and the study of typical landforms along the ES-SQF. Combined with field geological surveys, the ES-SQF is identified as a continuous, singular-fault structure extending approximately 68 km in length. The fault trends in the WNW direction and along its trace, distinctive features, such as ridges, gullies, and terraces, show clear evidence of synchronous left lateral displacement. This study investigates the Qingsha River and the Dongzhong River. High-resolution digital elevation models (DEMs) derived from UAV imagery were used to conduct a detailed mapping of faulted landforms. An analysis of stripping trench profiles and radiocarbon dating of collected samples indicates that the most recent surface-rupturing seismic event in the area occurred between 3500 and 2328 y BP, pointing to the existence of an active fault from the Holocene epoch. Using the LaDiCaoz program to restore and measure displaced terraces at the study site, combined with geomorphological sample collection and testing, we estimated the fault’s slip rate since the Holocene to be approximately 2.0 ± 0.3 mm/y. Therefore, the ES-SQF plays a critical role in strain distribution across the central–western segment of the Qilian–Haiyuan fault zone. Together with the Tuolaishan fault, it accommodates and dissipates the left lateral shear deformation in this region. Based on the slip rate and the elapsed time since the last event, it is estimated that a seismic moment equivalent to Mw 7.5 has been accumulated on the ES-SQF. Additionally, with the significant Coulomb stress loading on the ES-SQF caused by the 2016 Mw 5.9 and 2022 Mw 6.7 Menyuan earthquakes, there is a potential for large earthquakes to occur in the future. Our results also indicate that high-resolution remote sensing imagery can facilitate detailed studies of active tectonics. Full article

This study conducted multi-sensor image classification by utilizing Google Earth Engine (GEE) and applying satellite imagery from Korean Multi-purpose Satellite 3 (KOMPSAT-3), KOMPSAT-5 SAR, Compact Advanced Satellite 500-1 (CAS500-1), Sentinel-1, and Sentinel-2 within GEE. KOMPSAT-3/5 and CAS500-1 images are not provided by GEE. The land-use and land-cover (LULC) classification was performed using the random forest (RF) algorithm provided by GEE. The study experimented with 10 cases of various combinations of input data, integrating Sentinel-1/-2 imagery and high-resolution imagery from external sources not provided by GEE and those normalized difference vegetation index (NDVI) data. The study area is Boryeong city, located on the west coast of Korea. The classified objects were set to six categories, reflecting the region’s characteristics. The accuracy of the classification results was evaluated using overall accuracy (OA), the kappa coefficient, and the F1 score of the classified objects. The experimental results show a continued improvement in accuracy as the number of applied satellite images increased. The classification result using CAS500-1, Sentinel-1/-2, KOMPSAT-3/5, NDVI from CAS500-1, and NDVI from KOMPSAT-3 achieved the highest accuracy. This study confirmed that the use of multi-sensor data could improve classification accuracy, and the high-resolution characteristics of images from external sources are expected to enable more detailed analysis within GEE. Full article

The demands for growth and prosperity in developing countries have prompted Ogun State to initiate six economic development clusters oriented around its urban areas. However, little attention has been given to the environmental impact of these clusters in relation to temperature change and thermal consequences. Serving as a baseline study for the Abeokuta Cluster, whose implementation is still ongoing, this study analysed the surface urban heat island (SUHI) effects for 2003, 2013, and 2023 to determine whether variations in these effects exist over time. The study utilised satellite imagery from Landsat sensors and the cloud computing power of Google Earth Engine for data collection and analysis. Findings revealed that Abeokuta City experienced varying degrees of high SUHI effects, while the surrounding areas proposed for residential and industrial development in the Abeokuta Cluster showed low SUHI effects. The differences in SUHI effects within Abeokuta City across the years were found to be statistically significant (F_within = 3.158, p = 0.044; F_between = 5.065, p = 0.025), though this was not the case for the Abeokuta cluster as a whole. This study recommends urban planning strategies and policy interventions to combat SUHI effects in Abeokuta City, along with precautionary measures for the Abeokuta Cluster. Full article

Ecological sluices were constructed along the Tarim River to supplement the ecosystem’s water supply. However, the impact of water regulation by these sluices on the surface water area (SWA) and its relationship with the vegetation response remain unclear. To increase the efficiency of ecological water use, it is crucial to study the response of SWA to water control by the ecological gates and its relationship with vegetation restoration. We utilized the Google Earth Engine (GEE) cloud platform, which integrates Landsat-5/7/8 satellite imagery and employs methods such as automated waterbody extraction via mixed index rule sets, field investigation data, Sen + MK trend analysis, mutation analysis, and correlation analysis. Through these techniques, the spatiotemporal variations in SWA in the middle reaches of the Tarim River (MROTR) from 1990–2022 were analyzed, along with the relationships between these variations and vegetation restoration. From 1990–2022, the SWA in the MROTR showed an increasing trend, with an average annual growth rate of 12.47 km² per year. After the implementation of ecological gates water regulations, the SWA significantly increased, with an average annual growth rate of 28.8 km² per year, while the ineffective overflow within 8 km of the riverbank notably decreased. The NDVI in the MROTR exhibited an upward trend, with a significant increase in vegetation on the northern bank after ecological sluice water regulation. This intervention also mitigated the downward trend of the medium and high vegetation coverage types. The SWA showed a highly significant negative correlation with low-coverage vegetation within a 5-km range of the river channel in the same year and a significant positive correlation with high-coverage vegetation within a 15-km range. The lag effect of SWA influenced the growth of medium- and high-coverage vegetation. These findings demonstrated that the large increase in SWA induced by ecological gate water regulation positively impacted vegetation restoration. This study provides a scientific basis for water resource regulation and vegetation restoration in arid regions globally. Full article