Satellite Images Research Articles

The Role of Google Earth Engine in Flood Disaster Management: A Review of Capabilities and Challenges

This article provides a comprehensive overview of flood mapping using Google Earth Engine (GEE), emphasizing its significance in disaster management and mitigation. Flood mapping is crucial for understanding risks and preparing for flood events, which are becoming more frequent and severe due to climate change. GEE's advanced capabilities in processing and analyzing vast datasets of satellite imagery offer a potent tool for rapid and accurate flood mapping. Studies reviewed demonstrate GEE's application in various contexts, highlighting its effectiveness in generating timely and precise flood maps using methodologies like image processing techniques, machine learning algorithms, and hydrological modeling. Challenges such as technical complexity and data availability are noted, alongside the potential for future advancements integrating AI and big data analytics to enhance flood risk management strategies. The paper underscores GEE's role in advancing flood mapping efforts, contributing to better preparedness and response to flood disasters worldwide.

A Study on the Spatial Morphological Evolution and Driving Factors of Coral Islands and Reefs in the South China Sea Based on Multi-Source Satellite Imagery

The spatial morphology of coral islands and reefs is a fundamental physical and ecological attribute that reflects the developmental and evolutionary processes of coral islands and reefs. The spatial morphology of coral islands and reefs in the South China Sea is highly dynamic. Understanding the evolutionary trends of the spatial morphology of these coral islands and reefs is crucial for their sustainable development and utilization. This study proposes a set of stability evaluation indicators for reef spatial morphology and conducts a systematic analysis of the spatial morphological changes in coral islands and reefs in the South China Sea over the past 15 years, based on 96 satellite images. Additionally, the driving factors behind these changes are explored and discussed. The results indicate the following: (1) The spatial morphology of the Xisha islands and reefs exhibits more significant changes compared to the Nansha islands and reefs. Although both the Xisha and Nansha islands and reefs areas are increasing, the area change in Xisha is 1.3 times greater than that in Nansha. (2) The spatial morphology of the Xisha islands and reefs is shifting in all directions, while the Nansha islands and reefs show a more pronounced northwestward movement. (3) Both the Xisha and Nansha islands and reefs show an overall growth trend, with the growth rate of the Xisha islands and reefs being faster than that of the Nansha islands and reefs. The average growth rate of the Xisha islands and reefs is 1.77 times that of the Nansha islands and reefs. This research provides significant scientific evidence for the protection and resource management of coral islands and reefs in the South China Sea.

Landsat Surface Product Validation Instrumentation: The BigMAC Exercise

Users of remotely sensed Earth optical imagery are increasingly demanding a surface reflectance or surface temperature product instead of the top-of-atmosphere products that have been produced historically. Validating the accuracy of surface products remains a difficult task since it involves assessment across a range of atmospheric profiles, as well as many different land surface types. Thus, the standard approaches from the satellite calibration community do not apply, and new technologies need to be developed. The Big Multi-Agency Campaign (BigMAC) was developed to assess current technologies that might be used for the validation of surface products derived from satellite imagery, with emphasis on Landsat. Conducted in August 2021, in Brookings, SD, USA, a variety of measurement technologies were fielded and assessed for accuracy, precision, and deployability. Each technology exhibited its strengths and weaknesses. Handheld spectroradiometers are capable of surface reflectance measurements with accuracies within the 0.01–0.02 absolute reflectance units, but these are expensive to deploy. Unmanned Aircraft System (UAS)-based radiometers have the potential of making measurements with similar accuracy, but these are also difficult to deploy. Mirror-based empirical line methods showed improved accuracy potential, but their deployment also remains an issue. However, there are inexpensive radiometers designed for long-term autonomous use that exhibited good accuracy and precision, in addition to being easy to deploy. Thermal measurement technologies showed an accuracy potential in the 1–2 K range, and some easily deployable instruments are available. The results from the BigMAC indicate that there are technologies available today for conducting operational surface reflectance/temperature measurements, with strong potential for improvements in the future.

From Flood Mitigation to Environmental and Socioeconomic Disruption: A Case Study of the Langue de Barbarie Sand Spit Breach

In October 2003, an artificial canal was dug across the Langue de Barbarie sand spit at the mouth of the Senegal River to prevent the city of Saint-Louis (Senegal) from being submerged by floods. This study aimed to explore the multiple facets of this sudden environmental change to provide a holistic overview of the situation and a better understanding of man-made alterations of coastal features, a crucial step for implementing efficient management of such situations and developing appropriate mitigation and adaptation policies. Satellite imagery from the US Geological Survey was used to show the historical evolution of the breach, and a comprehensive overview of the existing literature was conducted to explore its hydrological, geomorphological, ecological, and socioeconomic impacts. Although the canal facilitated the rapid evacuation of floodwaters and saved the city from a major flooding event, the breach widened considerably, becoming the new river mouth and resulted in unforeseen adverse consequences. Environmental consequences included the partial dismantling of the spit, increased tidal range, salinization of land and water, and loss of habitat and local biodiversity. Socioeconomic consequences were severe, including the loss of agricultural land and reduced yields, declining fishing productivity, the destruction of villages, the displacement of entire communities, and the forced migration of many young people. Affected communities developed resilience strategies, with women playing a leading role in these adaptive responses. This study highlights the need for integrated coastal management and policies that consider both environmental and human factors, as well as for future research that will help improve the management of coastal ecosystem alterations.

Remote Sensing-Based Detection and Analysis of Slow-Moving Landslides in Aba Prefecture, Southwest China

Aba Tibetan and Qiang Autonomous Prefecture (Aba Prefecture), located in Southwest China, has complex geological conditions and frequent seismic activity, facing an increasing landslide risk that threatens the safety of local communities. This study aims to improve the regional geohazard database by identifying slow-moving landslides in the area. We combined Stacking Interferometric Synthetic Aperture Radar (Stacking-InSAR) technology for deformation detection, optical satellite imagery for landslide boundary mapping, and field investigations for validation. A total of 474 slow-moving landslides were identified, covering an area of 149.84 km2, with landslides predominantly concentrated in the river valleys of the southern and southeastern regions. The distribution of these landslides is strongly influenced by bedrock lithology, fault distribution, topographic features, proximity to rivers, and folds. Additionally, 236 previously unknown landslides were detected and incorporated into the local geohazard database. This study provides important scientific support for landslide risk management, infrastructure planning, and mitigation strategies in Aba Prefecture, offering valuable insights for disaster response and prevention efforts.

Fast report: preliminary analysis of coseismic landslides in the 2025 M6.4 Dapu earthquake

After the 2025 M6.4 Dapu earthquake, the Agency of Rural Development and Soil and Water Conservation (ARDSWC) identified 29 coseismic landslides using Sentinel-2 and PlanetScope satellite imagery. Two-thirds of these landslides occurred south of the epicenter, indicating a likely southward rupture. These landslides are found to (1) locate in areas where PGA exceeded 250 cm/s2 and PGV over 17 cm/s (2) occur on 30° to 50° slopes, often on southeast- to southwest-facing aspects. Dip slopes and the reactivation of historical landslides were key contributing factors. Although satellite imagery detected fewer landslides than other earthquakes with comparable magnitude, our field surveys revealed numerous fresh landslide scarps in areas with PGA over 400 cm/s2 and PGV around 30 cm/s. Our analysis provides useful information of coseismic landslide behaviors and the triggering factors in the Dapu event. These findings highlight the importance of detailed post-earthquake landslide mapping and field investigations, which provides key information for advanced hazard mitigation plans for seismically affected regions in preparation for the upcoming rainy season.

Application of Deep Learning in Glacier Boundary Extraction: A Case Study of the Tomur Peak Region, Tianshan, Xinjiang

Glaciers are one of the most important water resources in the arid regions of Xinjiang, making it crucial to accurately monitor glacier changes for the region’s sustainable development. However, due to their typical distribution in remote, high-altitude areas, large-scale and long-term field observations are often constrained by the high costs of manpower, resources, and finances. Globally, fewer than 40 glaciers have been monitored for more than 20 years, and, in China, only Glacier No. 1 at the headwaters of the Urumqi River has monitoring records exceeding 50 years. To address these challenges, this study analyzed glacier changes in the Tomur Peak region of the Tianshan Mountains over the past 35 years using Landsat satellite imagery. Through experiments with deep learning models, the results show that the 3-4-5 band combination performed best for glacier boundary extraction. The DeepLabV3+ model, with MobileNetV2 as the backbone, achieved an overall accuracy of 90.44%, a recall rate of 82.75%, and a mean Intersection over Union (IoU) that was 1.6 to 5.94 percentage points higher than other models. Based on these findings, the study further analyzed glacier changes in the Tomur Peak region, revealing an average annual glacier reduction rate of 0.18% and a retreat rate of 6.97 km2·a−1 over the past 35 years. This research provides a more precise and comprehensive scientific reference for understanding glacier changes in arid regions, with significant implications for enhancing our understanding of the impacts of climate change on glaciers, optimizing water resource management, and promoting regional sustainable development.

Detecting the Distribution of Callery Pear (Pyrus calleryana) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning

Detecting the Distribution of Callery Pear (Pyrus calleryana) in an Urban U.S. Landscape Using High Spatial Resolution Satellite Imagery and Machine Learning

The Effect of Land Cover on the Nectar Collection by Honeybee Colonies in Urban and Rural Areas

In the context of increasing urbanisation, the question arises as to whether urban environments can provide honeybee colonies with floral resources comparable to those available in rural areas. The present study sought to evaluate the impact of land cover on nectar collection by bees in urban and rural apiaries. To this end, changes in the mass of 10 hives located in five urban–rural site pairs were monitored over two years (2021–2022) to assess nectar yield, weight loss, and the number of foraging days. The 3 km surroundings of each apiary were analysed using Sentinel-2 satellite imagery from the S2GLC-PL (National Satellite Information System 2025). The analysis identified eight distinct land cover classes: anthropogenic, agricultural, broad-leaved forest, coniferous forest, grassland, shrubs, wetlands, and water bodies. The findings revealed no statistically significant variation in the total nectar collected between urban and rural colonies (72.9 kg vs. 64.5 kg; p > 0.6). However, urban colonies exhibited a significantly higher number of foraging days (67 vs. 56). No significant correlations were identified between specific land cover types and nectar yield. Principal component analysis (PCA) and clustering revealed distinct landscape gradients, yet these did not influence nectar collection. The findings of this study indicate that diverse urban environments have the capacity to support beekeeping to a similar extent as rural areas and may even have superior conditions, provided that the continuity and diversity of nectar plants are maintained.

Tree species composition governs urban phenological responses to warming

Urban environments are typically warmer than surrounding rural areas, providing a unique setting for studying phenological responses to climate warming. Phenological differences between urban and rural trees are driven by local climate and species composition. Yet, the extent to which species composition influences phenological responses to urbanization remains poorly understood. To address this, we combine manipulative experiments, satellite-derived phenology data, and georeferenced tree occurrence records. Our findings show that, across Northern Hemisphere cities, differences in the temperature sensitivity of spring phenology between urban and rural areas are largely driven by urban-rural variation in species composition, surpassing the effects of preseason temperature. This pattern is particularly pronounced in Asian cities, where urban areas exhibit 0.74 ± 0.24 days/°C higher temperature sensitivity than rural areas. In-depth analyses using experiments and high-resolution satellite imagery from Beijing further demonstrate species-specific phenological responses to urbanization, with urban-dominant species exhibiting higher temperature sensitivity in urban environments compared to rural ones. These findings show that both interspecific variation in temperature sensitivity and species-specific responses to urbanization contribute to the pronounced impact of species composition on urban-rural phenological patterns. Our study underscores the importance of considering species composition when studying phenological responses to climate warming, especially in urban contexts.

PreCM: The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation.

Semantic segmentation is an important branch of image processing and computer vision. With the popularity of deep learning, various convolutional neural networks have been proposed for pixel-level classification and segmentation tasks. In practical scenarios, however, imaging angles are often arbitrary, encompassing instances such as water body images from remote sensing and capillary and polyp images in the medical domain, where prior orientation information is typically unavailable to guide these networks to extract more effective features. In this case, learning features from objects with diverse orientation information poses a significant challenge, as the majority of CNN-based semantic segmentation networks lack rotation equivariance to resist the disturbance from orientation information. To address this challenge, this paper first constructs a universal convolutiongroup framework aimed at more fully utilizing orientation information and equipping the network with rotation equivariance. Subsequently, we mathematically design a padding-based rotation equivariant convolution mode (PreCM), which is not only applicable to multi-scale images and convolutional kernels but can also serve as a replacement component for various types of convolutions, such as dilated convolutions, transposed convolutions, and asymmetric convolution. To quantitatively assess the impact of image rotation in semantic segmentation tasks, we also propose a new evaluation metric, Rotation Difference (RD). The replacement experiments related to six existing semantic segmentation networks on three datasets (i.e., Satellite Images of Water Bodies, DRIVE, and Floodnet) show that, the average Intersection Over Union (IOU) of their PreCM-based versions respectively improve 6.91%, 10.63%, 4.53%, 5.93%, 7.48%, 8.33% compared to their original versions in terms of random angle rotation. And the average RD values are decreased by 3.58%, 4.56%, 3.47%, 3.66%, 3.47%, 3.43% respectively. The code can be download from https://github.com/XinyuXu414.

Remote Sensing of Discharge Ratios at River Channel Bifurcations

AbstractRiver channel bifurcations are crucial for distributing water and sediment on floodplains and deltas, but estimating discharge ratios between branches remains challenging. Using satellite imagery and in‐situ discharge data, we demonstrate that bifurcate channel widths can estimate discharge ratios at 23 of 27 bifurcations in 11 rivers worldwide, with good accuracy (R2 = 0.80) in 26 of 33 measurements. An empirical width‐discharge equation derived from 5,740 United States Geological Survey gauging stations further improves accuracy (R2 = 0.82). For best results, branch widths should be measured within one channel width of the bifurcation. The method is ineffective in cases influenced by tributaries, avulsion, or multiple branches. We conclude that channel width is effective for estimating discharge ratios, especially when paired with an empirical width‐discharge equation, potentially enhancing river discharge estimates from the Surface Water and Ocean Topography satellite mission, which currently lacks flow partitioning capabilities for bifurcations.

A multi-rule index to extract brine shrimp from satellite imagery: a case study in Ebinur Lake, China

ABSTRACT Brine shrimp are vital inhabitants of saltwater lakes, contributing significantly to economic and ecological systems. With increasing threats from environmental degradation and overharvesting, effective monitoring is urgently needed. Traditional field sampling methods are limited in scope and efficiency, necessitating a reliable remote sensing-based approach. However, Ebinur Lake’s complex spectral environment, characterized by poor water quality and diverse suspended particulates, poses challenges for satellite remote sensing accuracy. To overcome these issues, we developed a novel multi-rule extraction model based on Landsat data, leveraging the distinct short-wave infrared signatures of brine shrimp to enhance detection accuracy. We evaluated and validated this method using Landsat 8 and Sentinel-2 datasets, achieving a classification accuracy of 94.5% and a kappa coefficient of 0.88, surpassing existing methods. Additionally, our analysis of a decade of Landsat data in Ebinur Lake via Google Earth Engine revealed a correlation between brine shrimp distribution and lake surface area. Our model demonstrates high accuracy and scalability in mapping brine shrimp, making it a valuable tool for long-term, large-scale assessments in saline lakes. This capability holds significant potential for advancing fisheries research and informing conservation strategies.

Reviving Nature: Strategies for Ecosystem Restoration in a Deteriorated Southwestern Nigeria's Forest Reserve

Abstract- Forests are always depleted by human activities. The study focused on the deterioration of the Ikeji-ipetu forest reserve, Osun State. Concurrent methods of data collection were used in this study. Sampled plots of 10 m×10 m was delineated in the forest reserve, the woody species were identified, and the woody tree variables such as height and circumference were measured using an altimeter. The woody tree species were classified into different categories using the Integrated Taxonomic Information System (ITIS). The qualitative method employed was focus group discussion sessions of five elderly people between 45 years and above from one of the communities nearest to the Forest Reserve. The secondary data included a map on a scale of 1:50,000 and satellite imageries ArcGIS 10.1 of 1986 to 2016 of the study area. The study revealed the most abundant woody species was Gmelina arborea (29.9%). The Landsat TM of 1986 showed that the undisturbed land was 88% and that of 2016 (74.86%) with a difference of (13.14%). The average nitrogen value was 22.75 mg/l in forest land and 13.66 mg/l in cultivated land. Data were analyzed using descriptive statistics and content -analysis. A re-afforestation scheme was such as forest regrowth, and regeneration, sustainable resources management practices, and implementation of policies and regulations against illegal logging were some of the few restoration strategies suggested.

A deep learning pipeline to power infrastructure detection in high-resolution satellite images

ABSTRACT Power grids are essential infrastructure systems that form the backbone of modern economies. Ensuring reliable and up-to-date data on power infrastructure is crucial for effective risk management and resilience planning, especially in the face of natural hazards that threaten the stability of these systems. This study introduces an open-source pipeline leveraging deep learning to detect power infrastructure – specifically power towers and poles – from high-resolution satellite imagery. By applying a Faster R-CNN model with a ResNet-101 backbone on Worldview-3 imagery over Vietnam, the study achieved good performance metrics, including an AP50 of 60.6%, an F1-score of 74.7%, and an accuracy of 90.9%. Additionally, the study developed a comprehensive, open-access dataset of power infrastructure annotations, setting a foundation for future research in this field. This research highlights the potential of deep learning models in mapping power infrastructure on a large scale, contributing to risk assessment and improved power system modelling. The framework’s adaptability and proven effectiveness highlight its potential for application across various geographical contexts and in detecting other types of critical infrastructure.

CSDNet: automatic cloud and shadow detection from satellite images based on encoder decoder network

CSDNet: automatic cloud and shadow detection from satellite images based on encoder decoder network

Azov-type spits: long-term monitoring of morphodynamics and vegetation in response to changing environment.

Azov-type spits (ATS) are unique landforms located along the Northern coast of the Sea of Azov (NA) that have no global analogs. They play a vital role in delivering essential ecosystem services and significantly contribute to the economy of southern Ukraine. ATS are highly sensitive and dynamically responsive to environmental changes, including global and local climate changes, rising sea levels, geological shifts in the Ukrainian crystalline shield, internal shifts in the Sea of Azov and various anthropogenic influences. These factors significantly shape the ATS, influencing their capacity to accumulate biogenic material and sediments, thereby impacting vegetation cover, resilience and functioning within their ecological context. Our study on ATS morphodynamics and vegetation changes is based on a 95-year dataset that incorporates retrospective vegetation maps (1927-1929, 1934, 1996-1999), grassland releves (1995-1999) and satellite imagery (1975-2022) using specific standardized indices (NDVI, NDWI, NDMI, Thermal). We employed Earth Remote Sensing (ERS) tools due to the impracticality of field research amid the ongoing military occupation of ATS territories. Climate change vulnerability was assessed by examining surface air temperature and precipitation changes for the periods 1900-2021 and 1991-2021. Meteorological data for NA shows a consistent climate change trend, including rising annual surface temperatures (1.14 ±0.3°C/100 years) and increased annual precipitation (98 ±35 mm/100 years) over the last120 years. Recent decades have witnessed intensified aridization, with up to a 15% drop in precipitation and a 0.8°C per decade temperature increase, accompanied by increased evaporation. Our study reveals the ongoing transformation of ATS and their vegetation, primarily driven by inundation, aggravated by climate change and rising sea levels. ERS tools demonstrated their effectiveness in monitoring environmental changes under challenging circumstances, identifying general trends in the state of plant communities and validating our earlier forecasts for changes in vegetation cover. The increase in the area of halophytic meadow and marsh plant communities occurred alongside a certain decrease in their productivity, while the reduction in sandy-steppe plant community areas was accompanied by an increase in their productivity. The study provides a complex evaluation of the current anthropogenic impacts on the spits and their vegetation.

Enhancing Crop Yield Estimation in Spinach Crops Using Synthetic Aperture Radar-Derived Normalized Difference Vegetation Index: A Sentinel-1 and Sentinel-2 Fusion Approach

Accurate crop yield estimation is crucial for food security and effective crop management in precision agriculture. Previous studies have shown the correlation between remotely sensed data and crop yield, emphasizing the need for continuous time series of radiometric indices from satellite imagery. However, passive sensors are limited by cloud cover, restricting valid image acquisition. This study explored the integration of Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical data to enhance NDVI estimation and yield prediction of spinach. Random Forest Regression models were developed to predict NDVI from SAR data at two scales: (i) a general crop-scale model and (ii) specific plot-scale models. Both scales achieved R2 values above 0.9 for NDVI estimation, with better results at the plot scale. Integrating NDVI values derived from Sentinel-1 significantly improved yield estimation accuracy using NDVI time series compared to using NDVI from Sentinel-2 alone. The results indicated that plot-scale NDVI estimation had the lowest error rates (1.4%) and the highest R2 (0.89), outperforming the crop-scale model. The integration of SAR-based NDVI reduced data gaps caused by cloud cover and enabled earlier, more informed crop management decisions. These findings underscore the importance of SAR-based NDVI estimation for enhancing yield predictions in precision agriculture.

Modelling amphibian road crossing points in a dynamic environment

Abstract Roads are ubiquitous infrastructures that have detrimental effects on wildlife and contribute to increased mortality and fragmentation of animal populations. Although several mitigation measures are available to reduce road impacts, their planning rarely considers the dynamic nature of the environment, which may reflect into temporal variation in habitat suitability and connectivity for animal species. Consequently, the effectiveness of such measures may fall short of expectations. By combining high‐resolution satellite imagery and connectivity modelling, we propose a generalizable approach to identify the most probable crossing points across a barrier at different time snapshots. This information may be pivotal in planning mitigation measures that can take into account dynamic components. We collected occurrence data of three farmland‐adapted anurans and high spatiotemporal definition Sentinel‐2 multispectral images to build habitat suitability models that capture the relationship between the environment and the species within the study area (an agricultural area crossed by a highway). We then projected the models onto six snapshots from two subsequent amphibian breeding seasons. Finally, we used circuit theory‐based connectivity models to identify the areas with the highest probability of highway crossing for each snapshot/species. We found remarkable differences over time for each species, both in suitability and connectivity. Furthermore, the distribution and relative importance of the crossing points changed greatly between the 2 years as well as within the same. Some crossing points were stable over time, while others were important for a specific snapshot. Synthesis and applications. Not considering the spatiotemporal variability of the environment can lead to a loss of crucial information when modelling the localities at which the predicted flows of animals intersect the highway. The dynamics of road‐affected ecosystems can be taken into account using freely available remote sensing data. This can be an important element in achieving the goal of maintaining connectivity and minimizing wildlife mortality.

MSIM: A Multiscale Iteration Method for Aerial Image and Satellite Image Registration

The registration of aerial images and satellite images is a key step in leveraging complementary information from heterogeneous remote sensing images. Due to the significant intrinsic differences, such as scale, radiometric, and temporal differences, between the two types of images, existing multimodal registration methods tend to be either inaccurate or unstable when applied. This paper proposes a coarse-to-fine registration method for aerial images and satellite images based on the multiscale iteration method (MSIM). Firstly, an image pyramid is established, and feature points are extracted based on phase congruency. Secondly, the expression form of image descriptors is improved to more accurately describe image feature points, thereby increasing the matching success rate and achieving coarse registration between images. Finally, multiscale iterations are performed to find accurate matching points from top to bottom to achieve fine registration between images. In order to verify the effectiveness and accuracy of the algorithm, this paper also establishes a set of registration datasets of aerial and satellite captured images. Experimental results show that the proposed algorithm has high accuracy and good robustness, and effectively solves the problem of registration failure in existing algorithms when dealing with heterogeneous remote sensing images that have large scale differences.