High-resolution Satellite Imagery Research Articles

The Use of High-Resolution Satellite Imagery to Determine the Status of a Large-Scale Outbreak of Southern Pine Beetle

Timely detection of insect infestation (or other disturbance) in a forest is vital for an adequate response plan to be developed. To determine the status of an active infestation of southern pine beetle (Dendroctonus frontalis) in the Bienville National Forest, WorldView-2 imagery was utilized. Principal components analysis (PCA) was performed and correlated with spectral reflectance bands to assess differences between the classification of spectral reflectance bands and principal components. Unsupervised classification of combinations of principal components (e.g., combining principal components 1 and 2, principal component 1 alone, and principal component 2 alone) was performed and compared with combinations of principal component correlations with spectral reflectance bands (e.g., all bands, bands 1–5, bands 6–8, and bands 2, 4, and 5). Combining principal components 1 and 2 was more accurate than other methods, closely followed by spectral bands 1–5. Employing PCA will aid resource managers in quickly detecting areas of active insect infestation and allow them to deploy adequate response measures to prevent or mitigate continued outbreaks.

Enhancing global rainfall interception loss estimation through vegetation structure modeling

Accurate estimates of rainfall interception loss are crucial for modeling the water balance of forested areas. However, considerable regional variability exists in the interception process, and much uncertainty remains. This study enhances the estimation of rainfall interception loss at the global scale by integrating remote sensing products into the parameterization of Gash’s analytical model. We refer to this enhanced configuration as the Global Interception Model (GIM). High-resolution satellite imagery was used to derive vegetation indices and spectral reflectance, which were then employed in linear regression models to estimate canopy cover fraction (c) and vegetation water storage capacity (Sv). Their importance in ecological processes, and land and water resource management, makes the modeling of these parameters of particular interest. The other two parameters required to run the Gash model, namely the mean rainfall and evaporation rates under saturated canopy conditions, were obtained via the integration of MWSEP and ERA5-Land meteorological products. Modeling performance was evaluated using in situ measurements and gridded datasets. GIM estimates exhibited a superior performance statistic when compared to PMLv2 and GLEAMv3.7a. Our results demonstrate the high potential of this approach for improving the accuracy of rainfall interception loss estimates from local to global scales.

Temporal evolution of roof collapse from tephra fallout during the 2021-Tajogaite eruption (La Palma, Spain)

Although dominantly effusive, the 2021 Tajogaite eruption from Cumbre Vieja volcano (La Palma, Spain) produced a wide tephra blanket over 85 days of activity. About one month after the eruption onset, clean-up operations were implemented to mitigate the impact of tephra load on primary buildings. Here, we present a post-event impact assessment of 764 primary buildings, which expands our empirical knowledge of building vulnerability to tephra fallout to include impacts from long-lasting eruptions. Field observations are analyzed in the perspective of existing fragility curves, high-resolution satellite imagery and a reconstruction of the spatio-temporal evolution of the tephra blanket to characterize the evolution of roof collapse due to static loads over time. Thanks to a chronological correlation between the temporal evolution of tephra sedimentation and the timing of clean-up operations, we quantified their effectiveness in mitigating roof collapse. If no clean-up measures had been taken 11% of the surveyed buildings would have exceeded a 75% probability of roof collapse, while only 10 roof collapses have been observed (1.3% of the analysed buildings). This work provides key insights for further development of emergency plans for the management of long-lasting eruptions characterised by the sustained emission of tephra over weeks to months.

DSCA-PSPNet: Dynamic spatial-channel attention pyramid scene parsing network for sugarcane field segmentation in satellite imagery.

Sugarcane plays a vital role in many global economies, and its efficient cultivation is critical for sustainable development. A central challenge in sugarcane yield prediction and cultivation management is the precise segmentation of sugarcane fields from satellite imagery. This task is complicated by numerous factors, including varying environmental conditions, scale variability, and spectral similarities between crops and non-crop elements. To address these segmentation challenges, we introduce DSCA-PSPNet, a novel deep learning model with a unique architecture that combines a modified ResNet34 backbone, the Pyramid Scene Parsing Network (PSPNet), and newly proposed Dynamic Squeeze-and-Excitation Context (D-scSE) blocks. Our model effectively adapts to discern the importance of both spatial and channel-wise information, providing superior feature representation for sugarcane fields. We have also created a comprehensive high-resolution satellite imagery dataset from Guangxi's Fusui County, captured on December 17, 2017, which encompasses a broad spectrum of sugarcane field characteristics and environmental conditions. In comparative studies, DSCA-PSPNet outperforms other state-of-the-art models, achieving an Intersection over Union (IoU) of 87.58%, an accuracy of 92.34%, a precision of 93.80%, a recall of 93.21%, and an F1-Score of 92.38%. Application tests on an RTX 3090 GPU, with input image resolutions of 512 × 512, yielded a prediction time of 4.57ms, a parameter size of 22.57MB, GFLOPs of 11.41, and a memory size of 84.47MB. An ablation study emphasized the vital role of the D-scSE module in enhancing DSCA-PSPNet's performance. Our contributions in dataset generation and model development open new avenues for tackling the complexities of sugarcane field segmentation, thus contributing to advances in precision agriculture. The source code and dataset will be available on the GitHub repository https://github.com/JulioYuan/DSCA-PSPNet/tree/main.

Geomorphological and hydrological controls on sediment export in earthquake-affected catchments in the Nepal Himalaya

Abstract. Large earthquakes can contribute to mountain growth by building topography but also contribute to mass removal from mountain ranges through widespread mass wasting. On annual to decadal or centennial timescales, large earthquakes also have the potential to significantly alter fluvial sediment dynamics if a significant volume of the sediment generated reaches the fluvial network. In this contribution, we focus on the Melamchi–Indrawati and Bhote Koshi rivers in central Nepal, which have both experienced widespread landsliding associated with the 2015 Gorkha (Nepal) earthquake. Using a time series of high-resolution satellite imagery, we have mapped exposed sediment along the rivers from 2012–2021 to identify zones of active channel deposition and document changes over time. Counter to expectations, we show negligible increases in coarse-sediment accumulation along both river corridors since the Gorkha earthquake. However, an extremely high-concentration flow event on 15 June 2021 caused an approximately 4-fold increase in exposed sediment along a 30 km reach of the channel with up to 12 m of channel aggradation in the Melamchi–Indrawati rivers; this event was localised and did not impact the neighbouring Bhote Koshi catchment. Based on published reports, new helicopter-based photography, and satellite data, we demonstrate that this event was sourced from a localised rainfall event between 4500 and 4800 m and that a significant fraction of the sediment was supplied from sources that were unrelated to the landslides generated by the Gorkha earthquake.

Automatic Detection of Phytophthora pluvialis Outbreaks in Radiata Pine Plantations Using Multi-Scene, Multi-Temporal Satellite Imagery

This study demonstrates a framework for using high-resolution satellite imagery to automatically map and monitor outbreaks of red needle cast (Phytophthora pluvialis) in planted pine forests. This methodology was tested on five WorldView satellite scenes collected over two sites in the Gisborne Region of New Zealand’s North Island. All scenes were acquired in September: four scenes were acquired yearly (2018–2020 and 2022) for Wharerata, while one more was obtained in 2019 for Tauwhareparae. Training areas were selected for each scene using manual delineation combined with pixel-level thresholding rules based on band reflectance values and vegetation indices (selected empirically) to produce ‘pure’ training pixels for the different classes. A leave-one-scene-out, pixel-based random forest classification approach was then used to classify all images into (i) healthy pine forest, (ii) unhealthy pine forest or (iii) background. The overall accuracy of the models on the internal validation dataset ranged between 92.1% and 93.6%. Overall accuracies calculated for the left-out scenes ranged between 76.3% and 91.1% (mean overall accuracy of 83.8%), while user’s and producer’s accuracies across the three classes were 60.2–99.0% (71.4–91.8% for unhealthy pine forest) and 54.4–100% (71.9–97.2% for unhealthy pine forest), respectively. This work demonstrates the possibility of using a random forest classifier trained on a set of satellite scenes for the classification of healthy and unhealthy pine forest in new and completely independent scenes. This paves the way for a scalable and largely autonomous forest health monitoring system based on annual acquisitions of high-resolution satellite imagery at the time of peak disease expression, while greatly reducing the need for manual interpretation and delineation.

Land cover changes and hydropower in Bhutan: Analyzing trade-offs in economic and ecosystem impacts

Hydropower is recognized as a vital renewable, stable and clean energy source that plays a crucial role in sustainable development. However, it often entails significant environmental impacts on aquatic and terrestrial ecosystems, particularly in mountainous regions where its potential is greatest. This study assesses the land cover changes driven by the development of hydropower projects in Bhutan, specifically the projects Punatsangchu I, II, and Mangdechu, with a combined capacity of 2940 MWp. We employed high-resolution satellite imagery alongside historical land use data to quantify these changes. Our analysis reveals that over the course of around 17 years, 1400 ha of forest and 270 ha of agricultural land were cleared, leading to an average annual economic cost of USD 7.6 million. The relative forest cover loss, measured at 0.5 ha MWp−1, was significantly lower than earlier estimates of 2 ha MWp−1. The construction of transmission lines, often a neglected aspect, accounted for the majority (>80 %) of the forest area cleared. Conducting an economic analysis, the annual net benefits of hydropower generation and transmission from these plants are estimated at USD 217 million, about 9 % of Bhutan's 2020 GDP. However, these benefits significantly diminish to USD 8.6 million annually when only considering the transmission infrastructure. The study reveals that the trade-offs between the economic benefits of hydropower and the loss of ecosystem services are relatively modest but become more pronounced when excluding generation benefits and applying higher values to ecosystem services. Although the study assumes a complete loss of ecosystem services, the creation of transmission line corridors contributes to a higher landscape heterogeneity potentially benefitting biodiversity. The findings have significant implications for Bhutan's policy-making in spatial planning, energy, forestry, and agriculture, and highlight areas for further research on hydropower's environmental and economic impacts.

A generalized framework for agricultural field delineation from high-resolution satellite imageries

ABSTRACT Accurate digital data on agricultural fields are crucial for various agriculture applications. While deep learning methods have shown promise in delineating fields from high-resolution imagery, there is a lack of research evaluating key techniques for field boundary detection. Challenges also exist in converting detection results into high-quality fields. This study addresses these issues and proposes a generalized framework for agricultural field delineation (GF-AFD). First, we identify three key techniques for field boundary detection and apply them to MPSPNet model. Ablation and comparison experiments demonstrate significant performance enhancements due to techniques. They also prove effective for DeeplabV3+ model, which shares a similar architecture. The modified models outperform U-Net-based models and approach the state-of-the-art models. Second, we show that performing region segmentation on boundary results yields improved field shapes. To address weak boundary loss and unstable parameters issues in existing segmentation-based methods, we introduce the OWT method to enhance weak boundaries directionally before segmentation. We also develop a hierarchical merging method, leveraging the observational hierarchy of fields, resulting in stable parameters across regions and models. The proposed GF-AFD framework was validated cross three diverse Chinese counties. The results demonstrate the framework's robust performance, providing a valuable solution for delineating agricultural fields.

Use of satellite imagery to estimate distribution and abundance of Cumberland Sound beluga whales reveals frequent use of a glacial river estuary

Limiting disturbance in critical habitats is an important part of ensuring the well-being and sustainability of populations at risk, such as Cumberland Sound beluga whales (Delphinapterus leucas). Using non-disruptive Very High Resolution (VHR) satellite imagery, an emerging tool in cetacean monitoring, we aimed to estimate summer abundance and identify critical habitat for Cumberland Sound beluga whales. Specifically we looked in fiords that comprise their summer distribution, such as Clearwater Fiord where there is a large estuary, an important habitat to many beluga populations. Satellite images of the area were collected in 2020 and 2021, at 30 cm resolution, and in 2022 at 50 cm resolution. We evaluated beluga whale distribution using Kernel density, and identified critical habitats as areas consistently part of the beluga whale core distribution across years. Clearwater Fiord abundance estimates were corrected for whales that were too deep to be identified in the images. The estimates were significantly lower in 2021 (197 whales, 95%CI: 180-216) and 2022 (194 whales, 95%CI: 172-218) compared to 2020 (393 whales, 95%CI: 366-422). Other fiords were only imaged in 2021 and 2022, resulting in average corrected abundance estimates for all fiords of 462 (95% CI: 425-502) and 252 (95%CI: 226-280) beluga whales, respectively. Downsampling of 30 cm images to 50 cm resulted in up to 45% fewer whales detected. The only critical habitat identified within the summer distribution was in Clearwater Fiord, in or near the estuary freshwater plume and in a bay to the west of the plume. The identified critical habitats should be areas of consideration in the continued discussion on the protection and sustainability of the Cumberland Sound beluga whale population.

Integrating Satellite and UAV Technologies for Maize Plant Height Estimation Using Advanced Machine Learning

The integration of aerial monitoring, utilizing both unmanned aerial vehicles (UAVs) and satellites, alongside sophisticated machine learning algorithms, has witnessed a burgeoning prevalence within contemporary agricultural frameworks. This study endeavors to systematically explore the inherent potential encapsulated in high-resolution satellite imagery, concomitantly accompanied by an RGB camera seamlessly integrated into an UAV. The overarching objective is to elucidate the viability of this technological amalgamation for accurate maize plant height estimation, facilitated by the application of advanced machine learning algorithms. The research involves the computation of key vegetation indices—NDVI, NDRE, and GNDVI—extracted from PlanetScope satellite images. Concurrently, UAV-based plant height estimation is executed using digital elevation models (DEMs). Data acquisition encompasses images captured on days 20, 29, 37, 44, 50, 61, and 71 post-sowing. The study yields compelling results: (1) Maize plant height, derived from DEMs, demonstrates a robust correlation with manual field measurements (r = 0.96) and establishes noteworthy associations with NDVI (r = 0.80), NDRE (r = 0.78), and GNDVI (r = 0.81). (2) The random forest (RF) model emerges as the frontrunner, displaying the most pronounced correlations between observed and estimated height values (r = 0.99). Additionally, the RF model’s superiority extends to performance metrics when fueled by input parameters, NDVI, NDRE, and GNDVI. This research underscores the transformative potential of combining satellite imagery, UAV technology, and machine learning for precision agriculture and maize plant height estimation.

Forest Disturbance Monitoring Using Cloud-Based Sentinel-2 Satellite Imagery and Machine Learning.

Forest damage has become more frequent in Hungary in the last decades, and remote sensing offers a powerful tool for monitoring them rapidly and cost-effectively. A combined approach was developed to utilise high-resolution ESA Sentinel-2 satellite imagery and Google Earth Engine cloud computing and field-based forest inventory data. Maps and charts were derived from vegetation indices (NDVI and Z∙NDVI) of satellite images to detect forest disturbances in the Hungarian study site for the period of 2017-2020. The NDVI maps were classified to reveal forest disturbances, and the cloud-based method successfully showed drought and frost damage in the oak-dominated Nagyerdő forest of Debrecen. Differences in the reactions to damage between tree species were visible on the index maps; therefore, a random forest machine learning classifier was applied to show the spatial distribution of dominant species. An accuracy assessment was accomplished with confusion matrices that compared classified index maps to field-surveyed data, demonstrating 99.1% producer, 71% user, and 71% total accuracies for forest damage and 81.9% for tree species. Based on the results of this study and the resilience of Google Earth Engine, the presented method has the potential to be extended to monitor all of Hungary in a faster, more accurate way using systematically collected field-data, the latest satellite imagery, and artificial intelligence.

Developing the health effect assessment of landscape (HEAL) Tool: Assessing the health effects of community greenspace morphology design on non-communicable diseases

Neighborhood greenspace benefits health, yet few tools are available for estimating the health consequences of community greenspace design alternatives, especially prior to the implementation of a landscape design plan. Herein we present a machine learning based tool for predicting the prevalence of non-communicable diseases based on landscape design maps at the community scale. We achieve this based on data collected in five major metropolises in the United States. By using high-resolution satellite imagery and remote sensing technologies, landscape spatial design characteristics were extracted through spatial pattern analysis, allowing the measurement of verdancy, fragmentation, connectedness, aggregation, and shape of greenspaces. We established a model to estimate the prevalence of poor mental health, coronary heart disease, stroke, diabetes, chronic obstructive pulmonary disease, and physical inactivity at the census tract level by adopting a combination of random forest decision tree algorithm and spatial Gaussian process models. Model accuracy was found to be significantly higher than ordinary regression models. The model accounted for very high levels of variance in the specified morbidities; viz., poor mental health (97%), heart disease (93%), stroke (93%), diabetes (95%), COPD (94%), and physical inactivity (98%). This tool is implemented using a freely available programming language (R), and we offer the model accessible to the public. This tool enables urban planners and landscape designers to assess and compare the health effects of different greenspace design plans prior to implementation, thus providing policymakers and designers with evidence-rich alternatives during the health-promoting greenspace planning process.

Spatio-temporal NDVI changes of mangrove forest in West Bangkalan using high resolution imagery

Mangrove play a crucial role in coastal ecosystem, both ecologically and economically. The phenomenon of land use change in coastal areas is a serious issue, especially for mangrove ecosystems. Currently there is one of the data with the High Resolution Imagery category that can be used as an analysis of coastal areas. High resolution data can provide detailed information on changes in coastal areas. The case study conducted in this analysis is on the west coast of Bangkalan Regency, precisely in Arosbaya District. The assessment carried out in this study is the analysis of temporal variations in the Normalize Different Vegetation Index (NDVI) value in mangrove forest areas using High Resolution satellite imagery. The data used is PlanetScope image with 3 m spatial resolution with 4 spectral bands from 2018-2023. The results of the analysis show that the average value of NDVI in the study area is 0.66 with a quite high value distribution in the western and eastern parts. The temporal standard deviation value of NDVI shows that some locations have high values, reaching 0.5 in some locations. Analysis of the trend of change shows that locations with high standard deviation values have a tendency to have increasing trend values in the north (>0.2 per year) and there is also a decreasing trend in the south (<-0.2 per year). After identification, areas with increasing (positive) NDVI trends are areas that have experienced mangrove rehabilitation in recent years. While in areas with a downward trend there is a change in land use that was previously a mangrove forest area into ponds.

Enhancing the Detection of Coastal Marine Debris in Very High-Resolution Satellite Imagery via Unsupervised Domain Adaptation

Enhancing the Detection of Coastal Marine Debris in Very High-Resolution Satellite Imagery via Unsupervised Domain Adaptation

A modern method for building damage evaluation using deep learning approach - Case study: Flash flooding in Derna, Libya

Year after year, floods become more and more a frequent and destructive force of nature, causing significant infrastructure losses and loss of life. An accurate and rapid assessment is required to determine the degree of contamination. The present study proposes a modern method for building damage assessment using deep learning during the flash flood of Derna, Libya. For this reason, we first exploited SAR satellite data, captured before and after the flood, to accurately determine the flood extent. Next, the footprint of affected buildings within this extent was extracted using a deep learning approach (U-Net model) based on high-resolution satellite imagery (30 cm) from MAXAR. Finally, an additional analysis was carried out using VIIRS VNP46A2 data (500 m spatial resolution) to analyse the night light assessment. The results demonstrate the effectiveness of this method, given that 5877 buildings were submerged by water and 2002 buildings were totally or partially destroyed. Also taking into account the estimated night light, Derna's power supply was reduced by over 90% after the floods. The suggested approach is an effective tool for comprehending the global effects of floods and aiding in relief efforts.

Leveraging Deep Learning for High-Resolution Optical Satellite Imagery From Low-Cost Small Satellite Platforms

Leveraging Deep Learning for High-Resolution Optical Satellite Imagery From Low-Cost Small Satellite Platforms

Using Ray Tracing to Improve Bridge Monitoring With High-Resolution SAR Satellite Imagery

Using Ray Tracing to Improve Bridge Monitoring With High-Resolution SAR Satellite Imagery

Evaluation of U-Net transfer learning model for semantic segmentation of landslides in the Colombian tropical mountain region

Landslides in tropical regions, like the Colombian Andean region, pose unique challenges due to factors such as intense rainfall, steep slopes, and complex terrains. Mapping historical and current landslide activity through inventory maps is essential in tropical mountainous regions. While satellite data is commonly used for mapping, it can be time-consuming and manual-intensive, limiting inventory availability. Deep Learning (DL) models, especially Convolutional Neural Networks (CNNs), have shown promise in remote sensing applications with High Resolution (HR) imagery, including landslide detection. Despite advancements, their use in this field is still relatively limited. This study assesses the effectiveness of U-Net model, for automated landslide detection using spectral data from optical satellite imagery (RGB bands), two DEM-derived geo-indices (slope and curvature), and two Synthetic Aperture Radar (SAR) layers (VV amplitude pre- and post-landslide event in May 2015) across three image models (3, 5, and 7 bands). Initially, data is combined into multiband images, and the model is trained in the “La Argelia” river basin in Colombia’s Pacific region. Subsequently, the model is tested in the “La Liboriana” river basin in the western Andean region. The landslide detection results within the inference area are validated by comparing them with the landslide inventory and segmentation results. The U-Net model demonstrates good performance (F1-score around 0.70) for landslide detection, as confirmed in various geographical settings. By utilizing DL models and combining high-resolution satellite imagery, topographical, and SAR data, a comprehensive space-time mapping of landslides can be achieved. This approach has the potential to greatly improve the accuracy and effectiveness of landslide mapping, offering a more holistic view of the temporal dynamics related to these natural hazards.

Landslide Susceptibility Analysis of Jugal Rural Municipality, Sindhupalchok

Hilly and mountainous areas of Nepal, with challenging terrain, young geology, and heavy monsoon rainfall, are susceptible to landslides and slope instability. To analyze and prepare landslide susceptibility maps, this study selects a typical hilly area, the Jugal Rural Municipality in Sindhupalchok district. Twelve factors contributing to landslides were considered, including slope, aspect, elevation, geology, land use, proximity to roads and drainage, plan curvature, profile curvature, NDVI (Normalized Difference Vegetation Index), soil type and rainfall. Moreover, 286 landslides were identified using high-resolution satellite imagery and field verification as the landslide inventory. These landslides were then randomly divided into two sets: 70% for training and 30\% for validation. Bivariate statistical analysis was performed using factor maps and the landslide inventory map. Notably, the analysis revealed a Prediction Rate (PR) of 9.35 for 'Land use', the highest among all factors considered. Since land use is a dynamic factor, we recommend conducting an analysis of land use changes and their impact on landslide susceptibility. Such an assessment would be invaluable during the planning and execution phases of development projects in Nepal's disaster-prone regions.

Opportunities and Challenges of Remote Sensing, Geospatial Data, and Machine Learning in Obtaining Accessibility and Location Information for Sustainable Development in Indonesia

With the advancement of technologies so does the data collection method which creates a large, rapid, and diverse stream of data. Statistic Indonesia (BPS) has also encouraged to utilize this by starting to collect geospatial information on respondents and public facilities. To keep up with this a change needs to be made in processing methods to accommodate massive, high-dimensional, and multiform data collected in different forms such as machine learning. This progression also opens up a new opportunity for tackling various statistical data problems such as accessibility and location data. Remote sensing is one of the big data sources that undergoes a lot of changes shown in the high spatial and temporal resolution satellite imagery availability, together with the BPS geotagging data shows great promise in classifying land use and geospatial analysis. Even so, there are still some challenges in remote sensing as well as other geospatial data utilization. The goals of this review paper are to study the opportunities and challenges in utilizing remote sensing, geospatial data, and machine learning for accessibility and location information. In this paper, we explore the possibilities and limitations in its implementation into SDGs indicators that involve accessibility and location such as indicators 9.1.1, 11.1.1, 11.2.1, 11.3.1, and 11.7.1 including other variables needed for the calculation like access to public facilities. Moreover, our experiment using geotagging data shows potential in improving proportion estimation when compared to using a simple ratio. Our DEGURBA following the UN definition using machine learning LULC for dasymetric mapping also provides more insight compared to the existing data. We can conclude that there are great opportunities in applying remote sensing and other geospatial data to monitor the accessibility and location to further sustainable development in Indonesia.