Satellite Image Analysis Research Articles

EVALUATION OF TRANSPORT FLOW USING DEEP LEARNING METHODS OF SATELLITE IMAGES

The exponential growth of urbanization has led to increasing problems in traffic management, which require innovative solutions for efficient estimation of traffic flow. Deep learning methods are emerging as a powerful tool for processing and analyzing satellite images, and are being used for traffic flow estimation. This paper describes deep learning-based methods for traffic flow estimation using satellite imagery.

Facilitation cascades across space: Monitoring estuarine foundation species from satellites to the microscope

AbstractEstuaries are productive ecosystems that are vulnerable to human impacts and environmental disturbances. Estuaries are often inhabited by foundation species that facilitate other organisms by creating and modifying habitats. However, spatiotemporal variability and underpinning drivers of facilitation from estuarine foundation species are poorly studied, especially in the context of monitoring and conservation. Here, we combined the analyses of satellite, drone, and camera images, close‐up field sampling of quadrats and individuals, and laboratory microscopy, to quantify co‐occurrences between the cockle Austrovenus stutchburyi and green macroalga Ulva spp., and their associated invertebrate communities, across spatial resolutions and environmental gradients in a New Zealand estuary. We found higher abundance of Ulva in winter and higher abundance of Austrovenus at a site near the ocean. Furthermore, Ulva was, across space and time, often attached to Austrovenus, either live or dead shells, suggesting a hierarchy between a primary (cockle) and secondary (macroalgae) foundation species. Finally, Ulva provided a better habitat for mobile invertebrates than Austrovenus, and thereby increased estuarine diversity through a density‐dependent facilitation cascade, which also was consistent in space and time. Overall, our study showed that facilitation cascades can be indirectly inferred and monitored through remote sensing of foundation species using supplementary imaging methods, and that integration of data across scales allows researchers to better understand the drivers and consequences of facilitation from foundation species. These insights may aid in the development of efficient monitoring strategies and ultimately improve the management of estuarine ecosystems.

Due Diligence for Deforestation-Free Supply Chains with Copernicus Sentinel-2 Imagery and Machine Learning

At COP26, the Glasgow Leaders Declaration committed to ending deforestation by 2030. Implementing deforestation-free supply chains is of growing importance to importers and exporters but challenging due to the complexity of supply chains for agricultural commodities which are driving tropical deforestation. Monitoring tools are needed that alert companies of forest losses around their source farms. ForestMind has developed compliance monitoring tools for deforestation-free supply chains. The system delivers reports to companies based on automated satellite image analysis of forest loss around farms. We describe an algorithm based on the Python for Earth Observation (PyEO) package to deliver near-real-time forest alerts from Sentinel-2 imagery and machine learning. A Forest Analyst interprets the multi-layer raster analyst report and creates company reports for monitoring supply chains. We conclude that the ForestMind extension of PyEO with its hybrid change detection from a random forest model and NDVI differencing produces actionable farm-scale reports in support of the EU Deforestation Regulation. The user accuracy of the random forest model was 96.5% in Guatemala and 93.5% in Brazil. The system provides operational insights into forest loss around source farms in countries from which commodities are imported.

Impact of ash fallout of the 2023 Shiveluch volcano eruption (Kamchatka) on forest vegetation

The ash fallout of Shiveluch volcano (April 11, 2023, Kamchatka) is the most intensive volcanic ash fallout of the last 60 years. We present the results of the reconnaissance fi eld investigations supplemented with analyses of satellite images of the area for estimations of deposits distribution and area aff ected by the ash fallout. We also estimated the properties of fi ne grained ash of andesitic composition and its infl uence on the forest vegetation composed by Picea yezoensis (Siebold et Zucc.) Carrière, Larix cajanderi Mayr и Betula ermanii Cham. As a result of moderate- scale ash fallout in the forest (thickness of freshly deposited ash is 5–8 cm), the negative impact on vegetation was minimal because the ash was fi ne-grained and was deposited on a thick snowpack, and the leaves were not formed yet. The forest vegetation on lower elevations was not damaged at all but strong changes occurred in grass and bush vegetation. We have observed the diminished density of plant coverage, decreased size of grass vegetation and a decreased number of plant species. Calamagrostis purpurea (Trin.) Link. s. l., a broadly represented dominant species among grass vegetation, became less common, but Chamerion angustifolium (L.) Holub became more widespread. The possibility of small plants to grow through the ash layer turned out to be strongly reduced. Mosses and lichens in the forest have been buried under the ash, the recovery could take several decades. We have found a notable impact on plants by ash remobilized by strong wind, this impact is the strongest in the open areas and on forest edges. This process can continue for many years due to the large volume of the deposited ash covering the open spaces of the volcano foot.

Current Distribution of the Turkestan White Stork (Ciconia ciconia asiatica) in Kazakhstan

Over the last 100 years, the range of the White Stork Ciconia ciconia asiatica (Linnaeus, 1758) in Kazakhstan has greatly diminished; it has entirely disappeared in its former eastern and northern ranges, while the number of nesting sites has decreased in the remaining part of its habitat. The most recent specialized studies on the distribution of the White Stork here were conducted in the 1980s. Subsequently, ornithologists were only aware of isolated nests, and in the last 15 years, up until recently, in Kazakhstan, there was only one known active nest in the Zhambyl region. To clarify the current distribution of the White Stork in Kazakhstan, we conducted field research during the breeding season in places of its former distribution in the Zhambyl and Turkestan Regions. Nest surveys were conducted by visual observations using binoculars and a camera with a telephoto lens. During the expedition, 43 inhabited nests of the White Stork were found; information about another 4 nests was obtained from data survey and social networks. Analysis of satellite images allowed us to identify 12 nests located on power line pylons in the southern regions of the republic, specifically in the Keles, Zhetisay, and Maktaaral districts. In total, 59 White Stork nests were found in Kazakhstan. In addition, satellite images revealed more than 120 power line pylons with White Stork nests in the territory of Uzbekistan in close proximity to the Kazakhstan border. All literary and electronic sources available to the authors have been meticulously reviewed. By synthesizing these data, two maps were created: one delineating all recorded White Stork nesting sites across Kazakhstan and its neighboring territories, and the other illustrating the known contemporary and historical ranges of the White Stork in Kazakhstan. A cadastral survey accompanies new nest discoveries of the White Stork. Based on the newly acquired data, we conclude that the White Stork population in Kazakhstan is currently on the rise.

Improving Digital Satellite Image for security purposes

Satellite imagery is employed in many different fields of study. These pictures have serious quality problems. Image enhancement algorithms, however, can improve it in terms of contrast, brightness, feature elimination from noise contents, etc. These algorithms present and analyse the picture's properties by sharpening, focusing, or smoothing the image. Therefore, the specific application determines the goal of picture enhancement. This paper briefly overviews picture enhancement methods that produce optimal and progressive outcomes for satellite images used for secured remote sensing. To do this, various image enhancement techniques are used, which are widely used today to improve image quality across various image processing applications. Some commonly used image enhancement techniques include spatial filtering, contrast stretching, and histogram equalisation. These techniques aim to enhance the visual quality of satellite images by adjusting brightness and contrast and reducing noise. These methods can also improve the interpretability of the images for remote sensing purposes. The enhancement of satellite images finds use in several fields, particularly security. It is essential for security applications, including threat detection, border control, and surveillance. Security professionals may more effectively analyse and understand data to spot any dangers or questionable activity by boosting the visual details and general quality. Keywords: Satellite image analysis; mean filter; secured application; SVM; wavelet transformation

Remote sensing-enhanced transfer learning approach for agricultural damage and change detection: A deep learning perspective

With the continuous advancement of science and technology, there has been a growing awareness of safety among people worldwide. Natural disasters such as wildfires, earthquakes, and floods pose persistent threats to both lives and property on our planet, which serves as our fundamental habitat. While it is impossible to prevent or entirely avert these calamities, rapid identification of affected areas and prompt damage assessment post-disaster can significantly aid in the formulation of effective rescue strategies, ultimately saving more lives. This article delves into the application of transfer learning in satellite image damage assessment—a methodology that involves transferring previously acquired knowledge to enhance a model's adaptability to new tasks. Given the limited availability of datasets for satellite image analysis, transfer learning proves to be an effective approach. Specifically, the study proposes a transfer learning method based on YOLOv5 for satellite image damage assessment. Initially, a general convolutional neural network model is trained using a substantial dataset of natural images. Subsequently, the early layers of this model are frozen, while the later layers undergo training to adapt to satellite image data. Fine-tuning is then employed to further enhance the overall model performance. The results demonstrate that this approach yields a high accuracy rate in satellite image damage assessment. Moreover, compared to conventional deep learning methods, the proposed method effectively leverages pre-trained models' knowledge, thereby reducing data dependency. Additionally, it displays robust generalization capabilities across diverse tasks and datasets, underscoring its potential for facilitating transfer learning across various domains.

Image Analysis and Classification Using HRSVM-CNN for Land-Cover Classification by Using Remote Sensing Images

Objective: To effectively analyze diverse satellite images and derive valuable insights, it's crucial to employ efficient methods for classification and image processing. However, due to imperfections in image formats and sensor data, satellite imagery often contains flaws and inaccuracies, requiring extra steps to enhance its quality. The proposed solution involves two key techniques: segmenting the input image using a Hybrid HRSVM-CNN and classifying the resulting high-resolution remote sensing image using a Convolutional Neural Network. This combined approach addresses the challenges posed by image inconsistencies and aims to improve the accuracy and efficiency of current methods for satellite image analysis. Methods: In this research, a high-resolution Support Vector Machine-Convolutional Neural Network (Hybrid HRSVM-CNN) and texture characteristics are used to create an automated land identification method for satellite Remote sensing (RS) images. This approach's main focus is segmentation using the Bendlet Transform and Improved Chan-Vese, and it also does classification using a Hybrid HRSVM-CNN based on feature extraction and gray-level co-occurrence matrix algorithm. Findings: The proposed classification method's accuracy was evaluated against several other classification algorithms, including Semi-Supervised Graph Based Method (SSG), Conditional Random Fields (CRF), k-Nearest Neighbor (KNN), and Bi-layer Graph-based Learning (BLGL), Support Vector Machine (SVM), and Artificial Neural Networks (ANN). When compared with existing methods, the findings of the proposed method display excellent accuracy of 98.83%. Novelty: To start, an adaptive median filter is used to pre-process the satellite Remote sensing images, removing unwanted noises and other impacts. Following pre-processing, the image is segmented using the Bendlet Transform and Improved Chan-Vese algorithms. Gray-level co-occurrence matrix is utilized to extract texture information, and the Hybrid HRSVM-CNN is then used to categorize the various types of land. These applications frequently have a variety of issues that affect the categorization accuracy. A few significant factors, like location, irregularity, form, and diameter, reduce the process's overall accuracy. This research focuses on presenting a unique Land-Cover classification model in order to address such problems. The UC Merced Land Use dataset was considered in this research. Keywords: Bendlet Transform and Improved Chan­Vese Segmentation, Hybrid HRSVM­CNN, Land detection system, Satellite remote sensing images, Adaptive median filter, Gray­ level co­occurrence matrix

LinkNet-Spectral-Spatial-Temporal Transformer Based on Few-Shot Learning for Mangrove Loss Detection with Small Dataset

Mangroves grow in intertidal zones in tropical and subtropical regions, offering numerous advantages to humans and ecosystems. Mangrove monitoring is one of the important tasks to understand the current status of mangrove forests regarding their loss issues, including deforestation and degradation. Currently, satellite imagery is widely employed to monitor mangrove ecosystems. Sentinel-2 is an optical satellite imagery whose data are available for free, and which provides satellite imagery at a 5-day temporal resolution. Analyzing satellite images before and after loss can enhance our ability to detect mangrove loss. This paper introduces a LSST-Former model that considers the situation before and after mangrove loss to categorize non-mangrove areas, intact mangroves, and mangrove loss categories using Sentinel-2 images for a limited number of labels. The LSST-Former model was developed by integrating a fully convolutional network (FCN) and a transformer base with few-shot learning algorithms to extract information from spectral-spatial-temporal Sentinel-2 images. The attention mechanism in the transformer algorithm may effectively mitigate the issue of limited labeled samples and enhance the accuracy of learning correlations between samples, resulting in more successful classification. The experimental findings demonstrate that the LSST-Former model achieves an overall accuracy of 99.59% and an Intersection-over-Union (IoU) score of 98.84% for detecting mangrove loss, and the validation of universal applicability achieves an overall accuracy of more than 92% and a kappa accuracy of more than 89%. LSST-Former demonstrates superior performance compared to state-of-the-art deep-learning models such as random forest, Support Vector Machine, U-Net, LinkNet, Vision Transformer, SpectralFormer, MDPrePost-Net, and SST-Former, as evidenced by the experimental results and accuracy metrics.

Mesoscale mosaics of interannual variations in surface temperature, chlorophyll a concentration, and their relation in a coastal fishing ground

AbstractTo test the potential of high‐resolution satellite image analysis for assessing and predicting the mesoscale (<10 km in this study) effects of climate and environmental change on temperature and primary productivity in fishing grounds, we conducted satellite image analysis around an island in a coastal strait west of Japan from 2018 to 2023. We observed a distinct north–south gradient in sea surface temperature (SST) and chlorophyll a concentration (CHL) over approximately 20 km of the transect, which was likely affected by the current system. The model configuration suggests that the frequency of southward currents during winter–spring can control the magnitude of spring phytoplankton blooms. In the study region, an increase in SST at a rate of 0.06–0.13°C y−1 occurred during the study period, accompanied by a decrease in CHL. The north–south gradient in the rate of change suggests that the variation in the temperature and flow rate of the Kuroshio Current into the study area was due to these abrupt changes. The relationship between the annual mean SST and CHL was also spatially heterogeneous, showing a higher sensitivity of CHL to SST in the southwest of the island than in the north. In addition to the intrusion of warm and oligotrophic Kuroshio waters, the spread of less saline and more eutrophic coastal waters likely influenced this spatial heterogeneity. The satellite image analysis in the present study successfully revealed mesoscale mosaics of environmental conditions in coastal fishery grounds.

Evaluation of tectonic activity using morphometric indices: Study of the case of Taïliloute ridge (middle-Atlas region, Morocco)

In the Middle Atlas region, the Tizi N'Teghtène Fault System is a network of faults inherited from the Hercynian orogeny, which operated as normal faults during the Jurassic and reverse faults since the Miocene. The issue at hand is whether this fault system continues to be active today. To address this concern, focus has been placed on a central portion of the Tizi N'Teghtene Fault System, specifically the anticlinal ridge of Taïliloute. Determining the tectonically active segments of this ridge is crucial for structural analysis and the Quaternary evolution of this mountain chain. To achieve this, morphometric indices related to the evolution of watersheds and their streams have been employed. These indices include hypsometry, elongation ratio (Re), drainage asymmetry factor (AF), and the elongation profiles of various watercourses. These indicators provide insights into the degree of active longitudinal growth of the Taïliloute ridge. These parameters were determined through satellite image analysis using suitable software and geographic information systems (GIS). Tectonic activity analyses reveal that both flanks of this ridge exhibit ongoing tectonic activity, marked by the occurrence of normal faults and strike-slip faults during the Quaternary phase of the Alpine orogeny. It is concluded that the Tizi N'Teghtene Fault system remains tectonically active. This research contributes to a deeper understanding of the ongoing tectonic activities within the Tizi N'Teghtene Fault System, a matter of geological significance. By employing morphometric indices ad modern satellite image analysis techniques, a methodological innovation is presented by this study in assessing tectonic activity in mountainous regions. These results provide valuable insights into structural dynamics of the Middle Atlas, aiding in the understanding of its geological evolution. Furthermore, this research can have broader applications in seismic hazard assessment and land use planning, making it relevant beyond the immediate geographical boundaries of the study area.

The Spatio-Temporal Dynamics of Urban Green Spaces in Gweru City, Zimbabwe

The recognition of urban green spaces (UGS) is critical for sustainable strategies globally. UGS serve a critical function that spans the socioeconomic, environmental, and climatic divides, but their survival is jeopardised by the insatiable resource needs associated with perceived growth in developing nations. We used an explanatory sequential approach to conduct a situational analysis of Gweru City, Zimbabwe, to understand the spatio-temporal dynamics of UGS. Five Landsat pictures from 2000 to 2019 were utilised. At a five-year interval, four land use/land cover (LULC) clusters were identified using maximum likelihood classification: water bodies, green spaces, bare ground, and built-up areas. This was confirmed using real-world data with very high metrics (OA: 94%-97%; Kappa: 0.91-0.96). In addition to the use of satellite images, interviews with residents were used to supplement the data collected through the analysis of satellite images. Accordingly, the findings revealed that UGS in Gweru municipality has decreased by 5% during the last two decades (2000-2019). These findings were supported by locals who acknowledged that UGS were deteriorating in the suburbs, particularly in high-density areas. The terrible circumstances, according to the interviews, were caused by human activities, administrative deficiencies, natural disasters, and geology. As a result, current urban management approaches must support UGS, particularly in cities throughout the globe. Comprehending these variables is crucial for well-informed decision-making and efficient urban design and development

GEOGRAPHICAL FACTORS OF REVITALIZATION OF RURAL SETTLEMENTS “WITHOUT POPULATION

The article proposes a method for identifying “reviving” rural settlements (RS). Case studies of the Tver region RS revealed what features of the geographical location determine a settlement opportunities for revitalization. The previous typology, based on the analysis of satellite images, showed a considerable differentiation in the degree of RS degradation, classified according to the 2010 census as “without population”. Further work to determine the leading factors of revitalization was based on the study of those RS where the houses and outbuildings, identified by satellite images, have been preserved to the greatest extent. Nearness to rivers and water bodies, position relative to federal and regional highways, and location near the regional and/or district center were chosen as key features of the geographical location that have an effect on the prospects for revitalization of a territory. The presence of registered residents (according to current records) and demarcated cadastral plots are indicators of the RS revitalization. The study showed that one third of all RS, which fell into the category “without population” according to 2010 statistics, could now be considered “reviving”. A key factor in the revitalization of rural settlements of the Tver region is their nearness to the river, mainly to the Volga River. Another important factor is the location in the zone of influence of main centers, primarily the city of Tver. The main function is the recreational (dacha) use of such villages.

Spatial assessment of flood vulnerability and waterlogging extent in agricultural lands using RS-GIS and AHP technique-a case study of Patan district Gujarat, India.

Assessing and mapping flood risks are fundamental tools that significantly contribute to the enhancement of flood management strategies. Identifying areas that are susceptible to floods and devising strategies to reduce the risk of waterlogging is of utmost importance. In the present study, an integrated approach, combining advanced remote sensing technologies, Geographic Information Systems (GIS), and analytic hierarchy process (AHP), was adopted in the Patan district of Gujarat, India, with a coastline spanning over 1600km, to evaluate the numerous variables that contribute to the risk of flooding and waterlogging. After evaluating the flood conditioning factors and their respective weights using the analytic hierarchy process (AHP), the results were processed in GIS to accurately delineate areas that are prone to flooding. The results highlighted exceptional precision in identifying vulnerable areas, allowing for a thorough evaluation of the impact severity. The integrated approach yields valuable insights for multi-criteria assessments. The findings indicate that a significant portion of the district's land, precisely 8.94%, was susceptible to very high- risk of flooding, while 27.76% were classified as high-risk areas. Notably, 35.17% of the region was identified as having a moderate level of risk. Additionally, 20.96% and 7.15% were categorized as low-risk and very low-risk areas, respectively. Overall, the study highlights the need for proactive measures to mitigate the impact of floods on vulnerable communities. The research findings were verified by conducting ground truth and visual assessments using microwave satellite imagery (Sentinel-1). The aim of this validation was to test the accuracy of the study in identifying waterlogged agricultural areas and their extent based on AHP analysis. The ground verification and analysis of satellite images confirmed that the model accurately identified approximately 74% of the area categorized under high and very high flood vulnerability to be waterlogged and flooded. This research can provide valuable assistance to policymakers and authorities responsible for flood management by gathering necessary information about floods, including their intensity and the regions that are most susceptible to their impact. Additionally, it is crucial to implement corrective measures to improve soil drainage in vulnerable areas during heavy rainfall events. Prioritizing the adoption of sustainable agricultural practices and improving land use are also crucial for environmental conservation.

Flash flood prediction in Southwest Saudi Arabia using GIS technique and surface water models

A flash flood is one of the hazardous phenomena, especially in dry regions. In Saudi Arabia, Jazan Province experiences data scarcity especially historical hydrological data and a lack of studies related to flash flood analysis and the rainfall and runoff interrelationship. Thus, this research aims to study the rainfall-runoff inter-relation, predict flash floods, and to map the risk areas in Jazan Province by the geological, geomorphological, and hydrogeological characteristics along with digital elevation model (DEM), watershed modeling system (WMS) and HEC-HMS models. Jazan Province encompasses 25 drainage basins, receiving a considerable amount of rainfall (ranging from 100 to 500 mm) (August, October-November, March) which intermittently cause strong and destructive flash floods. The DEM was used for delineating the catchment (drainage basins) parameters. Physiographic parameters of the catchments have been analyzed for mapping the hazard degree of the flash flood strength. Further, basins with high hazard degrees of flash floods were selected to assess rainfall-runoff inter-relation using the HEC-HMS models, GIS, and morphometric parameters. Forty %, 8%, 52% of the study area are high, medium, and low hazard degrees of flash floods, respectively. The groundwater recharge in the study area was calculated through the integration of satellite image analysis, SWAT and GIS techniques and it ranges from 0.002 mm/km2/year to 8 mm/km2/year with an average of 2.5 mm/km2/year. Rainfall-runoff inter-relation of study basins, assessed based on the integration of WMS and HEC-HMS models, indicates that the resulting runoff volume ranges from 18.5 × 106 m3 to 473.1 × 106 m3 at a recurrence period of 5 and 100 years at rainfall events of 65 mm and 116.8 mm, respectively.

Large wood fluctuation and longitudinal connectivity conditions along a segment of the Blanco River (Chilean Patagonia)

Data collected between 2015 and 2022 was utilised to assess longitudinal connectivity and explain the temporal and spatial fluctuation of large wood (LW) along the Blanco River, which was severely affected by the 2008 eruption of the Chaitén Volcano in southern Chile. The study was performed along a ~ 10.6-km long segment, which was divided into two sub-segments (upper and lower). LW source areas were identified using information from previous research, complemented by the analysis of satellite images to cover the study period. LW fluctuation was studied for the period 2017–2022, using field data and images from an unmanned aerial vehicle along seven 80 m-long reaches located within the lower sub-segment of the river. Using the generated georeferenced orthomosaics and digital elevation models, LW and wood jams (WJs) locations, abundance, dimensions, volumes, and WJs stability were assessed, as well as wood deposition patterns. Streambank erosions and landslides were found to be the main LW sources. Considering wood sourcing, and the variations in the number of LW and WJs, in the dimensions of individual LW and WJs volume and deposition patterns as indicators, it was possible to infer the longitudinal connectivity conditions for the studied segment through time. The results showed that the upper and lower subsegments were poorly connected. However, changes in LW abundance over time, its dimensions and volumes, and the very low stability of WJs, and LW deposition patterns indicative of fluvial transport confirmed that the lower subsegment was longitudinally connected. The results also verified that the presence of LW did not affect water or sediment longitudinal connectivity along the fluvial system. The volume of individual LW and WJs showed a decreasing trend with time in all study reaches. As the bank erosions able to source LW to the channel are also reducing with time, pieces of wood deposited in the active channel may become the only way to sustain LW availability for the next few years. Things could change with the occurrence of an extreme and infrequent flood able to connect the upper and lower sub-segments and force the river to initiate a new phase of planform adjustments.

Geotechnologies in the Assessment of Eutrophication in the Barra Bonita Reservoir, São Paulo, Brazil

Objective: The objective of this study was to identify locations with higher eutrophication and, consequently, susceptible to the emergence of macrophytes in the Barra Bonita reservoir, SP. Theoretical background: The presence of macrophytes, such as Eichhornia crassipes, is influenced by ecological succession driven by human activities like introducing exotic species and discharging untreated nutrients. Effective management, including buffer zones, is suggested to reduce eutrophication, though some studies question their effectiveness on a large scale. Method: The analysis of the Normalized Difference Vegetation Index (NDVI) was conducted using remote sensing images obtained from Landsat 8 and 9 satellites. As a criterion for data acquisition, corresponding data for the study region were obtained over a one-year temporal scale with a maximum cloud cover of 0%. Results and conclusion: Analyzing the images, it is observable that the month of June 2023 exhibited areas with a higher vegetation index and, consequently, eutrophication processes. This trend gradually decreased in the months of August, September, and November. Research implications: The analysis of satellite images revealed specific patterns of eutrophication, suggesting a direct correlation between the geographical distribution of nutrients and the potential proliferation of macrophytes. Additionally, comparative studies of nutrient concentrations in tributaries indicate that urban pollution, besides affecting local water quality, contributed to eutrophication in the Barra Bonita reservoir. Originality/value: Through the NDVI, the eutrophication possibility in Barra Bonita’s Reservoir was evidentiated.

Effect of LULC Changes on Annual Water Yield in the Urban Section of the Chili River, Arequipa, Using the InVEST Model

Arequipa is a semi-desert city located in southern Peru which depends on the Chili River as its only water source. During recent years, this city has increased its number of inhabitants significantly as a result of internal migratory flows and population growth. Because of this, the city has undergone a rapid urbanization process which has increased the urban areas near the river and caused the destruction of agricultural areas, as well as their native vegetation. This change in land use can be quantified through satellite image analysis across many years, but as noted, there are no studies on its impact on water yield (WY) in the urban section of the river. Now, by using the Integrated Valuation of Ecosystem Services and Compensation (InVEST) model, which allows the WY of the study area to be evaluated in millimeters and cubic meters by introducing a series of variables, such as precipitation, reference evapotranspiration and types of land use classes, among others, it is possible to determine that the WY from the study area was 1,743,414 m3 in 1984 and 1,323,792 m3 in 2022; the urban area is the type of land use with the highest increase with respect to its percentage contribution to the WY, going from 30.43% to 49.62% between 1984 and 2022, respectively. The increase in urban area mitigated the loss of total WY, explained by a higher percentage runoff rate, surface flow and drainage problems in the study area.

Exploring spatiotemporal dynamics of NDVI and climate-driven responses in ecosystems: Insights for sustainable management and climate resilience

Understanding the intricate relationship between climate variables and the Normalized Difference Vegetation Index (NDVI) is essential for effective ecosystem management. This study focuses on the spatiotemporal dynamics of NDVI and its interaction with climate variables in the ecologically diverse Khyber Pakhtunkhwa (KPK) Province, Pakistan, from 2000 to 2022. The research methodology involves analyzing satellite images and meteorological datasets to examine NDVI and surface latent heat flux (SHF), total precipitation (TPP), temperature (T), soil temperature (ST), and total pressure (TP). KPK Province's ecological significance and complex climate-vegetation interactions drive the selection of this study area. The study uses multiple linear regression analysis to investigate how T, TPP, SHF, and TP influence NDVI. The Mann-Kendall test detects trends, with Sen's slope estimator quantifying trend magnitudes. Additionally, correlation coefficients provide insights into long-term changes and association strengths. The findings highlight a consistent upward trend in mean NDVI over the 23 years, revealing an overall increase in NDVI, particularly in vegetation-dense areas where it rose from 0.27 to 0.32. The research showed an annual growth rate of 0.84% in the entire area, with specific vegetated zones exhibiting a slightly lower rate of 0.80%. However, the average yearly increase in NDVI is higher in vegetation-specific zones (0.00237) compared to the whole area (0.00151). This increase in NDVI occurs alongside a statistically significant decrease in SHF and PPT, suggesting a complex adaptation of vegetation to changing climate conditions in the KPK Province. In contrast, SHF exhibits a statistically significant negative slope of −5.952e-06 (p < 0.05), indicating a pronounced downward trend. Similarly, Sen's slope estimate for precipitation demonstrates a significant negative trend of −0.0001 (p < 0.05), showing diminishing precipitation. The study uncovers intricate linkages between climate variables and vegetation dynamics within KPK Province. These insights have far-reaching implications, guiding decision-making in land management, conservation efforts, and global climate resilience strategies. Ultimately, the research underscores the critical role of data-driven approaches in shaping a greener and more sustainable future.

Multiscale and Multitemporal Remote Sensing for Neolithic Settlement Detection and Protection—The Case of Gorjani, Croatia

The decade of research concentrating on the area of Eastern Slavonia revealed an abundance of large and complex Middle and Late Neolithic sites. It changed profoundly how we perceive Middle and Late Neolithic settlements, including space, size and organization. The vast majority of these sites were detected through aerial reconnaissance and satellite image analysis. The observation of the sites was followed by intensive field surveys, which confirmed their attribution to the Middle and Late Neolithic period by surface finds. On those confirmed sites in the vicinity of Đakovo, Croatia, a magnetic survey was conducted on five sites, and the results confirmed the presence of large-scale Middle and Late Neolithic settlements with complex spatial organization and enclosure(s). The most complex remains so far are the sites Gorjani, Kremenjača and Topole, which we present in this paper, where one or two settlements remain covering an area of 70 hectares which is currently in the process of formal protection as a cultural landscape by the Ministry of Culture and Media of the Republic of Croatia. The special focus of this paper is the application of remote sensing in the detection, archaeological confirmation and protection of the site of Gorjani Topole.