Search

Seagrass beds play a vital ecological role by regulating climate, maintaining biodiversity, and sequestering carbon. Achieving accurate classification of seagrass beds across both time and space is of significant importance for efficient monitoring. This paper addresses the challenges of seagrass bed classification in remote sensing imagery and the difficulty of achieving temporal and spatial transferability of classification model. Leveraging a long-term Landsat satellite image time series spanning from 1976 to 2022 in the Yellow River Delta, we enhance the DeepLab V3+ network and propose a cross-temporal-spatial domain seagrass bed transfer learning classification approach. We utilize selectively chosen images from a few years in partial regions for training, introduce freeze-training and-unfreeze-training during the model training phase, and then transfer the model to achieve cross-temporal and cross-temporal-spatial domain classification on images from other years and regions. Additionally, we discuss the factors influencing the classification results. The research results indicate that: (1)The method we proposed has shown good results, achieving classification accuracy of 83.17% and 80.99% for seagrass beds in both cross-temporal and cross-temporal-spatial domains. (2) The classification results indicate that this method achieves an average classification accuracy higher by 16.18% compared to networks such as UNet, PSPNet, HRNet, UNet++, SegFormer, etc. under cross-temporal conditions and higher by 17.56% under cross-spatiotemporal conditions for seagrass bed classification. (3) Based on the classification results, it is observed that from 1973 to 1986, the overall area of seagrass beds in the Yellow River Delta had an initial growth trend, with the largest seagrass bed area recorded in 1986, reaching 4281.289 hectares. Subsequently, the seagrass beds showed an overall decreasing trend, and by 2019 they had almost completely disappeared. The cross-temporal-spatial domain seagrass bed transfer learning classification method proposed in this paper can provide valuable support for the monitoring, restoration, management, and utilization of seagrass ecosystems. [ABSTRACT FROM AUTHOR]

In this paper, a data-driven transfer learning (TL) model for locating tropical cyclone (TC) centers from satellite infrared images in the northwest Pacific is developed. A total of 2450 satellite infrared TC images derived from 97 TCs between 2015 and 2018 were used for this paper. The TC center location model (ResNet-TCL) with added residual fully connected modules is built for the TC center location. The MAE of the ResNet-TCL model is 34.8 km. Then TL is used to improve the model performance, including obtaining a pretrained model based on the ImageNet dataset, transferring the pretrained model parameters to the ResNet-TCL model, and using TC satellite infrared imagery to fine-train the ResNet-TCL model. The results show that the TL-based model improves the location accuracy by 14.1% (29.3 km) over the no-TL model. The model performance increases logarithmically with the amount of training data. When the training data are large, the benefit of increasing the training samples is smaller than the benefit of using TL. The comparison of model results with the best track data of TCs shows that the MAEs of TCs center is 29.3 km for all samples and less than 20 km for H2–H5 TCs. In addition, the visualization of the TL-based TC center location model shows that the TL model can accurately extract the most important features related to TC center location, including TC eye, TC texture, and contour. On the other hand, the no-TL model does not accurately extract these features. [ABSTRACT FROM AUTHOR]

This paper evaluates the effectiveness of restoring open‐water area in a wetland via a geographical framework that goes from a general perspective to a detailed view. The methodology relies on diachronic cartography, remote sensing through Landsat satellite imagery validated by in situ hydrological data (2000–2022), and details from field work. We analyzed the water surface area of Comana freshwater marsh in Southern Romania. The water surface area recorded a statistical change point synchronous to the restoration actions. The water surface area increased due to restoration actions in 2011 and then became relatively stable. Post‐restoration, the mean monthly discharge of Neajlov River correlates statistically with the water surface area. The water has low depths in the marsh; yet, the area covered by vegetation appears to be stable. The persistence of the effects for over a decade recommends Comana Marsh as a demonstrative case study in South‐Eastern Europe and for further monitoring activities. [ABSTRACT FROM AUTHOR]

The study of ancient irrigation is crucial in the archaeological research of arid regions. It covers a wide range of topics, with the Near East being the focus for decades. However, political instability and limited data have posed challenges to these studies. The primary objective is to establish a standardised method applicable to different arid environments using the Google Earth Engine platform, considering local relief of terrain and seasonal differences in vegetation. This study integrates multispectral data from LANDSAT 5, Sentinel-2, SAR imagery from Sentinel 1, and TanDEM-X (12 m and 30 m) DSMs. Using these datasets, calculations of selected vegetation indices such as the SMTVI and NDVSI, spectral decomposition methods such as TCT and PCA, and topography-based methods such as the MSRM contribute to a comprehensive understanding of landscape irrigation. This paper investigates the influence of modern environmental conditions on the visibility of features like levees and palaeo-channels by testing different methods and parameters. This study aims to identify the most effective approach for each case study and explore the possibility of applying a consistent method across all areas. Optimal results are achieved by combining several methods, adjusting seasonal parameters, and conducting a comparative analysis of visible features. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of training deep learning models for fire smoke scene detection from multi-sensor, multi-spectral satellite imagery, where spectral bands vary and training data is scarce, especially for new sensors. We introduce a novel cross-sensor transfer learning approach enhanced by spectral pattern extraction, notably aided by a deep learning (DL) module called Input Amplification (IA). Our contribution includes the creation of two datasets, Landsat_smk2770 and Sentinel2_smk, with varying spectral bands. We employ a model named IA_VIB_SD which incorporates IA and is designed specifically for fire smoke scene detection. We investigated the transferability of the Landsat_smk2770-trained IA_VIB_SD model to the Sentinel2_smk dataset using various transfer learning techniques, and compared the performance of the transferred model with the benchmark IA_VIB_SD model exclusively trained on pure Sentinel2_smk data. Our proposed transfer learning approach resulted in a transferred model with an average accuracy 5% higher than the benchmark model. Notably, Our proposed transfer learning approach outperformed existing transfer learning methods by more than 1% in terms of the accuracy, even when trained on a mere 10% of the Sentinel2_smk dataset. This research advances fire smoke scene detection from multi-sensor, multi-spectral satellite imagery. [ABSTRACT FROM AUTHOR]

The statutory planning of the urban landscape of Kuala Lumpur (KL) has been solely relied on a rigid and fixed quantitative specification without ecological evaluation, resulting in the loss of biodiversity, degradation of urban ecosystem services and liveability. Past research in the area of quantitative urban green space (UGS) planning and ecology were mainly concentrated in the provision, accessibility, and connectivity of UGS, but lacking in the ecological quality dimension. This paper intends to fill the knowledge gap by quantifying the ecological quality of UGS in multiple scales from tree, park, to city level with unmanned aerial vehicle (UAV) to map the leaf area index (LAI) in the city of KL. The estimation of KL LAI involves a two-step processes. In the first step, 9 UGSs under the management of local authority were selected for the mapping of the distribution of Normalized Differential Vegetation Index (NDVI) with Unmanned Aerial Vehicle (UAV). Concurrently, rigorous field works are conducted to sample field LAI of selected trees in all of the UGSs with AccuPAR LP80 Ceptometer. UGS LAI are estimated with regression of UAV NDVI and field LAI. Analysis of the result shows that there is a moderately strong relationship (R² = 0.56, RMSE =0.33) between UAV NDVI and field LAI and the established statistical equation is used for the estimation of UGS LAI covering all the parks. In the second step, the statistical relationship was upscaled to the entire city level with UGS LAI and SPOT-7 NDVI data (R² =0.50, RMSE = 0.94). The multiscale estimation of LAI provides an effective indicator of the landscape ecological performance among the different electoral area where targeted landscape enhancement and remediation policies can be formulated to improve urban sustainability. [ABSTRACT FROM AUTHOR]

With the wide application of remote sensing technology, target detection based on deep learning has become a research hotspot in the field of remote sensing. In this paper, aimed at the problems of the existing deep-learning-based desert land intelligent extraction methods, such as the spectral similarity of features and unclear texture features, we propose a multispectral remote sensing image desert land intelligent extraction method that takes into account band information. Firstly, we built a desert land intelligent interpretation dataset based on band weighting to enhance the desert land foreground features of the images. On this basis, we introduced the deformable convolution adaptive feature extraction capability to U-Net and developed the Y-Net model to extract desert land from Landsat remote sensing images covering the Inner Mongolia Autonomous Region. Finally, in order to analyze the spatial and temporal trends of the desert land in the study area, we used a structural equation model (SEM) to evaluate the direct and indirect effects of natural conditions and human activities, i.e., population density (PD), livestock volume (LS), evaporation (Evp), temperature (T), days of sandy wind conditions (LD), humidity (RH), precipitation (P), anthropogenic disturbance index (Adi), and cultivated land (CL). The results show that the F1-score of the Y-Net model proposed in this paper is 95.6%, which is 11.5% more than that of U-Net. Based on the Landsat satellite images, the area of desert land in the study area for six periods from 1990 to 2020 was extracted. The results show that the area of desert land in the study area first increased and then decreased. The main influencing factors have been precipitation, humidity, and anthropogenic disturbance, for which the path coefficients are 0.646, 0.615, and 0.367, respectively. This study will be of great significance in obtaining large-scale and long-term time series of desert land cover and revealing the inner mechanism of desert land area change. [ABSTRACT FROM AUTHOR]

Remote sensing plays a crucial role in detecting and monitoring natural resources, extending its applications to various fields, such as geography, topographical surveying, and geoscience disciplines, including land management, forest monitoring, crop identification, soil mapping, and ocean resource finding. Road extraction holds significant importance among these applications, contributing to the development of Geographic Information Systems (GIS). The automatic updating of GIS information has become essential in daily life. Road extraction stands out as a prominent application within remote sensing image systems, addressing challenges related to intensity and width. Intensity challenges involve variations in spectral or color values of roads, while width challenges pertain to the issues associated with the size and structure of roads during the extraction process. Addressing the challenges associated with road extraction from remote sensing imagery is crucial for achieving accurate and efficient results. This paper under consideration compares the conventional and contemporary methods of road extraction, emphasizing completeness and correctness metrics. Conventional methods involve techniques like CLAHistogramEqualization for enhancement and fuzzy c-mean clustering for extraction, resulting in incremental improvements. To enhance results further, images are de-noised using Gray World Optimization and iterative domain-guided image filtering. To improve efficiency in road extraction, the authors proposed a contemporary approach through probability neural networks with de-noised images. The comparison is made based on the completeness and correctness of both conventional and contemporary methods. [ABSTRACT FROM AUTHOR]

The classification of ship images has become a significant area of research within the remote sensing community due to its potential applications in maritime security, traffic monitoring, and environmental protection. Traditional monitoring methods like the Automated Identification System (AIS) and the Constant False Alarm Rate (CFAR) have their limitations, such as challenges with sea clutter and the problem of ships turning off their transponders. Additionally, classifying ship images in remote sensing is a complex task due to the spatial arrangement of geospatial objects, complex backgrounds, and the resolution limitations of sensor platforms. To address these challenges, this paper introduces a novel approach that leverages a unique dataset termed Heterogeneous Ship data and a new technique called the Spatial–Channel Attention with Bilinear Pooling Network (SCABPNet). First, we introduce the Heterogeneous Ship data, which combines Synthetic Aperture Radar (SAR) and optical satellite imagery, to leverage the complementary features of the SAR and optical modalities, thereby providing a richer and more-diverse set of features for ship classification. Second, we designed a custom layer, called the Spatial–Channel Attention with Bilinear Pooling (SCABP) layer. This layer sequentially applies the spatial attention, channel attention, and bilinear pooling techniques to enhance the feature representation by focusing on extracting informative and discriminative features from input feature maps, then classify them. Finally, we integrated the SCABP layer into a deep neural network to create a novel model named the SCABPNet model, which is used to classify images in the proposed Heterogeneous Ship data. Our experiments showed that the SCABPNet model demonstrated superior performance, surpassing the results of several state-of-the-art deep learning models. SCABPNet achieved an accuracy of 97.67% on the proposed Heterogeneous Ship dataset during testing. This performance underscores SCABPNet's capability to focus on ship-specific features while suppressing background noise and feature redundancy. We invite researchers to explore and build upon our work. [ABSTRACT FROM AUTHOR]

Atmospheric correction eliminates corruption in reflectance captured by satellite images due to atmospheric elements like gases, aerosols, and water vapours. Existing physics-based approaches employ radiative transfer models constructed using lookup tables computed for different atmospheric parameters. However, these approaches are computationally expensive and rely on estimates of parameters that are difficult to sense accurately. This paper proposes a deep learning model as an alternative to physics-based approaches. We present an end-to-end deep neural network trained on seasonally and spatially rich Landsat 8 satellite images without explicit atmospheric parameterization along with our analysis and its validation. We validate the model's effectiveness vis-a-vis Landsat 8's Land Surface Reflectance Code – LaSRC results in $RMSE \sim 0.042$ R M S E ∼ 0.042 , $SSIM \sim 0.97$ S S I M ∼ 0.97 , and correlation coefficient $r \sim 0.99$ r ∼ 0.99. For ground measurements by RadCalNet, the proposed model has an $RMSE \sim 0.053$ R M S E ∼ 0.053 , $SSIM \sim 0.90$ S S I M ∼ 0.90 , and $r \sim 0.88$ r ∼ 0.88. The results show that the model accurately predicts surface reflectance and correlates highly with reference data. [ABSTRACT FROM AUTHOR]

Models for bathymetry retrieval from multispectral images have not considered the errors caused by tidal fluctuation. A rigorous bathymetric model that considers the variation in tide height time series, including the tide height calculation and instantaneous tide height correction at the epoch of satellite flight into the bathymetric retrieval model, is proposed in this paper. The model was applied on Weizhou Island, located in Guangxi Province, China, and its accuracy verificated with four check lines and seven checkpoints. A scene from the Landsat 8 satellite image was used as experimental data. The reference ("true") water depth data collected by a RESON SeaBat 7125 multibeam instrument was used for comparison analysis. When satellite-derived bathymetry is compared, it is found that maximum absolute error, mean absolute error, and RMSE have decreased 54, 45, and 30% relative to that of the traditional model in the entire test field. The accuracy of the water depths retrieved by our model increased 30 and 56% when validated using four check lines and seven checkpoints, respectively. Therefore, it can be concluded that the model proposed in this paper can effectively improve the accuracy of bathymetry retrieved from Landsat 8 images. [ABSTRACT FROM AUTHOR]

Demand for food and water are increasing while the extent of arable land and accessible fresh water are decreasing. This poses global challenges as economies continue to develop and the population grows. With agriculture as the leading consumer of water, better understanding how water is used to produce food may help support the increase of Crop Water Productivity (CWP; kg/m3), the ratio of crop output per unit of water input (or crop per drop). Previous large-scale CWP studies have been useful for broad water use modeling at coarser resolutions. However, obtaining more precise CWP, especially for specific crop types in a particular area and growing season as outlined here are important for informing farm-scale water management decision making. Therefore, this study focused on California's Central Valley utilizing high-spatial resolution satellite imagery of 30 m (0.09 hectares per pixel) to generate more precise CWP for commonly grown and water-intensive irrigated crops. First, two products were modeled and mapped. 1. Landsat based Actual Evapotranspiration (ETa; mm/d) to determine Crop Water Use (CWU; m3/m2), and 2. Crop Productivity (CP; kg/m2) to estimate crop yield per growing season. Then, CWP was calculated by dividing CP by CWU and mapped. The amount of water that can be saved by increasing CWP of each crop was further calculated. For example, in the 434 million m2 study area, a 10% increase in CWP across the 9 crops analyzed had a potential water savings of 31.5 million m3 of water. An increase in CWP is widely considered the best approach for saving maximum quantities of water. This paper proposed, developed, and implemented a workflow of combined methods utilizing cloud computing based remote sensing data. The environmental implications of this work in assessing water savings for food and water security in the 21st century are expected to be significant. [ABSTRACT FROM AUTHOR]

This paper presents a unique case of the application of remote sensing methods in archaeological survey devoted to ancient pre-Roman Imperial roads in the Southern Levant. The results of our preparatory remote sensing research and subsequent fieldwork in Jordan and Israel between 22 February and 23 March 2023, within the framework of the research project entitled "Travel and Mobility in Hellenistic and Early Roman Palestine", are reported and discussed. Part of this project is a large-scale, systematic research attempt to discover additional ancient pre-Roman roads and to suggest a working methodology for future research. The methodology is supposed to combine remote sensing research and archaeological survey. The project's first fieldwork achieved several goals. First, the modern methods enabled us to provide a high-resolution capture of the detected features and artifacts, including the courses of ancient roads and the locations of road-related archaeological sites. Altogether, 105 road remains, 62 archaeological sites, and 14 pottery findings were identified; what is more, 11 GPS (Global Positioning System) tracks of ancient roads were registered. Second, we suggested necessary revisions to the previous state of research and reported new findings. For instance, newly discovered rock art evidence found along Glueck's Road confirms the continuity of the use of this road long into late antiquity and early Islam. Third, some methodological conclusions were reached. For example, a multi-source approach to identifying ancient roads including the use of archival cartographic sources, archival and modern satellite and aerial imagery, and the databases of archaeological sites is still necessary. However, there can be no doubt that spatial analyses and remote sensing studies must be accompanied by archaeological fieldwork, which is absolutely necessary for determining the dating of the roads (by dating the settlement and pottery) and a detailed identification of the road courses (particularly through the discovery of road-related infrastructure). [ABSTRACT FROM AUTHOR]

Recent developments in remote sensing provide very high-resolution imageries that are partially in competition with aerial images. This paper presents an evaluation of using IKONOS-2 and WorldView-2 satellite imageries for monitoring the growth of the built-up areas in the southern part of Assiut City between 2006 and 2016. In addition, a comparison between aerial orthoimage and satellite imagery was carried out. Also, a set of satellite imagery was downloaded from the Google Earth Pro application and used in this study to determine the rate of spatial growth in the southern part of Assiut City between 2011 and 2022. The results of this study show that: Most map features can be detected and manually recognized from WorldView-2 imageries at a good level, while building detection was perfect. The applied change detection technique using IKONOS-2 imagery and WorldView-2 imagery shows that the growth of the built-up area in the south part of Assiut City between 2006 and 2016 is 783499.2 m2, representing about 16.89 % of the total test area. Recent satellite imageries from open sources such as Google Earth were used successfully to determine the rate of spatial growth of the southern part of Assiut City in the period from 2011 to 2022. The spatial growth in this period was found to have increased dramatically, especially between 2014 and 2016. Remarkable negative changes were found in the agricultural lands due to the spatial growth of the built-up area in the south direction of Assiut City. [ABSTRACT FROM AUTHOR]

Today, with the non-stop expansion of urbanization, mapping urban areas and monitoring their dynamic changes have become challenges for governments and also a hot topic for researchers. Remote sensing imageries play a key role in urban studies, the extraction of urban built-up areas, and monitoring their changes. A variety of studies have proposed methods for the extraction of regional, national, and global built-up areas. However, the majority of them used limited features and applied a manual sample selection strategy for classification, leading to time-consuming and low-efficient algorithms. This paper proposes a fully automatic procedure to real-time extract built-up areas by integrating the Luojia 1–01 nighttime lights (NTL) images, Sentinel-2 multispectral data, Sentinel-1 Radar images, and SRTM elevation data in cloud-computing Google Earth Engine. Firstly, potential built-up areas (PBA) and non-built-up areas (NBA) are obtained by applying Otsu and multi-level thresholding to some of the extracted spectral-textural-spatial (STS) features and by applying logical rules. Secondly, built-up and non-built-up samples are automatically selected and are used to train a Support Vector Machine (SVM) supervised classifier and to classify the hybrid feature set so that a preliminary classified map (PCM) can be obtained. Thirdly, the PCMs are automatically corrected using the non-built-up area, and morphological operations in the so-called post-classification to provide a refined classified map (RCM) and final built-up map. Four study areas in Northern America, Europe (Scandinavia), the Middle East, and Eastern Asia were selected to test the proposed method. Also, five state-of-the-art built-up products, accompanied by Google Earth images, were used as the reference data. The results indicate that the proposed method can accurately and automatically select samples and map built-up areas with a spatial resolution of 10 m. Its performance is validated with an average overall accuracy of 94.4% and an average Kappa coefficient of 0.89 and by visual comparison of our method results with other reference data. The proposed method has significant potential to be used in real-time extracting built-up areas and in monitoring their dynamic changes on national and global scales. [ABSTRACT FROM AUTHOR]

Neural radiance fields (NeRFs) combining machine learning with differentiable rendering have arisen as one of the most promising approaches for novel view synthesis and depth estimates. However, NeRFs only applies to close-range static imagery and it takes several hours to train the model. The satellites are hundreds of kilometers from the earth. Satellite multi-view images are usually captured over several years, and the scene of images is dynamic in the wild. Therefore, multi-view satellite photogrammetry is far beyond the capabilities of NeRFs. In this paper, we present a new method for multi-view satellite photogrammetry of Earth observation called remote sensing neural radiance fields (RS-NeRFs). It aims to generate novel view images and accurate elevation predictions quickly. For each scene, we train an RS-NeRF using high-resolution optical images without labels or geometric priors and apply image reconstruction losses for self-supervised learning. Multi-date images exhibit significant changes in appearance, mainly due to cars and varying shadows, which brings challenges to satellite photogrammetry. Robustness to these changes is achieved by the input of solar ray direction and the vehicle removal method. NeRFs make it intolerable by requiring a very long time to train an easy scene. In order to significantly reduce the training time of RS-NeRFs, we build a tiny network with HashEncoder and adopted a new sampling technique with our custom CUDA kernels. Compared with previous work, our method performs better on novel view synthesis and elevation estimates, taking several minutes. [ABSTRACT FROM AUTHOR]

The carbon (C) and nitrogen (N) ratio is a key indicator of nutrient utilization and limitations in rangelands. To understand the distribution of herbivores and grazing patterns, information on grass quality and quantity is important. In heterogeneous environments, remote sensing offers a timely, economical, and effective method for assessing foliar biochemical ratios at varying spatial and temporal scales. Hence, this study provides a synopsis of the advancement in remote sensing technology, limitations, and emerging opportunities in mapping the C:N ratio in rangelands. Specifically, the paper focuses on multispectral and hyperspectral sensors and investigates their properties, absorption features, empirical and physical methods, and algorithms in predicting the C:N ratio in grasslands. Literature shows that the determination of the C:N ratio in grasslands is not in line with developments in remote sensing technologies. Thus, the use of advanced and freely available sensors with improved spectral and spatial properties such as Sentinel 2 and Landsat 8/9 with sophisticated algorithms may provide new opportunities to estimate C:N ratio in grasslands at regional scales, especially in developing countries. Spectral bands in the near-infrared, shortwave infrared, red, and red edge were identified to predict the C:N ratio in plants. New indices developed from recent multispectral satellite imagery, for example, Sentinel 2 aided by cutting-edge algorithms, can improve the estimation of foliar biochemical ratios. Therefore, this study recommends that future research should adopt new satellite technologies with recent development in machine learning algorithms for improved mapping of the C:N ratio in grasslands. [ABSTRACT FROM AUTHOR]

The paper presents the results of a two-year archaeological survey carried out in the Iraqi Kurdistan, namely within the Navkur plain that has been extensively explored by the University of Udine since 2012. The surveys were planned in advance using Remote Sensing products available online and processed with Google Earth Engine, a large-scale cloud computing service specifically designed to process geospatial big data and especially satellite imagery. Images from Landsat 5, Landsat 7 and Sentinel-2 platforms were selected, processed and assessed. After two years, an overall number of 46 new and previously unknown sites have been localized and surveyed, contributing to the knowledge of the past history of this portion of the Kurdistan region and testing the use of Remote Sensing cloud-computing applications in the context of Near Eastern archaeological research. [ABSTRACT FROM AUTHOR]

Despite several decades of observations of ice cover in Polish lakes, researchers have not broadly applied satellite images to date. This paper presents a temporal and spatial analysis of the variability in the occurrence of ice cover on lakes in the Drawskie Lakeland in the hydrological years 1984–2022 based on satellite data from Landsat missions 4, 5, 7, 8, and 9. The range of occurrence of ice cover was determined based on the value of the Normalised Difference Snow Index (NDSI) and blue spectral band ( ρ λ b l u e ). The determination of ice cover extent adopted ρ λ b l u e   values from 0.033 to 0.120 as the threshold values. The analysis covered 67 lakes with an area from 0.07 to 18.71 km2. A total of 53 images were analysed, 14 and 39 out of which showed full and partial ice cover, respectively. The cluster analysis permitted the designation of two groups of lakes characterised by an approximate range of ice cover. The obtained results were analysed in the context of the morphometric parameters of the lakes. It was evidenced that the range of the ice cover on lakes is determined by the surface area of the lakes; their mean and maximum depth, volume, length, and width; and the height of the location above sea level. The results of analyses of the spatial range of ice cover in subsequent scenes allowed for the preparation of maps of probability of ice cover occurrence that permit the complete determination of its variability within each of the lakes. Monitoring of the spatial variability in ice cover within individual lakes as well as in reference to lakes not subject to traditional observations offers new research possibilities in many scientific disciplines focused on these ecosystems. [ABSTRACT FROM AUTHOR]

Change detection in remote sensing images aims to accurately determine any significant land surface changes based on acquired multi-temporal image data, being a pivotal task of remote sensing image processing. Over the past few years, owing to its powerful learning and expression ability, deep learning has been widely applied in the general field of image processing and has demonstrated remarkable potentials in performing change detection in images. However, a majority of the existing deep learning-based change detection mechanisms are modified from single-image semantic segmentation algorithms, without considering the temporal information contained within the images, thereby not always appropriate for real-world change detection. This paper proposes a High-Resolution Triplet Network (HRTNet) framework, including a dynamic inception module, to tackle such shortcomings in change detection. First, a novel triplet input network is introduced, which is capable of learning bi-temporal image features, extracting the temporal information reflecting the difference between images over time. Then, a network is employed to extract high-resolution image features, ensuring the learned features preserving high-resolution characteristics with minimal reduction of information. The paper also proposes a novel dynamic inception module, which helps improve the feature expression ability of HRTNet, enriching the multi-scale information of the features extracted. Finally, the distances between feature pairs are measured to generate a high-precision change map. The effectiveness and robustness of HRTNet are verified on three popular high-resolution remote sensing image datasets. Systematic experimental results show that the proposed approach outperforms state-of-the-art change detection methods. [ABSTRACT FROM AUTHOR]

This paper proposes a semi-automatic green tide extraction method based on the NDVI to extract Yellow Sea green tides from 2008 to 2022 using remote sensing (RS) images from multiple satellites: GF-1, Landsat 5 TM, Landsat 8 OLI_TIRS, HJ-1A/B, HY-1C, and MODIS. The results of the accuracy assessment based on three indicators: Precision, Recall, and F1-score, showed that our extraction method can be applied to the images of most satellites and different environments. We traced the source of the Yellow Sea green tide to Jiangsu Subei shoal and the southeastern Yellow Sea and earliest advanced the tracing time to early April. The Gompertz and Logistic growth curve models were selected to predict and monitor the extent and duration of the Yellow Sea green tide, and uncertainty for the predicted growth curve was estimated. The prediction for 2022 was that its start and dissipation dates were expected to be June 1 and August 15, respectively, and the accumulative cover area was expected to be approximately 1190.90–1191.21 km2. [ABSTRACT FROM AUTHOR]

Satellite imagery is gaining popularity as a valuable tool to lower the impact on natural resources and increase profits for farmers. The purpose of this study is twofold: to mine the scientific literature to reveal the structure of this research domain, and to investigate to what extent scientific results can reach a wider public audience. To meet these two objectives, a Web of Science and a Twitter dataset were retrieved and analysed, respectively. For the academic literature, different performances of various countries were observed: the USA and China resulted as the leading actors, both in terms of published papers and employed researchers. Among the categorised keywords, "resolution", "Landsat", "yield", "wheat" and "multispectral" are the most used. Then, analysing the semantic network of the words used in the various abstracts, the different facets of the research in satellite remote sensing were detected. The importance of retrieving meteorological parameters through remote sensing and the broad use of vegetation indexes emerged from these analyses. As emerging topics, classification tasks for land use assessment and crop recognition stand out, alongside the use of hyperspectral sensors. Regarding the interaction of academia with the public, the analysis showed that it is practically absent on Twitter: most of the activity therein stems from private companies advertising their business. This shows that there is still a communication gap between academia and actors from other societal sectors. [ABSTRACT FROM AUTHOR]

This study identifies relevant globally available data to develop basin and water level variation models which can be used for scenario modelling. The case study for the current research is Lake Turkana in Kenya, which is the outlet of 3 main river basins: Omo, Turkwel and Keiro. Due to the lack of data, the present paper only considers the Omo River Basin, which contributes around 90% of the inflow into the lake. Lumped and semi-lumped hydrological models were developed using the USACE’s HEC-HMS tool. The calibration and validation were carried out using the EU computed discharges of the Global Flood Awareness System as observed flow. The validated model was used to assess the impact on the lake due to the operation of three reservoirs in the basin; Gibe I, II and III. The variation of the water level of Lake Turkana was determined by using the model builder tool in ArcGIS. The lake water level model was validated using the Normalized Difference Water Index of Landsat 5 and Landsat 7 satellite imagery. Finally, using the semi-lumped hydrological model and the lake water level variation model, two scenarios were simulated to assess the lake‘s condition due to three consecutive driest and wettest years. The semi-lumped model showed satisfactory goodness of fit compared to the lumped model, therefore it is concluded that it can be used to assess the impact of upstream developments in the Omo basin, on the shoreline and water level variations of Lake Turkana with reasonable accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a methodology based on medium resolution satellite images (Landsat Thematic Mapper and Enhanced Thematic Mapper), adapted and further developed from a variant of a Principal Components Analysis used for geological exploration, which took into consideration the spectral bands in the visible and infrared wavelengths where the minerals of interest exhibited diagnostic features. The method was developed to be applied for an inventory of mining wastes at pan-European scale and was successfully tested in known mining regions with closed exploitations in Upper Silesia (Poland), Romania and Slovakia. The results were validated against European (CORINE Land Cover) and national data sets. A Mining Anomaly Index was computed at catchment scale, to determine the most vulnerable river basins from which pollutants from the extractive industry could be further transported to the seas. In view of the present increased demand for metals and critical raw materials, the principles of the described methodology could be applied to the new satellite sensors, with increased ground and spectral resolution. [ABSTRACT FROM AUTHOR]

Forest changes caused by fires, clear-cuts, and Land Use/Land Cover (LULC) changes have negatively affected the climate, wildlife, and global ecosystem. By monitoring the forest changes, managers and planners can make appropriate decisions to preserve these natural areas. In this regard, this paper presents a novel deep learning-based forest change detection method including two main steps: (1) producing a new difference image enabling a more efficient distinction of changed and unchanged areas, and (2) generating a reliable forest change map by applying the recurrent residual-based U-Net deep neural network (R2U-Net) on the difference image. The recently introduced forest fused difference image (FFDI) is first improved by modifying its weighted angular operator as well as applying the fast local laplacian filter (FLLF) to generate an enhanced forest fused difference image (EFFDI). R2U-Net is subsequently used to segment the EFFDI into the changed and unchanged regions because it preserves their geometric shapes more effectively than other U-net variants. To assess the efficacy of the presented method, experimental results were conducted on four bi-temporal images acquired by the Sentinel 2 and Landsat 8 satellite sensors. The qualitative and quantitative results demonstrated the effectiveness of the proposed EFFDI in reflecting the true forest changes from the background. Moreover, compared with the other conventional U-Net-based models, including U-Net, ResU-Net, and U-Net ++, forest changes and their geometrical details were better preserved by R2U-Net. Furthermore, the proposed approach outperformed the other state-of-the-art supervised and unsupervised change detection methods in terms of quantitative and qualitative results, demonstrating its high potential for forest change detection applications. [ABSTRACT FROM AUTHOR]

In this paper, we propose an advanced scripting approach using Python and R for satellite image processing and modelling terrain in Côte d'Ivoire, West Africa. Data include Landsat 9 OLI/TIRS C2 L1 and the SRTM digital elevation model (DEM). The EarthPy library of Python and 'raster' and 'terra' packages of R are used as tools for data processing. The methodology includes computing vegetation indices to derive information on vegetation coverage and terrain modelling. Four vegetation indices were computed and visualised using R: the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index 2 (EVI2), Soil-Adjusted Vegetation Index (SAVI) and Atmospherically Resistant Vegetation Index 2 (ARVI2). The SAVI index is demonstrated to be more suitable and better adjusted to the vegetation analysis, which is beneficial for agricultural monitoring in Côte d'Ivoire. The terrain analysis is performed using Python and includes slope, aspect, hillshade and relief modelling with changed parameters for the sun azimuth and angle. The vegetation pattern in Côte d'Ivoire is heterogeneous, which reflects the complexity of the terrain structure. Therefore, the terrain and vegetation data modelling is aimed at the analysis of the relationship between the regional topography and environmental setting in the study area. The upscaled mapping is performed as regional environmental analysis of the Yamoussoukro surroundings and local topographic modelling of the Kossou Lake. The algorithms of the data processing include image resampling, band composition, statistical analysis and map algebra used for calculation of the vegetation indices in Côte d'Ivoire. This study demonstrates the effective application of the advanced programming algorithms in Python and R for satellite image processing. [ABSTRACT FROM AUTHOR]

Grassland pastures are crucial for the global food supply through their milk and meat production; hence, forage species monitoring is essential for cattle feed. Therefore, knowledge of pasture above-ground canopy features help understand the crop status. This paper finds how to construct machine learning models to predict above-ground canopy features in Brachiaria pasture from ground truth data (GTD) and remote sensing at larger (satellite data on the cloud) and smaller (unmanned aerial vehicles (UAV)) scales. First, we used above-ground biomass (AGB) data obtained from Brachiaria to evaluate the relationship between vegetation indices (VIs) with the dry matter (DM). Next, the performance of machine learning algorithms was used for predicting AGB based on VIs obtained from ground truth and satellite and UAV imagery. When comparing more than twenty-five machine learning models using an Auto Machine Learning Python API, the results show that the best algorithms were the Huber with R2 = 0.60, Linear with R2 = 0.54, and Extra Trees with R2 = 0.45 to large scales using satellite. On the other hand, short-scale best regressions are K Neighbors with an R2 of 0.76, Extra Trees with an R2 of 0.75, and Bayesian Ridge with an R2 of 0.70, demonstrating a high potential to predict AGB and DM. This study is the first prediction model approach that assesses the rotational grazing system and pasture above-ground canopy features to predict the quality and quantity of cattle feed to support pasture management in Colombia. [ABSTRACT FROM AUTHOR]

To date, no method utilizing satellite imagery exists for detailing the locations and functions of critical infrastructure across the United States, making response to natural disasters and other events challenging due to complex infrastructural interdependencies. This paper presents a repeatable, transferable, and explainable method for critical infrastructure analysis and implementation of a robust model for critical infrastructure detection in satellite imagery. This model consists of a DenseNet-161 convolutional neural network, pretrained with the ImageNet database. The model was provided additional training with a custom dataset, containing nine infrastructure classes. The resultant analysis achieved an overall accuracy of 90%, with the highest accuracy for airports (97%), hydroelectric dams (96%), solar farms (94%), substations (91%), potable water tanks (93%), and hospitals (93%). Critical infrastructure types with relatively low accuracy are likely influenced by data commonality between similar infrastructure components for petroleum terminals (86%), water treatment plants (78%), and natural gas generation (78%). Local interpretable model-agnostic explanations (LIME) was integrated into the overall modeling pipeline to establish trust for users in critical infrastructure applications. The results demonstrate the effectiveness of a convolutional neural network approach for critical infrastructure identification, with higher than 90% accuracy in identifying six of the critical infrastructure facility types. [ABSTRACT FROM AUTHOR]

Within water resources management, surface water area (SWA) variation plays a vital role in hydrological processes as well as in agriculture, environmental ecosystems, and ecological processes. The monitoring of long-term spatiotemporal SWA changes is even more critical within highly populated regions that have an arid or semi-arid climate, such as Iran. This paper examined variations in SWA in Iran from 1990 to 2021 using about 18,000 Landsat 5, 7, and 8 satellite images through the Google Earth Engine (GEE) cloud processing platform. To this end, the performance of twelve water mapping rules (WMRs) within remotely-sensed imagery was also evaluated. Our findings revealed that (1) methods which provide a higher separation (derived from transformed divergence (TD) and Jefferies–Matusita (JM) distances) between the two target classes (water and non-water) result in higher classification accuracy (overall accuracy (OA) and user accuracy (UA) of each class). (2) Near-infrared (NIR)-based WMRs are more accurate than short-wave infrared (SWIR)-based methods for arid regions. (3) The SWA in Iran has an overall downward trend (observed by linear regression (LR) and sequential Mann–Kendall (SQMK) tests). (4) Of the five major water basins, only the Persian Gulf Basin had an upward trend. (5) While temperature has trended upward, the precipitation and normalized difference vegetation index (NDVI), a measure of the country's greenness, have experienced a downward trend. (6) Precipitation showed the highest correlation with changes in SWA (r = 0.69). (7) Long-term changes in SWA were highly correlated (r = 0.98) with variations in the JRC world water map. [ABSTRACT FROM AUTHOR]

Surface water is a crucial resource and environmental element for human survival and ecosystem stability; therefore, accurate information on the distribution of surface water bodies is essential. Extracting this information on a large scale is commonly implemented using moderate- and low-resolution satellite images. However, the detection and analysis of more detailed surface water structures and small water bodies necessitate the use of very high-resolution (VHR) satellite images. The large-scale application of VHR images for water extraction requires convenient and accurate methods. In this paper, a method combining a pixel-level water index and image object detection is proposed. The method was tested using 2018/2019 multispectral 4-m resolution images obtained from the Chinese satellite Gaofen-2 across Beijing, China. Results show that the automatic extraction of water body information over large areas using the proposed method and VHR images is feasible. Kappa coefficient and overall accuracy of 0.96 and 99.8% after post-classification improvement were obtained for testing images inside the Beijing area. The Beijing water body dataset obtained included a total of 489.53 km2 of surface water in 2018/2019, 108.01 km2 of which were ponds with an area smaller than 2 km2. This study can be applied for water body extraction and mapping in other large regions and provides a reference for other methods for using VHR images to extract water body information on a large scale. [ABSTRACT FROM AUTHOR]

In this paper, we observed the tectono-geomorphological changes along the Dawki Fault and adjoining areas of Sylhet, Bangladesh using multitemporal Landsat satellite imageries from 1980 to 2020. The 40 years time lapse images were used to derive geomorphometric such as sinuosity index (SI), hydraulic sinuosity index (HSI), topographic sinuosity index (TSI), and lineament, directional and lineament density (LD) change analyses. To support these changes, other important parameters, i.e., Bouguer gravity anomaly (BGA) and digital elevation model (DEM) were considered based on their data availability. The present research observed spatiotemporal patterns in these parameters using remote sensing and GIS techniques, where multiple software platforms (i.e., ENVI 5.3, PCI Geomatica Banff 2020, Rockworks 16, ArcGIS 10.8 and MS Excel 2019) were utilized for mapping and data visualization. The study results from multiple parameters such as prominent lineament changes towards NE–SW directions matched well with the Dawki and nearby Disang faults, BGA data variations based on multiple transects, and elevation changes confirmed the increasing intensity of tectonic activity in the study area. Moreover, the lineament distributions, their concentrations, CV, and CSD have also confirmed the present tectonic movements which are especially observed in central, southern and northeastern directions. Research highlights: Tectono-geomorphological changes of the Dawki Fault and adjoining areas of Sylhet, Bangladesh were investigated. Geomorphological river sinuosity such as SSI, HSI, and TSI were measured based on the multi-temporal Landsat satellite data. Among the river sinuosity indices, TSI values were dominated over the HSI indicating the presence of tectonic activity in the study area. The study observed the lineament density change and its directional movements and increased tectonic activity along the Dawki Fault and adjoining areas. The digital elevation model (DEM) supports the tectonic activities and the change results indicating the subsidence and upliftment across the study area. [ABSTRACT FROM AUTHOR]

In the paper changes in vegetation and soil cover were identified by analyzing Landsat, Sentinel, Azerskay satellite images obtained in 2015-2021 on the basis of normalized vegetation differentiation index (NDVI) within the capabilities of ArcGIS program. The Vegetation Index (NDVI), calculated from satellite images, is widely used to track green vegetation on Earth. This study aims to investigate temporary changes in vegetation density, such as the distribution within the study area, the date of plant growth, and the date of reaching the highest density. This information was analyzed by ArcGIS. According to the results of the study, the vegetation activity started in the southern and northeastern part of the study area. It is shown that vegetation changes can be successfully tracked and analyzed with NDVI data. [ABSTRACT FROM AUTHOR]

The mangrove area in the Mahakam Delta has dynamically changed due to the land-use conversion for various purposes. Various remote sensing data can monitor the changes, for example, ALOS/PALSAR and Landsat imagery. However, there are limited studies that compare the use of both imageries to monitor such changes. This paper aims to compare the ability of two satellite imageries, i.e., ALOS/PALSAR and Landsat, to monitor the dynamic of mangrove areas. Two time-series data of ALOS/PALSAR and Landsat imagery for the acquisition period between 2007 and 2017 were analyzed using the Support Vector Machine (SVM) classification method on the Google Earth Engine (GEE). Landsat analysis results show an increase in the mangrove area of about 17,016 ha and a reduction of about 6,377 ha. ALOS/PALSAR images showed an increase of 15,903 ha and a reduction of 12,713 ha. The change detection results using two different imageries, i.e., Landsat and PALSAR, show slightly different results. Mangrove areas in 2007 and 2017 increased the area as detected from both Landsat and PALSAR. Landsat imaging classification is better at identifying mangroves from non-mangroves, although the 2007 classification results have flaws due to recording errors in striping. Because the quality of PALSAR 2007 and PALSAR 2017 images is not affected, the classification of PALSAR images is deemed more consistent in the area calculation. However, classification results in separating mangrove and non-mangrove near bodies of water are lacking. [ABSTRACT FROM AUTHOR]

Urban Heat Islands increase surface temperatures which impact the health and well-being of urban populations. Radiative forcing is impacted by changes to the land surface associated with urbanization that are particularly significant immediately after sunset. This paper aimed to analyze the behavior of UHI in different Local Climate Zones (LCZ) in Bragança city (Portugal), using Air Temperature (Ta), satellite images (Landsat 8), and on-site data. The methodology included a seasonal approach, integrating data with different scales (spatial, radiometric, and spectral) and qualitative and quantitative analyses. Google Earth Engine (GEE) optimized the processing time and computation requirement to generate the Land Surface Temperature (LST) maps. The integration of data with different scales corroborated the complementation of information/analysis and detected the correlation between the Ta and LST. However, the identification of the UHI was compromised due to the time of the passage of Landsat 8, and it was identified as the Urban Cool Island (UCI), a complementary effect of UHI, supporting the results of previous studies and for the use of Remote Sensing (RS) for thermal effects analysis. [ABSTRACT FROM AUTHOR]

Water resources is crucial for the continuity of life. Therefore, mapping water resources is required. Successful analysis of remotely sensed images can provide reliable information for water researches. However, it is very complex process to ensure that the maps created are not affected by shadows, cloud or other noise. In addition, it is necessary to successfully map all water types in various geographies. It is important that the method used is practical so that scientists who are not image analysts can use the large data pool provided by satellite images. In this paper, a novel algorithm for water body extraction from Landsat imagery is proposed. In this method, Corine data are used as auxiliary data to automatically generate training data. Four study areas with different characteristics, from different parts of the world, are used to test the proposed method. The results obtained are compared with other automatic classification methods. [ABSTRACT FROM AUTHOR]

Satellite hyperspectral remote sensing has gradually become an important means of Earth observation, but the existence of various types of noise seriously limits the application value of satellite hyperspectral images. With the continuous development of deep learning technology, breakthroughs have been made in improving hyperspectral image denoising algorithms based on supervised learning; however, these methods usually require a large number of clean/noisy training pairs, a target that is difficult to meet for real satellite hyperspectral imagery. In this paper, we propose a self-supervised learning-based algorithm, 3S-HSID, for denoising real satellite hyperspectral images without requiring external data support. The 3S-HSID framework can perform robust denoising of a single satellite hyperspectral image in all bands simultaneously. It first conducts a Bernoulli sampling of the input data, then uses the Bernoulli sampling results to construct the training pairs. Furthermore, the global spectral consistency and minimum local variance are used in the loss function to train the network. We use the training model to predict different Bernoulli sampling results, and the average of multiple predicted values is used as the denoising result. To prevent overfitting, we adopt a dropout strategy during training and testing. The results of denoising experiments on the simulated hyperspectral data show that the denoising performance of 3S-HSID is better than most state-of-the-art algorithms, especially in terms of maintaining the spectral characteristics of hyperspectral images. The denoising results for different types of real satellite hyperspectral data also demonstrate the reliability of the proposed method. The 3S-HSID framework provides a new technical means for real satellite hyperspectral image preprocessing. [ABSTRACT FROM AUTHOR]

Urban growth is a specific phenomenon to the evolution of cities, which exhibits over time through the fact that cities, from the moment they emerge, go through a continuous process of development and expansion. Urban growth means the spatial multiplication of the built-up (or otherwise valorized) land surfaces inside and outside the city boundary. Our research objective is to better understand all the dimensions affected by urban growth and their relationships, thus being necessary to use remote sensing techniques to identify the type of satellite imagery processed output that is best related to the economic and social indicators recorded statistically and historically. In the present paper, following the research carried out, the authors present the progress that they have made in terms of monitoring and studying the urban growth phenomenon for the city of Bucharest, based on the spatial patterns of the land use/land cover surfaces obtained through remote sensing of Landsat satellite imagery that emphasize the changes in the built-up land surfaces in more than four decades. Thus, the authors identified the changes at the macro scale of the city using the techniques of satellite remote sensing and established the most effective relationships to the historic, spatial, economic, and social statistical determinants. The results show which factors are decisive and which are the best land observations and forecasting techniques that can help the urban management of the city and its future development. The forecasting can be used both to estimate the chronological evolutions and future changes in urban surface and to think about city development policies and to surmount the absence of statistical socio-economic data. [ABSTRACT FROM AUTHOR]

Semantic segmentation of remote sensing images has many practical applications such as urban planning or disaster assessment. Deep learning-based approaches have shown their usefulness in automatically segmenting large remote sensing images, helping to automatize these tasks. However, deep learning models require large amounts of labeled data to generalize well to unseen scenarios. The generation of global-scale remote sensing datasets with high intraclass variability presents a major challenge. For this reason, data augmentation techniques have been widely applied to artificially increase the size of the datasets. Among them, photometric data augmentation techniques such as random brightness, contrast, saturation, and hue have been traditionally applied aiming at improving the generalization against color spectrum variations, but they can have a negative effect on the model due to their synthetic nature. To solve this issue, sensors with high revisit times such as Sentinel-1 and Sentinel-2 can be exploited to realistically augment the dataset. Accordingly, this paper sets out a novel realistic multi-temporal color data augmentation technique. The proposed methodology has been evaluated in the building and road semantic segmentation tasks, considering a dataset composed of 38 Spanish cities. As a result, the experimental study shows the usefulness of the proposed multi-temporal data augmentation technique, which can be further improved with traditional photometric transformations. [ABSTRACT FROM AUTHOR]

Riparian zones are dynamic ecosystems that form at the interface between the aquatic and terrestrial components of a landscape. They are shaped by complex interactions between the biophysical components of river systems, including hydrology, geomorphology, and vegetation. Remote sensing technology is a powerful tool useful for understanding riparian form, function, and change over time, as it allows for the continuous collection of geospatial data over large areas. This paper provides an overview of studies published from 1991 to 2021 that have used remote sensing techniques to map and understand the processes that shape riparian habitats and their ecological functions. In total, 257 articles were reviewed and organised into six main categories (physical channel properties; morphology and vegetation or field survey; canopy detection; application of vegetation and water indices; riparian vegetation; and fauna habitat assessment). The majority of studies used aerial RGB imagery for river reaches up to 100 km in length and Landsat satellite imagery for river reaches from 100 to 1000 km in length. During the recent decade, UAVs (unmanned aerial vehicles) have been widely used for low-cost monitoring and mapping of riverine and riparian environments. However, the transfer of RS data to managers and stakeholders for systematic monitoring as a source of decision making for and successful management of riparian zones remains one of the main challenges. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Central China Normal University is the property of Huazhong Normal University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Wildland fire is one of the most causes of deforestation, and it has an important impact on atmospheric emissions, notably CO². It occurs almost every year in Indonesia, especially during the dry season. Therefore, it is necessary to identify the burned areas from remote sensing images to establish the zoning map of areas prone to wildland fires. Many methods have been developed for mapping burned areas from low-resolution to medium-resolution satellite images. One of the popular approaches for mapping tasks is a deep learning approach using U-Net architecture. However, it needs a large amount of representative training data to develop the model. In this paper, we present a new dataset of burned areas in Indonesia for training or evaluating the U-Net model. We delineate burned areas manually by visual interpretation on Landsat-8 satellite images. The dataset is collected from some regions in Indonesia, and it consists of 227 images with a size of 512 x 512 pixels. It contains one or more burned scars or only the background and its labeled masks. The dataset can be used to train and evaluate the deep learning model for image detection, segmentation, and classification tasks related to burned area mapping. [ABSTRACT FROM AUTHOR]

Accurate understanding of daily evapotranspiration (ET) at field scale is of great significance for agricultural water resources management. The operational simplified surface energy balance (SSEBop) model has been applied to estimate field scale ET with Landsat satellite imagery. However, there is still uncertainty in the ET time reconstruction for cloudy days based on limited clear days' Landsat ET fraction (ETf) computed by SSEBop. The Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing data can provide daily surface observation over clear-sky areas. This paper presented an enhanced gap-filling scheme for the SSEBop ET model, which improved the temporal resolution of Landsat ETf through the spatio-temporal fusion with SSEBop MODIS ETf on clear days and increased the time reconstruction accuracy of field-scale ET. The results were validated with the eddy covariance (EC) measurements over cropland in northwestern China. It indicated that the improved scheme performed better than the original SSEBop Landsat approach in daily ET estimation, with higher Nash-Sutcliffe efficiency (NSE, 0.75 vs. 0.70), lower root mean square error (RMSE, 0.95 mm·d-1 vs. 1.05 mm·d-1), and percent bias (PBias, 16.5% vs. 25.0%). This fusion method reduced the proportion of deviation (13.3% vs. 25.5%) in the total errors and made the random error the main proportion, which can be reduced over time and space in regional ET estimation. It also evidently improved the underestimation of crop ET by the SSEBop Landsat scheme during irrigation before sowing and could more accurately describe the synergistic changes of soil moisture and cropland ET. The proposed MODIS and Landsat ETf fusion can significantly improve the accuracy of SSEBop in estimating field-scale ET. [ABSTRACT FROM AUTHOR]

In recent years, rapid urbanization and population growth have led to an overload of waste in big cities of Vietnam. Waste decomposition is always associated with the effects of heat generation as a result of the continuous aerobic and anaerobic processes, resulting in landfill surface temperature is significantly higher than the surrounding area. This paper presents the results of assessment of land surface temperature distribution in two largest landfills in Vietnam, including Nam Son landfill (Hanoi city, northern Vietnam) and Da Phuoc landfill (Ho Chi Minh city, southern Vietnam). Landsat 8 satellite image data is used to calculate land surface temperatures based on the split-window method. The results showed that the landfill surface temperature was much higher than the surrounding area, even compared to the areas characterized by impervious surfaces. The difference between the landfill surface temperature and temperature in areas covered by vegetation was about 20°C. The results obtained in this study provide input information to develop monitoring models of pollution at landfills. [ABSTRACT FROM AUTHOR]

Road detection based on convolutional neural networks (CNNs) has achieved remarkable performances for very high resolution (VHR) remote sensing images. However, this approach relies on massive annotated samples, and the problem of limited generalization for unseen images still remains. The manual pixel-level labeling process is also extremely time-consuming, and the performance of CNNs degrades significantly when there is a domain gap between the training and test images. In this paper, to address this problem, a global-local adversarial learning (GOAL) framework is proposed for cross-domain road detection. On the one hand, considering the spatial information similarities between the source and target domains, feature space driven adversarial learning is applied to explore the shared features across domains. On the other hand, the complex background of VHR remote sensing images, such as the occlusions and shadows of trees and buildings, makes some roads easy to recognize, while others are much more difficult. However, the traditional global adversarial learning approach cannot guarantee local semantic consistency. Therefore, a local alignment operation is introduced, which adaptively adjusts the weight of the adversarial loss according to the road recognition difficulty. Extensive experiments were conducted on different road datasets, including two public competition road datasets—SpaceNet and DeepGlobe—and our own large-scale annotated images from four cities: Boston, Birmingham, Shanghai, and Wuhan. The experimental results show that the proposed GOAL framework can clearly improve the cross-domain road detection performance, without any annotation of the target domain images. For instance, taking SpaceNet road dataset as the source domain, compared with the no adaptation method, the IOU performance of GOAL framework is increased by 14.36%, 5.49%, 4.51%, 5.63% and 15.14% on DeepGlobe, Boston, Birmingham, Shanghai, and Wuhan images, respectively, which demonstrates its strong generalization capability. [ABSTRACT FROM AUTHOR]

Researchers have recently begun investigating graph Convolutional neural networks for analyzing remotely sensed images. Modelling an image as a graph is a great way to understand its semantic, and applying the convolution on the graph structure have shown promising results in many real-world application. The hope is that such models help to improve the quality of land cover maps produced by the interpretation of satellite imagery. In this paper, we review recently proposed models based on graph convolution neural network architectures and discuss the challenge that could be taken up to improve the results of this technique and how can we use it for transfer learning between model. [ABSTRACT FROM AUTHOR]

Explainable machine learning has recently gained attention due to its contribution to understanding how a model works and why certain decisions are made. A so far less targeted goal, especially in remote sensing, is the derivation of new knowledge and scientific insights from observational data. In our paper, we propose an explainable machine learning approach to address the challenge that certain land cover classes such as wilderness are not well-defined in satellite imagery and can only be used with vague labels for mapping. Our approach consists of a combined U-Net and ResNet-18 that can perform scene classification while providing at the same time interpretable information with which we can derive new insights about classes. We show that our methodology allows us to deepen our understanding of what makes nature wild by automatically identifying simple concepts such as wasteland that semantically describes wilderness. It further quantifies a class's sensitivity with respect to a concept and uses it as an indicator for how well a concept describes the class. [ABSTRACT FROM AUTHOR]

Deep learning plays a major task in classification of unsupervised data, which utilises network enhanced learning. This technique proves to be powerful in remote sensing (RS) field for spatial data classification. In the existing environment, huge amounts of data from the earth observation satellites known as satellite images time series (SITS) are gathered, which can be utilised for observing the areas related to geography over through time. In this proposed model the time series model utilised is based on geography. There exists a challenge on how these types of information can be analysed in the field of remote sensing. Notable, techniques related to deep learning substantiated in dealing with remote sensing usually for classification of scene. In this paper, we propose an enhanced classification method involving Recurrent Neural Network (RNN) along with Random forest (RF) for land classification using satellite images, which are publicly available for various research purposes. We utilised spatial data gathered from the satellite images (i.e. time series). Our experimental classification is based on pixel and object-based classification. The attained analysis illustrates that the proposed model outperforms the other present day remote sensing classification techniques by producing 87% target accuracy of classification scene from satellite images. [ABSTRACT FROM AUTHOR]

Recently, the heavy precipitation occurred across the north of Iran caused an unprecedented flood. Due to the topographic conditions of the study area, not paying attention to the regular dredging of the river has caused a lot of problems for the local people. On the other hand, due to the frequent rainfall, the occurrence of flooding for a long time was another major problem. The combination of Remote Sensing and GIS can make a substantial contribution to flood assessment and management. In the present study, a fuzzy method is developed to show the hidden potential of Landsat satellite images for flood mapping. This paper presents the process of rapid access to water level information, which can provide valuable data for decision makers. The overall accuracy obtained for the flooded and damaged area is 87.23% and 46% respectively, and Root Mean Square Error (RMSE) of 27.68 cm is obtained for water-level based in the proposed algorithm. [ABSTRACT FROM AUTHOR]