Earth Surface Monitoring Research Articles

Evaluation of Cloud Masking Methods using Sentinel-2 Satellite Images on Google Earth Engine: A Case Study in Vietnam

The production of cloudless images from the optical satellite are critical in Earth surface monitoring. In 2015,Sentinel-2A was successfully launched into orbit by the European Space Agency. Sentinel-2 imagery is currently theprimary source of data for Earth monitoring. There are several ways to create cloudless images from multi-temporalSentinel-2 optical satellite imagery on the Google Earth Engine (GEE) platform. These include the Fmask (Function ofmask) method, the Fmask CDI (Cloud Displacement Index) method, and the Fmask CSP (Cloud Score Plus) method. Inthis paper, the authors build a program and evaluate the cloud masking methods on the GEE platform in Song Hinhdistrict, Phu Yen province, which is situated in the South-Central Coast region of Central Vietnam. The Song Hinh districtis a suitable study area for the evaluation of cloud masking methods on optical satellite images due to its diverse andcomplex terrain, which includes numerous peaks and valleys and a variety of climatic conditions. This article illustratesthe results of three cloud masking methods on Sentinel-2 images. In contrast to the Fmask method, the Fmask CDI andFmask CSP methods provide more benefits in detecting clouds and cloud shadows, resulting in more accurate outcomes

Improved Subsidence Assessment for More Reliable Excavation Activity in Tehran

This paper presents a particular tunneling method, the new Austrian tunneling method (NATM), which plays an important role in reducing subsidence of the surface and damage to structures in urban areas. It has a wide range of applications in shallow tunneling projects all over the world. In this study, numerical modeling of the third-line Metro tunnel in Tehran, which is designed and stabilized by the NATM, is under discussion. The foregoing tunnel is excavated manually with a one-meter advancing step. In this project, the constructors use a lattice girder and spray concrete with 31 cm thickness as the initial lining. A suitable numerical software for this modeling is PLAXIS 3D Tunnel, which allows high-resolution finite element modeling (FEM) of the studied object. The performance of this method is investigated and compared with that of other NATMs. The numerical modeling yielded a value of 30.01 mm for earth subsidence in the most damaged area of the settlement, which was confirmed with a dramatically low difference by earth surface monitoring. Moreover, this tunnel was drilled and excavated using various methods, among which the least settlement was obtained by the proposed method. The results are promising, and they indicate that tunneling with this method should continue to be used to expand the subway line in the city.

Earth-surface monitoring is at risk - more imaging tools are urgently needed.

Earth-surface monitoring is at risk - more imaging tools are urgently needed.

Evaluation of indicators for desertification risk assessment of Oleshky sands desertification based on Landsat data time series

Earth's surface monitoring allows the assessment of the dynamics and mapping of desertification indicators and is currently one of the priority research regions in remote sensing. In addition to the fact that desertification is a serious global threat to economic, social and food security, the risks of desertification have also become relevant for southern Ukraine. In recent years, climate change has become more and more noticeable in Ukraine. As a result, the time frames of the seasons are blurred, the boundaries of natural zones are shifting, abnormal values of meteorological indicators are increasingly observed, and the intensity of natural disasters is increasing. Since southern Ukraine is most vulnerable to adverse climate and landscape changes, including desertification, the article considered long-term landscape changes on the right bank of the Dnieper River in the Kherson region, mainly represented by sandy massifs of the Oleshky region, which are called the Oleshky Sands. Arid landscapes, which include the vast majority of Oleshky, are especially vulnerable to degradation processes, so space monitoring this territory is an urgent task given the current global climate changes. Within the framework of the presented study, the long-term dynamics of several indicators of desertification within the sandy arenas of the Oleshkovsky sands were mapped. Based on a series of multispectral space images obtained by Landsat satellites for the period 1986-2020 was considered. Spectral ranges characterize the key biophysical aspects of arid landscapes: the degree of soil moisture, vegetation density and sand distribution. Regression analysis was used to illustrate the dynamics of each indicator, which showed a general increase in each indicator over the experimental period. Furthermore, we determined the relationship between the values of the rise in desertification indicators and landscape changes that occurred in the research region, the classification of several images for different years was also carried out, and spatial and quantitative changes in the distribution of land cover classes were characterized.

Combining 2D encoding and convolutional neural network to enhance land cover mapping from Satellite Image Time Series

The use of high spatial resolution Satellite Image Time Series (SITS) provides an opportunity for a wide spectrum of Earth surface monitoring applications such as Land Use/Land Cover (LULC) mapping. Whereas the majority of Time Series (TS) classification literature concentrates on the analysis of raw 1D signals, here, we investigate a framework for LULC mapping based on 2D encoded multivariate SITS data to enhance their classification performances. In this novel approach, multivariate SITS data are transformed from 1D signals to 2D images using several encoding techniques namely Gramian Angular Summation field (GASF), Gramian angular difference field (GADF), Markov Transition Field (MTF), and Recurrence Plot (RP). Successively, a new multi-band image is derived and it is used as input to a state-of-the-art convolutional neural network (CNN) classification model. The possibility to effectively encode multivariate TS data into 2D representations paves the way to reuse the huge amount of research findings coming from the general field of computer vision and build on reliable and robust methods that have been demonstrated their quality in a multitude of downstream applications. Experiments carried out on three real-world benchmarks covering large spatial areas with contrasted land cover features, namely: Dordogne department in France, Reunion Island an oversee French territory and Koumbia municipality in Burkina Faso, underline the quality of the proposed framework when compared to standard approaches for land cover mapping from SITS and recent methods for multivariate TS classification. Matter of fact, our new framework outperforms the classification performances of standard land cover classification strategies based on the raw TS information achieving an average F1-score of 89.34%, 90.26% and 78.94% for the Reunion Island, Dordogne and Koumbia study site, respectively with an increasing of at least 2.5 points w.r.t. the best competing approach.

Quantifying Irrigated Winter Wheat LAI in Argentina Using Multiple Sentinel-1 Incidence Angles.

Synthetic aperture radar (SAR) data provides an appealing opportunity for all-weather day or night Earth surface monitoring. The European constellation Sentinel-1 (S1) consisting of S1-A and S1-B satellites offers a suitable revisit time and spatial resolution for the observation of croplands from space. The C-band radar backscatter is sensitive to vegetation structure changes and phenology as well as soil moisture and roughness. It also varies depending on the local incidence angle (LIA) of the SAR acquisition's geometry. The LIA backscatter dependency could therefore be exploited to improve the retrieval of the crop biophysical variables. The availability of S1 radar time-series data at distinct observation angles holds the feasibility to retrieve leaf area index (LAI) evolution considering spatiotemporal coverage of intensively cultivated areas. Accordingly, this research presents a workflow merging multi-date S1 smoothed data acquired at distinct LIA with a Gaussian processes regression (GPR) and a cross-validation (CV) strategy to estimate cropland LAI of irrigated winter wheat. The GPR-S1-LAI model was tested against in situ data of the 2020 winter wheat campaign in the irrigated valley of Colorador river, South of Buenos Aires Province, Argentina. We achieved adequate validation results for LAI with and RMSE CV = 0.88 m2 m-2. The trained model was further applied to a series of S1 stacked images, generating temporal LAI maps that well reflect the crop growth cycle. The robustness of the retrieval workflow is supported by the associated uncertainties along with the obtained maps. We found that processing S1 smoothed imagery with distinct acquisition geometries permits accurate radar-based LAI modeling throughout large irrigated areas and in consequence can support agricultural management practices in cloudprone agri-environments.

Potential and Limitation of PlanetScope Images for 2-D and 3-D Earth Surface Monitoring with Example of Applications to Glaciers and Earthquakes.- Supporting Document

Potential and Limitation of PlanetScope Images for 2-D and 3-D Earth Surface Monitoring with Example of Applications to Glaciers and Earthquakes.- Supporting Document

Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method

Medium-resolution remote sensing satellites have provided a large amount of long time series and full coverage data for Earth surface monitoring. However, the different objects may have similar spectral values and the same objects may have different spectral values, which makes it difficult to improve the classification accuracy. Semantic segmentation of remote sensing images is greatly facilitated via deep learning methods. For medium-resolution remote sensing images, the convolutional neural network-based model does not achieve good results due to its limited field of perception. The fast-emerging vision transformer method with self-attentively capturing global features well provides a new solution for medium-resolution remote sensing image segmentation. In this paper, a new multi-class segmentation method is proposed for medium-resolution remote sensing images based on the improved Swin UNet model as a pure transformer model and a new pre-processing, and the image enhancement method and spectral selection module are designed to achieve better accuracy. Finally, 10-categories segmentation is conducted with 10-m resolution Sentinel-2 MSI (Multi-Spectral Imager) images, which is compared with other traditional convolutional neural network-based models (DeepLabV3+ and U-Net with different backbone networks, including VGG, ResNet50, MobileNet, and Xception) with the same sample data, and results show higher Mean Intersection Over Union (MIOU) (72.06%) and better accuracy (89.77%) performance. The vision transformer method has great potential for medium-resolution remote sensing image segmentation tasks.

Potential and Limitation of PlanetScope Images for 2-D and 3-D Earth Surface Monitoring With Example of Applications to Glaciers and Earthquakes

The Planet PlanetScope cubesat constellation acquires high-resolution optical images which cover the entire surface of the Earth daily, enabling an unprecedented capability to monitor the Earth surface changes. However, our analysis reveals artifacts of the geometry of PlanetScope images related to the imaging system and processing issues, limiting the usability of these data for various earth science applications, including the monitoring of glaciers, dune motion, or the measurement of ground deformation due to earthquakes and landslides. Here we analyze these artifacts and propose ways to remediate them. We use two examples to evaluate the data and assess the performance of our proposed approaches. The first is the ground deformation caused by the 2019 Ridgecrest earthquake sequence, California, and the second is the 2018-2019 surge of the Shisper glacier in the Karakorum. Using an image correlation technique, we show that PlanetScope images exhibit several geometric artifacts, such as scene-to-scene misregistration, inconsistence geolocation accuracy between spectral bands, and topographic artifacts. Altogether these artifacts make a quantitative analysis of ground displacement difficult and inaccurate. We present a method that remediates most of these geometric artifacts. In addition, we propose a framework for selecting the most appropriate images and a procedure for refining the Rational Function Model (RFM) of unrectified images to monitor surface displacements and topography changes in 3D. These tools should enhance the use of PlanetScope images for Earth Science applications.

IGS-CMAES: A Two-Stage Optimization for Ground Deformation and DEM Error Estimation in Time Series InSAR Data

Interferometric synthetic aperture radar (InSAR) has become an increasingly recognized remote sensing technology for earth surface monitoring. Slow and subtle terrain displacements can be estimated using time-series InSAR (TSInSAR) data. However, a substantial increase in the availability of exclusive time series data necessitates the development of more efficient and effective algorithms. Research in these areas is usually carried out by solving complicated optimization problems, which is very computationally expensive and time-consuming. This work proposes a two-stage black-box optimization framework to jointly estimate the average ground deformation rate and terrain digital elevation model (DEM) error. The method performs an iterative grid search (IGS) to acquire coarse candidate solutions, and then a covariance matrix adaptive evolution strategy (CMAES) is adopted to obtain the final local results. The performance of our method is evaluated using both simulated and real datasets. Both quantitative and qualitative comparisons using different optimizers support the reliability and effectiveness of our work. The proposed IGS-CMAES achieves higher accuracy with a significantly fewer number of objective function evaluations than other established algorithms. It offers the possibility for wide-area monitoring, where high precision and real-time processing is essential.

Small spacecraft-based space system for real-time Earth surface monitoring

The paper presents basic results of exploratory design studies into a space system for real-time monitoring of the Earth surface based on small spacecraft* for Earth remote sensing, which provides acquisition in real time of highly detailed Earth surface images with resolution of 0.7–1.0 m, a swath of 20 km and 15m in-plane georeferencing accuracy from a ~300 km orbit with a mass of spacecraft ~200 kgf repeating with high frequency (at least every 1.0–1.5h). The said parameters are in line with the current state of the art and are quite feasible for our country’s industry. _________________________________________ * — for the purposes of this paper ‘small spacecraft’ is a 150-220 kg spacecraft. Key words: small spacecraft, space system, Earth remote sensing, satellite bus, payload module, electro-optical equipment, multipurpose ground facility, combined ground station, services of space monitoring of the Earth surface.

From reanalysis to satellite observations: gap-filling with imbalanced learning

Increasing the spatial coverage and temporal resolution of Earth surface monitoring can significantly improve forecasting or monitoring capabilities in the context of smart city, such as extreme weather forecasting, ecosystem monitoring and anthropogenic impact monitoring. As an essential data source for Earth’s surface monitoring, most satellite observations exist data gaps due to various factors like the limitations of measuring equipment, the interferences of environments, and the delay or loss of data updates. Although many efforts have been conducted to fill the gaps in the last decade, the existing techniques cannot efficiently address the problem. In this paper, we extensively study the gap-filling problem of satellite observations using imbalanced learning. Specifically, we propose a framework called Reanalysis to Satellite (R2S) to simulate satellite observations with reanalysis data. In the R2S framework, we propose a generic method called Spatial Temporal Match (STM), matching reanalysis data and satellite observations to construct the Reanalysis-Satellite (R-S) dataset used to train the model. Based on the R-S dataset, we propose a novel method called Semi-imbalanced (SIMBA) to handle the imbalance problem of gap-filling by taking advantages of traditional machine learning and imbalanced learning. We construct a hybrid model in the R2S framework for the Soil Moisture Active Passive (SMAP) satellite observations of the tropical cyclone wind speed. Extensive experiments demonstrate the hybrid model outperforms the traditional machine learning model and closely approximates in situ observations.

Optimization of Optical Image Geometric Modeling, Application to Topography Extraction and Topographic Change Measurements Using PlanetScope and SkySat Imagery

The volume of data generated by earth observation satellites has increased tremendously over the last few decades and will increase further in the coming decade thanks in particular to the launch of nanosatellites constellations. These data should open new avenues for Earth surface monitoring due to highly improved spectral, spatial and temporal resolution. Many applications depend, however, on the accuracy of the image geometric model. The geometry of optical images, whether acquired from pushbroom or frame systems, is now commonly represented using a Rational Function Model (RFM). While the formalism has become standard, the procedures used to generate these models and their accuracies are diverse. As a result, the RFM models delivered with commercial data are commonly not accurate enough for 3-D extraction, subpixel registration or ground deformation measurements. In this study, we present a methodology for RFM optimization and demonstrate its potential for 3D reconstruction using tri-stereo and multi-date Cubesat images provided by SkySat and PlanetScope, respectively. We use SkySat data over the Morenci Mine, Arizona, which is the largest copper mine in the United States. The re-projection error after the RFM refinement is 0.42 pix without using ground control points (GCPs). Comparison of our Digital Elevation Model (DEM with ~3 m GSD) with a reference DEM obtained from an airborne LiDAR survey (with ~1 m GSD) over stable areas yields a standard deviation of the elevation differences of ~3.9 m. The comparison of the two DEMs allows detecting and measuring the topographic changes due to the mine activity (excavation and stockpiles). We assess the potential of PlanetScope data, using multi-date DOVE-C images from the Shisper glacier, located in the Karakoram (Pakistan), which is known for its recent surge. We extracted DEMs in 2017 and 2019 before and after the surge. The re-projection error after the RFM refinement is 0.38 pix without using GCPs. The accuracy of our DEMs (with ~9 m GSD) is evaluated through comparison with the SRTM DEM (GSD ~30 m) and with a DEM (GSD ~2 m) calculated from Geoeye-1 (GE-1) and World-View-2 (WV-2) stereo images. The standard deviation of the elevation differences in stable areas between the PlanetScope DEM and SRTM is ~12 m, and ~7 m with the GE-1&WV-2 DEM. The mass transfer due to the surge is clearly revealed from a comparison of the 2017 and 2019 DEMs. The study demonstrates that, with the proposed scheme for RFM optimization, times series of DEM extracted from SkySat and PlanetScope images can be used to measure topographic changes due to mining activities or ice flow, and could also be used to monitor geomorphic processes such as landslides, or coastal erosion for example.

Object-Based Multi-Temporal and Multi-Source Land Cover Mapping Leveraging Hierarchical Class Relationships

European satellite missions Sentinel-1 (S1) and Sentinel-2 (S2) provide at high spatial resolution and high revisit time, respectively, radar and optical images that support a wide range of Earth surface monitoring tasks, such as Land Use/Land Cover mapping. A long-standing challenge in the remote sensing community is about how to efficiently exploit multiple sources of information and leverage their complementarity, in order to obtain the most out of radar and optical data. In this work, we propose to deal with land cover mapping in an object-based image analysis (OBIA) setting via a deep learning framework designed to leverage the multi-source complementarity provided by radar and optical satellite image time series (SITS). The proposed architecture is based on an extension of Recurrent Neural Network (RNN) enriched via a modified attention mechanism capable to fit the specificity of SITS data. Our framework also integrates a pretraining strategy that allows to exploit specific domain knowledge, shaped as hierarchy over the set of land cover classes, to guide the model training. Thorough experimental evaluations, involving several competitive approaches were conducted on two study sites, namely the Reunion island and a part of the Senegalese groundnut basin. Classification results, 79% of global accuracy on the Reunion island and 90% on the Senegalese site, respectively, have demonstrated the suitability of the proposal.

Combining Sentinel-1 and Sentinel-2 Satellite Image Time Series for land cover mapping via a multi-source deep learning architecture

The huge amount of data currently produced by modern Earth Observation (EO) missions has allowed for the design of advanced machine learning techniques able to support complex Land Use/Land Cover (LULC) mapping tasks. The Copernicus programme developed by the European Space Agency provides, with missions such as Sentinel-1 (S1) and Sentinel-2 (S2), radar and optical (multi-spectral) imagery, respectively, at 10 m spatial resolution with revisit time around 5 days. Such high temporal resolution allows to collect Satellite Image Time Series (SITS) that support a plethora of Earth surface monitoring tasks. How to effectively combine the complementary information provided by such sensors remains an open problem in the remote sensing field. In this work, we propose a deep learning architecture to combine information coming from S1 and S2 time series, namely TWINNS (TWIn Neural Networks for Sentinel data), able to discover spatial and temporal dependencies in both types of SITS. The proposed architecture is devised to boost the land cover classification task by leveraging two levels of complementarity, i.e., the interplay between radar and optical SITS as well as the synergy between spatial and temporal dependencies. Experiments carried out on two study sites characterized by different land cover characteristics (i.e., the Koumbia site in Burkina Faso and Reunion Island, a overseas department of France in the Indian Ocean), demonstrate the significance of our proposal.

Evaluating the potential of post-processing kinematic (PPK) georeferencing for UAV-based structure- from-motion (SfM) photogrammetry and surface change detection

Abstract. Images captured by unmanned aerial vehicles (UAVs) and processed by structure-from-motion (SfM) photogrammetry are increasingly used in geomorphology to obtain high-resolution topography data. Conventional georeferencing using ground control points (GCPs) provides reliable positioning, but the geometrical accuracy critically depends on the number and spatial layout of the GCPs. This limits the time and cost effectiveness. Direct georeferencing of the UAV images with differential GNSS, such as PPK (post-processing kinematic), may overcome these limitations by providing accurate and directly georeferenced surveys. To investigate the positional accuracy, repeatability and reproducibility of digital surface models (DSMs) generated by a UAV–PPK–SfM workflow, we carried out multiple flight missions with two different camera–UAV systems: a small-form low-cost micro-UAV equipped with a high field of view (FOV) action camera and a professional UAV equipped with a digital single lens reflex (DSLR) camera. Our analysis showed that the PPK solution provides the same accuracy (MAE: ca. 0.02 m, RMSE: ca. 0.03 m) as the GCP method for both UAV systems. Our study demonstrated that a UAV–PPK–SfM workflow can provide consistent, repeatable 4-D data with an accuracy of a few centimeters. However, a few flights showed vertical bias and this could be corrected using one single GCP. We further evaluated different methods to estimate DSM uncertainty and show that this has a large impact on centimeter-level topographical change detection. The DSM reconstruction and surface change detection based on a DSLR and action camera were reproducible: the main difference lies in the level of detail of the surface representations. The PPK–SfM workflow in the context of 4-D Earth surface monitoring should be considered an efficient tool to monitor geomorphic processes accurately and quickly at a very high spatial and temporal resolution.

Land Surface Temperature Retrieval from Sentinel-3A Sea and Land Surface Temperature Radiometer, Using a Split-Window Algorithm

Land surface temperature (LST) is a crucial parameter in the interaction between the ground and the atmosphere. The Sentinel-3A Sea and Land Surface Temperature Radiometer (SLSTR) provides global daily coverage of day and night observation in the wavelength range of 0.55 to 12.0 μm. LST retrieved from SLSTR is expected to be widely used in different fields of earth surface monitoring. This study aimed to develop a split-window (SW) algorithm to estimate LST from two-channel thermal infrared (TIR) and one-channel middle infrared (MIR) images of SLSTR observation. On the basis of the conventional SW algorithm, using two TIR channels for the daytime observation, the MIR data, with a higher atmospheric transmittance and a lower sensitivity to land surface emissivity, were further used to develop a modified SW algorithm for the nighttime observation. To improve the retrieval accuracy, the algorithm coefficients were obtained in different subranges, according to the view zenith angle, column water vapor, and brightness temperature. The proposed algorithm can theoretically estimate LST with an error lower than 1 K on average. The algorithm was applied to northern China and southern UK, and the retrieved LST captured the surface features for both daytime and nighttime. Finally, ground validation was conducted over seven sites (four in the USA and three in China). Results showed that LST could be estimated with an error mostly within 1.5 to 2.5 K from the algorithm, and the error of the nighttime algorithm involved with MIR data was about 0.5 K lower than the daytime algorithm.

Live Monitoring of Earth Surface (LiMES): A framework for monitoring environmental changes from Earth Observations

Global environmental changes are mostly induced by human activities (e.g., food and energy production, urbanization, mining activities). To assess and understand these changes that are occurring all around the planet, regular and continuous monitoring is an essential condition. However, due to the potentially large area spread over numerous locations that need to be followed, this usually leads to a low frequency of monitoring of environmental changes of only a few selected sites at best.With the increasing number of freely and openly accessible big remotely-sensed Earth Observations (EO) Data repositories and the increasing capabilities of open and interoperable software solutions it is now possible to automate various EO data processing tasks to monitor environmental changes at large scale.This paper presents the Live Monitoring of Earth Surface (LiMES) framework that helps to automate image processing tasks in transforming raw data into information and knowledge through workflows using interoperable processing service chains for monitoring environmental changes. Both benefits and limitations are demonstrated and discussed through the implementation of a prototype to facilitate the update on the status of some of the 278 UNEP Environmental Hotspots. We believe that such a framework can help to reduce the gap between massive volumes of EO data and the users such as International Organizations (IO) in order to help them better fulfil their environmental monitoring mandates by bringing raw data to a level which can be used by non-remote sensing experts for basic impacts assessments.

Data Fixing Algorithm in Radiosonde Monitoring Process

Earth surface monitoring can give information that may be used in complex analysis of the air conditions, temperature, humidity etc. Data from a vertical profile of the atmosphere is also essential for accurate thunderstorm forecasting. That data is collected by radiosondes – telemetry instruments carried into the atmosphere usually by balloons. Sometimes, due to the hostile conditions of upper troposphere, incorrect data can be generated by radiosonde sensors. In this paper, a new algorithm is developed for fixing the incorrect data, i.e. missing or out of specific range values. The proposed algorithm was tested both on benchmarks and real data generated by radiosondes. About 70% of significantly damaged test data volume was recovered. Up to 100% of real data was fixed.

INFORMATION MODELING OF WASTE DISPOSAL SITES

The paper proposes a methodology for developing information model or database of waste disposal sites /WDS/ or landfill sites, applying received remotely and in-situ data from Earth surface monitoring, especially including procedures of morphological processing, data normalization and visualization models. The overall structure and composition of the information model, described subsystems, classes, objects, and attributes (properties) of the data, are presented. The possibility of formation of new information relations, that arise between different kinds of information, through morphological (in particular, the morphemic) processing “raw” information at the input, for example, between the classifiers (waste products, settlements, economic activities, etc.), is described. The paper used methods of system analysis, methods of mathematical linguistics, space monitoring methods. For example a structure of constructing the database, the archive and the classifier of unauthorized waste disposal facilities (solid waste landfills, waste piles, municipal landfills, and others) is presented. The scheme of data model describes the components (tables) as part of the model: general information, geometric and geographic parameters of geo-referenced data, including data for adjacent territorial-administrative facilities, etc.