Earth Observation Applications Research Articles

TEACHING GEOGRAPHIC INFORMATION SCIENCE CONCEPTS WITH QGIS AND THE LIVING TEXTBOOK – TOWARDS A SUSTAINABLE AND INCLUSIVE DISTANCE EDUCATION

Abstract. In 2020, many students could not travel due to the restrictions imposed by the COVID pandemic. In response, Faculty ITC of the University of Twente offered the online course Principles and Applications of Geographic Information Systems and Earth Observation as the first quartile of a full presential MSc. Programme. The course used the flipped classroom strategy to enhance student's ability to choose the learning strategy that best fitted their learning styles and was developed around four principles: (1) The course was Exercise led - students were introduced to concepts from the exercise descriptions; (2) Every concept taught was demonstrated and operationalized; (3) To emphasize the focus on concept learning, only two software tools were used - QGIS and the Living Textbook; (4) The software tools should be inclusive and encourage technological independence. The first three elements were evaluated by comparing the student feedback, the evaluation questionnaires and the academic attainment levels of the 2020 course with the in-house. The inclusiveness and technological independence were measured via the institutional impact. The results were positive for the new course setup, with students performing slightly better when compared with 2019 in-house edition of the course. The course had a significant institutional impact by contributing to a deeper commitment to open-source software tools. Open source is now the primary choice for teaching, with ITC becoming a QGIS-certified organization.

Optimal bandwidth and computing resource allocation in low earth orbit satellite constellation for earth observation applications

The next step in Earth Observation (EO) constellations will be leveraging Inter-Satellite Links (ISLs) to form a network where information generated by the EO application can be transmitted, in such a way that, by endowing spacecrafts with processing capacity, observation data may be processed directly in orbit by any satellite of the constellation. However, since bandwidth and on-board processing capacity are valuable resources, strategies to appropriately routing the information and deciding on which node it has to be processed shall be defined. In this work, we formalize and solve an optimal bandwidth and computing resource allocation problem in Low Earth Orbit (LEO) satellite constellation for EO applications. In order to deal with the complexity of the proposed optimization problem, we also present two heuristics requiring different computational effort. In the proposed problem formalization, processing can happen on any node of the network (i.e., either on the data source satellite, on any other satellite of the constellation or on ground station). After having validated the proposed heuristics by comparing their results to the optimization problem ones, we apply them to a real orbital scenario, showing their ability to reduce both total cost and data delivery delay to ground with respect to state-of-the-art solutions.

Taking Artificial Intelligence Into Space Through Objective Selection of Hyperspectral Earth Observation Applications: To bring the “brain” close to the “eyes” of satellite missions

Taking Artificial Intelligence Into Space Through Objective Selection of Hyperspectral Earth Observation Applications: To bring the “brain” close to the “eyes” of satellite missions

Cloud Removal in Remote Sensing Using Sequential-Based Diffusion Models

The majority of the optical observations collected via spaceborne optical satellites are corrupted by clouds or haze, restraining further applications of Earth observation; thus, exploring an ideal method for cloud removal is of great concern. In this paper, we propose a novel probabilistic generative model named sequential-based diffusion models (SeqDMs) for the cloud-removal task in a remote sensing domain. The proposed method consists of multi-modal diffusion models (MmDMs) and a sequential-based training and inference strategy (SeqTIS). In particular, MmDMs is a novel diffusion model that reconstructs the reverse process of denosing diffusion probabilistic models (DDPMs) to integrate additional information from auxiliary modalities (e.g., synthetic aperture radar robust to the corruption of clouds) to help the distribution learning of main modality (i.e., optical satellite imagery). In order to consider the information across time, SeqTIS is designed to integrate temporal information across an arbitrary length of both the main modality and auxiliary modality input sequences without retraining the model again. With the help of MmDMs and SeqTIS, SeqDMs have the flexibility to handle an arbitrary length of input sequences, producing significant improvements only with one or two additional input samples and greatly reducing the time cost of model retraining. We evaluate our method on a public real-world dataset SEN12MS-CR-TS for a multi-modal and multi-temporal cloud-removal task. Our extensive experiments and ablation studies demonstrate the superiority of the proposed method on the quality of the reconstructed samples and the flexibility to handle arbitrary length sequences over multiple state-of-the-art cloud removal approaches.

Earth observations into action: the systemic integration of earth observation applications into national risk reduction decision structures

PurposeAs stated in the United Nations Global Assessment Report 2022 Concept Note, decision-makers everywhere need data and statistics that are accurate, timely, sufficiently disaggregated, relevant, accessible and easy to use. The purpose of this paper is to demonstrate scalable and replicable methods to advance and integrate the use of earth observation (EO), specifically ongoing efforts within the Group on Earth Observations (GEO) Work Programme and the Committee on Earth Observation Satellites (CEOS) Work Plan, to support risk-informed decision-making, based on documented national and subnational needs and requirements.Design/methodology/approachPromotion of open data sharing and geospatial technology solutions at national and subnational scales encourages the accelerated implementation of successful EO applications. These solutions may also be linked to specific Sendai Framework for Disaster Risk Reduction (DRR) 2015–2030 Global Targets that provide trusted answers to risk-oriented decision frameworks, as well as critical synergies between the Sendai Framework and the 2030 Agenda for Sustainable Development. This paper provides examples of these efforts in the form of platforms and knowledge hubs that leverage latest developments in analysis ready data and support evidence-based DRR measures.FindingsThe climate crisis is forcing countries to face unprecedented frequency and severity of disasters. At the same time, there are growing demands to respond to policy at the national and international level. EOs offer insights and intelligence for evidence-based policy development and decision-making to support key aspects of the Sendai Framework. The GEO DRR Working Group and CEOS Working Group Disasters are ideally placed to help national government agencies, particularly national Sendai focal points to learn more about EOs and understand their role in supporting DRR.Originality/valueThe unique perspective of EOs provide unrealized value to decision-makers addressing DRR. This paper highlights tangible methods and practices that leverage free and open source EO insights that can benefit all DRR practitioners.

G-reqs, a New Model Proposal for Capturing and Managing In Situ Data Requirements: First Results in the Context of the Group on Earth Observations

In the field of Earth observation, the importance of in situ data was recognized by the Group on Earth Observations (GEO) in the Canberra Declaration in 2019. The GEO community focuses on three global priority engagement areas: the United Nations 2030 Agenda for Sustainable Development, the Paris Agreement, and the Sendai Framework for Disaster Risk Reduction. While efforts have been made by GEO to open and disseminate in situ data, GEO did not have a general way to capture in situ data user requirements and drive the data provider efforts to meet the goals of its three global priorities. We present a requirements data model that first formalizes the collection of user requirements motivated by user-driven needs. Then, the user requirements can be grouped by essential variable and an analysis can derive product requirements and parameters for new or existing products. The work was inspired by thematic initiatives, such as OSCAR, from WMO, OSAAP (formerly COURL and NOSA) from NOAA, and the Copernicus In Situ Component Information System. The presented solution focuses on requirements for all applications of Earth observation in situ data. We present initial developments and testing of the data model and discuss the steps that GEO should take to implement a requirements database that is connected to actual data in the GEOSS platform and propose some recommendations on how to articulate it.

Multi-Annual Evaluation of Time Series of Sentinel-1 Interferometric Coherence as a Tool for Crop Monitoring.

Interferometric coherence from SAR data is a tool used in a variety of Earth observation applications. In the context of crop monitoring, vegetation indices are commonly used to describe crop dynamics. The most frequently used vegetation indices based on radar data are constructed using the backscattered intensity at different polarimetric channels. As coherence is sensitive to the changes in the scene caused by vegetation and its evolution, it may potentially be used as an alternative tool in this context. The objective of this work is to evaluate the potential of using Sentinel-1 interferometric coherence for this purpose. The study area is an agricultural region in Sevilla, Spain, mainly covered by 18 different crops. Time series of different backscatter-based radar vegetation indices and the coherence amplitude for both VV and VH channels from Sentinel-1 were compared to the NDVI derived from Sentinel-2 imagery for a 5-year period, from 2017 to 2021. The correlations between the series were studied both during and outside the growing season of the crops. Additionally, the use of the ratio of the two coherences measured at both polarimetric channels was explored. The results show that the coherence is generally well correlated with the NDVI across all seasons. The ratio between coherences at each channel is a potential alternative to the separate channels when the analysis is not restricted to the growing season of the crop, as its year-long temporal evolution more closely resembles that of the NDVI. Coherence and backscatter can be used as complementary sources of information, as backscatter-based indices describe the evolution of certain crops better than coherence.

A Survey on SAR and Optical Satellite Image Registration

After decades of research, automatic synthetic aperture radar (SAR)-optical registration remains an unsolved problem. SAR and optical satellites utilize different imaging mechanisms, resulting in imagery with dissimilar heterogeneous characteristics. Transforming and translating these characteristics into a shared domain has been the main challenge in SAR-optical matching for many years. Combining the two sensors will improve the quality of existing and future remote sensing applications across multiple industries. Several approaches have emerged as promising candidates in the search for combining SAR and optical imagery. In addition, recent research has indicated that machine learning-based approaches have great potential for filling the information gap posed by utilizing only one sensor type in Earth observation applications. However, several challenges remain, and combining them is a multi-step process where no one-size-fits-all approach is available. This article reviews traditional, state-of-the-art, and recent development trends in SAR-optical co-registration methods.

A generalized control chart for anomaly detection in SAR imagery

Synthetic aperture radar (SAR) imagery is widely used in Earth observation (EO) applications such as land-use change monitoring and target detection. For such applications, it is important to have accurate knowledge of the statistical properties of SAR images to make good use of the information available. Therefore, it is essential to have appropriate statistical distributions to model the SAR data. In this context, the goal of this paper is threefold. First, a new parameterization of the Burr XII distribution that generalizes some widely used distributions for modeling SAR data is proposed. Second, based on the reparameterized distribution, a generalized control chart for anomaly detection in digital images is introduced. Using Monte Carlo simulations, the power detection of the proposed control chart by the empirical run length distribution is evaluated. Finally, the proposed methodology is applied to a real problem of anomaly detection. The problem of interest is the detection of military targets concealed in a forest region. The results suggest the relevance of the proposal to detect anomalies in SAR imagery, evidencing its practical applicability in EO problems.

Tunicate Swarm Algorithm with Deep Learning Based Land Use and Cover Change Detection in Nallamalla Forest India

Every biological system on the planet is severely impacted by environmental change, and its primary driver is deforestation. Meanwhile, quantitative analysis of changes in Land Use and Land Cover (LULC) is one of the prominent ways to manage and understand land transformation; thus, it is essential to inspect the performance of various techniques for LULC mapping to recognize the better classifier to more applications of earth observation. This article develops a Tunicate Swarm Algorithm with Deep Learning Enabled Land Use and Land Cover Change Detection (TSADL-LULCCD) technique in Nallamalla Forest, India. The presented TSADL-LULCCD technique mainly focuses on the identification and classification of land use in the Nallamalla forest using LANDSAT images. To accomplish this, the presented TSADL-LULCCD technique employs a dense EfficientNet model for feature extraction. In addition, the Adam optimizer is applied for the optimal hyper parameter tuning of the dense EfficientNet approach. For land cover classification, the TSADL-LULCCD technique exploits the Deep Belief Network (DBN) approach. To tune the hyper parameters related to the DBN system, the TSA is used. The experimental validation of the TSADL-LULCCD algorithm is tested on LANDSAT-7-based Nallamalla region images. The experimental results stated that the TSADL-LULCCD technique exhibits better performance over other existing models in terms of different evaluation measures.

A CNN-Based Sentinel-2 Image Super-Resolution Method Using Multiobjective Training

Deep learning methods have become ubiquitous tools in many Earth observation applications, delivering state-of-the-art results while proving to generalize for a variety of scenarios. One such domain concerns the Sentinel-2 (S2) satellite mission, which provides multispectral images in the form of 13 spectral bands, captured at three different spatial resolutions: 10, 20, and 60 m. This research aims to provide a super-resolution mechanism based on fully convolutional neural networks (CNNs) for upsampling the low-resolution (LR) spectral bands of S2 up to 10-m spatial resolution. Our approach is centered on attaining good performance with respect to two main properties: consistency and synthesis. While the synthesis evaluation, also known as Wald’s protocol, has spoken for the performance of almost all previously introduced methods, the consistency property has been overlooked as a viable evaluation procedure. Recently introduced techniques make use of sensor’s modulation transfer function (MTF) to learn an approximate inverse mapping from LR to high-resolution images, which is on a direct path for achieving a good consistency value. To this end, we propose a multiobjective loss for training our architectures, including an MTF-based mechanism, a direct input–output mapping using synthetically degraded data, along with direct similarity measures between high-frequency details from already available 10-m bands, and super-resolved images. Experiments indicate that our method is able to achieve a good tradeoff between consistency and synthesis properties, along with competitive visual quality results.

Local Window Attention Transformer for Polarimetric SAR Image Classification

Convolutional neural networks (CNNs) have recently found great attention in image classification since deep CNNs have exhibited excellent performance in computer vision. Owing to their immense success, of late, scientists are exploring the functionality of transformers in Earth observation applications. Nevertheless, the primary issue with transformers is that they demand significantly more training data than CNN classifiers. Thus, the use of these transformers in remote sensing is considered challenging, notably in utilizing polarimetric SAR (PolSAR) data, due to the insufficient number of existing labeled data. In this letter, we develop and propose a vision transformer-based framework that utilizes 3D and 2D CNNs as feature extractors and, in addition, local window attention for the effective classification of PolSAR data. Extensive experimental results demonstrated that the developed model PolSARFormer obtained better classification accuracy than the state-of-the-art vision Swin Transformer and FNet algorithms. The PolSARFormer outperformed the Swin Transformer and FNet by the margin of 5.86% and 17.63%, in terms of average accuracy in the San Francisco data benchmark. Moreover, the results over the Flevoland dataset illustrated that the PolSARFormer exceeds several other algorithms, including the ResNet (97.49%), Swin Transformer (96.54%), FNet (95.28%), 2D CNN (94.57%), and AlexNet (91.83%), with a kappa index of 99.30%. The code will be made available publicly at https://github.com/aj1365/PolSARFormer.

STDMANet: Spatio-Temporal Differential Multiscale Attention Network for Small Moving Infrared Target Detection

Infrared target detection has important applications in rescue and Earth observation. However, the disadvantages of low signal-to-clutter ratios and severe background noise interference for infrared imaging pose great challenges to the detection technology for infrared dim targets. Most algorithms only extract features from the spatial domain, while the lack of temporal information results in unsatisfactory detection performance when the difference between the target and the background is not significant enough. Although some methods utilize temporal information in the detection process, these nonlearning-based methods fail to incorporate the complex and changeable background, and need to adjust parameters according to the input. To tackle this problem, we proposed a Spatio-Temporal Differential Multiscale Attention Network (STDMANet), a learning-based method for multiframe infrared small target detection in this article. Our STDMANet first used the temporal multiscale feature extractor to obtain spatiotemporal (ST) features from multiple time scales and then resorted them to the spatial multiscale feature refiner to enhance the semantics of ST features on the premise of maintaining the position information of small targets. Finally, unlike other learning-based networks that require binary masks for training, we designed a mask-weighted heatmap loss to train the network with only center point annotations. At the same time, the proposed loss can balance missing detection and false alarm, so as to achieve a good balance between finding the targets and suppressing the background. Extensive quantitative experiments on public datasets validated that the proposed STDMANet could improve the metric <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${F_{1}}$ </tex-math></inline-formula> score up to 0.9744, surpassing the state-of-the-art baseline by 0.1682. Qualitative experiments show the proposed method could stably extract foreground moving targets from video sequences with various backgrounds while reducing false alarm rate better than other recent baseline methods.

GeoKG'2022 Workshop Report: The 1st ACM SIGSPATIAL International Workshop on Geospatial Knowledge Graphs

The topic of knowledge graphs (KGs) has recently attracted extensive attention in both industry and academia. Knowledge graphs are a new paradigm for representing, retrieving, integrating, and reasoning data from highly heterogeneous and multimodal sources. For example, international conferences, such as the Knowledge Graph Conference, have emerged in the past years, not to mention the increasing number of specialized workshops on KGs co-located with major computer science conferences, including Knowledge Graph Workshop at KDD 2021, Workshop for Deep Learning in Knowledge Graphs at ISWC 2021, Workshop on Knowledge Graph Construction at ESWC 2021, to name but a few. Also, the number of KGs-related papers accepted at these major conferences, including SIGSPATIAL, is rapidly increasing. Meanwhile, we also witness the increasing popularity of knowledge graph technologies in geography, geoinformatics, and GIScience domains. There are growing numbers of knowledge graph-related manuscripts accepted to the top geospatial-related venues, such as the International Journal of Geographical Information Science, Transactions in GIS, the International Journal of Applied Earth Observation and Geoinformation, and so on. Transactions in GIS also held two special issues about knowledge graphs: 1) Symbolic and Subsymbolic GeoAI: Geospatial Knowledge Graphs and Spatially Explicit Machine Learning [4], and 2) Knowledge-based GIS (K-GIS): Theories, Techniques and Applications. In addition, government agencies, industries, and non-governmental organizations (NGOs) are also lifting resources on topics of exploring KGs to build up interdisciplinary science and applications. One example is NSF's Accelerate Convergence Program, which promotes the idea of building an Open Knowledge Network to harness the data revolution. Funded by this program, the KnowWhereGraph is presently among the largest geo-enabled knowledge graphs, which integrates 28 different data layers at the intersection between humans and their environment [2].

Earth Observation Applications and the Right to Privacy: Within and Beyond the COVID-19 Pandemic

Earth Observation (EO) applications interact with many industries and government practices. When EO applications touch upon data being able to identify individuals or certain groups, the processing methods adopted therein entail the balance between public interests in EO applications and the values of privacy protection. It then raises the question of whether and to what extent the EO data comes under privacy protection. This study builds on the methodologies of positive law analysis and normative analysis, with supplementary discussions on the role of EO applications in the COVID-19 pandemic. In recognising the conclusion that the right to privacy entails restrictions on data processing within EO applications, the principle of proportionality calls for solutions to fill the gaps in the regulatory framework. Though legislative solutions are possible in theory, it is not an easy job to get consensus among States in practice. A more appropriate solution lies in introducing a privacy ranking regime internationally, with supplementary enforcement practices on the regional and national levels.

Radiative Transfer Model Comparison with Satellite Observations over CEOS Calibration Site Libya-4

Radiative transfer models of the Earth’s atmosphere play a critical role in supporting Earth Observation applications such as vicarious calibration. In the solar reflective spectral domain, these models usually account for the scattering and absorption processes in the atmosphere and the underlying surface as well as the radiative coupling between these two media. A range of models is available to the scientific community with built-in capabilities making them easy to operate by a large number of users. These models are usually benchmarked in idealised but often unrealistic conditions such as monochromatic radiation reflected by a Lambertian surface. Four different 1D radiative transfer models are compared in actual usage conditions corresponding to the simulation of satellite observations. Observations acquired by six different space-borne radiometers over the pseudo-invariant calibration site Libya-4 are used to define these conditions. The differences between the models typically vary between 0.5 and 3.5% depending on the spectral region and the shape of the sensor spectral response.

Generating images for Supervised Hyperspectral Image Classification with Generative Adversarial Nets

With the advancement of remote sensing technologies, hyperspectral imagery has garnered significant interest in the remote sensing community. These developments have inspired improvement in various hyperspectral images (HSI) classification applications, such as land cover mapping, amongst other earth observation applications. Deep Neural Networks have revolutionized image classification tasks in areas of computer vision. However, in the domain of hyperspectral images, insufficient training samples have been earmarked as a significant bottleneck for supervised HSI classification. Moreover, acquiring HSI from satellites and other remote sensors is expensive. Thus, researchers have turned to generative models to leverage the existing data to increase training samples, such as particularly generative adversarial networks (GAN). This paper explores the use of a vanilla GAN to generate synthetic data. The network employed in this paper was built using a deep learning python package, PyTorch and tested on a popular HSI dataset called Indian Pines dataset. The network achieved an overall accuracy of 64%. While promising, there is still room for improvement.

The use of remote sensing and GIS for land use and land cover mapping in Eswatini: A Review

Remote sensing and GIS are often used to assess spatiotemporal variations for land use/land cover (LULC) monitoring and classification. While LULC monitoring and classification has been undertaken in Eswatini, little attention has been given to ascertaining covered thematic areas, methods of image classification, and approaches and techniques for improving classification accuracy. This paper summarises and synthesizes the progress made in the Kingdom of Eswatini regarding the application of remote sensing and GIS in LULC monitoring and classification. Eight thematic areas (water resources mapping; land degradation; forestry; wildfire detection; urban expansion; crop production; disease surveillance; general mapping) dominate evaluated LULC studies, employing three LULC classification methods (classic; manual; advanced). While some studies include strengths and weaknesses of LULC classification techniques applied, others do not. This review shows that only two advanced classifiers (random forest; object-based) were identified from the reviewed articles. In addition, reviewed studies applied only two approaches (use of multi temporal data; fine spatial resolution data) and three techniques (use of ancillary data; post-classification procedure; the use of multisource data) for improving classification accuracy. Furthermore, the review finds that limited LULC investigations have been covered in Eswatini with a specific focus on the Sustainable Development Goals (SDGs). As such, this review recommends 1) the inclusion of higher resolution imagery for mapping purposes, 2) the adaptation of strengths and weaknesses for any image classification technique employed in future publications, 3) the use of more varied approaches and techniques for improving classification accuracy and area estimates, 4) inclusion of standard errors or confidence intervals for error-adjusted area estimates as part of accuracy assessment reporting, 5) the application of advanced image classifiers, and 6) the application of Earth Observation (EO) Analysis Ready Data (ARD) in the production of information for the support of the SDGs.

An Unsupervised Cascade Fusion Network for Radiometrically-Accurate Vis-NIR-SWIR Hyperspectral Sharpening

Hyperspectral sharpening has been considered an important topic in many earth observation applications. Many studies have been performed to solve the Visible-Near-Infrared (Vis-NIR) hyperpectral sharpening problem, but there is little research related to hyperspectral sharpening including short-wave infrared (SWIR) bands despite many hyperspectral imaging systems capturing this wavelength range. In this paper, we introduce a novel method to achieve full-spectrum hyperspectral sharpening by fusing the high-resolution (HR) Vis-NIR multispectral image (MSI) and the Vis-NIR-SWIR low-resolution (LR) hyperspectral image (HSI). The novelty of the proposed approach lies in three points. Firstly, our model is designed for sharpening the full-spectrum HSI with high radiometric accuracy. Secondly, unlike most of the big-dataset-driven deep learning models, we only need one LR-HSI and HR-MSI pair for training. Lastly, per-pixel classification is implemented to test the spectral accuracy of the results.

Snow detection in alpine regions with Convolutional Neural Networks: discriminating snow from cold clouds and water body

ABSTRACT Accurately monitoring the variation of snow cover from remote sensing is vital since it assists in various fields including prediction of floods, control of runoff values, and the ice regime of rivers. Spectral indices methods are traditional ways to realize snow segmentation, including the most common one – the Normalized Difference Snow Index (NDSI), which utilizes the combination of green and short-wave infrared (SWIR) bands. In addition, spectral indices methods heavily depend on the optimal threshold to determine the accuracy, making it time-consuming to find optimal values for different places. Convolutional neural networks ensemble model with DeepLabV3+ was employed as sub-models for snow segmentation using (Sentinel-2), which aims to distinguish clouds and water body from snow. The imagery dataset generated in this article contains sites in global alpine regions such as Tibetan Plateau in China, the Alps in Switzerland, Alaska in the United States, Southern Patagonian Icefield in Chile, Tsylos Provincial Park, Tatsamenie Peak, and Dalton Peak in Canada. To overcome the limitation of DeepLabV3+, which only accepts three channels as input features, and the need to use six features: green, red, blue, near-infraRed, SWIR, and NDSI, 20 three-channel DeepLabV3+ sub-models, were constructed with different combinations of three features and then ensembled together. The proposed ensemble model showed superior performance than benchmark spectral indices method, with mIoU values ranging from 0.8075 to 0.9538 in different test sites. The results of this project contribute to the development of automated snow segmentation tools to assist earth observation applications.