The view from somewhere: What remote sensing still has to learn about the satellite gaze

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Remote Sensing and Global Environmental Change

Remote sensing technology has emerged as a vital tool for monitoring and sustainably managing the environment. This paper reviews recent advances in remote sensing and their applications for environmental sustainability. A comprehensive literature review was conducted focusing on high-resolution analysis, temporal change detection, and hyper-spectral monitoring. Applications highlighted include detailed urban habitat mapping, assessing shoreline erosion, tracking forest disturbances, monitoring crop health, detecting pollution, and mapping coral reef degradation. The results showcase the quantitative insights remote sensing provides across diverse sustainability issues like climate change, urban planning, conservation, and disaster response. The paper emphasizes how ongoing improvements in remote sensing are enhancing environmental modelling capabilities and information availability, playing a key role in evidence-based decision-making for sustainable resource management. References Acharya, T.D. and Lee, D.H., 2019. Remote Sensing and Geospatial Technologies for Sustainable Development: A Review of Applications. Sensors & Materials, 31. Avtar, R., Komolafe, A.A., Kouser, A., Singh, D., Yunus, A.P., Dou, J., Kumar, P., Gupta, R.D., Johnson, B.A., Minh, H.V.T. and Aggarwal, A.K., 2020. Assessing sustainable development prospects through remote sensing: A review. Remote sensing applications: Society and environment, 20, p.100402. Asif, D. M., & Shaheen, A. (2022). Creating a High-Performance Workplace by the determination of Importance of Job Satisfaction, Employee Engagement, and Leadership. Journal of Business Insight and Innovation, 1(2), 9–15. https://doi.org/10.9876/jbii.v1i2.10 Asif, M., Pasha, M. A., Mumtaz, A., & Sabir, B. (2023). Causes of Youth Unemployment in Pakistan. Inverge Journal of Social Sciences, 2(1), 41-50. Bibri, S. E., & Bibri, S. E. (2018). Data science for urban sustainability: Data mining and data-analytic thinking in the next wave of city analytics. Smart Sustainable Cities of the Future: The Untapped Potential of Big Data Analytics and Context–Aware Computing for Advancing Sustainability, 189-246. Bibri, S. E., & Krogstie, J. (2017). The core enabling technologies of big data analytics and context-aware computing for smart sustainable cities: a review and synthesis. Journal of Big Data, 4, 1-50. Estoque, R.C., 2020. A review of the sustainability concept and the state of SDG monitoring using remote sensing. Remote Sensing, 12(11), p.1770. Franklin, S.E., 2001. Remote sensing for sustainable forest management. CRC press. Kour, R., Singh, S., Sharma, H.B., Naik, T.S.S.K., Shehata, N., Pavithra, N., Ali, W., Kapoor, D., Dhanjal, D.S., Singh, J. and Khan, A.H., 2023. Persistence and remote sensing of agri-food wastes in the environment: Current state and perspectives. Chemosphere, p.137822. Kouziokas, G.N. and Perakis, K., 2017. Decision support system based on artificial intelligence, GIS and remote sensing for sustainable public and judicial management. European Journal of Sustainable Development, 6(3), pp.397-397. Lai, Y. (2022). Urban Intelligence for Carbon Neutral Cities: Creating Synergy among Data, Analytics, and Climate Actions. Sustainability, 14(12), 7286. Li, F., Yigitcanlar, T., Nepal, M., Nguyen, K., & Dur, F. (2023). Machine Learning and Remote Sensing Integration for Leveraging Urban Sustainability: A Review and Framework. Sustainable Cities and Society, 104653. Li, J., Pei, Y., Zhao, S., Xiao, R., Sang, X. and Zhang, C., 2020. A review of remote sensing for environmental monitoring in China. Remote Sensing, 12(7), p.1130. Liang, A., Yan, D., Yan, J., Lu, Y., Wang, X. and Wu, W., 2023. A Comprehensive Assessment of Sustainable Development of Urbanization in Hainan Island Using Remote Sensing Products and Statistical Data. Sustainability, 15(2), p.979. Liang, A., Yan, D., Yan, J., Lu, Y., Wang, X., & Wu, W. (2023). A Comprehensive Assessment of Sustainable Development of Urbanization in Hainan Island Using Remote Sensing Products and Statistical Data. Sustainability, 15(2), 979. Pande, C. B., & Moharir, K. N. (2023). Application of hyperspectral remote sensing role in precision farming and sustainable agriculture under climate change: A review. Climate Change Impacts on Natural Resources, Ecosystems and Agricultural Systems, 503-520. Prince, S.D., 2019. Challenges for remote sensing of the Sustainable Development Goal SDG 15.3.1 productivity indicator. Remote Sensing of Environment, 234, p.111428. Rochon, G.L., Johannsen, C.J., Landgrebe, D.A., Engel, B.A., Harbor, J.M., Majumder, S. and Biehl, L.L., 2004. Remote sensing as a tool for achieving and monitoring progress toward sustainability. Technological choices for sustainability, pp.415-428. Seyam, M. M. H., Haque, M. R., & Rahman, M. M. (2023). Identifying the land use land cover (LULC) changes using remote sensing and GIS approach: A case study at Bhaluka in Mymensingh, Bangladesh. Case Studies in Chemical and Environmental Engineering, 7, 100293. Tékouabou, S. C., Chenal, J., Azmi, R., Toulni, H., Diop, E. B., & Nikiforova, A. (2022). Identifying and Classifying Urban Data Sources for Machine Learning-Based Sustainable Urban Planning and Decision Support Systems Development. Data, 7(12), 170. West, H., Quinn, N., & Horswell, M. (2019). Remote sensing for drought monitoring & impact assessment: Progress, past challenges and future opportunities. Remote Sensing of Environment, 232, 111291. White, J. C., Coops, N. C., Wulder, M. A., Vastaranta, M., Hilker, T., & Tompalski, P. (2016). Remote sensing technologies for enhancing forest inventories: A review. Canadian Journal of Remote Sensing, 42(5), 619-641. Xiuwan, C., 2002. Using remote sensing and GIS to analyse land cover change and its impacts on regional sustainable development. International journal of remote sensing, 23(1), pp.107-124. Yang, X.X. ed., 2021. Urban remote sensing: monitoring, synthesis and modeling in the urban environment. John Wiley & Sons. Zhu, L., Suomalainen, J., Liu, J., Hyyppä, J., Kaartinen, H., & Haggren, H. (2018). A review: Remote sensing sensors. Multi-purposeful application of geospatial data, 19-42.

Recent advancement in artificial intelligence (AI) has created new vistas in various applications of image processing during the last two decades. Image-processing techniques have been adopted in many fields like electronics and telecommunications, medical science, remote sensing (RS), biotechnology, robotics, etc. The RS is one area where interpretation of image and associated processing techniques are very important in different stages of earth observation study. This area has drawn a lot of research interest in the advancement of image-processing techniques for long. The RS research focuses on the classification of satellite images, as the deliverables of classification process are the basic foundation for many application areas of natural resources and environment. During the last few decades, considerable amount of attempts has been made to examine the efficiency of conventional image processing techniques for enhancement of image quality as well as the classification accuracy of RS images. The current literature has shown significant potentials of machine learning (ML) approaches in object detection and pattern recognition with a high success rate. The classification process has raised considerable issues and interests when the characteristic of the landscape becomes too complex. The ML-based classification approaches have been found effective on many benchmark RS datasets. This chapter explores the issues and challenges of image-processing techniques in the classification of high-dimensional RS datasets. It discusses the potential of AI/ML-based approaches by showcasing a case study on the classification of Airborne ROSIS-3 hyperspectral sensor data. Finally, it provides the concluding remarks of the chapter and gives possible research directions for object detection and classification from very-high-resolution (VHR) RS dataset like unmanned aerial vehicle (UAV) imagery using deep learning (DL) techniques.

Deep learning approaches have contributed to the rapid development of Remote Sensing (RS) image interpretation. The most widely used training paradigm is to utilize ImageNet pre-trained models to process RS data for specified tasks. However, there are issues such as domain gap between natural and RS scenes, and the poor generalization capacity of RS models. It makes sense to develop a foundation model with general RS feature representation. Since a large amount of unlabeled data is available, the self-supervised method has more development significance than the fully supervised method in remote sensing. However, most of the current self-supervised methods use contrastive learning, whose performance is sensitive to data augmentation, additional information, and selection of positive and negative pairs. In this paper, we leverage the benefits of generative self-supervised learning for RS images, and propose a Remote sensing foundation Model framework called RingMo, which consists of two parts. First, a large-scale dataset is constructed by collecting two million RS images from satellite and aerial platforms, covering multiple scenes and objects around the world. Second, we propose an RS foundation model training method designed for dense and small objects in complicated RS scenes. We show that the foundation model trained on our dataset with RingMo method achieves state-of-the-art on eight datasets across four downstream tasks, demonstrating the effectiveness of the proposed framework. Through in-depth exploration, we believe it is time for RS researchers to embrace generative self-supervised learning and leverage its general representation capabilities to speed up the development of RS applications.

The past years have witnessed great progress on remote sensing (RS) image interpretation and its wide applications. With RS images becoming more accessible than ever before, there is an increasing demand for the automatic interpretation of these images. In this context, the benchmark datasets serve as an essential prerequisites for developing and testing intelligent interpretation algorithms. After reviewing existing benchmark datasets in the research community of RS image interpretation, this article discusses the problem of how to efficiently prepare a suitable benchmark dataset for RS image interpretation. Specifically, we first analyze the current challenges of developing intelligent algorithms for RS image interpretation with bibliometric investigations. We then present the general guidances on creating benchmark datasets in efficient manners. Following the presented guidances, we also provide an example on building RS image dataset, i.e., Million Aerial Image Dataset (Online. Available: https://captain-whu.github.io/DiRS/0 ), a new large-scale benchmark dataset containing a million instances for RS image scene classification. Several challenges and perspectives in RS image annotation are finally discussed to facilitate the research in benchmark dataset construction. We do hope this article will provide the RS community an overall perspective on constructing large-scale and practical image datasets for further research, especially data-driven ones.

With the significant improvements in Earth observation (EO) technologies, remote sensing (RS) data exhibit the typical characteristics of Big Data. Propelled by the powerful feature extraction capabilities of intelligent algorithms, remote sensing image interpretation has drawn remarkable attention and achieved progress. However, the semantic relationship and domain knowledge hidden in massive RS images have not been fully exploited. To the best of our knowledge, a comprehensive review of recent achievements regarding semantic graph-based methods for comprehension and interpretation of remote sensing images is still lacking. Specifically, this article discusses the main challenges of remote sensing image interpretation and presents a systematic survey of typical semantic graph-based methodologies for RS knowledge representation and understanding, including the Ontology Model, Geo-Information Tupu, and Semantic Knowledge Graph. Furthermore, we categorize and summarize how the existing technologies address different challenges in RS image interpretation based on semantic graph-based methods, which indicates that the semantic information about potential relationships and prior knowledge of variant RS targets are central to the solution. In addition, a case study of RS geological interpretation based on the semantic knowledge graph is demonstrated to show the promising capability of intelligent RS image interpretation. Finally, the future directions are discussed for further research.

With the rapid development of the remote sensing monitoring and computer vision technology, the deep learning method has made a great progress to achieve applications such as earth observation, climate change and even space exploration. However, the model trained on existing data cannot be directly used to handle the new remote sensing data, and labeling the new data is also time-consuming and labor-intensive. Unsupervised Domain Adaptation (UDA) is one of the solutions to the aforementioned problems of labeled data defined as the source domain and unlabeled data as the target domain, i.e., its essential purpose is to obtain a well-trained model and tackle the problem of data distribution discrepancy defined as the domain shift between the source and target domain. There are a lot of reviews that have elaborated on UDA methods based on natural data, but few of these studies take into consideration thorough remote sensing applications and contributions. Thus, in this paper, in order to explore the further progress and development of UDA methods in remote sensing, based on the analysis of the causes of domain shift, a comprehensive review is provided with a fine-grained taxonomy of UDA methods applied for remote sensing data, which includes Generative training, Adversarial training, Self-training and Hybrid training methods, to better assist scholars in understanding remote sensing data and further advance the development of methods. Moreover, remote sensing applications are introduced by a thorough dataset analysis. Meanwhile, we sort out definitions and methodology introductions of partial, open-set and multi-domain UDA, which are more pertinent to real-world remote sensing applications. We can draw the conclusion that UDA methods in the field of remote sensing data are carried out later than those applied in natural images, and due to the domain gap caused by appearance differences, most of methods focus on how to use generative training (GT) methods to improve the model’s performance. Finally, we describe the potential deficiencies and further in-depth insights of UDA in the field of remote sensing.

Chapter 13 Methods of Estimating Plant Productivity and CO2 Flux in Agro-Ecosystems – Liking Measurements, Process Models, and Remotely Sensed Information

To study the impact of water level changes on the distribution of snails around lakes, and to study the possibility of forecasting the distribution of snails according to changes of water level reacted by remote sensing images. All information including water level information of Xingzi Hydrometric Station from 1997 to 2007, twelve TM images of Poyang Lake between 1998 and 2006 were collected. The water areas of Poyang Lake was extracted by MNDWI threshold approach, and the relationships between water areas from TM images and water level from Hydrometric Station was analyzed; Majiawan and Menqiantan marshland of Zhuxi village, Xingzi county was chosen as study pilot to set frames and investigate snails 2991 frames in 2007, and the information of snails of this pilot from 1998 to 2006 was collected to analyze the relationships between snails and water level. The water areas of Poyang Lake extracted from Remote Sensing images from 1998 to 2006 was 1658.73 - 5873.48 km(2), and the corresponding daily water level of Xingzi Hydrometric Station was 9.96 - 21.72 m, according to correlation analysis, they were positive correlation relationship, the correlation coefficient was 0.96 (P < 0.01), and build a model: S = 5189.96 x ln(h) - 10 284.97; the percent of frames with living snail of zhuxi pilot from 1998 - 2007 was 28.33% - 77.46%, the corresponding monthly average water level of last August was 13.19 - 21.96 m, the corresponding highest water level of last year was 15.97 - 21.96 m, according to correlation analysis. The percent of frames with living snail of zhuxi pilot was negatively correlated with the corresponding monthly average water level of last August and the corresponding highest water level of last year, and the correlation coefficient was -0.69 (P < 0.05), and -0.77 (P < 0.01) respectively. Water areas of Poyang Lake extracted from remote sensing images could well express the actual changes of water level, and the highest water level ahead of the year investigating snails influence the distribution of snails, thus we can estimate the distribution of snails around lakes by remote sensing images.

Compared with conventional airborne remote sensing application to engineering geological investigation, High precision Unmanned Aerial Vehicle Remote Sensing (UAV-RS) technology can improve work condition with advantages of high flexibility, low cost, high efficiency and up-to-date situation acquisition. Especially, it has very important engineering significance for quick and urgent geological disaster reconnaissance along transportation lines. In the paper, some aspects of application to transportation-line (pipeline, highway and railway) engineering geological investigation were discussed. The concerned key points, including components of UAV-RS system, data processing workflow and image interpretation were analyzed. As a case study, a UAV-RS application project for transportation-line geological disaster investigation was given. The utilization of this new remote sensing technology successfully collected and discovered potential geological disasters and provided scientific data for timely decision-making.

Hyper-temporal remote sensing for digital soil mapping: Characterizing soil-vegetation response to climatic variability

A benchmark data set for aircraft type recognition from remote sensing images

On a daily basis, political decisions are made, often with their full extent of impact being unclear. Not seldom, the decisions and policy measures implemented result in direct or indirect unintended negative impacts, such as on the natural environment, which can vary in time, space, nature, and severity. To achieve a more sustainable world with equitable societies requires fundamental rethinking of our policymaking. It calls for informed decision making and a monitoring of political impact for which evidence-based knowledge is necessary. The most powerful tool to derive objective and systematic spatial information and, thus, add to transparent decisions is remote sensing (RS). This review analyses how spaceborne RS is used by the scientific community to provide evidence for the policymaking process. We reviewed 194 scientific publications from 2015 to 2020 and analysed them based on general insights (e.g., study area) and RS application-related information (e.g., RS data and products). Further, we classified the studies according to their degree of science–policy integration by determining their engagement with the political field and their potential contribution towards four stages of the policy cycle: problem identification/knowledge building, policy formulation, policy implementation, and policy monitoring and evaluation. Except for four studies, we found that studies had not directly involved or informed the policy field or policymaking process. Most studies contributed to the stage problem identification/knowledge building, followed by ex post policy impact assessment. To strengthen the use of RS for policy-relevant studies, the concept of the policy cycle is used to showcase opportunities of RS application for the policymaking process. Topics gaining importance and future requirements of RS at the science–policy interface are identified. If tackled, RS can be a powerful complement to provide policy-relevant evidence to shed light on the impact of political decisions and thus help promote sustainable development from the core.

Remote-sensing images play a crucial role in a wide range of applications and have been receiving significant attention. In recent years, great efforts have been made in developing various methods for intelligent interpretation of remote-sensing images. Generally speaking, machine learning-based methods of remote-sensing image interpretation require a large number of labeled samples and there are still not enough annotated datasets in the field of remote sensing. However, manual annotation of remote-sensing images is usually labor-intensive and requires expert knowledge and the accuracy of annotation results is relatively low. The goal of this paper is to propose a novel tile-level annotation method of remote-sensing images to obtain remote-sensing datasets which are well-labeled and contain accurate semantic concepts. Firstly, we use a set of images with defined semantic concepts to represent the training set and divide them into several nonoverlapping regions. Secondly, the color features, texture features, and spatial features of each region are extracted, and discriminative features are obtained by the weight optimization feature fusion method. Then, the features are quantized into visual words by applying a density-based clustering center selection method and an isolated feature point elimination method. And the remote-sensing images can be represented by a series of visual words. Finally, the LDA model is used to calculate the probabilities of semantic categories for each region. The experiments are conducted on remote-sensing images which demonstrate that our proposed method can achieve good performance on remote-sensing image tile-level annotation. The implications of our research can obtain annotated datasets with accurate semantic concepts for intelligent interpretation of remote-sensing images.