Space Research Articles

Review of models for estimating 3D human pose using deep learning

Human pose estimation (HPE) is designed to detect and localize various parts of the human body and represent them as a kinematic structure based on input data like images and videos. Three-dimensional (3D) HPE involves determining the positions of articulated joints in 3D space. Given its wide-ranging applications, HPE has become one of the fastest-growing areas in computer vision and artificial intelligence. This review highlights the latest advances in 3D deep-learning-based HPE models, addressing the major challenges such as accuracy, real-time performance, and data constraints. We assess the most widely used datasets and evaluation metrics, providing a comparison of leading algorithms in terms of precision and computational efficiency in tabular form. The review identifies key applications of HPE in industries like healthcare, security, and entertainment. Our findings suggest that while deep learning models have made significant strides, challenges in handling occlusion, real-time estimation, and generalization remain. This study also outlines future research directions, offering a roadmap for both new and experienced researchers to further develop 3D HPE models using deep learning.

From Single to Multi-Material 3D Printing of Glass-Ceramics for Micro-Optics.

Feynman's statement, "There is plenty of room at the bottom", underscores vast potential at the atomic scale, envisioning microscopic machines. Today, this vision extends into 3D space, where thousands of atoms and molecules are volumetrically patterned to create light-driven technologies. To fully harness their potential, 3D designs must incorporate high-refractive-index elements with exceptional mechanical and chemical resilience. The frontier, however, lies in creating spatially patterned micro-optical architectures in glass and ceramic materials of dissimilar compositions. This multi-material capability enables novel ways of shaping light, leveraging the interaction between diverse interfaced chemical compositions to push optical boundaries. Specifically, it encompasses both multi-material integration within the same architectures and the use of different materials for distinct architectural features in an optical system. Integrating fluid handling systems with two-photon lithography (TPL) provides a promising approach for rapidly prototyping such complex components. This review examines single and multi-material TPL processes, discussing photoresin customization, essential physico-chemical conditions, and the need for cross-scale characterization to assess optical quality. It reflects on challenges in characterizing multi-scale architectures and outlines advancements in TPL for both single and spatially patterned multi-material structures. The roadmap provides a bridge between research and industry, emphasizing collaboration and contributions to advancing micro-optics.

2D Ising critical couplings from quantum gravity

Using an exact holographic duality formula between the inhomogeneous 2D Ising model and 3D quantum gravity, we provide a formula for “real” zeros of the 2D Ising partition function on finite trivalent graphs in terms of the geometry of a 2D triangulation embedded in the three-dimensional Euclidean space. The complex phase of those zeros is given by the dihedral angles of the triangulation, which reflect its extrinsic curvature within the ambient 3D space, while the modulus is given by the angles within the 2D triangles, thus encoding the intrinsic geometry of the triangulation. Our formula cannot cover the whole set of Ising zeros, but we conjecture that a suitable complexification of these “real” zeros would provide a more thorough formula. Nevertheless, in the thermodynamic limit, in the case of flat planar 2D triangulations, our Ising zeros’ formula gives the critical couplings for isoradial graphs, confirming its generality. Finally, the formula naturally extends to graphs with arbitrary valence in terms of the geometry of circle patterns embedded in 3D space. This approach shows an intricate, but precise, new relation between statistical mechanics and quantum geometry. Published by the American Physical Society 2025

Space–time decay rates of a nonconservative compressible two–phase flow model

This paper concerns the space–time decay rates of strong solution to a nonconservative compressible two–phase flow model in the whole space R3. Based on the previous temporal decay results, it is shown that the space–time decay rate of k(0 ≤ k ≤ N)–order spatial derivative of the strong solution in weighted Lebesgue space Lγ2 is t−34−k2+γ for any integer N ≥ 2. The methods mainly involve delicate weighted energy estimates and interpolation tricks.

An intriguing coincidence between the majority of vast polar structure dwarfs and a recent major merger at the M31 position

A significant part of the Milky Way (MW) dwarf galaxies orbit within a Vast POlar Structure (VPOS), which is perpendicular to the Galactic disc and whose origin has not yet been identified. It includes the Large Magellanic Cloud (LMC) and its six dynamically associated dwarf galaxies. Andromeda Galaxy (M31) experienced a major merger two to three billion years ago, and its accurate modelling predicts that an associated tidal tail is pointing towards the Galaxy. Here, we tested a possible association between M31 tidal tail particles and MW dwarf galaxies, focusing first on the LMC and its associated dwarfs since they are less affected by ram pressure. We traced back these dwarf galaxy orbits by one billion years and calculated their association with the tidal tail particles in the 6D phase space, based on their proper motion from Gaia DR3. We find that for low-mass MW models (total mass less than 5 × 1011 M⊙), the separation in the 6D space can be less than 1σ for most of the M31 modelling, albeit with a significant degree of freedom due to the still unknown proper motion of M31. We further discover that many other dwarfs could also be associated with the M31 tidal tails if their motions had been radially slowed, as expected from the ram pressure exerted by the MW corona. This intriguing coincidence could explain the origin of the VPOS, which resulted from a matter exchange between M31 and MW.

Integrated 3D reservoir modelling for the unconventional reservoir prospects: a case study of Upper Cretaceous Brown Limestone reservoir, South Geisum field, Gulf of Suez, Egypt

The Gulf of Suez basin (GOS) hosts over eighty conventional oilfields spanning from the Pre-Cambrian to the Recent. This research focuses on a segment of the (GOS) sequence within the territories managed by PGM Company. It outlines a methodology for evaluating unconventional resource potential within the Brown Limestone interval of Upper Cretaceous age in this region. The Brown Limestone interval serves not only as a crucial source rock but also as a fractured reservoir widespread across many oilfields. Due to intricate reservoir architecture, diverse lateral variations in facies and the heterogeneity of the reservoir quality, uncertainties prevail. These challenges impede the optimization of reservoir exploitation throughout the GOS Basin. This study employs an integrated approach utilizing diverse datasets and techniques to ascertain the precise structural setting, property attributes of the Upper Cretaceous Brown Limestone and forecast its complex geometry in three-dimensional space within the study area. The study aims to assess the reservoir and trap heterogeneity under various scenarios to create a robust 3D static model dictating the structural and property complexities. The objective of the model is to enhance the precision of reserve estimates and provide crucial support for decision-making in the development planning of the South Geisum oilfield.

AirCanvas using OpenCV and MediaPipe

Human-Computer Interaction (HCI) has undergone significant transformations with the advent of Artificial Intelligence (AI) and Machine Learning (ML), enhancing the ways in which users engage with computing systems. This paper introduces AirCanvas, a novel hands-free digital interaction tool that leverages air gestures for intuitive and seamless computer control. The system uses advanced image processing techniques, specifically OpenCV for visual data analysis and MediaPipe for accurate hand gesture recognition, enabling users to manipulate virtual environments without physical touch. By integrating a standard webcam as the primary sensor, AirCanvas offers an accessible solution for gesture-based interaction, eliminating the need for specialized external hardware like motion sensors or gloves. Users can perform a variety of tasks such as virtual drawing, cursor control, and presentation navigation with simple hand gestures in 3D space. The system's gesture recognition capabilities are powered by deep learning models trained on large datasets of hand movements, ensuring robust performance in diverse lighting and environmental conditions. The potential applications of AirCanvas are far-reaching, ranging from interactive art creation to more practical uses in assistive technology, where people with mobility impairments can benefit from hands-free control. In the field of robotics, the tool can enable more natural human-robot interaction, while in gaming, it can introduce new forms of immersive gameplay through gesture-based interfaces. Furthermore, the tool's open-source nature allows for further customization and enhancement, fostering innovation and collaboration in various industries. As human-computer interaction continues to evolve, AirCanvas represents a significant step forward in making technology more intuitive, engaging, and accessible for all users.

Motion Hologram: Jointly optimized hologram generation and motion planning for photorealistic 3D displays via reinforcement learning.

Holography is capable of rendering three-dimensional scenes with full-depth control and delivering transformative experiences across numerous domains, including virtual and augmented reality, education, and communication. However, traditional holography presents 3D scenes with unnatural defocus and severe speckles due to the limited space bandwidth product of the spatial light modulator (SLM). Here, we introduce Motion Hologram, a holographic technique that accurately portrays photorealistic and speckle-free 3D scenes. This technique leverages a single hologram and a learnable motion trajectory, which are jointly optimized within a deep reinforcement learning framework. Specifically, we experimentally demonstrated that the proposed technique could achieve a 4- to 5-dB PSNR improvement of focal stacks in comparison with traditional holography and could successfully depict speckle-free, high-fidelity, and full-color 3D displays using only a commercial SLM. We believe that the proposed method promises a prospective form of holographic displays that will offer immersive viewing experiences for audiences.

A New Control Approach for a Multi-Controlled Wheelchair Utilizing Deep Learning Framework and Raspberry Pi

This article describes the construction and control mechanisms of a multiple control wheelchair (MCW) aimed to aid individuals with amyotrophic lateral sclerosis (ALS) and lower limb disabilities. The MCW has been tested in the laboratory on a total of 10 patients, among them 3 with lower limb disabilities, 6 elderly patients, and 1 patient with ALS. The proposed wheelchair can navigate in any direction using object detection techniques powered by OpenCV. Employing a deep learning algorithm, it performs real-time object detection and tracks its current position in various environmental conditions. The MCW can be controlled using a joystick, internet of things (IoT), or a combination of both. A novel aspect of this work is the implementation of a deep learning framework on a Raspberry Pi processor, allowing the wheelchair to navigate in any direction based on the user’s needs. The Raspberry Pi interfaces with all sensors, camera, and additional peripherals through serial communication, enabling monitoring and control via an android mobile application. This setup effectively reduces the physical distance between the user and the caregiver. During the test, a range of functional measurements were taken, including assessments of the object detection process and the performance of hardware components such as sensors and motors connected to the system. The current system is unable to precisely determine an object’s position during detection, but ongoing research is focused on enhancing the system’s capability to accurately map objects in 3D space for improved wheelchair navigation.

Typological analysis of the dynamic characteristics of overflows under homogeneous urban form: evidence from Hong Kong’s back alleys

ABSTRACT Urban form refers to the geometric characteristics of a city in two- and three-dimensional space. Homogeneous urban forms often weaken regional characteristics, leading to a decline in urban vitality, among other issues. However, research has generally focused on fixed elements, such as buildings and streets, while paying less attention to semi-fixed elements, such as “overflow” (i.e. movable personal items that people place in public spaces), which plays a crucial role in shaping urban form. This study aims to explore the characteristics of overflow forms in urban spaces. Using a typological approach, it classifies overflows in Hong Kong’s back alleys. The Pearson chi-squared test examines the relationship between position and internal arrangement of overflows, while the Kruskal – Wallis and Nemenyi tests assess the differences in scale among various types of positions and internal arrangements. The findings reveal the dynamic characteristics of overflows, offering insights into how urban residents personalize public spaces in response to challenges and opportunities presented by governmental regulations and the built environment. By introducing new perspectives and research objects into the study of urban form, this study provides valuable ideas for micro-scale urban design and mitigating the homogeneous urban form.

A Novel Stochastic Interacting Particle-Field Algorithm for 3D Parabolic-Parabolic Keller-Segel Chemotaxis System

We introduce an efficient stochastic interacting particle-field (SIPF) algorithm with no history dependence for computing aggregation patterns and near singular solutions of parabolic-parabolic Keller-Segel (KS) chemotaxis system in three-dimensional (3D) space. In our algorithm, the KS solutions are approximated as empirical measures of particles coupled with a smoother field (concentration of chemo-attractant) variable computed by a spectral method. Instead of using heat kernels that cause history dependence and high memory cost, we leverage the implicit Euler discretization to derive a one-step recursion in time for stochastic particle positions and the field variable based on the explicit Green’s function of an elliptic operator of the form Laplacian minus a positive constant. In numerical experiments, we observe that the resulting SIPF algorithm is convergent and self-adaptive to the high-gradient part of solutions. Despite the lack of analytical knowledge (such as a self-similar ansatz) of a blowup, the SIPF algorithm provides a low-cost approach to studying the emergence of finite-time blowup in 3D space using only dozens of Fourier modes and by varying the amount of initial mass and tracking the evolution of the field variable. Notably, the algorithm can handle multi-modal initial data and the subsequent complex evolution involving the merging of particle clusters and the formation of a finite time singularity with ease.

P-765. Enhancing Tuberculosis (TB) Surveillance with Artificial Intelligence: Utilizing Latent Semantic Indexing (LSI) to Automatically Detect TB Cases

Abstract Background Reducing TB surveillance incurs significant costs, as effective control and societal impact minimization rely on robust, ongoing surveillance systems that integrate and analyze comprehensive data for prompt action. Our study supports integrating artificial intelligence (LSI) into TB and other notifiable disease monitoring frameworks to improve trackingFigure 1Binary Matrix of 125 Terms: Presence vs. Absence of Root Keywords Retrieved from the Patient ElectronicRecord for the LSI Automatic Retrieval System.Binary Matrix of 125 Terms: Presence vs. Absence of Root Keywords Retrieved from the Patient Electronic Record for the LSI Automatic Retrieval System. Methods In 2024, we developed a novel application within Datamart A.R.G.U.S.—Assistant for Recovery and Guarding of Urgent and Epidemiological Sentinels—a cloud-based platform hosted on AWS and developed by our team. This application integrates with hospital systems (MV) and laboratory systems (MATRIX and GAL) to enhance the surveillance of healthcare-associated infections (HAI) and notifiable diseases. Data from both hospital and outpatient care are encoded into a binary matrix of 125 terms (root keywords) extracted from patient electronic records. This matrix is then processed using Singular Value Decomposition (SVD) within an LSI-based information retrieval system (Fig. 1). In our model, each patient is represented as a point in a 125-dimensional hyperdimensional space. When projected into three-dimensional space, this framework allows for effective clustering and classification of notifiable Diseases (Fig. 2), specifically TB (Fig. 3).Figure 2:3D Visualization of High-Dimensional Data: Comparing Mandatory Notifiable Diseases versus Non-Notifiable Diseases. Both patient types are well separated in the space, enabling automatic clustering and classification.3D Visualization of High-Dimensional Data: Comparing Mandatory Notifiable Diseases versus Non-Notifiable Diseases. Both patient types are well separated in the space, enabling automatic clustering and classification. Results The LSI-based matrix was constructed using data from January 2023 to February 2024, encompassing a sample of 17,895 cases (lines) across 125 presence versus absence terms, with each case classified as either a notifiable or non-notifiable disease. The 125-dimensional matrix was reduced to 28 factors using SVD. The sensitivity and specificity of the Euclidean distance were better than those of cosine similarity when automatically identifying TB cases in 1,970 independent queries (Fig. 4).Figure 3:3D Visualization of High-Dimensional Data: Comparing Tuberculosis versus Other Mandatory Notifiable Diseases versus Non-Notifiable Diseases. The three types of patients are well separated in the space, enabling automatic clustering and classification.3D Visualization of High-Dimensional Data: Comparing Tuberculosis versus Other Mandatory Notifiable Diseases versus Non-Notifiable Diseases. The three types of patients are well separated in the space, enabling automatic clustering and classification. Conclusion Artificial Intelligence (LSI), significantly enhances the surveillance of TB and other notifiable diseases by enabling real-time, automated case identification up to one day prior (D-1). This advancement allows surveillance personnel to complete their tasks more efficiently, thereby preventing outbreaks and reducing the risk of unforeseen fatalities.Figure 4:Performance Comparison of Cosine vs. Euclidean Distance Metrics in Automatically Identifying TB Cases Using LSI: Euclidean Distance Demonstrates Superior Accuracy and Has Been Integrated into Datamart A.R.G.U.S. for Real-Time Identification of TB and Other Notifiable Diseases as of the Previous Workday (D-1).Performance Comparison of Cosine vs. Euclidean Distance Metrics in Automatically Identifying TB Cases Using LSI: Euclidean Distance Demonstrates Superior Accuracy and Has Been Integrated into Datamart A.R.G.U.S. for Real-Time Identification of TB and Other Notifiable Diseases as of the Previous Workday (D-1). Disclosures All Authors: No reported disclosures

Identifying Galactic Substructures in 5D Space Using All-sky RR Lyrae Stars in Gaia DR3

Abstract Motivated by the vast gap between photometric and spectroscopic data volumes, there is great potential in using 5D kinematic information to identify and study substructures of the Milky Way. We identify substructures in the Galactic halo using 46,575 RR Lyrae stars (RRLs) from Gaia Data Release 3, with photometric metallicities and distances newly estimated by X.-Y. Li et al. Assuming a Gaussian prior distribution of radial velocity, we calculate the orbital distribution characterized by the integrals of motion for each RRL, based on its 3D positions, proper motions, and corresponding errors, and then apply the friends-of-friends algorithm to identify groups moving along similar orbits. We have identified several known substructures, including the Sagittarius stream, the Hercules-Aquila Cloud (HAC), the Virgo Overdensity (VOD), Gaia-Enceladus-Sausage (GES), the Orphan-Chenab stream, Cetus-Palca, the Helmi streams, Sequoia, Wukong, and the Large Magellanic Cloud leading arm, as well as 18 unknown groups. Our findings indicate that the HAC and VOD have kinematic and chemical properties remarkably similar to GES, with most HAC and VOD members exhibiting eccentricity as high as GES, suggesting that they may share a common origin with GES. The ability to identify low-mass and spatially dispersed substructures further demonstrates the potential of our method, which breaks the limit of spectroscopic surveys and is competent for probing substructures throughout the whole Galaxy. Finally, we also identify 18 unknown groups with good spatial clustering and proper-motion consistency, suggesting the possibility of further excavation of Milky Way substructures in the future with only 5D data.

Angle and Range Unambiguous Estimation with Nested Frequency Diverse Array MIMO Radars

This paper proposes an unambiguous method for joint angle and range estimation in colocated multiple-input multiple-output (MIMO) radar using the nested frequency diverse array (NFDA). Unlike a conventional phased array (PA), the transmission beampattern of FDA-MIMO radar depends not only on angle but also on range, which enables the precise identification of ambiguous regions in the two-dimensional frequency space. As a result, we can simultaneously estimate the angle and range of targets using FDA-MIMO radar, even when range ambiguity exists. By employing a nested array configuration, the degrees of freedom (DOFs) of the FDA are expanded. This expansion leads to improved accuracy in parameter estimation and enables a greater number of identifiable targets. In addition, the Cramér–Rao lower bound (CRLB) and the algorithm complexity are obtained to facilitate performance analysis. The simulation outcomes are presented to showcase the superior performance of the suggested approach.

COOL-LAMPS. VII. Quantifying Strong-lens Scaling Relations with 177 Cluster-scale Strong Gravitational Lenses in DECaLS

Abstract We estimate the Einstein-radius-enclosed total mass for 177 cluster-scale strong gravitational lenses identified by the ChicagO Optically selected Lenses Located At the Margins of Public Surveys (COOL-LAMPS) collaboration with lens redshifts ranging from 0.2 ⪅ z ⪅ 1.0 using the brightest-cluster-galaxy (BCG) redshift and an observable proxy for the Einstein radius. We constrain the Einstein-radius-enclosed luminosity and stellar mass by fitting parametric spectral energy distributions to aperture photometry from the Dark Energy Camera Legacy Survey (DECaLS) in the g-, r-, and z-band Dark Energy Camera filters. We find that the BCG redshift, enclosed total mass, and enclosed luminosity are strongly correlated and well described by a planar relationship in 3D space. We find that the enclosed total mass and stellar mass are correlated with a logarithmic slope of 0.50 0 − 0.031 + 0.029 , and the enclosed total mass and stellar-to-total mass fraction are correlated with a logarithmic slope of − 0.49 5 − 0.033 + 0.032 . In tandem with the small radii within which these slopes are constrained, this may suggest invariance in baryon conversion efficiency and feedback strength as a function of cluster-centric radii in galaxy clusters. Additionally, the correlations described here should have utility in ranking strong-lensing candidates in upcoming imaging surveys—such as Rubin/Legacy Survey of Space and Time—in which an algorithmic treatment of strong lenses will be needed due to the sheer volume of data these surveys will produce.

Multimodal Augmented Reality System for Real-Time Roof Type Recognition and Visualization on Mobile Devices

The utilization of augmented reality (AR) is becoming increasingly prevalent in the integration of virtual reality (VR) elements into the tangible reality of the physical world. It facilitates a more straightforward comprehension of the interconnections, interdependencies, and spatial context of data. Furthermore, the presentation of analyses and the combination of spatial data with annotated data are facilitated. This is particularly evident in the context of mobile applications, where the combination of real-world and virtual imagery facilitates enhances visualization. This paper presents a proposal for the development of a multimodal system that is capable of identifying roof types in real time and visualizing them in AR on mobile devices. The current approach to roof identification is based on data made available by public administrations in an open-source format, including orthophotos and building contours. Existing computer processing technologies have been employed to generate objects representing the shapes of building masses, and in particular, the shape of roofs, in three-dimensional (3D) space. The system integrates real-time data obtained from multiple sources and is based on a mobile application that enables the precise positioning and detection of the recipient’s viewing direction (pose estimation) in real time. The data were integrated and processed in a Docker container system, which ensured the scalability and security of the solution. The multimodality of the system is designed to enhance the user’s perception of the space and facilitate a more nuanced interpretation of its intricacies. In its present iteration, the system facilitates the extraction and classification/generalization of two categories of roof types (gable and other) from aerial imagery through the utilization of deep learning methodologies. The outcomes achieved suggest considerable promise for the advancement and deployment of the system in domains pertaining to architecture, urban planning, and civil engineering.

Effect of cleft palate type and manufacturing method on feeding plate adaptation: A volumetric micro-computed tomography analysis.

Feeding plates for cleft palate patients have been used by clinicians for many years to temporarily close the oro-nasal communication until definitive treatment with surgical techniques. The current in vitro study aimed to evaluate the adaptation of the feeding plates manufactured by two different techniques for three cleft types. Feeding plates were manufactured with conventional compression molding (CM) and 3-dimensional (3D) additive manufacturing on main models representing bilateral cleft, unilateral right, and unilateral left cleft types (n=10). The 3D volumetric space between the feeding plate and the corresponding main model was measured by micro-CT to evaluate the adaptation. The adaptation of the plates was assessed based on three different measurement regions: anterior, left, and right. Repeated measure analysis of variance (ANOVA), three factorial ANOVA, and post hoc Bonferroni tests were used as statistical analysis (α=0.05). CM groups showed higher volumetric space measurements between the base and master model than 3D groups regardless of measurement region and cleft type, which refers to misfit (p˂0.05). Cleft type differed in the adaptation of 3D groups yet not in CM groups (p˂0.05). The volumetric space evaluation for the right measurement region resulted in higher values regardless of manufacturing method and cleft type (p˂0.05). Considering that 3D-printed feeding plates showed better adaptation compared to conventionally manufactured plates for all cleft types, 3D printing can be suggested as the manufacturing method of choice for feeding plates.

Wormhole solutions in deformed space-time

We construct and analyse wormhole solutions in quantised space-time. The field equations are constructed from the deformed wormhole metric in the proper reference frame using tetrads. The spatial geometry of the wormhole is analysed in kappa space-time. Further, modifications to the conditions that ensure traversibility of the wormhole are studied and it is found that the necessity of the exotic matter persists in the non-commutative case as in the commutative space-time. Casimir energy is considered a possible source for exotic matter and it is shown that the time to pass through the wormhole as well as the amount of exotic matter required to create the wormhole reduce due to non-commutativity of space-time.

Force-Driven Model for Automated Clear Aligner Staging Design Based on Stepwise Tooth Displacement and Rotation in 3D Space

This study introduced a novel force-driven automated staging design method for clear aligners, aimed at enhancing treatment planning efficiency and outcomes. The method simplified the alignment process into a force-driven mechanics model that calculates forces and moments exerted on teeth while adhering to Newton’s third law, determining their displacement and rotation at each position. An optimal path was generated by iteratively moving teeth from their initial to target positions and subsequently divided into stages based on a predefined step size. The algorithm was implemented in C++ and incorporated into the WebGL-based SmarteeCheck3.0 software for visualization. In a maxillary extraction case, the automated staging method (0.25 mm step size) generated 51 stages in merely 5 s, while manual staging (>0.25 mm step size) necessitated 30 min to achieve 55 stages. In a molar distalization case, the automated method demonstrated similar efficiency advantages, generating 30 stages for the maxilla and 34 for the mandible, compared to 41 stages each in manual staging. The automated staging approach yielded shorter and more precise tooth movement paths that adhered to aligner biomechanics and physical principles, surpassing the limitations of manual staging. For cases requiring entire arch displacement, the method incorporated sequential movements with anchorage control to maintain force equilibrium. This innovative method substantially improved design efficiency and accuracy, ultimately elevating the efficacy of clear aligner therapy, although further biomechanical analyses and experimental validations are needed to refine the model parameters.

Monitoring of Soil Salinity in the Weiku Oasis Based on Feature Space Models with Typical Parameters Derived from Sentinel-2 MSI Images

Soil salinization, as one of the types of land degradation, is a global threat. It not only poses serious ecological problems, but also poses great challenges for the sustainable utilization of land resources, especially in arid and semi-arid areas. The Weiku Oasis is undoubtedly one of the typical areas under severe salinization. The wide spread of saline soil brings numerous negative impacts to the local region. To prevent the escalation of soil salinization, timely monitoring of soil salinization is urgently needed for informed decision-making. Remote sensing technology can obtain large-scale datasets in a short period, allowing researchers to carry out the rapid and accurate investigation of soil salinization. Sentinel-2 images have a relatively high spatial resolution and provide red-edge bands data, referring to bands 5, 6, and 7, and the use of red-edge bands is a new approach to estimate soil salinization in the Weiku Oasis. In this study, we selected five typical indices (NDre1, RNDSI, MSAVI, NDWI, SI3, with the first two being red-edge indices) from twenty potential indices to construct multiple two-dimensional feature space models. Consequently, an optimal and novel monitoring index for soil salinization in the Weiku Oasis was developed. The result showed that: (1) The monitoring index MSAVI-RNDSI, which includes red-edge indices, had the highest inversion accuracy of R2 = 0.7998 and MAE = 3.3444; (2) The red-edge salinity indices effectively captured the conditions of salinization, with the feature space model composed of red-edge indices achieving an average inversion accuracy of R2 = 0.7902; (3) Land-use type was identified as the primary factor affecting the degree of soil salinization in the study area. The proposed approach provides a highly accurate and high-resolution soil salinity mapping strategy.