Coverage Area Research Articles

Tethered Balloon Cluster Deployments and Optimization for Emergency Communication Networks

Natural disasters can severely disrupt conventional communication systems, hampering relief efforts. High-altitude tethered balloon base stations (HATBBSs) are a promising solution to communication disruptions, providing wide communication coverage in disaster-stricken areas. However, a single HATBBS is insufficient for large disaster zones, and limited resources may restrict the number and energy capacity of available base stations. To address these challenges, this study proposes a cluster deployment of tethered balloons to form flying ad hoc networks (FANETs) as a backbone for post-disaster communications. A meta-heuristic-based multi-objective particle swarm optimization (MOPSO) algorithm is employed to optimize the placement of balloons and power control to maximize target coverage and system energy efficiency. Comparative analysis with a stochastic algorithm (SA) demonstrates that MOPSO converges faster, with significant advantages in determining optimal balloon placement. The simulation results show that MOPSO effectively improves network throughput while reducing average delay and packet loss rate.

Detection of Flight Target via Multistatic Radar Based on Geosynchronous Orbit Satellite Irradiation

As a special microwave detection system, multistatic radar has obvious advantages in covert operation, anti-jamming, and anti-stealth due to its configuration of spatial diversity. As a high-orbit irradiation source, a geosynchronous orbit satellite (GEO) has the advantages of a low revisit period, large beam coverage area, and stable power of ground beam compared with traditional passive radar irradiation sources. This paper focuses on the key technologies of flight target detection in multistatic radar based on geosynchronous orbit satellite irradiation with one transmitter and multiple receivers. We carry out the following work: Firstly, we aim to address the problems of low signal-to-noise ratio (SNR) and range cell migration of high-speed cruise targets. The Radon–Fourier transform constant false alarm rate detector-range cell migration correction (RFT-CFAR-RCMC) is adopted to realize the coherent integration of echoes with range cell migration correction (RCM) and Doppler phase compensation. It significantly improves the SNR. Furthermore, we utilize the staggered PRF to solve the ambiguity and obtain multi-view data. Secondly, based on the aforementioned target multi-view detection data, the linear least square (LLS) multistatic positioning method combining bistatic range positioning (BR) and time difference of arrival positioning (TDOA) is used, which constructs the BR and TDOA measurement equations and linearizes by mathematical transformation. The measurement equations are solved by the LLS method, and the target positioning and velocity inversion are realized by the fusion of multistatic data. Finally, using target positioning data as observation values of radar, the Kalman filter (KF) is used to achieve flight trajectory tracking. Numerical simulation verifies the effectiveness of the proposed process.

Low dose Adenoviral Vammin gene transfer induces myocardial angiogenesis and increases left ventricular ejection fraction in ischemic porcine heart

This preliminary study investigated if VEGFR-2 selective adenoviral Vammin (AdVammin) gene therapy could induce angiogenesis and increase perfusion in the healthy porcine myocardium. Also, we determined using a clinically relevant large animal model if AdVammin gene therapy could improve the function of a chronically ischemic heart. Low doses of AdVammin (dose range 2 × 109–2 × 1010 vp) gene transfers were performed into the porcine myocardium using an endovascular injection catheter. AdCMV was used as a control. The porcine model of chronic myocardial ischemia was used in the ischemic studies. The AdVammin enlarged the mean capillary area and stimulated pericyte coverage in the target area 6 days after the gene transfers. Using positron emission tomography 15O-radiowater imaging, we demonstrated that AdVammin gene therapy increased perfusion in healthy myocardium at rest. AdVammin treatment also increased ejection fraction at stress in the ischemic heart, as detected using left ventricular cine angiography. In addition, we demonstrated successful in vivo imaging of enhanced angiogenesis using [68Ga]NODAGA-RGD peptide. However, AdVammin also increased tissue permeability and was associated with significant pericardial fluid accumulation, limiting AdVammin’s therapeutic potential and emphasizing the importance of correct dosage.

An edge server placement based on graph clustering in mobile edge computing

With the exponential growth of mobile devices and data traffic, mobile edge computing has become a promising technology, and the placement of edge servers plays a key role in providing efficient and low-latency services. In this paper, we investigate the issue of edge server placement and user allocation to reduce transmission delay between base stations and servers, and balance the workload of individual servers. To this end, we propose a graph clustering-based edge server placement model by fully considering the constraints such as the distance, coverage area and number of channels of base stations. The model mainly consists of a two-layer graph convolutional network (GCN) component and a differentiable version of K-means clustering component, which transforms the server placement problem into an end-to-end learning optimization problem on a graph. It trains the GCN network to achieve the best clustering results with the expectation of average delay and load balancing as the loss function to obtain the edge server placement and user assignment scheme. We conducted experiments based on the Shanghai Telecom dataset, and the results show the effectiveness of our approach in both latency reduction and load balancing.

Mobility Prediction Algorithms for Handover Management in Heterogeneous LiFi and RF Networks: An Ensemble Approach

Light Fidelity (LiFi) is a communication technology that operates in the Visible Light (VL) region, using light as a medium to enable ultra-high-speed communication. The spectrum occupied by LiFi does not overlap with the Radio Frequency (RF) spectrum. Thus, they can be used in a hybrid manner to enhance the Quality of Service (QoS) for users. However, in a heterogeneous LiFi and RF network, users experience constant handovers due to the small coverage area of the LiFi and their frequent movement. This study proposes an intelligent handover scheme, where the network parameters of the users are used to train four machine learning models, namely an Artificial Neural Network (ANN), an Adaptive Neurofuzzy Inference System (ANFIS), a Support Vector Machine (SVM), and a Regression Tree (RT), to predict the mobility of the users, so that the central network can have a priori mobility information to ensure seamless connectivity. Furthermore, the performance of the standalone models was enhanced by integrating ensemble learning techniques such as the Simple Averaging Ensemble (SAE), Weighted Averaging Ensemble (WAE), and a Meta-Learning Ensemble (MLE). The results show that the ensemble algorithms improved prediction performance, with an average error decrease of 44.40%, 53.53%, and 61.03% for SAE, WAE, and MLE, respectively, which further demonstrated the effectiveness and robustness of using ensemble algorithms to predict user mobility.

Leveraging RTLS to assess clinical space utilisation

Investment in physical space is a key strategic decision for healthcare managers. Understanding the current utilisation of clinical space is a significant input for this decision. Historically, direct observation or analysis of electronic health record (EHR) timestamps has been used to assess ambulatory space utilisation. Manual observation is prohibitively expensive, prospective and infeasible for large spaces. EHR data is limited to electronically captured workflows and to the quality of data capture. Two pilots explored the efficacy of real-time location systems (RTLS) to assess outpatient space utilisation to assist healthcare management professionals to make space allocation decisions. RTLS was shown to be viable, with accuracy that was not different from EHR-derived utilisation. RTLS had the following benefits: (a) more granular information, (b) data coverage in areas without EHR timestamps and (c) real-time assessment of utilisation. RTLS is an option for ambulatory care managers to understand the needed space for clinical operations.

A Novel Approach to Node Coverage Enhancement in Wireless Sensor Networks Using Walrus Optimization Algorithm

Wireless Sensor Networks (WSNs) are crucial components of modern technology, supporting applications like healthcare, industrial automation, and environmental monitoring. This research aims to design intelligent and adaptive sensor networks by integrating metaheuristics with node coverage optimization in WSNs. By incorporating metaheuristics and optimizing node coverage, WSNs can become more resilient and robust, leading to the development of self-adapting, self-organizing networks capable of efficiently covering dynamic and diverse environments. This research introduces the Walrus Optimization Algorithm for Node Coverage Enhancement in WSNs, called the WaOA-NCEWSN technique. The primary goal of this technique is to optimize the coverage of a target region using a limited number of Sensor Nodes (SNs) and by improving their placement. The WaOA is inspired by walrus behaviours like feeding, migrating, breeding, escaping, roosting, and gathering in response to environmental signals. The WaOA-NCEWSN technique uses an objective function that defines the coverage ratio, representing the maximum probability of coverage in a 2D-WSN monitoring area. Comparative analysis with other models using 50, 75, 100, and 200 nodes shows that the WaOA-NCEWSN technique performs better. The compilation times for the WaOA-NCEWSN technique are 5.14s, 6.48s, 6.54s, and 7.47s for 50, 75, 100, and 200 nodes, respectively. Experimental results indicate that the WaOA-NCEWSN technique offers superior coverage performance compared to other models.

Development of a Flood Impact Assessment Framework Integrating Crowdsourced Data and Geospatial Information for Data Sparse Urban Regions

High spatial heterogeneity of urban floods poses challenges in its modeling and assessment, and a flood database is a basic requirement but it is lacking for many cities. The proposed Twitter-based framework addresses the issues via developing a finer resolution flood database and a product. The framework has multiple components including data quality control, validation of flood database via newspapers and flood impact assessment. Three flood events differing in rainfall characteristics are selected to showcase the utility of the proposed framework for the city of Hyderabad, India. Analysis of tweets highlighted the resourcefulness of video tweets and wide coverage of the study area in terms of flood reporting. Tweets exhibited an association with tweet time and rainfall aspects. Further, tweets based flood locations are found to be in agreement with newspaper based flooding instances. A novel flood impact score (FIS) is developed for each flood location using analytical hierarchy process based weights for five variables (Twitter based attributes, rainfall, elevation), and the use of FIS is demonstrated in identifying flood impact areas. These kinds of databases and products, with a scope to improve further, serve as a potential tool to cater flood preparedness and management thereby making cities flood resilient.

Fusion algorithms on identifying vacant parking spots using vision-based approach

<div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p>In densely populated cities, parking space scarcity results in issues like traffic congestion and difficulty finding parking spots. Recent advancements in computer vision have introduced methods to address parking lot management challenges. The availability of public image datasets and rapid growth in deep learning technology has led to vision-based parking management studies, offering advantages over sensor-based systems in comprehensive area coverage, cost reduction, and additional functionalities. This study presents an innovative fusion algorithm that integrates object detection with occupancy state algorithms to accurately identify vacant parking spaces. The employment of the YOLOv7 framework for vehicle instance segmentation, combined with three occupancy algorithms Euclidean distance (ED), intersection over reference (IoR), and intersection over union (IoU) are compared to determine the occupancy state of observed areas. The proposed method is evaluated using the CNRPark-EXT dataset, and its performance is compared with state-of-the-art methods. As a result, the proposed approach demonstrates robustness under varying conditions. It outperforms existing methods in terms of system evaluation performance, achieving accuracies of 98.88%, 97.99%, and 90.04% for ED, IoR, and IoU, respectively. This fusion detection method enhances adaptability and addresses occlusions, emphasizing YOLOv7’s advantages and accurate shape approximation for slot annotation. This study contributes valuable insights for effective parking management systems and has potential usage in the real-world implementation of intelligent transportation systems.</p></div></div></div>

Investigation on energy and mass distribution characteristics of granules in the composite heat exchanger

A composite heat exchanger for high-temperature granule waste heat recovery is proposed. Granular mass and energy distribution within the composite heat exchanger are simulated via the CFD-DEM coupling method. The effects of granular size, cooling gas velocity, and granular mass flow rate on granular distribution and the temperature distribution are analyzed. Results demonstrated that under the combined action of airflow impact force and gravity, the granule produces an uneven distribution in time and space. Larger granule tends to be positioned closer to the gas inlet horizontally. Along the direction from the gas inlet to the gas outlet, granules exhibit a trend of decreasing size, mass, and temperature. The influence of gas velocity predominantly affects the area coverage rate, whereas the effect of granular mass flow rate is minimal. The area coverage rate initially increases with rising gas velocity and subsequently decreases, peaking at 73.8% at 12 m/s. After the heat exchange process reached a stable state, the number of contacting granules accounted for only 0.37% of the total granules, making heat conduction between granules negligible. Convective heat transfer dominates, accounting for approximately 86.52% of the total heat exchange, while radiation heat transfer accounts for about 13.48%.

Euclid: The rb−M* relation as a function of redshift

Core ellipticals, which are massive early-type galaxies with almost constant inner surface brightness profiles, are the result of dry mergers. During these events, a binary black hole (BBH) is formed, destroying the original cuspy central regions of the merging objects and scattering stars that are not on tangential orbits. The size of the emerging core correlates with the mass of the finally merged black hole (BH). Therefore, the determination of the size of the core of massive early-type galaxies provides key insights not only into the mass of the black hole, but also into the origin and evolution of these objects. In this work, we report the first Euclid-based dynamical mass determination of a supermassive black hole (SMBH). To this end, we study the center of NGC 1272, the second most luminous elliptical galaxy in the Perseus cluster, combining the Euclid Visible Camera (VIS) photometry coming from the Early Release Observations (EROs) of the Perseus cluster with the Visible Integral-field Replicable Unit Spectrograph (VIRUS) spectroscopic observations at the Hobby-Eberly Telescope (HET). The core of NGC 1272 is detected on the Euclid VIS image. Its size is 1.​​″29 ± 0.​​″07 or 0.45 kpc, which was determined by fitting PSF-convolved core-Sérsic and Nuker-law functions. We deproject the surface brightness profile of the galaxy, finding that the galaxy is axisymmetric and nearly spherical. The two-dimensional stellar kinematics of the galaxy is measured from the VIRUS spectra by deriving optimally regularized non-parametric line-of-sight velocity distributions. Dynamical models of the galaxy are constructed using our axisymmetric and triaxial Schwarzschild codes. We measure a BH mass of (5 ± 3)×109 M⊙, which is in line with the expectation from the MBH − rb correlation, but is eight times larger than predicted by the MBH − σ correlation (at 1.8σ significance). The core size, rather than the velocity dispersion, allows one to select galaxies harboring the most massive BHs. The spatial resolution, wide area coverage, and depth of the Euclid (Wide and Deep) surveys allow us to find cores of passive galaxies that are larger than 2 kpc at a redshift of up to 1.

Corrosion Inhibition of Mild Steel by Plumeria rubra Flower Extract: Electrochemical and Computational Study

AbstractThe corrosion inhibition efficiency of Plumeria rubra flower extract (PRFE) on 5LX70 mild steel in 4% NaCl aqueous medium was studied by electrochemical impedance spectroscopy (EIS), potentiodynamic polarization (PDP), and density functional theory (DFT). The PRFE was analyzed by FTIR for the confirmation of functional groups in the extract molecules. EIS and PDP methods indicated that the corrosion inhibition was increased with an increase in the concentration of inhibitor, with a surface area coverage of 90.12%. Polarization results revealed that PRFE is a mixed‐type inhibitor. A maximum corrosion inhibition of 90.98% was achieved at 120 ppm of extract concentration. Quantum chemical parameters of the inhibitor molecules were calculated using the DFT method to ascertain the relation between the parameters and inhibition efficiency. Molecular descriptors like HOMO, LUMO, energy gap, absolute electronegativity, electrostatic surface potential, and so on, were determined, and found that the inhibitor molecules favorably formed a protective layer on the metal surface. The Mulliken charge analysis of the constituent atoms of selected PRFE molecules further supported in identifying the active sites for binding with the mild steel surface. Experimental results have confirmed that PRFE is a good corrosion inhibitor for mild steel which was further affirmed by the computational study.

A drone-based population survey of Delacour's langur (Trachypithecus delacouri) in the karst forests of northern Vietnam

The Critically Endangered Delacour's langur (Trachypithecus delacouri) is presently found only in a few isolated karst areas in northern Vietnam, where conducting field surveys has proven challenging due to the difficult terrain. Accurate population estimates from a scientifically sound method are needed to inform management of the species. From October to December 2022, we used a drone equipped with optical and thermal cameras to survey the species in Kim Bang Forest, a critical site for the species. We estimated langur abundance from the resulting point count data using N-mixture models including abiotic and biotic variables. We also compared the effectiveness and efficiency of the drone method with two commonly used ground-based methods. The drone survey recorded 16 groups with 104 individuals. We estimated a density of 0.87 groups per km2 and a population of 25 groups and 175 individuals. This estimate is 80–113 % higher than previous ground-based estimates, attributed primarily to the higher area coverage by the drone survey. The estimate reaffirms the conservation importance of Kim Bang Forest for the species. The modelling also indicated that Delacour's langur abundance was correlated negatively with Assamese macaque (Macaca assamensis) presence and positively with vegetation productivity. Other variables (elevation, terrain ruggedness and distance to forest edge) were much less important in explaining langur abundance. Compared to the ground-based methods, the drone approach proved effective and resource-efficient for surveying Delacour's langurs. We recommend the drone method for future Delacour's langur surveys, with potential applicability to other arboreal mammals in difficult-to-access karst forests.

Slotted ALOHA Based Practical Byzantine Fault Tolerance (PBFT) Blockchain Networks: Performance Analysis and Optimization

Practical Byzantine Fault Tolerance (PBFT) is one of the most popular consensus mechanisms for the consortium and private blockchain technology. It has been recognized as a candidate consensus mechanism for the Internet of Things networks as it offers lower resource requirements and high performance when compared with other consensus mechanisms such as proof of work. In this paper, by considering the blockchain nodes are wirelessly connected, we model the network nodes distribution and transaction arrival rate as Poisson point process and we develop a framework for evaluating the performance of the wireless PBFT network. The framework utilizes slotted ALOHA as its multiple access technique. We derive the end-to-end success probability of the wireless PBFT network which serves as the basis for obtaining other key performance indicators namely, the optimal transmission interval, the transaction throughput and delay, and the viable area. The viable area represents the minimum PBFT coverage area that guarantees the liveness, safety, and resilience of the PBFT protocol while satisfying a predefined end-to-end success probability. Results show that the transmission interval required to make the wireless PBFT network viable can be reduced if either the end-to-end success probability requirement or the number of faulty nodes is lowered.

Progress towards the control of invasive alien species in the Cape Floristic Region’s protected areas

This paper assesses progress towards the control of biological invasions in 18 protected areas (PAs) covering 677 584 ha in the Cape Floristic Region (CFR), and whether progress has been sufficient to achieve Target 6 of the Kunming-Montreal Global Biodiversity Framework. We used eight indicators for assessing the inputs (quality of the regulatory framework, money spent and planning coverage for species and protected areas), outputs (species and protected areas treated), and outcomes (effectiveness of species and protected area treatments) of management. The estimated money spent over 13 years (2010–2022) was ZAR 976 million, or ZAR 75 million per year. Management plans for PAs were assessed as adequate over 78.5% of the area, but only six out of 226 regulated invasive species had species-specific control plans in place. A total of 567 alien species occurred in the CFR’s PAs, 226 of which were regulated species (i.e. species that had to be controlled), 126 (55.8%) of which received some management. Spending was highly skewed, with over 60% of all funding spent on trees and shrubs in the genus Acacia. Management efforts reached 24% of the land within the CFR’s protected areas, with higher coverage in national parks (60%) than in provincial nature reserves (9%). Management effectiveness was assessed as either permanent, effective or partially effective for 29 species (20 due to biological control), and ineffective for 25; for the remainder, there was either no management or effectiveness could not be evaluated. We conclude that some progress has been made with respect to controlling invasive alien species in the CFR, but that insufficient and declining funding remains a significant barrier to effective management. To increase efficiency, it will be necessary to secure additional funding from more diversified sources, make more use of biological control and prescribed fire, and regularly monitor the outcomes of management.

Mapping nanoparticle formation and substrate heating effects: a fluence-resolved approach to pulsed laser-induced dewetting

This study investigates the fluence-dependent evolution of gold nanoparticles formed through single nanosecond pulsed laser dewetting of a gold thin film on a fused silica substrate. By employing a well-defined Airy-like laser spatial profile and reconstructing scanning electron microscope images across the irradiation spot into a panoramic view, we achieve a detailed continuous analysis of the nanoparticle formation process. Our morphological analysis, combined with finite element thermal simulations directly correlated with the applied fluence, identifies two distinct thresholds. The first threshold corresponds to the dewetting of the gold film at its melting point, resulting in large, sparse nanoparticles. The second threshold, where the substrate temperature reaches values near its melting point, leads to the formation of numerous small nanoparticles and a significant increase in coverage area. Notably, the formation of these small nanoparticles is attributed to substrate heating, which alters the interaction between the molten gold film and the substrate, increasing adhesion. Contact angle measurements of the nanoparticles confirm this change, revealing a shift in wettability, and highlighting the crucial role of substrate heating in modulating the interactions leading to nanoparticle formation. Our findings underscore the intricate interplay between laser fluence, material properties, and substrate interactions in pulsed laser dewetting, with the well-defined laser profile offering valuable insights into these dynamics.

Protected area coverage of the full annual cycle of migratory butterflies.

Effective conservation of migratory species relies on habitat protection throughout their annual cycle. Although protected areas (PAs) play a central role in conservation, their effectiveness at conserving habitats across the annual cycle of migratory species has rarely been assessed. We developed seasonal ecological niche models for 418 migratory butterfly species across their global distribution to assess whether they were adequately represented in the PAs across their full annual cycle. PA coverage was inadequate in at least one season for 84% of migratory butterflies, adequate for only 17% of species in one season, and inadequate for 45% of species in all seasons. There was marked geographic variation in PA coverage: 77% of species met representation targets in Sri Lanka, for example, but only 32% met targets in Italy. Our results suggest that coordinated efforts across multiple countries will be needed to develop international networks of PAs that cover the full annual cycle of migratory insects and that conservation measures, in addition to the establishment and maintenance of PAs, are likely to be needed to effectively conserve these species.

UAV Cruise Strategies Based on Initial Attack

Forest fires not only cause severe damage to ecosystems and biodiversity but also directly threaten the safety of human societies. Given the significant increase in both the frequency and intensity of forest fires worldwide, especially under extreme climate conditions, efficient fire detection and initial attack (IA) are particularly critical. The initial attack is a key stage in forest fire control, and the time taken for fire detection is a crucial factor influencing the success of the initial attack. In response to the challenges of forest fire prevention and control, this study explores Unmanned Aerial Vehicle (UAV) cruising strategies, aiming to develop appropriate approaches based on regional characteristics and provide efficient periodic monitoring solutions for areas with high ecological value and challenging accessibility. By optimizing UAV patrol routes, this research seeks to maximize coverage in areas with lower initial attack success rates and significantly reduce fire detection time, thereby improving detection efficiency. We developed and applied four optimization strategies, random search, high-risk first (HRF), nearest high-risk first (NHRF), and a genetic algorithm-based (GA-based) strategy, to compare different UAV flight routes. To evaluate the deployment effectiveness of the four UAV cruise strategies, we introduced two evaluation metrics: Average Grid Risk (AGR) and Average Distance Risk (ADR). Experimental results showed that the NHRF and GA-based strategies performed better. Specifically, NHRF achieved the highest high-risk coverage, ranging from 51.5% to 71.3%, significantly outperforming the random search strategy (4–7%) and the HRF strategy (23.1–37.5%). The GA-based algorithm achieved the highest grid coverage, ranging from 30% to 59.8%, far surpassing the random search strategy (4–6.6%) and the HRF strategy (10.2–19.1%). Additionally, the NHRF and GA-based strategies delivered the best AGR and ADR performance, respectively. The application of these innovative strategies and evaluation metrics enhances forest fire prevention through periodic monitoring and supports more efficient firefighting efforts.

Enhancing Bird Diversity in Urban Parks: Insights from the Futian Mangrove Ecological Park, Shenzhen

Small urban parks and green spaces, serving as essential recreational venues for city residents, also play a vital and irreplaceable role in maintaining urban biodiversity. It is of great importance to design and plan these areas in a way that integrates multiple habitats for various species while accommodating residents’ usage. This study, carried out at the Futian Mangrove Ecological Park located in Shenzhen, Guangdong Province, China, chose birds as indicator species to assess biodiversity within the park. Site inventory was undertaken from May to September 2022 and from October 2022 to April 2023. We quantitatively described the park’s habitats by examining primary environmental factors, along with 3 primary environmental factors and 11 secondary factors. A correlation analysis was then performed between these factors and bird diversity to gain insights into birds’ habitat preferences across different habitat types and at a finer scale of plant communities. Furthermore, bird clusters in the study case were categorized by foraging guilds and foraging patterns, and their distributions were studied at both the habitat patch scale and the plant community scale. Our findings reveal that, at the habitat patch scale, water surface area and grass coverage significantly positively impact bird diversity. At the plant community scale, plant communities with different structural characteristics vary in their importance to bird clusters with distinct characteristics. In areas with high human disturbance, shrub coverage is crucial for bird habitat protection. Additionally, we discovered that the impact of anthropogenic sound differs among bird species, highlighting the complexity of human disturbance factors on bird habitat preferences. Accordingly, we proposed several design recommendations aimed at enhancing bird diversity in parks, including increasing water body areas, reducing the distance between habitats and water surfaces, enhancing herbaceous plant coverage, and controlling anthropogenic sound.

Developing novel spectral indices for precise estimation of soil pH and organic carbon with hyperspectral data and machine learning.

Accurate soil pH and soil organic carbon (SOC) estimations are vital for sustainable agriculture, as pH affects nutrient availability, and SOC is crucial for soil health and fertility. Hyperspectral imaging provides a faster, non-destructive, and economical alternative to standard soil testing. The study utilizes imaging spectroscopic data from the Africa Soil Information Service (AfSIS) and Land Use and Coverage Area Frame Survey (LUCAS-2009) hyperspectral datasets, capturing spatially distributed spectral information. Machine learning (ML) approaches using high-dimensional spectral bands can be computationally expensive, while those using spectral indices are typically limited to multispectral data. This study addresses these challenges by comparing soil pH and SOC prediction using ML models, with both existing spectral indices and individual hyperspectral bands as input features. Results demonstrate that hyperspectral bands outperform existing indices in predictive accuracy, with R values ranging from 0.8 to 0.94 for both soil pH and SOC. To further enhance prediction performance, this study proposes novel spectral indices-soil pH index (SPI) and soil organic carbon index (SOCI)-specifically designed for hyperspectral data using principal component analysis (PCA) and artificial neural networks (ANN). The proposed SPI and SOCI indices address multicollinearity issues and high dimensionality in raw spectral bands, significantly improving predictive accuracy. The SPI and SOCI indices achieve R values of 0.86 for AfSIS soil pH, 0.945 for LUCAS-2009 soil pH, 0.952 for AfSIS SOC, and 0.963 for LUCAS-2009 SOC. These results show that the proposed spectral indices provide a practical solution for precision agriculture, enhancing soil pH and SOC estimations.