Search Results (7,865)

Background: Anxiety is a frequent clinical problem that becomes disabling when excessive or persistent. Cyclitols are naturally occurring polyhydroxy compounds, and inositols are the most abundant cyclitols in eukaryotic cells; several stereoisomers have been proposed as candidates for CNS-relevant effects. Methods: A narrative review was conducted using a structured search of biomedical bibliographic databases. The search was centered on myo-inositol, scyllo-inositol, and D-chiro-inositol in relation to anxiety-related outcomes. Results: The retrieved literature suggests some biological plausibility for anxiolytic effects of selected inositol stereoisomers through pathways related to intracellular signaling and neurotransmission. However, the available evidence is uneven and remains limited. The most informative findings concern myo-inositol and include both preclinical and clinical studies, whereas data on scyllo-inositol and D-chiro-inositol are scarce, particularly in relation to anxiety-related outcomes. Conclusions: Current evidence suggests a possible anxiolytic role of selected inositol stereoisomers; however, the existing data are limited and heterogeneous, and do not allow for definitive clinical conclusions. Further research is required. Full article

Objective: To provide a comprehensive literature review of original work on artificial intelligence in ocular oncology. Methods: Scoping review of PubMed-indexed original articles (n = 94) on the use of artificial intelligence in ocular oncology, retrieved during the month of February 2026 and independently screened by two ocular oncologists. Results: Most of the literature on artificial intelligence (AI) in ocular oncology focuses on uveal melanoma and its differentials (n = 39, 41%), followed by retinoblastoma (n = 14, 15%) and orbital tumors (n = 12, 13%). The purpose of using the AI models was to screen, diagnose, and classify the disease (n = 59, 62%) and to treat, predict outcomes, and monitor the disease (n = 35, 37%). Most literature (n = 32, 34%) on AI in ocular oncology originates from China. Datasets comprised images in 78% (n = 73) of the studies, clinical parameters in 14% (n = 13), and omics data in 12% (n = 11). Most studies worked on developing AI models (n = 83, 88%), of which two reached a deployment stage. Few studies evaluated or incorporated pre-existing models (n = 11, 12%). Supervised learning strategy was most commonly employed (n = 75, 80%). Among studies that developed AI models, traditional machine learning architectures were used in 36, deep learning in 39, and a combination in 8. Most studies (n = 59, 63%) were at a Clinical AI Readiness Evaluator Technology Readiness Level 4, i.e., at the prototype development stage. Conclusions: Despite the limitation of a single database search, a surge in AI applications in ocular oncology after 2020 is evident. Most studies are in the model development stage, and few have been deployed in the real world for clinical implementation. Very few models have proven effective in real-world clinics and the community, holding promise for the future. Full article

The rapid growth of Earth science observation and simulation data has made efficient data classification increasingly challenging, particularly under conditions of limited annotation resources and continuously evolving data semantics. Conventional classification methods rely heavily on large-scale labeled datasets, which are costly to construct and difficult to adapt to dynamic classification systems. This paper proposes a hierarchical classification framework for Earth science data that leverages large language models (LLMs) and explicitly incorporates hierarchical label relationships to constrain model inference and enhance classification consistency across complex, domain-specific semantic spaces. The framework further integrates retrieval-augmented generation (RAG) and knowledge graph (KG) techniques to introduce external domain knowledge and explicit semantic constraints, enhancing contextual understanding, interpretability, and adaptability to semantic evolution. A benchmark dataset with a two-level hierarchical label structure is constructed based on official NASA metadata. Experimental results demonstrate that by integrating few-shot learning and label space optimization strategies, the proposed framework steadily outperforms various baseline methods in hierarchical classification tasks. Compared with the Bert-BiLSTM model, it achieves an absolute improvement of 8.68% in Micro-F1 and 29.92% in Macro-F1 on the overall hierarchical paths. The framework demonstrates clear advantages in long-tailed data distributions, particularly for minority classes, highlighting its potential for scalable annotation and efficient management of large-scale Earth science datasets. Full article

Background: Mental illness constitutes one of the greatest worldwide health burdens. The use of artificial intelligence (AI) and virtual reality (VR) is becoming increasingly relevant in mental health. Nevertheless, evidence regarding their integrated application remains sparse. This scoping review identified existing evidence on AI-integrated VR in mental health care, including clinical applications, reported outcomes, and future research directions. Methods: The Population, Concept, and Context framework was used as the eligibility criteria. The mental health-related studies considered were original studies that addressed explicit AI integration using VR systems or workflows and had at least one outcome or clinical or implementation finding. PubMed, Scopus, Web of Science, and PsycINFO were searched to retrieve English-language studies published between January 2020 and February 2026. Results: The available evidence is heterogeneous, generally small, and primarily focused on feasibility or predictive modeling. The focus of applications is on the assessment or prediction of anxiety spectrum conditions, trauma and post-traumatic stress disorders, stress, and panic disorder/agoraphobia. Most of the research examines immersive VR with multimodal inputs and machine-learning-based prediction models. However, the field remains largely in an early stage, with a lack of standardization, implementation readiness, safety reporting, and real-world validation. Conclusions: AI-integrated VR can be considered as a promising but emerging field, and further development requires stricter, more clinically based, and implementation-focused studies that can help establish safe, effective, and scalable implementation in mental health care. Furthermore, pragmatic, multicenter research directly investigates whether AI-integrated VR has additional clinical value compared to regular VR or regular care in mental health care. Full article

Dense retrieval pipelines often rely on large candidate pools before reranking, making candidate generation and downstream scoring a practical bottleneck. This paper studies training-free binary projection filtering as a lightweight pre-filter for reducing the candidate set before dense reranking. Rather than presenting it as a universally superior retrieval method or a validated speedup technique, we ask a narrower practical question: how far can the candidate pool be reduced before average top-rank quality, retained relevance, and query-level reliability begin to break down? We evaluate the approach on five BEIR datasets: SciFact, NFCorpus, FiQA, ArguAna, and TREC-COVID. The revised evaluation compares exhaustive Dense retrieval, FAISS-HNSW, FAISS-IVF-Flat, and Binary+Dense retrieval, and includes projection-dimension ablations over $D_b\in \{128,256,512,1000\}$, candidate-budget ablations over $K\in \{50,100,200,500\}$, five-seed robustness analysis, and typo-perturbed queries. In addition to MRR@10, nDCG@10, and Recall@100, we report filter-stage metrics including Retained@K, catastrophic failure rate, and Best Relevant Survival. Across datasets, Binary+Dense often remains close to exhaustive Dense retrieval in average top-rank metrics at representative operating points, but the filter-stage behavior is strongly collection-dependent. Larger $D_b$ and K generally improve retained relevance and reduce catastrophic failures, but they also increase filtering cost or reduce the degree of pruning. The latency results show that structural candidate reduction does not translate into consistent end-to-end wall-clock speedup in the current Python 3.16/NumPy implementation. Taken together, the results suggest that training-free binary projection filtering is best understood as a calibration-sensitive pre-filter and failure risk analysis mechanism rather than as a replacement for Dense or ANN retrieval. Full article

The basic renovation of old urban communities is an important livelihood project for urban renewal, but there are many problems in the decision-making of renovation schemes, such as strong dependence on experience, lack of quantitative basis for multi-objective trade-off, and difficulty in describing residents’ risk attitude. Combining Case-Based Reasoning (CBR) and utility theory, this paper constructs a set of intelligent decision support models driven by data and knowledge. First of all, through literature analysis and expert investigation, a decision-making index system is established, which includes four dimensions and 16 quantitative indicators: policy and financial support, residential conditions and needs, residents’ consensus and social coordination, and implementation management and long-term maintenance. Secondly, the framework representation method is used to describe the reconstruction case, a hybrid retrieval strategy combining inductive retrieval and nearest-neighbor retrieval is designed, and the subjective and objective data combination weights are calculated by using AHP and the entropy method. On this basis, a loss utility function and risk aversion coefficient based on accident and public opinion data (a = 0.02) are introduced to modify the similarity calculation results to describe the risk avoidance behavior of decision-makers. Through 40 real renovation projects, a case base is built, and two types of target cases, “typical inclusive” (F5) and “key renovation” (F35), are selected for empirical verification. The results show that the model can effectively retrieve similar cases, and the similarity ranking changes in line with risk aversion expectations after utility correction. Taking F5 as an example, by reusing and revising the reconstruction scheme of a similar case, targeted suggestions are generated, which give consideration to safety, economy and operability. This model provides a new quantifiable and reusable method for scientific decision-making in basic renovation of old residential areas. Full article

Background and Objectives: Endometriosis is a multifactorial gynecological condition associated with impaired fertility; however, its impact on embryo competence remains incompletely understood. This study aimed to evaluate embryo competence through a stepwise analysis of IVF outcomes across the developmental continuum, while also comparing patients with endometriosis and controls. Materials and Methods: A retrospective observational study was conducted, including 160 patients undergoing IVF, comprising 55 patients with endometriosis and 105 controls. Clinical and embryological data were analyzed sequentially across key developmental stages, including oocyte retrieval, metaphase II (MII) oocyte formation, fertilization (2PN), embryo development, and euploidy in a subgroup undergoing preimplantation genetic testing for aneuploidy (PGT-A). Stage-specific efficiency rates were calculated, and correlations between early- and late-developmental parameters were assessed. In addition, comparative analysis between groups was performed. Results: A progressive decline in developmental efficiency was observed across the IVF continuum, with approximately one-quarter of retrieved oocytes reaching the embryo stage and only a small proportion ultimately resulting in euploid Blastocysts. Strong positive correlations were identified among early-stage parameters, particularly retrieved oocytes, MII oocytes, and embryo yield (r = 0.77–0.96, p < 0.001), indicating that ovarian response and oocyte maturity significantly influence downstream outcomes. However, efficiency-based parameters showed limited predictive value for chromosomal competence. A moderate association was observed between MII oocytes and euploid Blastocysts (r = 0.58), whereas the relationship between embryo number and euploidy remained weak. Comparative analysis revealed no statistically significant differences between the endometriosis and control groups across the evaluated embryological parameters (p > 0.05 for all comparisons), suggesting that sequential analyses may provide complementary insight beyond direct comparisons. Conclusions: IVF outcomes follow a sequential developmental trajectory with a progressive decline in efficiency across stages. In endometriosis, early developmental competence appears to be affected, while chromosomal competence remains relatively preserved. Full article

X-band marine radar shadow features are widely applied to wave height estimation. Since the shadow fraction rises with the distance from the radar antenna, wave slope estimation is sensitive to the selected analysis region. To resolve this issue, a wave height estimation method is proposed by adopting the optimal shadowed fraction which is unrelated to the boundary selection of the analysis area. Within this paper, the shadow fraction is computed on the basis of the mechanism of radar image shadow imaging. Instead of adopting the widely used Smith fitting function, the wave slope with the non-shadow areas is achieved by using the obtained shadow fraction and the grazing angle. The collected marine radar images, totaling 450 h, are employed to demonstrate the performance of the proposed wave height retrieval method. Compared with fundamental shadow statistical approach, the root mean square error of the proposed method decreases by 0.19 m, and the correlation coefficient increases by 0.10. Meanwhile, the execution time of the presented algorithm has significantly decreased. Full article

The rapid growth of data-intensive applications has increased the demand for efficient storage in large-scale key-value (KV) stores. Disaggregated memory architectures provide a scalable solution by separating compute and memory resources via RDMA. However, existing indexing schemes in these environments suffer from poor read efficiency, significantly degrading overall system throughput and scalability. Specifically, learned indexes often encounter substantial read amplification during remote data retrieval due to prediction errors. In addition, caching full keys incurs a high cache footprint, limiting the effective cache capacity on compute nodes and leading to additional remote memory accesses. This paper presents FPCache, a fingerprint-rectified learned index cache for disaggregated memory. We propose a fingerprint-assisted two-stage read approach to mitigate read amplification. FPCache first retrieves a compact fingerprint array for local matching. It then converts range reads into precise point accesses and directly reads the corresponding data item, thereby avoiding reading the entire range and reducing extra data transfers. Next, we design a fingerprint-offset compression strategy to maximize cache density. Leveraging fixed-length fingerprints and position offsets enables compute nodes to retain significantly more hotspot data within limited memory resources. Experimental evaluations using various YCSB workloads demonstrate that FPCache consistently outperforms state-of-the-art methods. Compared to systems like CHIME and ROLEX, FPCache improves system throughput by up to 62% and effectively maintains stable access efficiency under diverse data distributions. Full article

Background: Rural and remote health systems are diverse; while many of these settings face persistent workforce shortages and access gaps, not all are underserved. Nurses play a critical role in improving access, continuity, and quality of care in these contexts. However, evidence on their roles, the challenges they face, and the outcomes associated with their contributions remains fragmented. Objective: To map the roles, challenges, and reported outcomes of nurses working in rural and remote healthcare settings, and to examine the quality and scope of the available evidence. Design: This study employed JBI scoping review methodology and is reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR). Methods: Eligible studies involved registered nurses (RNs) and nurse practitioners (NPs) providing care in rural or remote settings and reporting at least one outcome related to patients, services, or health systems. Six bibliographic databases (PubMed/MEDLINE, CINAHL, Embase, Scopus, Web of Science, Cochrane Library) plus Google Scholar for supplementary grey literature retrieval and targeted grey literature were searched (from 1 January 2000 to 30 September 2025). The lead author conducted screening and data extraction, supported by a 10% calibration pilot and structured peer debriefing. Design-specific critical appraisal was undertaken descriptively to inform interpretation but did not determine inclusion. Results: From 22 primary empirical studies (plus 2 contextual-only entries; 24 total, nurses’ roles clustered into direct clinical care, care coordination/navigation, telehealth facilitation, and health promotion. Reported outcomes were predominantly in access/utilization (e.g., time-to-care), quality and safety indicators, and patient-reported outcomes/experiences; clinical endpoints were less common. Conclusions: Nurses in rural and remote settings enact broad, adaptive roles that appear to support healthcare access and service continuity. The evidence base is predominantly descriptive, and causal claims about effectiveness cannot be drawn from the available studies. Standardized outcome frameworks, multi-reviewer methodologies, and effectiveness-focused primary research are needed to advance this field. Full article

Grassland fire is one of the major disasters threatening regional ecological security. Its occurrence, development, and spread are closely related to the spatial distribution and coverage of surface vegetation and snow cover across grassland areas. As the primary combustible fuel source, higher vegetation coverage increases fuel load and continuity, thereby directly determining grassland fire danger levels and accelerating fire spread velocity. In contrast, snow cover imposes an indirect regulatory effect on the spatiotemporal pattern of fire danger factors: it lowers surface temperature, raises near-surface humidity, and restricts the germination and growth of herbaceous vegetation in cold seasons, which effectively reduces available combustible materials and weakens regional fire hazard conditions. Therefore, accurately obtaining the coverage status of vegetation (direct combustible fuel factor) and snow cover (indirect fire-regulating factor) in complex grassland scenarios is the essential premise for reliable grassland fire danger monitoring, early warning, disaster prevention and control, and regional ecological management. Aiming at the practical problems in complex grassland scenarios (such as undulating terrain, uneven vegetation growth, large differences in snow depth, and complex lighting conditions), including difficulty in extracting vegetation and snow-covered areas, blurred and confusing boundaries, and low accuracy in coverage calculation, which seriously restrict the technical bottleneck of precise monitoring of grassland fire danger factors, this study takes near-ground images collected by grassland fire danger factor monitoring stations as the core data source, and proposes an improved UNet image segmentation model combined with image segmentation technology and deep learning methods to realize precise extraction of vegetation and snow-covered areas and efficient calculation of coverage in complex scenarios. To improve the model’s feature extraction ability, boundary localization accuracy, and reduce model parameters and computational overhead, the CBAM-ASPP (Convolutional Block Attention Module—Atrous Spatial Pyramid Pooling) module is integrated at the end of the encoding path. The attention mechanism is used to enhance the weight of key features, and the multi-scale receptive field of atrous spatial pyramid pooling is utilized to strengthen the model’s ability to fuse features of vegetation and snow areas of different scales. The residual attention mechanism is introduced in the upsampling stage to effectively alleviate the gradient disappearance problem, improve the model’s ability to accurately locate the boundaries of vegetation and snow areas, and reduce segmentation errors. In the training process, a dynamically weighted hybrid loss function is adopted to dynamically adjust the weights according to the segmentation difficulty of different types of samples during training, optimize the model training effect, and improve the segmentation accuracy and generalization ability. Experiments were conducted using near-ground images of typical complex grassland scenarios as the dataset, and the performance of the proposed model was verified through comparative experiments. The results show that in the vegetation segmentation task, the mean Intersection over Union (mIoU) of the model reaches 84.70%, and the accuracy rate is 91.28%, which are 1.48 and 1.58 percentage points higher than those of the standard UNet model, respectively. In the snow segmentation task, the mIoU of the model reaches 92.74%, and the accuracy rate is 94.19%, which are 2.39 and 2.36 percentage points higher than those of the standard UNet model, respectively. At the same time, the number of parameters of the model is reduced by 12.85% compared with the standard UNet. Also, its comprehensive performance is significantly better than that of mainstream image segmentation models such as FCN, SegNet, and DeepLabv3+. Based on the standardized time-series data retrieved by the optimized segmentation model, this study further constructs a Grassland Fire Risk Index (GFRI) using the Analytic Hierarchy Process (AHP). Pearson correlation verification confirms that the GFRI has an extremely significant positive correlation with historical fire frequency, accurately capturing the seasonal dynamic rhythm of regional grassland fire occurrence. This integrated framework of intelligent segmentation and fire risk quantification provides a reliable technical solution for grassland fire factor monitoring, dynamic fire risk assessment, early warning systems, and refined regional ecological management. Full article

Full-waveform hyperspectral LiDAR offers a new approach for precise forest ecological monitoring by simultaneously acquiring the three-dimensional structure and continuous spectral information of targets. However, uncertainty in the backscattering cross-section and the inseparability of the reflectance coefficient lead to systematic underestimation of multi-echo reflectance retrieved using traditional methods. This limitation significantly hinders quantitative applications. The existing multi-echo reflectance correction using neighborhood single-echo reflectance (MCNS) method provides an effective solution by establishing proportional models between similar targets, laying an important foundation for the extraction of multi-echo reflectance. However, its applicability in complex forest scenes is limited due to its dependence on specific vegetation single-echo samples. To address this, an iterative correction method based on ground reflectance baseline, namely Bare-Ground-Echo-Based Iterative Correction of Multi-Echo Reflectance for Hyperspectral LiDAR (BGE-ICMER), is proposed. Using ground single-echo reflectance as a stable baseline, a multi-target energy distribution model is constructed based on energy conservation, and backscattering cross-section proportions for each echo are iteratively solved to recover true reflectance. Validation using a high-fidelity dataset generated by the Large-Scale remote sensing data and image Simulation framework (LESS) confirmed the effectiveness of the proposed method. This dataset encompasses three typical tree species with vegetation layers ranging from two to four, incorporates micro-topographic ground surfaces and ten spectral channels from 500 to 1000 nm, thereby capturing the structural and spectral complexity of real forests. The results showed that coefficients of determination (R²) between the corrected and true reflectance exceeded 0.9560, with an RMSE below 0.0418 and MAE below 0.0360. The average relative error was reduced from 26.66% to 10.07%, representing a 62.22% improvement in accuracy. Even in the most challenging scenarios with four-layer vegetation occlusion within this dataset, no significant error accumulation occurred. These results demonstrate the robustness and effectiveness of the proposed method for multi-echo reflectance extraction. This study lays a foundation for more accurate forest biochemical attribute assessment and enables the vertical characterization of multiple targets using high-resolution spectral reflectance. Full article

Background/Objectives: Term and preterm premature ruptures of membranes (PROM and PPROM) are serious pregnancy complications associated with adverse maternal and neonatal outcomes. Although widely studied in the global literature, data on the risk factors and outcomes of PROM and PPROM in the Middle East and North Africa (MENA) region remain limited. This mapping review aimed to identify and assess existing evidence and highlight gaps in knowledge regarding risk factors for PROM, including preterm PROM, and related maternal and neonatal outcomes among women in the region. Methods: We conducted a comprehensive and systematic search of articles published in English and Arabic between January 2000 and June 2025 across Scopus, Embase, Web of Science, and PubMed/Medline. Eligible studies included observational and interventional studies conducted in MENA countries. Data were extracted and synthesised using thematic mapping. Results: Out of 5359 retrieved records, 136 met the inclusion criteria. The main study design was cross-sectional (51 studies), followed by case–control (41), cohort (26), and 15 randomised controlled trials. The geographic distribution of the evidence varied significantly. Research has mainly focused on PROM and its biological risk factors, such as infections and chronic medical conditions. Psychological and environmental factors have been the least reported. Neonatal and gestational outcomes have frequently been addressed, whereas maternal outcomes have received less attention. Conclusions: The findings reveal significant geographic, thematic, and methodological disparities in research throughout the MENA region. The results underscore the need for further studies on the prevention and identification of women at higher risk of PROM. Full article

Background/Objectives: Spinal cord stimulation (SCS) is an established therapy for chronic refractory pain, but its clinical value depends on whether benefit persists beyond the early post-implant period. Although short-term SCS studies are abundant, reports with follow-up of 24 months or longer are dispersed, methodologically heterogeneous, and difficult to interpret across indications and stimulation platforms. This scoping review aimed to map the clinical literature reporting SCS outcomes at ≥24 months, characterize the represented populations and modalities, summarize the long-term outcome domains assessed, and identify major methodological and clinical gaps in the evidence base. Methods: This PRISMA-ScR-informed scoping review applied a Population–Concept–Context framework. PubMed/MEDLINE and Scopus were searched through April 2026, yielding 6866 records before deduplication. Following staged title/abstract screening, iterative full-text retrieval, and the reconciliation of overlapping publications, 292 unique full-text reports were assessed for eligibility. Studies reporting original clinical SCS data with extractable outcomes at ≥24 months were included. No meta-analysis or formal GRADE assessment was undertaken, as the objective was evidence mapping rather than pooled effect estimation. Results: The final evidence map comprised 65 unique reports representing a cumulative report-level population of 11,518 participants across non-overlapping cohorts. The literature was dominated by non-randomized evidence (55 observational reports; 10 randomized or randomized-derived). The most frequent indication was mixed chronic pain (30/65; 46.2%), followed by failed back surgery syndrome/persistent spinal pain syndrome (FBSS/PSPS; 16/65; 24.6%), chronic back and/or leg pain (6/65; 9.2%), complex regional pain syndrome (CRPS; 5/65; 7.7%), and painful diabetic neuropathy (PDN; 4/65; 6.2%). Most reports involved conventional or unspecified SCS (47/65; 72.3%), with smaller contemporary clusters for 10 kHz high-frequency SCS and ECAP-controlled closed-loop SCS. The most frequently reported outcome domains were pain durability, function and quality of life, device-related outcomes, and opioid use. At a descriptive level, the literature more often supported persistence of benefit than complete erosion of effect, particularly in spinal pain populations and in contemporary PDN and closed-loop SCS cohorts. Interpretation was constrained by outcome heterogeneity, cohort overlap, mixed indication categories, and inconsistent opioid and device-maintenance reporting. Conclusions: The long-term SCS literature supports the view that durable benefit is achievable in a substantial patient subset, particularly in FBSS/PSPS populations, and in more recent evidence, in PDN, nonsurgical refractory back pain, and closed-loop SCS cohorts. The evidence base remains heterogeneous and does not support a uniform certainty-ranked estimate across indications and technologies. Future studies should prioritize indication-specific cohorts, standardized multidomain outcome reporting, and transparent separation of unique cohorts from secondary analyses of the same clinical populations. Full article

Biomass burning is a major source of atmospheric pollution. However, rapid and quantitative assessment of particulate matter in smoke plumes remains challenging, owing to the physical uncertainties, limited coverage, and labor-intensive quality control of conventional monitoring approaches. Existing image-based deep learning methods typically address either smoke detection or air quality assessment separately. To address this gap, we develop a Unified Smoke Detection and Aerosol Estimation Framework (SDAF), a three-stage deep learning approach evaluated using a smoke-rich airborne dataset. The framework integrates smoke localization with PM₁ estimation by combining a YOLOv11-based detector with an optimized convolutional neural network. The model achieves high accuracy under in-plume conditions (R² of 0.985). However, its performance degrades under out-of-plume conditions due to substantial differences in visual features between the two domains. Consequently, direct across-domain transfer performs poorly, whereas region of interest (ROI)-level fine-tuning substantially improves performance for out-of-plume images (R² of 0.621). Despite these promising results, fundamental limitations remain. Image-based PM₁ estimation is intrinsically ill-posed due to the non-unique mapping between visual observations and particle mass. Overall, the framework enables an integrated workflow from smoke localization to quantitative PM₁ estimation using image data alone, offering a scalable solution for biomass burning monitoring and air quality assessment while highlighting the fundamentally indirect nature of image-based PM₁ inference relative to spatially resolved retrievals. Full article