Search Results (2,621)

Climatic drought shapes wildfire regimes, yet the multi-timescale lagged responses of high-intensity wildfires to drought and their spatial heterogeneity remain unclear in subtropical monsoon forests. We integrated long-term MODIS satellite observations and monthly drought metrics (SPEI, VPD, VAP, and precipitation) across subtropical China during 2005–2024. We used Spearman rank correlation to identify multi-scale drought–wildfire relationships and constructed zero-inflated negative binomial generalized linear mixed models (ZINB-GLMM) to quantify multi-temporal drought, vegetation, and anthropogenic effects. Our results showed that 64.7% of 0.5° grid cells experienced high-intensity wildfires, with 77.8% of events occurring in the cold dry season (November–March). Concurrent dry conditions (low SPEI, VAP, precipitation) generally increased fire susceptibility, while atmospheric aridity (high VPD) showed spatially dipolar effects. The 1–3-month lagged model had the highest explanatory power (R² = 0.54), identifying antecedent moisture deficit as the dominant driver. Dense vegetation amplified drought–fire synergies, especially in southeastern and southwestern China. Model predictive performance was strong overall, but lower accuracy in northern areas suggests additional local factors modulate wildfire risk there. This study provides a satellite-based spatiotemporal modeling framework that may serve as a methodological reference for ecological informatics-based wildfire early warning and climate-adaptive management in subtropical and analogous monsoon regions. Full article

Wearable inertial measurement units (IMUs) offer an objective, low-cost basis for Parkinson’s disease (PD) assessment, but multi-task clinical protocols yield heterogeneous recordings across body locations and small cohorts, and it is unclear whether such data can support reliable PD detection without training deep models from scratch. We therefore ask whether a motion-pretrained representation transfers to this setting, and quantify how much of the discriminative signal it supplies. Each subject is represented by five task-level motion embeddings, one per clinical task, produced by a frozen pretrained spatio-temporal graph convolutional network (ST-GCN) that fuses the thirteen body-worn sensors into a whole-body embedding; a three-layer Transformer with validity-mask weighting aggregates these tokens for binary PD-versus-control classification on the WearGait-PD cohort (181 subjects: 100 PD, 81 controls). Under a leakage-free nested protocol with repeated subject-disjoint stratified 5-fold cross-validation (5 seeds; 25 estimates per model) and paired significance testing, the model attains a balanced accuracy of 0.834 ± 0.087, macro-F1 of 0.842 ± 0.094, and AUC of 0.842 ± 0.103. It leads six classical baselines and a spectrogram-CNN on accuracy-based metrics, though random forest, gradient boosting, and the spectrogram-CNN edge ahead on AUC; after correction for fold correlation, none of these between-model differences is significant. The one robust finding is a transfer effect: replacing the pretrained encoder with a random one of identical architecture lowers balanced accuracy by 15.5 points when frozen (p = 0.043) and 20.4 when trained end-to-end (p = 0.014). Discrimination is preserved under 1:1 age matching (0.846) and across both genders, so it is not explained by age imbalance. Motion-pretrained skeletal encoders thus supply the majority of the discriminative signal, while the aggregator contributes gains inseparable from noise at this cohort size. Full article

Prostate adenocarcinoma is characterized by substantial inter-patient heterogeneity, limiting the clinical reliability of conventional diagnostic tools, including prostate-specific antigen testing. This limitation underscores the need for robust molecular biomarkers that may complement conventional diagnostic tools, highlighting the urgent need for biomarkers capable of enhancing diagnostic accuracy and enabling more precise risk stratification. In the present study, transcriptomic data from The Cancer Genome Atlas (TCGA) were analyzed using an integrative bioinformatics and machine learning pipeline., The proposed workflow was designed as a stepwise and reproducible biomarker prioritization framework in which differential expression analysis, functional enrichment, protein–protein interaction (PPI) based network interpretation, graph-convolutional feature selection, and hybrid ensemble machine learning were sequentially integrated. Differential gene expression analysis was combined with pathway enrichment (Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Reactome), protein–protein interaction network construction, and graph-convolutional feature selection. Multiple machine learning algorithms, including Random Forest, Gradient Boosting Machine, Support Vector Classifier, Artificial Neural Network, and AdaBoost, were systematically evaluated. A hybrid ensemble model integrating Gradient Boosting Machine and Random Forest (GBM+RF) was subsequently developed. Model performance was assessed using accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic (ROC) and externally validated using the independent GSE14206 dataset. The analysis revealed a coordinated molecular pattern characterized by dysregulated cell cycle activity and enhanced interferon-mediated immune signaling. Protein–protein interaction analysis identified STAT1 and PLK1 as highly connected network hub genes within immune-related and cell-cycle-associated modules. Among the evaluated models, the hybrid GBM+RF framework achieved the highest predictive performance on the TCGA dataset, with AUC: 0.9526; Accuracy: 97.49%. External validation using the GSE14206 dataset confirmed the robustness of this model (AUC: 0.9156; Accuracy: 91.53%). These findings support a broader multi-gene candidate signature in prostate adenocarcinoma, in which machine learning prioritized genes such as XAF1, APP, RPA3, IFIH1, UBE2D2, RSAD2, KIF2C, and PLK1, while STAT1 and PLK1 provided complementary network-level biological relevance. The proposed framework provides a robust and transferable strategy for biomarker discovery and precision oncology. Full article

This paper presents a numerical-computational analysis of ${\mathsf{\ell }}_2$-regularized logistic learning for binary intrusion detection under heterogeneous datasets, class imbalance, and cross-dataset shift. Rather than proposing a new intrusion detection architecture, the study examines how numerical conditioning, feature scaling, feature set design, threshold selection, false negative behavior, false alarm behavior, and distribution shift affect operational detection performance. Experiments were conducted on CICIDS2017, UNSW-NB15, and CIRA-CIC-DoHBrw-2020 using reproducible train–validation–test protocols over five fixed random seeds. The numerical audit showed that standard scaling reduced the spectral condition number of traffic feature matrices by several orders of magnitude across datasets and feature configurations. However, scaling did not produce uniformly monotonic predictive gains: in some cases, raw feature optimization achieved comparable or higher F1-score, whereas scaled preprocessing produced more controlled false alarm behavior. In-domain experiments showed that dataset-specific features may improve ranking metrics such as area under the receiver-operating-characteristic curve (AUROC) or area under the precision–recall curve (AUPR) without necessarily improving thresholded operational metrics. Cross-dataset transfer experiments revealed strong source–target asymmetry, with transferred thresholds producing either near-zero positive detection or excessive false alarms. Additional robustness experiments with Random Forest and XGBoost improved in-domain F1-score and false negative rate (FNR), but did not eliminate off-domain degradation, with high FNR persisting under direct cross-dataset transfer. Finally, a Kolmogorov–Smirnov-based distribution shift analysis showed that in-domain discrepancies were small, whereas cross-dataset discrepancies were consistently large under common standardized traffic features. These findings suggest that numerical stability, ranking quality, thresholded detection performance, false negative and false alarm behavior, and distribution shift should be analyzed jointly when evaluating intrusion detection models. Full article

Groundwater nitrate contamination is delayed, spatially heterogeneous and difficult to screen with sparse monitoring, especially when exceedance probability and exposure concern must be considered together. We analysed 157 shallow groundwater samples from Handan City, China, collected in 2023, and 14 environmental predictors to map NO₃⁻ exceedance above 50 mg/L. Random forest, support vector machine (SVM) and XGBoost classifiers were evaluated by repeated stratified testing and spatial block cross-validation, with SHAP used to interpret model responses. Ordinary kriging and the USEPA non-carcinogenic risk framework estimated adult and child hazard quotients (HQs), and exceedance probability was cross-classified with child HQ in a probability–HQ matrix. Thirty-one samples (19.7%) exceeded the threshold. Although SVM achieved the highest ROC-AUC, XGBoost was retained for early-warning mapping because it better controlled missed exceedances. High-probability zones were concentrated in central-western and urban-fringe Handan. SHAP responses indicated that hydroclimatic, hydrogeological, land-use, terrain and soil factors jointly shaped model discrimination, without implying source attribution. Children had higher HQs than adults. At P = 0.5, general protection, exceedance-warning, concentration-verification and priority-intervention zones occupied 81.26%, 18.40%, 0.01% and 0.33% of the area, respectively. The framework supports targeted monitoring and drinking-water verification rather than fixed contamination boundaries. Full article

Accurate lithofacies identification in carbonate reservoirs is essential for reservoir characterization and development decision-making. However, the strong heterogeneity of carbonate rocks, nonlinear responses of well logging parameters, and imbalance among lithofacies samples significantly limit the performance of conventional machine learning methods. To address these challenges, an improved K-Nearest Neighbor (KNN) lithofacies identification method is proposed in this study using logging data from the Mishrif Formation in the Halfaya Oilfield, Iraq. A total of 600 samples from five wells (X1–X5) were used for model construction and validation. Four carbonate lithofacies types, including grainstone, packstone, wackestone, and marl, were identified based on core observation and thin-section analysis. Five logging parameters, including GR, AC, CNL, DEN, and RT, were selected to construct the feature space. A hybrid SMOTE–NearMiss-1 sampling strategy was introduced to alleviate class imbalance, while a feature-weighted Manhattan distance and distance-weighted voting mechanism were developed to improve the discrimination capability of KNN. The results show that the improved KNN model achieved an overall accuracy of 84.44%, outperforming the baseline KNN model (78.89%) as well as other comparison models, including Random Forest (RF, 76.67%) and Backpropagation Neural Network (BPNN, 75.56%). The area under the ROC curve (AUC) values for all lithofacies classes range from 0.917 to 0.989, indicating robust classification performance. In addition, balanced accuracy and macro-F1 score demonstrate improved recognition performance for minority lithofacies. The predicted lithofacies profiles show good agreement with the core interpretation results and effectively capture vertical lithofacies variations. This study demonstrates that the improved KNN method provides an effective data-driven approach for carbonate reservoir lithofacies characterization, especially under conditions of heterogeneous geological environments and limited labeled samples. Full article

As extreme heat events increase in frequency, intensity, and duration due to climate change, forecasting these events has become vital for early warning systems, public health preparedness, and climate adaptation strategies, especially in parts of the world that are already subject to extreme heat, such as tropical regions. In recent years, machine learning (ML) has increasingly been applied to environmental and meteorological data to improve the prediction of heatwaves and extreme heat events. This scoping review examines global peer-reviewed literature on the application of ML techniques for extreme heat prediction using environmental variables. This includes heatwave prediction, environmental and meteorological predictors used in these models, and the geographical distribution of existing research. A total of 23 peer-reviewed studies meeting the inclusion criteria were included in the review, following the PRISMA-ScR guidelines. The findings indicate that artificial neural networks and random forest models were most frequently reported as high performing within individual studies. However, direct comparisons across studies are limited by heterogeneity in prediction targets, validation strategies, lead times, heatwave definitions, and performance metrics. Temperature-related variables, especially maximum temperature, were consistently identified as the most influential predictors across studies. Furthermore, the evidence base was heavily concentrated in Europe, Asia, and North America, with comparatively limited representation from low- and middle-income countries respective to population, despite these regions often experiencing disproportionate impacts of climate change and extreme heat exposure. By synthesising current evidence on ML-based heatwave prediction, associated environmental predictors, and geographical research trends, this review provides insights to support the development of more robust, context-aware, and globally representative heatwave forecasting frameworks. Full article

Biomass pyrolysis produces three major product fractions—bio-oil, syngas, and biochar—whose yields are governed by nonlinear interactions among feedstock composition, catalyst properties, and operating conditions. Accurate prediction of these product yields remains challenging because literature-derived pyrolysis data are heterogeneous and unevenly distributed across the experimental space. In this study, an interpretable machine-learning framework was developed to predict biomass pyrolysis product yields using readily accessible descriptors from proximate/ultimate analysis, catalyst characterization, and process operation. A curated dataset containing 297 experimental records and 14 input descriptors was used to benchmark multiple regression algorithms, including linear and regularized linear models, support vector regression, k-nearest-neighbour regression, Random Forest, Extra Trees, gradient boosting regression trees, XGBoost, and CatBoost. Target-specific models were developed for bio-oil, syngas, and biochar to maximize the use of available yield data without imputing missing target values. The results showed that nonlinear tree-based ensembles outperform linear and distance-based approaches, while the optimal model depends on the product fraction. SHAP and feature-importance analyses further reveal distinct descriptor–yield relationships. Bio-oil prediction is mainly influenced by catalyst acidity, BET surface area, volatile matter, ash content, and temperature; syngas prediction is dominated by temperature and feedstock composition; and biochar prediction is strongly associated with heating rate, residence time, ash, fixed carbon, and oxygen content. This work provides a transparent data-driven tool for product-yield prediction and descriptor prioritization in biomass pyrolysis. The results showed that nonlinear tree-based ensembles consistently outperformed linear and distance-based approaches. On the independent test set, XGBoost achieved R² = 0.834, RMSE = 5.503 wt%, and MAE = 4.371 wt% for bio-oil, and R² = 0.790, RMSE = 5.427 wt%, and MAE = 3.791 wt% for syngas. GBRT achieved R² = 0.739, RMSE = 3.966 wt%, and MAE = 2.706 wt% for biochar. Repeated five-fold cross-validation further produced mean R² values of 0.783, 0.698, and 0.745 for bio-oil, syngas, and biochar, respectively. Full article

In this study, honey samples collected from the Varda Plateau (İkizdere Valley, Rize) and Yusufeli regions of northeastern Türkiye were comprehensively characterized in terms of their melissopalynological, physicochemical, elemental, and volatile properties. Ten honey samples collected from different apiaries were analyzed. Melissopalynological results identified two samples as monofloral Castanea sativa (chestnut) honeys and three samples as Myosotis-dominant honeys, while the remaining samples were classified as multifloral. The pollen spectra reflected the rich floristic diversity of the region, shaped by both forest vegetation and high-altitude herbaceous flora. Moisture and proline analyses indicated that the investigated samples were consistent with the characteristics of natural and well-matured honeys. Volatile compound analysis by HS-SPME/GC–MS revealed substantial qualitative and quantitative differences among samples, with chestnut and Myosotis honeys generally exhibiting more distinctive aroma profiles than multifloral honeys. Benzaldehyde, furfural, nonane, and linalool derivatives were among the most frequently detected volatile compounds, although their relative abundances varied considerably among samples. Elemental analysis identified potassium as the predominant mineral in all honey samples, while significant variability was observed for Fe, Zn, Mn, Ni, and Cu concentrations. Particularly, the Yusufeli samples were characterized by markedly higher Fe and Cu contents than the Varda samples, indicating a strong geographical influence on elemental composition. Multivariate analyses, including PCA, HCA, and UpSet analysis, confirmed considerable compositional heterogeneity and demonstrated that both botanical and geographical origins contribute to honey differentiation. Overall, the findings provide new insights into the chemical and botanical characteristics of chestnut, Myosotis, and multifloral honeys from the Eastern Black Sea region and highlight the value of integrated analytical and chemometric approaches for honey characterization, classification, and origin assessment. Full article

Plant diversity is often expected to enhance soil organic carbon (SOC) storage through greater and more heterogeneous plant inputs, but its relationships with functionally distinct SOC fractions in natural forests remain uncertain. This study compiled published SOC fraction data from 341 surface soil observations in natural forests across China and spatially matched these records with gridded plant alpha diversity, forest age, climate, topographic and soil properties datasets to evaluate biotic and abiotic associations with SOC, particulate organic carbon (POC), mineral-associated organic carbon (MAOC) and MAOC/SOC. Linear regression, multiple regression, piecewise structural equation modelling and stratified analyses were used to evaluate whether plant diversity was associated with the absolute accumulation and relative stabilization of SOC fractions. Plant alpha diversity was negatively associated with ln[SOC], ln[POC] and ln[MAOC] at the national scale, whereas its bivariate relationship with MAOC/SOC was weak. After accounting for forest age and environmental covariates, plant alpha diversity remained negatively related to the absolute contents of SOC fractions while showing a positive association with MAOC/SOC. Forest age was positively associated with ln[SOC], ln[POC] and ln[MAOC], and POC was more strongly related to plant diversity and forest age than MAOC. In contrast, MAOC and MAOC/SOC were more strongly associated with mineral protection potential, soil pH and precipitation background. Structural equation models indicated that mineral protection potential and mean annual precipitation were associated with greater MAOC accumulation and SOC allocation to the mineral-associated fraction, whereas temperature and topography were linked to MAOC partly through indirect associations with soil physicochemical conditions. Stratified analyses showed that plant diversity associations varied among forest types and climatic backgrounds. Additional interaction models showed that mineral protection potential significantly moderated the associations between plant alpha diversity and ln[SOC], ln[POC] and ln[MAOC], with negative diversity associations weakening under higher mineral protection potential. These findings indicate that plant diversity associations with SOC fractions in natural forests cannot be interpreted as universally positive input relationships. Instead, their direction and strength depend on hydroclimatic context and soil mineral protection, especially for the absolute accumulation of SOC fractions. Full article

This study addresses the problem of pre-harvest fruit commodity grade prediction in intelligent orchards. To overcome the limitations of conventional post-harvest grading systems, including delayed quality evaluation, the limited representation capability of single-modality approaches, and the difficulty of modeling heterogeneous agricultural information collected throughout the growing season, this study proposes STF-Former, a spatiotemporal multimodal Transformer framework for pre-harvest fruit quality prediction. Rather than relying solely on static visual observations, the proposed framework formulates fruit quality prediction as a multimodal spatiotemporal learning problem by jointly exploiting phenotypic evolution, environmental dynamics, and field management information across different growth stages. Through stage-aware temporal modeling and cross-modal representation learning, STF-Former captures the dynamic interactions between fruit developmental processes and environmental water–fertilizer conditions, providing a unified prediction framework for both commodity grades and key quality indicators. This design improves the interpretability of quality formation and establishes a methodological framework for integrating heterogeneous agricultural data in precision orchard management. Experimental results demonstrate that the proposed method achieves significant advantages in both classification and regression tasks. In the commodity grade classification task, STF-Former achieves an Accuracy of $0.887$, a Precision of $0.875$, a Recall of $0.861$, a Macro-F1 score of $0.868$, and an AUC of $0.924$, substantially outperforming traditional machine-learning methods (Random Forest and XGBoost) as well as mainstream unimodal deep-learning models. In the regression task for key quality indicators, superior performance is consistently achieved across multiple agronomic metrics, where the mean absolute error (MAE) is $3.41$ mm for fruit diameter, $11.85$ g for single fruit weight, $0.057$ for coloration index, $0.81$ °Brix for soluble solid content, and $2.68$ N for firmness, with an overall $R^2$ reaching $0.846$. These results validate the effectiveness and robustness of multimodal spatiotemporal learning for accurate pre-harvest fruit quality prediction. The proposed framework provides a practical technical solution for intelligent orchard management, harvest planning, and data-driven precision agriculture, while offering a scalable paradigm for integrating multimodal sensing and temporal learning in smart agricultural systems. Full article

New-quality productive forces provide an important conceptual lens for understanding how innovation-driven development, digital empowerment, and the green transition jointly support sustainable regional development. From a geographical perspective, this study develops a multidimensional evaluation system for new-quality productive forces based on the three elements of productive forces: laborers, means of labor, and objects of labor. Using panel data for 31 provincial-level administrative units in China from 2012 to 2022, we integrate the entropy weight method, standard deviation ellipse, exploratory spatiotemporal data analysis, the obstacle degree model, and the random forest model to examine the spatiotemporal evolution and influencing mechanisms of new-quality productive forces. The results show that: (1) China’s new-quality productive forces increased steadily during the study period, but their overall level remained relatively low and regional disparities continued to widen. Spatially, they exhibited a pronounced “high in the east and low in the west” pattern, with South China and East China maintaining leading positions and Guangdong and Jiangsu forming a dual-core growth structure. (2) The spatial center of gravity remained southeast of the Hu Huanyong Line, and its expansion direction was broadly parallel to this line, indicating a relatively stable spatial configuration. The ESTDA results further reveal significant positive spatial autocorrelation, strong temporal inertia, and marked path dependence in local spatial transitions. (3) High-tech talent supply, innovation and entrepreneurship vitality, and ecological governance capacity constitute the main internal bottlenecks constraining the development of new-quality productive forces. The analysis of external factors indicates that economic scale and population size are the primary predictors of NQPF development, whereas government intervention, openness, urbanization, and industrial structure exhibit varying degrees of nonlinearity and regional heterogeneity. These findings enrich the geographical interpretation of new-quality productive forces and provide empirical evidence for formulating differentiated regional innovation policies and productivity transformation strategies. Full article

Pinus densata is an endemic and dominant conifer in subalpine forests along the southeastern margin of the Tibetan Plateau, where it plays important ecological roles and provides high-resolution tree-ring records for assessing climate–growth relationships. However, the extent to which climatic controls on growth vary among sites with contrasting habitat conditions within the same region remains insufficiently resolved. In this study, we investigated P. densata at three sites in northwestern Yunnan, southwestern China: Yulong Snow Mountain (YL), Haba Snow Mountain (HB), and Shika Snow Mountain (SK). Residual tree-ring width chronologies were developed and analyzed by using response function analysis, redundancy analysis (RDA), and moving-window correlation analysis to identify key climatic factors and evaluate site-specific and temporal variation in growth–climate relationships. The results showed that radial growth responses differed markedly among sites. At YL and HB, ring width was negatively associated with mean temperature in May and positively associated with May precipitation, suggesting that early-growing-season moisture availability may play an important role under warm conditions before full monsoon onset. Warmer conditions in August generally favored growth at both sites. In contrast, radial growth at SK was positively associated with September mean temperature, suggesting a stronger association with late-growing-season thermal conditions at the higher-elevation site. RDA further retained current May mean temperature, current August mean temperature, and previous December precipitation as significant explanatory variables, indicating that radial-growth variation was linked to both current-year thermal conditions and antecedent winter moisture. Moving-window analysis showed that growth–climate relationships varied in strength and direction over time, with distinct site-specific patterns. Overall, these findings indicate that climatic responses of P. densata radial growth in northwestern Yunnan showed spatial heterogeneity and temporal non-stability. This study provides dendroecological evidence that site-level differences and temporal non-stability should be considered when assessing the potential responses of monsoon-influenced subalpine forests to ongoing regional warming. Full article

Understanding microclimatic variability at the land–atmosphere interface is essential for improving knowledge of atmospheric moisture dynamics in heterogeneous mountainous ecosystems. This study analyzes atmospheric relative humidity and soil moisture variability in an experimental Juglans neotropica Diels plantation located in the Ecuadorian Andes under real field conditions. An autonomous photovoltaic-powered monitoring system equipped with low-cost environmental sensors was deployed continuously for 60 days, generating more than 86,000 environmental measurements of atmospheric relative humidity above and below the canopy, together with soil moisture observations. The results revealed persistent vertical humidity stratification associated with canopy structure, characterized by systematically higher atmospheric humidity beneath the canopy compared to the upper atmospheric layer (ΔRH ≈ −36%). Strong intersensor coherence was observed between canopy levels (r = 0.8535), indicating stable temporal consistency in atmospheric variability patterns throughout the monitoring period. Soil moisture exhibited comparatively more stable temporal dynamics than atmospheric humidity, suggesting partial microclimatic decoupling between atmospheric and edaphic layers. The observed humidity gradients remained temporally stable during both daytime and nighttime conditions, supporting the interpretation of canopy-mediated atmospheric buffering processes within the plantation environment. From an ecological perspective, the results indicate that vegetation structure contributes to localized moisture retention, attenuation of short-term atmospheric fluctuations, and regulation of near-surface microclimatic conditions under heterogeneous Andean environmental conditions. Rather than focusing on instrumentation performance, the study provides empirical evidence of persistent canopy-related atmospheric regulation and moisture stratification in a native Andean forest species under continuous field monitoring conditions. These findings contribute to the understanding of land–atmosphere interactions, ecohydrological dynamics, and vegetation-mediated microclimatic regulation in mountainous ecosystems. Full article

Guided forest bathing is increasingly incorporated into resort wellness portfolios, yet tourism evaluations often report average programme outcomes without examining how guests differ at entry or what the findings imply for product and service design. This prospective one-group pre–post field study examined a three-day guided forest bathing programme delivered as part of the organised wellness offer of a forest-rich Northern Adriatic resort. Of 150 enrolled adults, 132 provided matched questionnaires. Six study-specific experiential and relational dimensions were assessed before and after the programme: nature connectedness, restorative perception, sensory awareness, environmental-ethical sensitivity, planetary health orientation, and intention to continue nature-based self-care. All six post-programme scores were higher after Holm adjustment. The largest standardised differences were observed for sensory awareness (mean difference = 0.91, Cohen’s dz = 1.42), restorative perception (mean difference = 0.61, Cohen’s dz = 1.17), and future nature-based self-care (mean difference = 0.59, Cohen’s dz = 1.04). Change in sensory awareness correlated with change in restorative perception (r = 0.62) and nature connectedness (r = 0.58). Previous nature contact, nature-related hobbies, and spiritual-existential orientation predicted baseline nature connectedness, whereas integrative health orientation, wellness self-care, spirituality, and expectations predicted baseline future self-care. In baseline-adjusted models, lower previous forest contact was associated with higher post-programme sensory awareness. Because the study had no control group, these differences cannot be attributed specifically to guided forest bathing rather than to the wider resort stay, time away from routine, recreation, social interaction, expectancy, or repeated measurement. Co-created restorative value is proposed only as an interpretive framework and was not measured as a construct. For tourism and hospitality management, the findings generate testable decisions concerning guest onboarding, adaptive facilitation, guide training, expectation management, and the development of low-infrastructure nature-based wellness products. Full article