Saved Queries

A study on the hydrogen storage of composite materials derived from alloy glass in the system of Zr-Pd-Pt was conducted through the integration of multiple methodologies. The alloy following heat treatment in air at temperatures ranging from 280 °C to 800 °C showed a precipitated structure comprising metallic Pd-Pt particles and a ZrO₂ matrix. In the sample treated at 280 °C, the spillover phenomenon of absorbed hydrogen was suggested. The plateau region of the hydrogen pressure–concentration (PCT) isotherm showed the gradient profiles for the samples oxidized at 400 °C, 600 °C, and 800 °C. In the equilibrium absorption process, the ΔH° of approximately 38 kJ/mol was proposed, and the highest storage of hydrogen was H/Pd = 0.61 by the sample oxidized in air at 600 °C. The temperature programmed reduction (TPR) results exhibited rapid hydrogen release behavior at temperatures ranging from 50 °C to 65 °C. The findings offer novel insights into the microstructure, fabrication process, and overall hydrogen absorption/desorption properties of the composites prepared from a Zr-Pd-Pt alloy glass. Full article

(This article belongs to the Special Issue Composite Materials for Hydrogen Storage)

►▼ Show Figures

Figure 1

12 pages, 2340 KB

Open AccessArticle

The Effect of Light on Plant Growth and Physiology of Acmella radicans and A. paniculata in China

by Xiaohan Wu, Fengping Zheng, Zhijie Wang, Qiurui Li, Kexin Yang, Gaofeng Xu, Yunhai Yang, David Roy Clements, Shaosong Yang, Bin Yao, Guimei Jin, Shicai Shen, Fudou Zhang and Michael Denny Day

Diversity 2025, 17(10), 709; https://doi.org/10.3390/d17100709 (registering DOI) - 13 Oct 2025

Abstract

Acmella radicans (Jacquin) R.K.Jansen is an annual herb native to Central America. In China, it is becoming increasingly invasive and often co-occurs with the native congener A. paniculata (Wall. ex DC.) R.K.Jansen in some habitats. In order to understand the invasion mechanism of A. radicans, we investigated the growth parameters of both the invasive A. radicans and the native congener, A. paniculata, under different light conditions (5%, 25%, 50%, 75%, and 100% of light availability) using potted plants in a glasshouse. Light level, plant species, and their interaction were significant, with plant species generally having a greater effect than light level. Acmella radicans and A. paniculata showed great phenotypic plasticity to various light intensities and had a similar trend with increased shade. The plasticity indices of all parameters of A. radicans, except for branch length and inflorescence number, were greater than those of A. paniculata under the same light intensity. The physiological parameters for A. radicans under both favorable (high light intensity) and unfavorable (low light intensity) conditions showed less inhibition than those of A. paniculata. All these responses indicated that A. radicans had greater phenotypic plasticity and higher adaptability to low light, which may contribute to its invasion success. Full article

(This article belongs to the Special Issue Ecology, Distribution, Impacts, and Management of Invasive Plants)

►▼ Show Figures

Figure 1

19 pages, 1801 KB

Open AccessArticle

Enhancing Lemon Leaf Disease Detection: A Hybrid Approach Combining Deep Learning Feature Extraction and mRMR-Optimized SVM Classification

by Ahmet Saygılı

Appl. Sci. 2025, 15(20), 10988; https://doi.org/10.3390/app152010988 (registering DOI) - 13 Oct 2025

Abstract

This study presents a robust and extensible hybrid classification framework for accurately detecting diseases in citrus leaves by integrating transfer learning-based deep learning models with classical machine learning techniques. Features were extracted using advanced pretrained architectures—DenseNet201, ResNet50, MobileNetV2, and EfficientNet-B0—and refined via the minimum redundancy maximum relevance (mRMR) method to reduce redundancy while maximizing discriminative power. These features were classified using support vector machines (SVMs), ensemble bagged trees, k-nearest neighbors (kNNs), and neural networks under stratified 10-fold cross-validation. On the lemon dataset, the best configuration (DenseNet201 + SVM) achieved 94.1 ± 4.9% accuracy, 93.2 ± 5.7% F1 score, and a balanced accuracy of 93.4 ± 6.0%, demonstrating strong and stable performance. To assess external generalization, the same pipeline was applied to mango and pomegranate leaves, achieving 100.0 ± 0.0% and 98.7 ± 1.5% accuracy, respectively—confirming the model’s robustness across citrus and non-citrus domains. Beyond accuracy, lightweight models such as EfficientNet-B0 and MobileNetV2 provided significantly higher throughput and lower latency, underscoring their suitability for real-time agricultural applications. These findings highlight the importance of combining deep representations with efficient classical classifiers for precision agriculture, offering both high diagnostic accuracy and practical deployability in field conditions. Full article

(This article belongs to the Topic Digital Agriculture, Smart Farming and Crop Monitoring)

30 pages, 2655 KB

Open AccessArticle

Phase-Aware Complex-Spectrogram Autoencoder for Vibration Preprocessing: Fault-Component Separation via Input-Phasor Orthogonality Regularization

by Seung-yeol Yoo, Ye-na Lee, Jae-chul Lee, Se-yun Hwang, Jae-yun Lee and Soon-sup Lee

Machines 2025, 13(10), 945; https://doi.org/10.3390/machines13100945 (registering DOI) - 13 Oct 2025

Abstract

We propose a phase-aware complex-spectrogram autoencoder (AE) for preprocessing raw vibration signals of rotating electrical machines. The AE reconstructs normal components and separates fault components as residuals, guided by an input-phasor phase-orthogonality regularization that defines parallel/orthogonal residuals with respect to the local signal phase. We use a U-Net-based AE with a mask-bias head to refine local magnitude and phase. Decisions are based on residual features—magnitude/shape, frequency distribution, and projections onto the normal manifold. Using the AI Hub open dataset from field ventilation motors, we evaluate eight representative motor cases (2.2–5.5 kW: misalignment, unbalance, bearing fault, belt looseness). The preprocessing yielded clear residual patterns (low-frequency floor rise, resonance-band peaks, harmonic-neighbor spikes), and achieved an area under the receiver operating characteristic curve (ROC-AUC) = 0.998–1.000 across eight cases, with strong leave-one-file-out generalization and good calibration (expected calibration error (ECE) ≤ 0.023). The results indicate that learning to remove normal structure while enforcing phase consistency provides an unsupervised front-end that enhances fault evidence while preserving interpretability on field data. Full article

(This article belongs to the Section Machines Testing and Maintenance)

19 pages, 20391 KB

Open AccessArticle

Radar-Based Gesture Recognition Using Adaptive Top-K Selection and Multi-Stream CNNs

by Jiseop Park and Jaejin Jeong

Sensors 2025, 25(20), 6324; https://doi.org/10.3390/s25206324 (registering DOI) - 13 Oct 2025

Abstract

With the proliferation of the Internet of Things (IoT), gesture recognition has attracted attention as a core technology in human–computer interaction (HCI). In particular, mmWave frequency-modulated continuous-wave (FMCW) radar has emerged as an alternative to vision-based approaches due to its robustness to illumination changes and advantages in privacy. However, in real-world human–machine interface (HMI) environments, hand gestures are inevitably accompanied by torso- and arm-related reflections, which can also contain gesture-relevant variations. To effectively capture these variations without discarding them, we propose a preprocessing method called Adaptive Top-K Selection, which leverages vector entropy to summarize and preserve informative signals from both hand and body reflections. In addition, we present a Multi-Stream EfficientNetV2 architecture that jointly exploits temporal range and Doppler trajectories, together with radar-specific data augmentation and a training optimization strategy. In experiments on the publicly available FMCW gesture dataset released by the Karlsruhe Institute of Technology, the proposed method achieved an average accuracy of 99.5%. These results show that the proposed approach enables accurate and reliable gesture recognition even in realistic HMI environments with co-existing body reflections. Full article

(This article belongs to the Special Issue Sensor Technologies for Radar Detection)

13 pages, 773 KB

Open AccessArticle

Convective Drying of Pirul (Schinus molle) Leaves: Kinetic Modeling of Water Vapor and Bioactive Compound Retention

by José Arturo Olguín-Rojas, Ariana Martinez-Candelario, Irving David Pérez-Landa, Paulina Aguirre-Lara, Maria Mariana González-Urrutia and Manuel González-Pérez

Processes 2025, 13(10), 3259; https://doi.org/10.3390/pr13103259 (registering DOI) - 13 Oct 2025

Abstract

Schinus molle L. is a tree commonly found in agricultural fields, deserts, and semi-arid areas of central Mexico. Its distinctive aroma makes it a source of essential oil, extracted mainly from the bark and fruits. The leaves contain phenolic compounds, and their extracts have demonstrated antimicrobial activity. Obtaining these extracts requires a prior drying process. This study aimed to evaluate the effect of convective drying on phenolic compounds in pirul leaves and determine the thermodynamic properties of the process, including the effective diffusivity of water vapor (D) and activation energy (Ea). Drying kinetics were conducted at different air-drying temperatures (30, 40, and 50 °C) at a constant rate of 1 ms⁻¹, and the results were fitted to the second Fick’s law and semi-empirical models. After drying, a decrease in total flavonoid content was observed as the drying temperature increased, with losses of 37%, 49%, and 62% at 30, 40, and 50 °C, respectively. The final values ranged from 37.96 to 21.02 mg QE/100 g of dry leaf. The D varied between 1.32 × 10⁻¹² and 6.71 × 10⁻¹² m² s⁻¹, with an Ea of 66.06 kJ mol⁻¹. The fitting criteria (R², RMSE, AIC/BIC) indicated that the Logarithmic model best described the kinetics at 30–40 °C, while Page was adequate at 50 °C. These findings suggest an inverse relationship between drying temperature and flavonoid content, while higher temperatures accelerate water vapor diffusivity, reducing the processing time, as observed in plant matrices. Full article

(This article belongs to the Special Issue Pharmaceutical Potential and Application Research of Natural Products)

►▼ Show Figures

Figure 1

17 pages, 1106 KB

Open AccessArticle

Calibrated Global Logit Fusion (CGLF) for Fetal Health Classification Using Cardiotocographic Data

by Mehret Ephrem Abraha and Juntae Kim

Electronics 2025, 14(20), 4013; https://doi.org/10.3390/electronics14204013 (registering DOI) - 13 Oct 2025

Abstract

Accurate detection of fetal distress from cardiotocography (CTG) is clinically critical but remains subjective and error-prone. In this research, we present a leakage-safe Calibrated Global Logit Fusion (CGLF) framework that couples TabNet’s sparse, attention-based feature selection with XGBoost’s gradient-boosted rules and fuses their class probabilities through global logit blending followed by per-class vector temperature calibration. Class imbalance is addressed with SMOTE–Tomek for TabNet and one XGBoost stream (XGB–A), and class-weighted training for a second stream (XGB–B). To prevent information leakage, all preprocessing, resampling, and weighting are fitted only on the training split within each outer fold. Out-of-fold (OOF) predictions from the outer-train split are then used to optimize blend weights and fit calibration parameters, which are subsequently applied once to the corresponding held-out outer-test fold. Our calibration-guided logit fusion (CGLF) matches top-tier discrimination on the public Fetal Health dataset while producing more reliable probability estimates than strong standalone baselines. Under nested cross-validation, CGLF delivers comparable AUROC and overall accuracy to the best tree-based model, with visibly improved calibration and slightly lower balanced accuracy in some splits. We also provide interpretability and overfitting checks via TabNet sparsity, feature stability analysis, and sufficiency (k95) curves. Finally, threshold tuning under a balanced-accuracy floor preserves sensitivity to pathological cases, aligning operating points with risk-aware obstetric decision support. Overall, CGLF is a calibration-centric, leakage-controlled CTG pipeline that is interpretable and suited to threshold-based clinical deployment. Full article

(This article belongs to the Special Issue Advances in Algorithm Optimization and Computational Intelligence)

►▼ Show Figures

Figure 1

21 pages, 424 KB

Open AccessArticle

Investigating the Effects of Soil Type and Potassium Fertiliser Timing on Potassium Leaching: A Five-Soil Lysimeter Study

by Thomas P. McCarthy, John B. Murphy and Patrick J. Forrestal

Soil Syst. 2025, 9(4), 110; https://doi.org/10.3390/soilsystems9040110 (registering DOI) - 13 Oct 2025

Abstract

Potassium (K) is essential for grassland productivity, but soil K leaching can reduce fertiliser use efficiency, increasing environmental losses. International evidence suggests soil type and K fertiliser timing influence K leaching, yet limited data exist for Ireland’s diverse soil types. This study investigated the effects of K fertiliser timing (autumn, winter, and spring) and soil type on K leaching using a controlled lysimeter facility with five representative Irish soils sown with perennial ryegrass. Potassium fertiliser (125 kg K ha⁻¹) was applied in October, December, or February, with leachate collected from October to April. Soil type affected cumulative K leaching (1.4–9.8 kg ha⁻¹; p ≤ 0.001), with the greatest losses observed in sandy soils. Potassium and nitrogen uptake in spring-harvested grass were also influenced by soil type (p ≤ 0.05), with strong positive correlation between the two nutrients (R² = 0.78; p ≤ 0.001). Temporally, significant interactions (p ≤ 0.05) between K application timing and sampling date were found for K leachate in three of the five soils tested. Autumn and winter applications tended to increase cumulative leaching risk, especially on coarser-textured soils such as the Oakpark soil (p ≤ 0.05). The study indicates that applying K in early spring will tend to reduce leaching K losses, particularly on sandy soils. Full article

(This article belongs to the Topic Soil Health and Nutrient Management for Crop Productivity)

36 pages, 3396 KB

Open AccessArticle

Graph-Enhanced Prompt Tuning for Evidence-Grounded HFACS Classification in Power-System Safety

by Wenhua Zeng, Wenhu Tang, Diping Yuan, Bo Zhang, Na Xu and Hui Zhang

Energies 2025, 18(20), 5389; https://doi.org/10.3390/en18205389 (registering DOI) - 13 Oct 2025

Abstract

Power-system safety is fundamental to protecting lives and ensuring reliable grid operation. Yet, hierarchical text classification (HTC) methods struggle with domain-dense accident narratives that require cross-sentence reasoning, often yielding limited fine-grained recognition, inconsistent label paths, and weak evidence traceability. We propose EG-HPT (Evidence-Grounded Hierarchy-Aware Prompt Tuning), which augments hierarchical prompt tuning with Global Pointer-based nested-entity recognition and a sentence–entity heterogeneous graph to aggregate cross-sentence cues; label-aware attention selects Top-k evidence nodes and a weighted InfoNCE objective aligns label and evidence representations, while a hierarchical separation loss and an ancestor-completeness constraint regularize the taxonomy. On a HFACS-based power-accident corpus, EG-HPT consistently outperforms strong baselines in Micro-F1, Macro-F1, and path-constrained Micro-F1 (C-Micro-F1), with ablations confirming the contributions of entity evidence and graph aggregation. These results indicate a deployable, interpretable solution for automated risk factor analysis, enabling auditable evidence chains and supporting multi-granularity accident intelligence in safety-critical operations. Full article

(This article belongs to the Special Issue AI, Big Data, and IoT for Smart Grids and Electric Vehicles)

18 pages, 1472 KB

Open AccessArticle

Influence of Surface Energy and Phase Composition on Electroadhesive Interactions

by Konstantin I. Sharov, Valentina Yu. Stepanenko, Ramil R. Khasbiullin, Vladimir V. Matveev, Uliana V. Nikulova and Aleksey V. Shapagin

Polymers 2025, 17(20), 2739; https://doi.org/10.3390/polym17202739 (registering DOI) - 13 Oct 2025

Abstract

The aim of the study is to investigate the influence of the physicochemical characteristics of the molecular and supramolecular structure of polymers on electroadhesive interactions and their change under the action of a constant electric field. Currently, this effect is modeled in electroadhesion studies, but the range of variable parameters is limited and includes permittivity, moisture content, and surface roughness. It is important to consider other physicochemical parameters, such as material crystallinity and surface characteristics, changes in which can affect the magnitude of electroadhesive forces. In this study, the electric field strength was varied by altering the constant voltage in the range of 3–8 kV. Polyethylene, ethylene-vinyl acetate copolymers, and polyvinyl acetate were used as substrates for adhesive systems. The influence of the concentration of vinyl acetate groups, which determine the energy characteristics of the surface, and the degree of crystallinity on electroadhesive interactions under conditions of an external constant electric field and without it was traced. The degree of crystallinity was varied both by the cooling rate and the orientation during drawing. It was shown that by changing the polar component of the surface energy and the proportion of the crystalline phase in the substrate, electroadhesive interactions can be increased by 4 times to 120 Pa compared to polyethylene. The obtained laws are explained by the local dipoles induced by polar functional groups, which enhance the polymer’s surface interactions with other materials and external fields. At the same time, the fixation of macromolecules in crystalline regions complicates polarization under the influence of an electric field. Full article

(This article belongs to the Special Issue Synthesis, Design, Preparation and Processing of Functional Polymer Composites)

33 pages, 3983 KB

Open AccessArticle

Real-Time EEG Decoding of Motor Imagery via Nonlinear Dimensionality Reduction (Manifold Learning) and Shallow Classifiers

by Hezzal Kucukselbes and Ebru Sayilgan

Biosensors 2025, 15(10), 692; https://doi.org/10.3390/bios15100692 (registering DOI) - 13 Oct 2025

Abstract

This study introduces a real-time processing framework for decoding motor imagery EEG signals by integrating manifold learning techniques with shallow classifiers. EEG recordings were obtained from six healthy participants performing five distinct wrist and hand motor imagery tasks. To address the challenges of high dimensionality and inherent nonlinearity in EEG data, five nonlinear dimensionality reduction methods, t-SNE, ISOMAP, LLE, Spectral Embedding, and MDS, were comparatively evaluated. Each method was combined with three shallow classifiers (k-NN, Naive Bayes, and SVM) to investigate performance across binary, ternary, and five-class classification settings. Among all tested configurations, the t-SNE + k-NN pairing achieved the highest accuracies, reaching 99.7% (two-class), 99.3% (three-class), and 89.0% (five-class). ISOMAP and MDS also delivered competitive results, particularly in multi-class scenarios. The presented approach builds upon our previous work involving EEG datasets from individuals with spinal cord injury (SCI), where the same manifold techniques were examined extensively. Comparative findings between healthy and SCI groups reveal consistent advantages of t-SNE and ISOMAP in preserving class separability, despite higher overall accuracies in healthy subjects due to improved signal quality. The proposed pipeline demonstrates low-latency performance, completing signal processing and classification in approximately 150 ms per trial, thereby meeting real-time requirements for responsive BCI applications. These results highlight the potential of nonlinear dimensionality reduction to enhance real-time EEG decoding, offering a low-complexity yet high-accuracy solution applicable to both healthy users and neurologically impaired individuals in neurorehabilitation and assistive technology contexts. Full article

(This article belongs to the Section Wearable Biosensors)

►▼ Show Figures

Figure 1

30 pages, 24475 KB

Open AccessArticle

Integration of Network Pharmacology, Molecular Docking, and In Vitro Nitric Oxide Inhibition Assay to Explore the Mechanism of Action of Thai Traditional Polyherbal Remedy, Mo-Ha-Rak, in the Treatment of Prolonged Fever

by Chinnaphat Chaloemram, Ruchilak Rattarom, Anake Kijjoa and Somsak Nualkaew

Pharmaceuticals 2025, 18(10), 1541; https://doi.org/10.3390/ph18101541 (registering DOI) - 13 Oct 2025

Abstract

Background: Prolonged fever (PF) is one of the most challenging clinical conditions due to its complex molecular mechanisms and limited effective treatments. Objective: The current study aimed to explore the mechanism of action of Mo-Ha-Rak (MHR), a Thai traditional polyherbal remedy, in PF treatment. Methods: Integration of network pharmacology, molecular docking, and inhibition of nitric oxide (NO) production in LPS-induced RAW264.7 macrophages approaches were used. Results: The study identified 86 potential active compounds, 131 potential therapeutic targets, and 9 hub genes for MHR. Key targets with the highest degree of connectivity in PF, including TNF, IL6, IL1B, PTGS2, STAT3, and NFKB1, are closely associated with arachidonic acid metabolism pathways, which play critical roles in infections, inflammation, cell proliferation, and apoptosis in the PF microenvironment. Molecular docking analysis suggested that core compounds exhibited strong binding affinities for four key targets, viz. TNF, IL6, IL1B, and PTGS2, with binding energies ranging from −4.1 to −9.8 kJ/mol. MHR exhibited dose-dependent reduction of NO production at concentrations of 10–100 µg/mL. Among the biomarkers of MHR tested, ellagic acid, loureirin A, resveratrol, and rhein showed potential to inhibit NO production. Conclusions: This study demonstrates that MHR exerts its therapeutic effects on PF through a complex network of multiple compounds, targets, and pathways. These findings highlight the mechanisms of PF and the role of MHR in modulating the arachidonic acid metabolism pathway, which underlies the development of fever. Full article

(This article belongs to the Section Natural Products)

17 pages, 12944 KB

Open AccessArticle

Experimental Study on Backwater-Assisted Picosecond Laser Trepanning of 304 Stainless Steel

by Liang Wang, Rui Xia, Jie Zhou, Yefei Rong, Changjian Wu, Long Xu, Xiaoxu Han and Kaibo Xia

Metals 2025, 15(10), 1138; https://doi.org/10.3390/met15101138 (registering DOI) - 13 Oct 2025

Abstract

This study focuses on the high-precision microhole machining of 304 stainless steel and explores a backwater-assisted picosecond laser trepanning technique. The laser used is a 30 W green picosecond laser with a wavelength of 532 nm, a repetition rate of 1000 kHz, and a pulse width of less than 15 ps. Experiments were conducted under both water-based and non-water-based laser processing environments to systematically investigate the effects of laser power and scanning cycles on hole roundness, taper, and overall hole quality. The experimental results further confirm the advantages of the backwater-assisted technique in reducing slag accumulation, minimizing roundness variation, and improving hole uniformity. In addition, thermal effects during the machining process were analyzed, showing that the water-based environment effectively suppresses the expansion of the heat-affected zone and mitigates recast layer formation, thereby enhancing hole wall quality. Compared with conventional non-water-based methods, the backwater-assisted approach demonstrates superior processing stability, better hole morphology, and more efficient thermal management. This work provides a reliable technical route and theoretical foundation for precision microhole machining of stainless steel and exhibits strong potential for engineering applications. Full article

(This article belongs to the Special Issue Laser Processing of Metallic Material)

►▼ Show Figures

Figure 1

22 pages, 6988 KB

Open AccessArticle

Efficacy of Hybrid Photovoltaic–Thermal and Geothermal Heat Pump System for Greenhouse Climate Control

by Chung Geon Lee, Geum Choon Kang, Jae Kyung Jang, Sung-Wook Yun, Jong Pil Moon, Hong-Seok Mun and Eddiemar Baguio Lagua

Energies 2025, 18(20), 5386; https://doi.org/10.3390/en18205386 (registering DOI) - 13 Oct 2025

Abstract

This study evaluated the performance of a hybrid heat pump system integrating photovoltaic–thermal (PVT) panels with a standing column well (SCW) geothermal system in a strawberry greenhouse. The PVT panels, installed over 10% of the area of a 175 m³ greenhouse, stored excess solar heat in an aquifer to offset the reduced efficiency of the geothermal source during extended operation. The results showed that the hybrid system can supply 11,253 kWh of heat energy during the winter, maintaining the night time indoor temperature at 10 °C even when outdoor conditions dropped to −10.5 °C. The PVT system captured 11,125 kWh of solar heat during heating the off season, increasing the heat supply up to 22,378 kWh annually. Additionally, the system generated 3839 kWh of electricity, which significantly offset the 36.72% of the annual pump system electricity requirements, enhancing the system coefficient of performance (COP) of 3.38. Strawberry production increased by 4% with 78% heating cost saving compared to a kerosene boiler system. The results show that the PVT system effectively supports the geothermal system, improving heating performance and demonstrating the feasibility of hybrid renewable energy in smart farms to enhance efficiency, reduce fossil fuel use, and advance carbon neutrality. Full article

21 pages, 10326 KB

Open AccessArticle

Evaluating the Sustainable Development of Red Cultural Tourism in Yunnan, China, Using GIS and Machine Learning Methods

by Zetong Zhou, Feng Cheng, Siyi Shen, Yechuan Gao, Zhi Li and Jie Wang

Reg. Sci. Environ. Econ. 2025, 2(4), 32; https://doi.org/10.3390/rsee2040032 (registering DOI) - 13 Oct 2025

Abstract

Against the backdrop of the accelerated integration of culture and tourism in China, red cultural tourism, as an important component of China’s cultural tourism system, urgently requires a systematic assessment of its development status and synergistic impact mechanisms. This study takes the Long March tourism resources in Yunnan as the research object and constructs a comprehensive evaluation system integrating social influence and ecological carrying capacity. By applying GIS spatial analysis, as well as K-means and XGBoost machine learning models, the development level of red cultural tourism in Yunnan is quantitatively assessed. Furthermore, the interpretable SHAP model is employed to identify the contribution of each evaluation indicator and to analyze the relationships among development levels under three different indicator models. The results reveal that (1) the development level of red cultural tourism in Yunnan generally exhibits a spatial pattern of being lower in the northwest and higher in the southeast; (2) transportation accessibility (TA), average annual precipitation (AAP), and average annual temperature (AAT) are the dominant indicators influencing the development level; (3) there are significant disparities in development levels among cities, indicating that future development needs to comprehensively consider both the social influence and ecological carrying capacity of red cultural tourism resources and adhere to a “social–ecological” synergistic development mechanism. This study not only uncovers the synergistic impacts of social and ecological dimensions on the development of red cultural tourism in Yunnan but also provides theoretical and data support for the optimization and sustainable development of Yunnan’s red cultural tourism resources. Full article

(This article belongs to the Topic Sustainability and Regional Development: Foundations and Challenges for This Symbiotic Relationship)

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 1687.

Go to page 1 2 3 4 5

Search Results (84,332)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI