Search Results (126)

Archaeological research fundamentally relies on detecting features to uncover hidden historical information. Airborne (aerial) LiDAR technology has significantly advanced this field by providing high-resolution 3D terrain maps that enable the identification of ancient structures and landscapes with improved accuracy and efficiency. This technical note comprehensively reviews 45 recent studies to critically examine the integration of Machine Learning (ML) and Deep Learning (DL) techniques, particularly Convolutional Neural Networks (CNNs), with airborne LiDAR derivatives for automated archaeological feature detection. The review highlights the transformative potential of these approaches, revealing their capability to automate feature detection and classification, thus enhancing efficiency and accuracy in archaeological research. CNN-based methods, employed in 32 of the reviewed studies, consistently demonstrate high accuracy across diverse archaeological features. For example, ancient city walls were delineated with 94.12% precision using U-Net, Maya settlements with 95% accuracy using VGG-19, and with an IoU of around 80% using YOLOv8, and shipwrecks with a 92% F1-score using YOLOv3 aided by transfer learning. Furthermore, traditional ML techniques like random forest proved effective in tasks such as identifying burial mounds with 96% accuracy and ancient canals. Despite these significant advancements, the application of ML/DL in archaeology faces critical challenges, including the scarcity of large, labeled archaeological datasets, the prevalence of false positives due to morphological similarities with natural or modern features, and the lack of standardized evaluation metrics across studies. This note underscores the transformative potential of LiDAR and ML/DL integration and emphasizes the crucial need for continued interdisciplinary collaboration to address these limitations and advance the preservation of cultural heritage. Full article

Gastrodia elata, known as Tianma in Chinese, is a valuable medicinal and nutritional resource. The favorable climate of Zhaotong City, Yunnan Province, China, facilitates its growth and nurtures rich biocultural diversity associated with Tianma in the region. Local people not only cultivate Tianma as a traditional crop but have also developed a series of traditional knowledge related to its cultivation, processing, medicinal use, and culinary applications. In this study, field surveys employing ethnobotanical methods were conducted in Yiliang County, Zhaotong City, from August 2020 to May 2024, focusing on Tianma. A total of 114 key informants participated in semi-structured interviews. The survey documented 23 species (and forms) from seven families related to Tianma cultivation. Among them, there were five Gastrodia resource taxa, including one original species, and four forms. These 23 species served as either target cultivated species, symbiotic fungi (promoting early-stage Gastrodia germination), or fungus-cultivating wood. The Fagaceae family, with 10 species, was the most dominant, as its dense, starch-rich wood decomposes slowly, providing Armillaria with a long-term, stable nutrient substrate. The cultural importance (CI) statistics revealed that Castanea mollissima, G. elata, G. elata f. flavida, G. elata f. glauca, G. elata f. viridis, and Xuehong Tianma (unknown form) exhibited relatively high CI values, indicating their crucial cultural significance and substantial value within the local community. In local communities, traditionally processed dried Tianma tubers are mainly used to treat cardiovascular diseases and also serve as a culinary ingredient, with its young shoots and tubers incorporated into dishes such as cold salads and stewed chicken. To protect the essential ecological conditions for Tianma, the local government has implemented forest conservation measures. The sustainable development of the Tianma industry has alleviated poverty, protected biodiversity, and promoted local economic growth. As a distinctive plateau specialty of Zhaotong, Tianma exemplifies how biocultural diversity contributes to ecosystem services and human well-being. This study underscores the importance of biocultural diversity in ecological conservation and the promotion of human welfare. Full article

The elongated tortoise (Indotestudo elongata), a Critically Endangered (CR) species, faces numerous threats across its range. Yet, the ecological and anthropogenic factors affecting its conservation in fragmented habitats remain poorly understood. This study integrated field surveys and community questionnaires to assess the distribution drivers and local perceptions, such as attitudes, knowledge, conservation practices, and perceived threats, in the Jalthal Forest, one of the last remnants of suitable habitat for the elongated tortoise in eastern Nepal. Using ArcMap, we established 138 randomly selected grids (500 m × 500 m) to evaluate the environmental covariates of tortoise occurrence and anthropogenic pressures. Generalized linear models revealed that tortoise occurrence was negatively associated with dense ground cover (β = −3.50, p = 0.017) and human disturbance (β = −8.11, p = 0.019). Surveys of local residents from community forest user groups (n = 236 respondents) indicated strong local support for tortoise conservation (69% willing to protect the species). Despite this, the respondents identified persistent threats, including hunting for bushmeat and traditional medicine (74%), habitat degradation (65%), and forest fires. While 60% of the respondents recognized the threatened species status, significant knowledge gaps regarding that status and ongoing illegal exploitation persisted. These findings underscore the need for targeted habitat management, reduced anthropogenic pressures, and community-led initiatives to align local attitudes with conservation actions. This study provides critical baseline data for conserving the elongated tortoise in human-modified landscapes and emphasizes the necessity of integrated ecological and socio-cultural strategies for its long-term survival. Full article

The coastal region of Klaipėda (Lithuania) has experienced major political, economic, social, and cultural transformations since the 20th century. Landscapes as evolving expressions of land use and land cover patterns offer a valuable lens to analyse these changes. This study examines the evolution of physical landscape structures across the pre-Soviet, Soviet, and post-Soviet periods, using historical maps and open-access geospatial data. An ontological approach, combined with morphological and configurational metrics, reveals four major and relatively persistent landscape structures: hydrological systems (sea, lagoon, rivers), forest cover, farming intensity (from extensive grassland use to intensive arable farming), and semi-natural environments. Their structural evolution reflects broader cultural factors, such as contrasting land use traditions between former Prussian and Russian territories. The study also highlights the impact of Soviet collectivisation, marked by irrigation networks, agricultural intensification, and forest expansion. The post-Soviet period is characterised by widespread farmland abandonment and fragmentation, revealing new spatial dynamics and challenges in land reappropriation. Landscape transformations are predominantly structured around agricultural dynamics. Although the analysis was limited by the incomplete availability of data for this specific land use class, the centrality of agriculture in shaping territorial organisation is evident and reinforces the strong rural identity associated with the landscape. Full article

Wooded grasslands are agroforestry systems of high biological and cultural value, which are increasingly threatened by land-use abandonment in Mediterranean marginal areas. In the central-southern Apennines, little is known about their ecological dynamics under different management regimes. This study assesses how three management intensities (High: mowing plus grazing; Low: grazing only; and Abandoned: no management for ~50 years) affect the wooded grasslands in a protected area of the Central Apennines. Vascular plant composition and cover were recorded along radial transects from isolated Fagus sylvatica L. trunks to the adjacent grassland, with plots grouped in four positions (Trunk, Mid-canopy, Edge, and Grassland). The canopy cover, shrub height, species richness, and ecological roles of species were analysed. The results show that light availability, driven by canopy and shrub cover, shapes a gradient from shade-adapted species near the trunk to heliophilous grassland species in open areas. In the Abandoned site, shrub encroachment reduces light even beyond the canopy, facilitating the spread of shade-tolerant and pre-forest species, accelerating succession towards a closed-canopy forest. High-intensity management preserves floristic gradients and grassland species, while Low-intensity management shows early signs of succession at the canopy edge. These findings highlight the importance of traditional mowing and grazing in maintaining the biodiversity and ecological functions of wooded grasslands and emphasize the need for timely interventions where management declines. Full article

Ethnobotanical knowledge and biodiversity are critical components of sustainable natural resource management, especially in regions undergoing rapid environmental and socio-economic change. In Northeast Thailand, traditional plant knowledge is deeply intertwined with local cultural identity but faces increasing threats from urbanization, agricultural expansion, and generational shifts. This study presents a floristic and ethnobotanical survey of the Khanthararat Public Benefit Forest, a community-managed remnant forest in Maha Sarakham Province, documenting 110 plant species from 42 families. The Fabaceae family was the most diverse, consistent with other tropical ecosystems. Predominantly native species (85.45%) indicate minimal disturbance, while introduced (11.82%) and endemic species (2.73%) reflect ecological complexity. Ethnobotanical data revealed 34 wild edible species, 33 medicinal plants, and 19 ornamental species used by the local community, highlighting the forest’s vital role in supporting livelihoods and cultural practices. High Use Values (UVs) for species such as Spondias pinnata and Coccinia grandis underline their dual importance in food and medicine. Informant Consensus Factor (Fic) values demonstrate strong agreement on plant use for reproductive and musculoskeletal health, reflecting well-established traditional knowledge. The findings underscore the forest’s dual significance as an ecological hotspot and a repository of cultural heritage, providing essential ecosystem services including biodiversity conservation, climate regulation, and cultural provisioning. By integrating traditional knowledge with biodiversity assessment, this study offers valuable insights for community-based conservation strategies that sustain both ecological integrity and cultural resilience in Northeast Thailand. Full article

Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis. Despite the improvements in diagnostic techniques, the accuracy of TB diagnosis is still low. In recent years, the development of artificial intelligence (AI) has opened up new possibilities in diagnosing and treating TB with high accuracy compared to traditional methods. Traditional diagnostic techniques, such as sputum smear microscopy, culture tests, and chest X-rays, are time-consuming, with less sensitivity for the detection of TB in patients. Due to the new developments in AI, advanced diagnostic and treatment techniques have been developed with high accessibility, speed, and accuracy. AI, including various specific methodologies, is becoming vital in managing TB. Machine learning (ML) methodologies, such as support vector machines (SVMs) and random forests (RF), alongside deep learning (DL) technologies, particularly convolutional neural networks (CNNs) for image analysis, are employed to analyze diverse patient data, including medical images and biomarkers, to enhance the accuracy and speed of tuberculosis diagnosis. This study summarized the benefits and drawbacks of both traditional and AI-driven TB diagnosis, highlighting how AI can support traditional techniques to increase early detection, lower misdiagnosis, and strengthen international TB control initiatives. Full article

Tribals are known as the torchbearers of ethnobotany. Traditional plant-derived utility products (PUPs) are environmentally friendly, cost-effective, and easy to handle, and are extensively used by the forest-dwelling Gaddi and Sippi tribes of the Union Territory (UT) of Jammu and Kashmir for their subsistence. The present study is an attempt to document the invaluable traditional knowledge on wild plants and PUPs possessed by the Gaddi and Sippi tribes before it perishes completely, as this knowledge is transmitted orally to the next generation. Semi-structured schedules were used for the collection of data regarding the method of making and usage of PUPs and the plant species used for making such products. The cultural importance index (CI) and factor informant consensus (F_ic) were calculated to find the predominant plant species and the consensus among informants for species used in making PUPs, respectively. A total of 52 plant species from 28 families and 46 genera are used in the study area for making 93 PUPs. Tools, with a 55.9% contribution, were the major PUP category. Cedrus deodara, used for making 36 PUPs and having a 4.9 CI value, was the most utilized and important tree species for the Gaddi and Sippi tribes. The values of F_ic ranged between 0.97 (miscellaneous PUPs) and 0.99 (containers/storage PUPs). The present study documented 43 plant species as new ethnobotanical records from the UT of Jammu and Kashmir for their use in traditional plant products. The Gaddi and Sippi tribes in the study area have extensive knowledge about forest-based PUPs and the associated plant species. This invaluable knowledge can be exploited for developing new resources for some value-added traditional plant products and agro-based cottage industries, which could play an important role in socio-economic upliftment and livelihood promotion of tribals. Full article

Monitoring algal growth rates and estimating microalgae concentration in photobioreactor systems are critical for optimizing production efficiency. Traditional methods—such as microscopy, fluorescence, flow cytometry, spectroscopy, and macroscopic approaches—while accurate, are often costly, time-consuming, labor-intensive, and susceptible to contamination or production interference. To overcome these limitations, this study proposes an automated, real-time, and cost-effective solution by integrating machine learning with image-based analysis. We evaluated the performance of Decision Trees (DTS), Random Forests (RF), Gradient Boosting Machines (GBM), and K-Nearest Neighbors (k-NN) algorithms using RGB color histograms extracted from images of Scenedesmus dimorphus cultures. Ground truth data were obtained via manual cell enumeration under a microscope and dry biomass measurements. Among the models tested, DTS achieved the highest accuracy for cell count prediction (R² = 0.77), while RF demonstrated superior performance for dry biomass estimation (R² = 0.66). Compared to conventional methods, the proposed ML-based approach offers a low-cost, non-invasive, and scalable alternative that significantly reduces manual effort and response time. These findings highlight the potential of machine learning–driven imaging systems for continuous, real-time monitoring in industrial-scale microalgae cultivation. Full article

This article explores Greco-Roman mythology through the lens of ecocriticism, focusing on how sacred landscapes and natural elements were imagined as animate, divine, and morally instructive forces. In ancient Mediterranean cultures, nature was not merely a passive setting for human action but a dynamic presence—rivers that judged, groves that punished, and mountains that sheltered or revealed. Texts such as Ovid’s Metamorphoses, Virgil’s Georgics, and Homer’s epics present nature as both sacred and sentient, often intervening in human affairs through transformation, vengeance, or protection. Forests, springs, and coastlines functioned as thresholds between human and divine, civilization and wilderness, mortal and eternal. By analyzing these representations, this article reveals a rich tradition in which nature teaches, punishes, guides, and transforms, long before ecological consciousness became a formalized discipline. Drawing connections between classical literary landscapes and contemporary environmental concerns, the article argues that myth can inform today’s ecological imagination, offering an alternative to extractive, anthropocentric paradigms. Recovering the reverence and narrative agency once granted to nature in classical thought may help us rethink our ethical relationship with the environment in the age of climate crisis. Full article

Background/Objectives: This study investigates the application of machine learning (ML) techniques in diagnosing speech sound disorders (SSDs) in Saudi Arabic-speaking children, with a specific focus on phonological biomarkers, particularly Infrequent Variance (InfrVar), to improve diagnostic accuracy. SSDs are a significant concern in pediatric speech pathology, affecting an estimated 10–15% of preschool-aged children worldwide. However, accurate diagnosis remains challenging, especially in linguistically diverse populations. Traditional diagnostic tools, such as the Percentage of Consonants Correct (PCC), often fail to capture subtle phonological variations. This study explores the potential of machine learning models to enhance diagnostic accuracy by incorporating culturally relevant phonological biomarkers like InfrVar, aiming to develop a more effective diagnostic approach for SSDs in Saudi Arabic-speaking children. Methods: Data from 235 Saudi Arabic-speaking children aged 2;6 to 5;11 years were analyzed using several machine learning models: Random Forest, Support Vector Machine (SVM), XGBoost, Logistic Regression, K-Nearest Neighbors, and Naïve Bayes. The dataset was used to classify speech patterns into four categories: Atypical, Typical Development (TD), Articulation, and Delay. Phonological features such as Phonological Variance (PhonVar), InfrVar, and Percentage of Consonants Correct (PCC) were used as key variables. SHapley Additive exPlanations (SHAP) analysis was employed to interpret the contributions of individual features to model predictions. Results: The XGBoost and Random Forest models demonstrated the highest performance, with an accuracy of 91.49% and an AUC of 99.14%. SHAP analysis revealed that articulation patterns and phonological patterns were the most influential features for distinguishing between Atypical and TD categories. The K-Means clustering approach identified four distinct subgroups based on speech development patterns: TD (46.61%), Articulation (25.42%), Atypical (18.64%), and Delay (9.32%). Conclusions: Machine learning models, particularly XGBoost and Random Forest, effectively classified speech development categories in Saudi Arabic-speaking children. This study highlights the importance of incorporating culturally specific phonological biomarkers like InfrVar and PhonVar to improve diagnostic precision for SSDs. These findings lay the groundwork for the development of AI-assisted diagnostic tools tailored to diverse linguistic contexts, enhancing early intervention strategies in pediatric speech pathology. Full article

The Honghe Hani Rice Terraces, a UNESCO World Heritage agroecosystem, embody a millennia-old synergy of cultural heritage and ecological resilience, yet face declining water yields amid land-use intensification and climate variability. This study employs the InVEST model and geographic detector analysis to quantify water-yield dynamics from 2010 to 2020 and identify their spatial and mechanistic drivers. Annual water yield averaged 558 mm, with cultivated lands contributing 33% of total volume, while built-up areas reached 980 mm per unit in 2018. A 31% decline by 2020, driven by cropland fragmentation and tourism growth, revealed persistent-yield hotspots in forested central-eastern terraces and cold spots in southwestern dryland margins. Land-use pattern accounted for 80–95% of yield variability, exacerbated by temperature interactions. Forests, delivering 68.7 million m³ over the decade, highlight the hydrological significance of traditional landscape mosaics. These findings advocate reforestation in critical recharge zones, terrace restoration to preserve agroecological integrity, and regulated tourism integrating rainwater harvesting to sustain water security and cultural heritage. By blending hydrological modeling with socio-cultural insights, this study provides a scalable framework for safeguarding terraced agroecosystems worldwide, aligning heritage conservation with sustainable development. Full article

The integration of the Amazon into the global commodities market requires ensuring the rational use of resources to meet market and socio-political demands, such as the UN’s 2030 Agenda. Responsible production practices are essential to address the current demand for sustainable land use and resource management. This study reviewed the literature (2004–2024) on the opportunities and challenges of implementing and consolidating sustainable production systems in the Amazon. It found a low distribution of studies across Brazilian Amazon states and a surge in publications since 2015, focusing on agroforestry systems and forest management. Challenges include socio-political limitations that hinder public decision-making, leading to inefficient policies, as well as economic issues, lack of know-how, inadequate infrastructure, poor logistics, and cultural resistance. Nevertheless, these systems offer opportunities such as intensified and diversified production, carbon sequestration, and soil and forest conservation. Finally, future research should consider political, social, and economic aspects to facilitate the transition from traditional to sustainable models, supporting strategies for consolidating these systems in the Amazon. Full article

Mediterranean chestnut forests represent ecologically and economically important systems that support biodiversity while providing timber, non-timber forest products, and cultural services. However, traditional management practices are undergoing substantial shifts, with potential implications for forest structure and biodiversity. This study investigates how variation in forest structure and management intensity influences woodpecker communities in chestnut-dominated forests on Mount Paiko, northern Greece. Standardized surveys were conducted at 26 sites stratified by management intensity, and structural forest characteristics such as tree diameter, basal area, and deadwood volume were quantified. Species richness, abundance, and habitat use (feeding and nesting signs) were assessed in relation to these variables. Seven woodpecker species were detected, with distinct differences in species composition across management types. Feeding activity was positively associated with mean tree diameter, while basal area showed a significant negative correlation with woodpecker diversity. Canonical correspondence analysis revealed species-specific preferences along structural gradients, highlighting the association of the Black and Lesser Spotted woodpeckers with larger-diameter trees and deadwood-rich stands. Our results underscore the role of structural heterogeneity in supporting diverse woodpecker assemblages and highlight the need to integrate biodiversity conservation into chestnut forest management, particularly through selective retention of large trees and deadwood elements. Full article

Zingiberaceae is a diverse and culturally significant plant family across tropical Asia, yet in Roi Et Province, Thailand, it has remained poorly documented. This study aimed to provide the first comprehensive assessment of Zingiberaceae in Roi Et Province, Thailand. Previous studies in the region have been limited and did not systematically document species occurrence. The assessment began with an overview of species diversity, followed by an investigation of their ethnobotanical uses, an evaluation of their horticultural potential, and an assessment of their conservation status. Field surveys were conducted throughout Roi Et Province across various habitat types using exploratory sampling to record all observable Zingiberaceae species. Species were identified based on morphological characteristics and comparisons with existing taxonomic literature. A total of 97 species were recorded, including 86 native and 11 introduced taxa, with 23 species endemic to Thailand and 25 species featuring new distributions reported for the province. Species richness was highest in cultivated habitats, likely reflecting the active role of traditional agroecosystems in conserving both native and introduced taxa. Natural habitats such as wetlands and dry evergreen forests hosted species with restricted distributions, underscoring the need to preserve ecological heterogeneity. Ethnobotanical interviews revealed widespread local use of rhizomes and inflorescences for food, medicine, ornamentation, and ceremonial purposes. Phenological observations indicated synchronized flowering and fruiting aligned with the monsoon season, which are traits that supports successful reproduction but may also increase vulnerability under shifting climate regimes—highlighting the importance of monitoring for conservation and guiding optimal harvest timing. These findings demonstrate that both natural and cultivated systems are integral to maintaining Zingiberaceae diversity in the region. Conservation strategies should prioritize habitat protection, support traditional cultivation practices, and promote further research into economically and culturally valuable species. Full article