Exploring the association between the built environment and positive sentiments of tourists in traditional villages in Fuzhou, China

Ecological Informatics, Journal Year: 2024, Volume and Issue: 80, P. 102465 - 102465

Published: Jan. 11, 2024

Promoting positive emotional experiences for tourists is crucial sustaining development in rural areas. However, existing research has limited focus on the built environment, particularly developing a framework to evaluate environmental sentiment small medium scale with detailed indicators. This study addresses this gap by examining impact of environment tourists' emotions. Natural Language Processing (NLP) technologies are employed analyze web text data and determine average index traditional villages Fuzhou, China. Additionally, were acquired through HRnet segmentation model Matlab. To assess association between indicators index, we used eXtreme Gradient Boosting (XGBoost), SHapley Additive exPlanation (SHAP) model, ArcMap software. The demonstrated that (1) spatial distribution was significant. Houfu Village (9.91), Qianhu (9.88), Ximen (9.75) had highest scores, while Doukui (−0.85), Jiji (0.2), Qiaodong (0.55) lowest. (2) have most significant Openness, Greenness, Color Complexity, contribution value above 0.7—followed Enclosure, Visual Entropy, Ground Exposure, 0.5 0.7. Furthermore, analyzing interaction mechanism showed non-linear relationship. characteristics associated high scores openness range 0.2 0.5, greenness 0.4 0.6, color complexity 0.3 0.5. provides observations pertinent sustainable village environments. findings contribute an understanding how these elements might be effectively designed improve settings.

Language: Английский

---

Integrating monetary and non-monetary valuation for ecosystem services in Piatra Craiului national park, Southern Carpathians: a comprehensive approach to sustainability and conservation

Frontiers in Forests and Global Change, Journal Year: 2024, Volume and Issue: 7

Published: March 1, 2024

The concept of ecosystem services and their valuation has gained significant attention in recent years due to the profound interdependence interconnectedness between humans ecosystems. As several studies on forest have stressed human-nature interactions lately, research study area, environmental conditions shows rapid changes while human pressures forests intensify. Thus, questions are as follows: (i) what monetary non-monetary value provided by Piatra Craiului National Park (ii) relationship with other variables, focusing identifying differences resemblances each approach. R PASTECS package was utilized analyze primary statistical indicators for both values, revealing variability results (s% 141% s% 62%). Both assessments were computed at management unit level data used Forest Management plans photograph analysis which services. correlation nature culture assessed through social-media based method, highly known stimulate participant engagement quantitative computation PCA method visualization. highlighted that, terms, minimum identified €34 maximum exceeded €570,000 values ranged from 1 5 (kernel score). reveals a substantial types valuations. Strong associations certain variables (monetary carbon stock stand volume), moderate connections (slope productivity), weaker relationships (non-monetary altitude, age slope, type flora altitude productivity) revealed. findings valuable insights policymakers, land managers, stakeholders involved natural resource conservation, emphasizing importance considering economic non-economic benefits decision-making processes. integrated approach this how we can better assess mixed services, contributing ongoing actions raising awareness social responsibility.

Language: Английский

---

Black or white, color aberrations in rufous-collared sparrow Zonotrichia capensis

Ornithology Research, Journal Year: 2024, Volume and Issue: 32(4), P. 404 - 409

Published: Aug. 12, 2024

Language: Английский

---

Volunteered Geographic Information

Published: Dec. 8, 2023

This open access book presents methods for retrieval, semantic representation, and analysis of VGI; geovisualization user interactions related to VGI.

Language: Английский

---

Mining crowdsourced text to capture hikers' perceptions associated with landscape features and outdoor physical activities

Ecological Informatics, Journal Year: 2023, Volume and Issue: 78, P. 102332 - 102332

Published: Oct. 10, 2023

Outdoor recreation provides vital interactions between humans and ecological systems with a range of mental physical benefits for people. Despite the increased number studies using crowdsourced online data to assess how people interact landscape during recreational activities, focus remains largely on mapping spatial distribution visitors or analyzing content shared images little work has been done quantify perceptions emotions assign landscape. In this study, we used textual from an outdoor activity-sharing platform (Wikiloc), applied Natural Language Processing (NLP) methods correlation analysis capture hikers' associated features activities. Our results indicate eight clusters based semantic similarity words ranging four describing (“ecosystems, animals & plants”, “geodiversity”, “climate weather”, “built cultural heritage”), one cluster activities three indicating (“aesthetics”, “joy restoration” “physical effort sensation”). The association revealed that “ecosystems, plants” is likely stimulate all identified perceptions, suggesting these natural are important hikers their experience. Moreover, strongly associate “outdoor activities” both sensation” highlighting health well-being in landscapes. study shows potential Wikiloc as valuable source human-nature can provide significant advances understanding peoples' preferences while recreating. These findings help inform planners region by focusing elements peoples perceive be (i.e. plants”).

Language: Английский

---

West Atlantic coastal marine biodiversity: the contribution of the platform iNaturalist

Aquatic Ecology, Journal Year: 2023, Volume and Issue: 58(1), P. 57 - 71

Published: Oct. 9, 2023

Language: Английский

---

Can citizen science and social media images support the detection of new invasion sites? A deep learning test case with Cortaderia selloana

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102602 - 102602

Published: April 16, 2024

Deep learning has advanced the content analysis of digital data, unlocking opportunities for detecting, mapping, and monitoring invasive species. Here, we tested ability open source classification object detection models (i.e., convolutional neural networks: CNNs) to identify map plant Cortaderia selloana (pampas grass) in mainland Portugal. CNNs were trained over citizen science images then applied social media (from Flickr, Twitter, Instagram, Facebook), allowing classify or detect species 77% situations. Images where was identified mapped, using their georeferenced coordinates time stamp, showing previously unreported occurrences C. selloana, a tendency expansion from 2019 2021. Our study shows great potential deep learning, data detection, plants, and, by extension, supporting follow-up management options.

Language: Английский

---

Artificial intelligence correctly classifies developmental stages of monarch caterpillars enabling better conservation through the use of community science photographs

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 7, 2024

Rapid technological advances and growing participation from amateur naturalists have made countless images of insects in their natural habitats available on global web portals. Despite automated species identification, traits like developmental stage or health remain underexplored manually annotated, with limited focus automating these features. As a proof-of-concept, we developed computer vision model utilizing the YOLOv5 algorithm to accurately detect monarch butterfly caterpillars photographs classify them into five stages (instars). The training data were obtained iNaturalist portal, first classified annotated by experts allow supervised models. Our best trained demonstrates excellent performance object detection, achieving mean average precision score 95% across all instars. In terms classification, YOLOv5l version yielded performance, reaching 87% instar classification accuracy for classes test set. approach show promise developing detection models insects, resource that can be used large-scale mechanistic studies. These photos hold valuable untapped information, we've released our collection as an open dataset support replication expansion methods.

Language: Английский

---

Seeing through a new lens: exploring the potential of city walking tour videos for urban analytics

International Journal of Digital Earth, Journal Year: 2023, Volume and Issue: 16(1), P. 2555 - 2573

Published: July 4, 2023

City Walking Tour Videos (CWTVs) are a novel source of Volunteered Geographic Information providing street-level imagery through video sharing platforms such as YouTube. We demonstrate that these videos contain rich information for urban analytical applications, by conducting mobility study. detect transport modes with focus on active (pedestrians and cyclists) motorised (cars, motorcyclists trucks). chose the Paris our area interest given rapid expansion bicycle network response to Covid-19 pandemic compiled corpus encompassing more than 66 hours footage. Through detection street names in placename containing timestamps we extracted georeferenced 1169 locations at which summarise detected modes. Our results show high potential CWTVs studying applications. significant shifts mix before during well weather effects volumes pedestrians cyclists. Combined observed increase data availability over years suggest have considerable other applications field analytics.

Language: Английский

---

Characterizing nature-based recreation preferences in a Mediterranean small island environment using crowdsourced data

Ecosystems and People, Journal Year: 2023, Volume and Issue: 19(1)

Published: Nov. 13, 2023

Nature-based recreation is a key ecosystem service that contributes to positive physical and mental welfare but, at the same time, nature-based recreational activities can increase human pressure impacts on natural areas biodiversity. Understanding people's preference for visiting settings challenging due data methodological limitations. Social media be used map recreation. However, variation in popularity of platforms limitations accessibility are highlighting importance exploring using different sources. We analyzed complementary crowdsourced an automated content analysis refined by manual identification assess services across Maltese archipelago. A images uploaded Flickr between 2015 2021 was performed Google Vision machine learning algorithm identify interactions nature visitation patterns were modeled based landscape characteristics, environmental variables socio-economic parameters. compared complemented with publicly available geolocated from iNaturalist platform. Significant difference found spatial distribution data. Generalized linear models identified coastal areas, protected habitats via road network as significant predictors visits. Localities higher percentage people receiving old age unemployment benefits also positively correlated users' Finally, we discussed how low resource methodology developed here preferences which should prioritized ecological restoration efforts.

Language: Английский

---