EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sustainable tourism and environmental impact assessment based on Big Data

Shaoli Quan

Data and Metadata · 15.05.2026 · 5 · 787

DOI: 10.56294/dm2026787 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data and Metadata, online erschienen am 15.05.2026. Verfasst von Shaoli Quan. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Big data enables monitoring of tourism’s environmental impacts through mobility, satellite, and social data. Existing research applies machine learning for prediction and assessment. However, existing research face limitations in data integration, scalability, privacy concerns, and a lack of standardized frameworks for sustainable tourism decision-making.

Objective

This research proposed a big data–driven analysis for sustainable tourism and environmental impact assessment using advanced machine learning techniques.

Method

The Kaggle platform provides access to a dataset of 9,321 samples on tourism and environmental impact, collected from relevant tourism authorities and environmental agencies. The data involve rigorous preprocessing, including data cleaning with missing value handling, which prevents bias and incomplete records, and Min–Max normalization to scales standardizes, ensuring quality and consistency. Feature extraction is followed by Linear Discriminant Analysis (LDA) to identify hidden patterns and correlations between tourism intensity and environmental degradation indicators such as land-use change, vegetation density, and resource consumption. The Killer Whale Algorithm-tuned Weighted Random Forest (KWA-Weighted RF) is used in predictive modelling to estimate tourism demand and assess environmental effect trends. KWA optimizes hyperparameters, improving both search efficiency and prediction accuracy. Weighted RF increases robustness by emphasizing critical characteristics and managing imbalance.

Results

Experimental results demonstrate that the proposed Python-based big data-driven models achieve accuracy (98,7 %), precision (96,3 %), [user2.1][w2.2]recall (95,1 %), F1-score (95,7 %), Kappa (0,964), MAE (0,112), RMSE (0,168), and AUC (0,982) in both tourism demand estimation and environmental impact classification.

Conclusion

The findings highlight that sustainable tourism management can be significantly enhanced through data analytics and AI-based decision support systems.

Zitieren

APA

Quan, S. (2026). Sustainable tourism and environmental impact assessment based on Big Data. Data and Metadata, 5, 787. https://doi.org/10.56294/dm2026787

Vancouver

Quan S. Sustainable tourism and environmental impact assessment based on Big Data. Data and Metadata. 2026;5:787. doi:10.56294/dm2026787

BibTeX
@article{Quan2026,
  author = {Quan, Shaoli},
  title = {Sustainable tourism and environmental impact assessment based on Big Data},
  journal = {Data and Metadata},
  year = {2026},
  volume = {5},
  pages = {787},
  doi = {10.56294/dm2026787}
}
Kostenlos starten →