Mapping agrotourism potential using geospatial data and random forest: A case study from Bali

5Citations
Citations of this article
41Readers
Mendeley users who have this article in their library.

Abstract

Bali, Indonesia, renowned for its cultural heritage and natural beauty, has untapped potential in agrotourism, offering a sustainable avenue for economic diversification and cultural preservation. This study aims to identify and map agrotourism potential in Gianyar Regency using advanced geospatial analysis and the Random Forest algorithm, integrating antrophogenic and environmental variables. Ten key factors were analyzed, including proximity to tourist attractions, tourism facilities, and road networks, as well as environmental variables such as NDVI, LSWI, elevation, slope, temperature, and rainfall. A total of 410 data points, including 111 existing agrotourism locations, were utilized to develop and validate the model. The Random Forest algorithm demonstrated strong performance, achieving an accuracy of 86%, a recall of 72%, and an F1 score of 78%. The model’s high specificity (92%) and low false positive rate (8%) underscored its reliability in excluding unsuitable areas while accurately classifying high-potential zones. Variable importance analysis revealed NDVI (13.13%) and LSWI (13.11%) as the most critical factors, highlighting the significance of soil fertility and moisture in agrotourism suitability. The zoning map categorized land into five potential levels, with 10.11% identified as having very high potential, concentrated in subdistricts like Tegallalang and Payangan. Tegallalang, with its iconic Subak rice terraces, exemplifies the integration of agricultural sustainability and cultural heritage, while Payangan offers interactive horticulture and plantation experiences. Priority villages for development, including Tampaksiring, Kedewatan, and Keliki, demonstrated >50% agrotourism potential, underscoring their suitability for targeted investment and strategic planning. This study provides a robust framework for data-driven agrotourism development, combining geospatial technology with sustainable tourism strategies. It highlights the importance of optimizing natural and cultural assets to enhance Bali’s global appeal while ensuring economic and environmental sustainability. Future research should refine zoning models with additional parameters and collaborative approaches to maximize the potential of agrotourism in rural areas.

Cite

CITATION STYLE

APA

Ustriyana, I. N. G., Saifulloh, M., Diara, I. W., & Suyarto, R. (2025). Mapping agrotourism potential using geospatial data and random forest: A case study from Bali. Ecological Engineering and Environmental Technology, 26(3), 1–16. https://doi.org/10.12912/27197050/199323

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free