For modeling the number of visits in Stopi\'{c}a cave (Serbia) we consider
the classical Auto-regressive Integrated Moving Average (ARIMA) model, Machine
Learning (ML) method Support Vector Regression (SVR), and hybrid NeuralPropeth
method which combines classical and ML concepts. The most accurate predictions
were obtained with NeuralPropeth which includes the seasonal component and
growing trend of time-series. In addition, non-linearity is modeled by shallow
Neural Network (NN), and Google Trend is incorporated as an exogenous variable.
Modeling tourist demand represents great importance for management structures
and decision-makers due to its applicability in establishing sustainable
tourism utilization strategies in environmentally vulnerable destinations such
as caves. The data provided insights into the tourist demand in Stopi\'{c}a
cave and preliminary data for addressing the issues of carrying capacity within
the most visited cave in Serbia.

在本研究中，我们考虑了经典的自回归移动平均（ARIMA）模型、机器学习方法支持向量回归（SVR）以及将经典概念和机器学习相结合的混合神经土地方法（NeuralPropeth）来建模塞尔维亚的 Stopića 洞穴的访问次数。最准确的预测结果来自于包含季节性和时间序列增长趋势的 NeuralPropeth 模型。此外，使用浅层神经网络模型来建模非线性，并将 Google Trend 作为外部变量纳入模型。对于管理结构和决策者来说，建模旅游需求非常重要，因为它适用于在环境脆弱目的地（如洞穴）制定可持续旅游利用策略。该研究提供了关于塞尔维亚最繁忙洞穴 - Stopića 洞穴的游客需求的见解，并初步提供了解决游客承载力问题的数据。