Integrated Environmental Assessment and Management — Volume 00, Number 00—pp. 1–11 Received: 3 March 2020 | Returned for Revision: 4 May 2020 | Accepted: 21 September 2020 1 Decision Analysis Human Activities Impact Prediction in Vegetation Diversity of Lar National Park in Iran Using Artiﬁcial Neural Network Model Ali Jahani*† and Maryam Saffariha‡ †Natural Environment and Biodiversity Department, College of Environment, Karaj, Iran ‡College of Natural Resources, University of Tehran, Tehran, Iran ABSTRACT The effects of livestock and tourism on vegetation include loss of biodiversity and in some cases species extinction. To evaluate these stressor–effect relationships and provide a tool for managing them in Iran's Lar National Park, we developed a multilayer perceptron (MLP) artiﬁcial neural network model to predict vegetation diversity related to human activities. Recreation and restricted zones were selected as sampling areas with maximum and minimum human impacts. Vegetation diversity was measured as the number of species in 210 sample plots. Twelve landform and soil variables were also recorded and used in model development. Sensitivity analyses identiﬁed human intensity class and soil moisture as the most sig- niﬁcant inputs inﬂuencing the MLP. The MLP was strong with R 2 values in training (0.91), validation (0.83), and test data sets (0.88). A graphical user interface was designed to make the MLP model accessible within an environmental decision support system tool for national park managers, thus enabling them to predict effects and develop proactive plans for managing human activities that inﬂuence vegetation diversity. Integr Environ Assess Manag 2020;00:1–11. © 2020 SETAC Keywords: Lar National Park Multilayer perceptron Decision support system Vegetation diversity INTRODUCTION Although national parks are among the most popular tourist destinations (Zhang et al. 2014) and ecotourism has positive effects on the national, regional, and local econo- mies, ecotourism may also result in negative social and ecological impacts (Brenner and Job 2012). Traditional an- imal breeding and livestock grazing on rangelands within national parks also have direct and indirect effects on veg- etation. These desires for access and economic beneﬁt can conﬂict with the desire to conserve ecology, biodiversity, and cultural values in national parks (Shirani Sarmazeh et al. 2018a, 2018b). For example, the International Union for Conservation of Nature (IUCN) considers conservation planning as a char- acteristic of conservation areas, deﬁned as follows: “a clearly deﬁned geographical space, recognized, dedicated and managed, through legal or other effective means, to achieve the long‐term conservation of nature with associated eco- system services and cultural values” (IUCN 2008). In Iran, the main goal of managing national parks is to minimize the impact of human activities such as tourism and livestock husbandry. The effects of livestock and tourism on vegetation include loss of biodiversity, deteri- oration of plant communities, reduced plant regeneration, and in some instances, species extinction (Zhong et al. 2011; Jahani, Feghhi et al. 2016). Numerous reports have shown that species richness decreases with increasing intensity of human activities in grasslands (Pourmohammad et al. 2020). Furthermore, livestock grazing and tourism can affect plant regeneration (Ballantyne and Pickering 2012; Javanmiri Pour et al. 2013) and the risk of extinction for some species (Newsome et al. 2013). For example, a comparison of the diversity and density of vegetation in the intensive recreation and restricted zones of Qamishloo National Park in Iran revealed that the average vegetation density in the restricted zone was 2.13 times higher than in the intensive recreation zone, and there was a signiﬁcant difference in diversity (Shirani Sarmazeh et al. 2018a). Also, Pongpattananurak's (2018) research on the effects of human activities on the degradation of vegetation at Thap Lan National Park, Thailand, reported that the percentage of ground vegetation and the number and density of trees were signiﬁcantly reduced in the area. It is clear that practical tools are needed to measure and predict the ecological effects of human activities on vegetation struc- ture (Marion et al. 2016; Shirani Sarmazeh et al. 2018b). In particular, methods are needed to predict the diversity of plant species in areas affected by human activities and the ecological and anthropogenic factors that inﬂuence vege- tation diversity. The main aim of the present research is to develop a mathematical model to predict vegetation di- versity under ecological conditions and human activities. Integr Environ Assess Manag 2020:1–11 © 2020 SETAC DOI: 10.1002/ieam.4349 * Address correspondence to Ajahani@ut.ac.ir Published 24 September 2020 on wileyonlinelibrary.com/journal/ieam.