Davood Jamini

The occurrence of environmental hazards, including landslides, has numerous consequences for the environment and human society. Among them, rural communities located in mountainous areas are more exposed to environmental hazards, including landslides. Rural settlements located in the Cultural Landscape of Hawraman, due to their location in the mountainous region, are no exception to the aforementioned rule and are always at risk of landslides. Given the global importance of rural settlements located in the Cultural Landscape of Hawraman, which was registered as a World Heritage Site by UNESCO in 2021, identifying rural settlements at risk of landslides can be an important step for crisis management in this region. Therefore, the main purpose of this research is to spatially analyze rural settlements at risk of landslides in western Iran, which has been carried out as a case study in the Cultural Landscape of Hawraman. In order to achieve the main objective of the research, 21 factors affecting the occurrence of landslides have been used, and the opinions of experts and researchers have been used to weight the factors. In order to achieve the main objective of the research, the fuzzy overlap approach and the two operators or and Sum have been used. The results of the study of the status of 319 rural settlements located in the Cultural Landscape of Hawraman in terms of landslide risk using the OR method showed that none of the villages in the study area were located in very low risk or medium risk zones. However, 21.7 percent of the villages (equivalent to 23 villages) were located in the low-risk zone, 31.79 percent (equivalent to 253 villages) in the high-risk zone, and 48.13 percent (equivalent to 43 villages) in the very high-risk zone. Also, the results of the Sum method in this regard showed that 2.51 percent of villages (equivalent to 8 villages) are in the very low risk zone, 14.73 percent of villages (equivalent to 47 villages) are in the low risk zone, 24.76 percent (equivalent to 79 villages) are in the medium risk zone, 35.42 percent (equivalent to 113 villages) are in the high risk zone, and 22.57 percent (equivalent to 72 villages) are in the very high risk zone in terms of landslide occurrence. The results of comparing the performance of OR and SUM methods in landslide risk zoning showed that in terms of the results obtained (percentage of area, percentage of number of villages, percentage of households and percentage of rural population located in high risk and very high-risk zones), the OR method had a stricter performance compared to the SUM method.

Flooding is one of the most frequent environmental hazards that, in addition to human and financial losses, has irreparable environmental impacts every year. The cultural landscape of Hawraman, which has been registered as a UNESCO World Heritage Site in recent years, can be prone to flood hazards due to its location in a relatively mountainous area. Since numerous rural settlements are located in this geographical space, flood risk zoning in this area can be of great help in managing this hazard in this area. Therefore, the main goal of the present study is to identify rural settlements exposed to flooding in the cultural landscape of Hawraman. In order to achieve the main goal of the study, 21 effective criteria for flooding have been used. In order to analyze spatial layers, a fuzzy overlap approach and two sum and or methods have been used. It should be noted that 377 flood points have been extracted using Sentinel radar data and in the context of the GEE system. The study of the location of 319 rural settlements using the or method showed: None of the villages in the study area are located in the very low risk zone, 0.94 percent of the villages (equivalent to 3 villages) are in the low risk zone, 21.63 percent (equivalent to 69 villages) are in the medium risk zone, 43.57 percent (equivalent to 139 villages) are in the high risk zone, and 22.55 percent (equivalent to 108 villages) are in the very high risk zone. Examining the status of all rural settlements using the sum method showed: None of the villages in the study area are located in the very low risk zone, and 27.6 percent of the villages (equivalent to 20 villages) are in the low risk zone, 41.07 percent (equivalent to 131 villages) are in the medium risk zone, 41.69 percent (equivalent to 133 villages) are in the high risk zone, and 10.97 percent (equivalent to 35 villages) are in the very high risk zone. The results of comparing the performance of or and sum methods in flood risk zoning in the cultural landscape of Hawraman showed that in terms of the criteria of percentage of area, percentage of the number of villages, percentage of households and percentage of rural population located in high risk and very high risk zones, the or method Compared with the sum method, it has a stricter performance.

Due to the positive effects of geotourism on environmental protection and various aspects of rural development, it is considered as one of the most important sustainable development strategies. For this reason, a large number of beneficiaries are looking for maximum exploitation of its benefits. Therefore, studies related to the development of geotourism can be important from different aspects. In this regard, the aim of this quantitative and applied research has been carried out with a combination of descriptive-analytical and correlational methods. The main goal is to investigate the effects of geotourism and identify factors related to it, as well as to identify obstacles and solutions for the development of geotourism in the local community, which was conducted as a case study in three villages of Yuzbashi Kandi (Kurdistan Province), Quri Qaleh (Kermanshah Province) and Ali Sadr (Hamadan Province). Hamadan province). In order to achieve the main goal of the research, 314 people were randomly selected as a statistical sample. The results of investigating the impact of geotourism on rural development showed that the average value of 3.3 was higher than the average. The results of the correlation coefficient showed that the variables of education, monthly income, main job, advertising, financial support of the public sector, financial investment of the private sector, social capital of the local community, holding training courses and active cooperation of rural managers respectively with a correlation coefficient of 0.114, 217. 0, 0.213, 0.338, 0.525, 0.504, 0.341, 0.397 and 0.193 have had a significant relationship with the dependent variable. The results of the exploratory factor analysis showed that the most important challenges for the development of geotourism from the perspective of the rural community are: Weak advertising and limited tourist accommodation (15.352 percent), weak local management and transportation infrastructure (11.576 percent), administrative limitations and weak knowledge and financial base (11.37 percent), weak marketing and diversity of destinations (429 10.00 percent), cultural-security challenges (8.294 percent) and weak health infrastructure (7.507 percent). The results of identifying the most important solutions for the development of geotourism from the point of view of the local community showed that the development and improvement of transportation infrastructure, especially the roads leading to villages, Development of advertising and marketing in order to increase tourism attraction, Construction of a parking lot in the vicinity of the caves, Development and promotion of job creation and entrepreneurship in the tourism sector, improvement and renovation of health and treatment services and facilities, are 5 important strategies that have been repeated 83, 81, 76, 74 and 64 times respectively.

In recent decades, many villagers in different parts of the world who were looking for a solution to overcome the crises caused by neglect of the agricultural sector, considering the existing capacities, took advantage of the presence of non-native people (tourists) in the villages and by combining agricultural and tourism activities, they largely overcame the existing economic challenges. However, despite the implementation of such a model in other countries, this issue has been addressed less in our country; so that in the villages studied in the present study, despite the high agricultural capacities; no comprehensive planning has been carried out in the field of tourism activities, therefore, tourism activities have been mostly of the type of mass tourism, which is irresponsible and untargeted, and its expansion has led to an increase in the demand for land purchase, and the loss of high-quality agricultural lands. The continuation of this trend brings a false economy for the villagers, and on the other hand, the sustainability of agriculture also faces serious risks. In this regard, the present study aims to identify the factors affecting the development of community-based agricultural tourism in the villages under study. The study area is selected rural areas of Kurdistan province, which have high agricultural capacities due to their geographical location, especially their specific topography. Native residents have also been engaged in these activities for a long time; and in the last decade, they have faced a very high volume of tourist arrivals. The data and information in question were collected from the rural areas of this county; five target villages (Xian, Dorud, Nashur Sofli, Dolab, and Qazneh) were selected from three counties. The statistical population includes the local community (land-owning farmers), which in the first stage, using the Cochran formula, was calculated as a sample population of 242 people for the entire village, and in the next stage, the share of each village was determined according to the population ratio. The research method used in this study is descriptive-analytical, survey-type, and the information collected using a questionnaire was analyzed using SPSS and PLS software. The findings of the study indicate that there is no pattern related to agricultural tourism in the region and there is only the pattern of daily tourism and ecotourism houses. The findings also show that the components of awareness (2.090) and participation (2.159) have the greatest impact on agricultural tourism and on the other side of the model, the social (1.17), environmental-infrastructure (13.22) and political and institutional (67.22) components have the greatest impact on CBT. Finally, to understand the situation of the studied villages, the results showed that the village of Xiyan has the most suitable situation among the selected villages studied based on CBT and the villages of Dorud and Nashur Sofli have the most suitable situation for the creation and development of community-based agricultural tourism, respectively.

Rural communities are highly dependent on their surrounding environment, especially agricultural land. For this reason, the dynamics and productivity of agricultural lands and, on the contrary, the erosion and destruction of agricultural lands, directly and indirectly affect the livelihood process and the quality of life of the rural community. According to the studies conducted, agricultural lands located in the rural settlements of Kuloche region in Bijar county are highly exposed to ditch erosion. Considering the importance of the category of resilience and identifying its determinants in empowering the rural community, in order to reduce the damage caused by various hazards such as ditch erosion, the main goal of this quantitative and applied research is to investigate the state of resilience and identify factors related to it using machine learning algorithms. which was conducted as a case study in four villages of Khanbaghi, Kuloche, Ghori Chai and Saifabad located in Kuloche area of Bijar county. The statistical population of the research includes all the household heads of the mentioned villages, among whom 150 people are considered as a statistical sample. The main tool for collecting field data is a researcher-made questionnaire, the validity and reliability of which has been confirmed by using common methods. SPSS software, IGR method and four algorithms ANN-RBF, SVM, CART and REPTree were used to analyze the collected data. The results of the research regarding the resilience of the rural community against ditch erosion showed that the resilience of 79.3% of the respondents was at very low and low levels, 1.3% at the medium level and 19.3% at the very high level. The results of the IGR method showed that the most important factors affecting the resilience of the rural community against ditch erosion in order of importance are: adaptation to environmental hazards (0.838), support institutions (0.805), agricultural policies (0.76), migration (0.743), land quality (0.724), destruction of pastures, forests and wildlife (0.722), drought and water scarcity (0.722), land use change (0.722) and the number of natural disasters occurred (0.078). The results of comparing the performance of the four used algorithms showed that the CART algorithm had the best performance in predicting the resilience of the rural community against ditch erosion.

Landslide is one of the most important natural hazards, which causes various economic, social and environmental damages. In the meantime, communities that have a higher capacity in terms of resilience suffer less damage from landslides. Therefore, identifying the determinants of resilience is an important step in improving the level of resilience and reducing damages caused by landslides. There are several rural settlements in the vicinity of the Kamiyaran - Marivan road, which are at high risk of landslides. Considering the importance of resilience in reducing damages caused by landslides, investigating the resilience of local communities living in these villages and predicting factors affecting their resilience against landslides is the main goal of this research which was conducted as a case study among the residents of four villages (Kashtar, Deagah, Tefin and Mazi Ben villages). The statistical population of the research includes 513 heads of rural households, among them, 150 are considered as a statistical sample. The main tool for data collection is a researcher-made questionnaire, whose validity and reliability have been confirmed. SPSS software and machine learning algorithms were used for data analysis. The results of the research showed that the resilience of the local community was 4%, 31.3%, 35.3%, 18.7% and 10.7%, respectively, at very low, low, medium, high and very high levels. The results of examining the importance of factors affecting resilience using the IGR method showed that the most important factors affecting resilience against landslides in order of importance are: Job satisfaction, adaptation to environmental hazards, main job, local and regional management, institutional-supportive factors, contingency, education, agricultural policies, household income, side job and damage caused by environmental hazards. The results of comparing the performance of machine learning algorithms for predicting landslide resilience based on RMSE (Root Mean Square Error) and ROC (System Performance Characteristic) criteria showed that LMT algorithm has the best performance among the investigated algorithms.

Arsenic is one of the heavy metals that can directly and indirectly pose serious threats to the environment of a region in various ways, including soil and water pollution. Bijar county is one of the geographical areas located in Kurdistan province, whose environment is in an unfavorable condition in terms of arsenic pollution. Considering the importance of resilience in dealing with all kinds of hazards, measuring the resilience of residents exposed to pollution and predicting the factors affecting resilience can play an important role in reducing the risks caused by arsenic. Therefore, the main goal of the current research is to measure and predict the resilience of communities exposed to arsenic pollution in Bijar county. The statistical population of the research consists of residents of six villages of the county (Najaf Abad, Bashuki, Ibrahim Abad, Baba Nazar, Gundok, Ali Abad), which are exposed to more arsenic pollution than other villages and among them, 150 people are considered as a statistical sample. The main research tool for data collection is a researcher-made questionnaire, whose validity and reliability have been confirmed by following the principles of field research. SPSS software and machine learning algorithms (NBTree, Bayesian network, Naïve Bayes and Random Forest) have been used for data analysis. The results of the research showed that the state of resilience in the study area of the majority of respondents (78%) is at high and very high levels. The results of examining the importance of factors affecting arsenic resistance with the IGR method showed that the most important factors affecting resistance in order of importance are: Age (0.343), education (0.271), monthly household expenses (0.232), number of unemployed (0.226), knowledge (0.181), household size (0.171), ownership of capital resources ( 0.17), contingent events (0.116) and main job (0.108). The results of comparing the performance of machine learning algorithms for predicting resilience against arsenic showed that among the investigated algorithms, the NBTree algorithm had the best performance in predicting resilience against arsenic.

Identifying the effective factors in the occurrence of fire and zoning the sensitivity to its occurrence is one of the basic tools to achieve fire control and countermeasures. Forest fire modeling is very important to identify the distribution of forest fires based on scientific methods. In this research, the Information Gain Ratio (IGR) technique and the Average Merit index were used to evaluate the predictive power of factors affecting the occurrence of forest fires in Marivan County. The results of these methods showed that among the 14 effective factors considered at the beginning, 12 factors were involved in the occurrence of fire, which include: annual average wind speed, altitude, relative humidity, precipitation, average maximum temperature , distance from the road, land use, road density, distance from residential areas, NDVI, solar radiation and slope. Also, the results showed that the two factors of slope direction and topographic humidity index were removed from the final modeling due to the mean value of merit equal to zero. Meanwhile, the variables of average wind speed, altitude and relative humidity compared to other variables had the greatest impact on the occurrence of fire. Also, after training all three applied machine learning models, including random forest models, support vector machine and logistic regression, their performance in the field of finding the potential of fire occurrence was measured using statistical criteria. Therefore, in terms of training samples, the random forest model (0.98) had higher accuracy than the support vector machine model (0.931). The value of sensitivity index in random forest and support vector machine models was 0.982 and 0.934, respectively. This means that the random forest model is able to correctly classify 1.98% of fire pixels as fire-dominated areas, which has a higher predictive power than the support vector machine model. The prepared maps were classified into five classes of very low sensitivity, low sensitivity, medium sensitivity, high sensitivity and very high sensitivity based on the Natural Breaks classification method. Also, the area and the percentage of the area of the fire potential floors were extracted for all three models. The results of all three models for the potential of fire showed that the western and southwestern parts of Marivan have a higher fire risk potential than other parts of Marivan. ROC curve method was used to validate all three models. The results showed that among the random forest model, support vector machine and logistic regression, the highest accuracy was assigned to the support vector machine model (0.997).