Aims: In the present study, random forest (RF) and support vector machine (SVM) were used to assess the applicability of ensemble modeling in landslide susceptibility assessment across the Kolijan Rostaq Watershed in Mazandaran Province, Iran.
Materials & Methods: Both models were used in two modeling modes: 1) A solitary use (i.e., SVM and RF) and 2) Their ensemble with a bivariate statistical model named the weights of evidence (WofE) which then generated two more models, namely SVM-WofE and RF-WofE. Further, the resulting maps of each stage were dually coupled using the weighted arithmetic mean operation and an intermodal blending of the previous stages.
Findings: Accuracy of the models was assessed via the receiver operating characteristic (ROC) curves based on which the goodness-of-fit of the SVM and the SVM-WofE models were 0.817 and 0.841, respectively, while their respective prediction accuracy values were found to be 0.848 and 0.825. The goodness-of-fit of the RF and the RF-WofE models respectively was 0.9 and 0.823, while their respective prediction accuracy values were found to be 0.886 and 0.823. The goodness-of-fit and prediction power of SVM and SVM-WofE ensemble were respectively 0.859 and 0.873. The same increasing pattern was evident for the ensemble of RF and RF-WofE where their goodness-of-fit and prediction power increased, respectively, up to 0.928 and 0.873. Moreover, the goodness-of-fit and prediction power of RF-SVM ensemble were increased up to 0.932 and 0.899, respectively. The results of the averaged Kappa values throughout a 10-fold cross-validation test as an auxiliary accuracy assessment attested to the same results obtained from the ROC curves.
Conclusion: Successive intermodal ensembling approach is a simple and self-explanatory method so far as the context of many data mining techniques with a highly complex structure has been simply benefitted from the weighted averaging technique.

Introduction
With the growth of urbanization and the expansion of cities, suburban villages are influenced by their central city. The size of agricultural land is reduced, will change to residential and industrial use, and will shift to urban features, though they still have many differences with the city. In fact, the Rural Space Organization is transforming, growing and developing in a way that retains some of its traditional features and embraces many of the characteristics of urbanization. In this context, it can be said that the suburban villages are strongly influenced by the growth and development of the cities and their relations with their development, but these effects are manifested mainly in the increase of population and physical expansion of the rural settlements around the cities, and they have little to do with economic and social development within the framework of sustainable rural development. These villages usually face numerous challenges such as environmental pollution, inadequate land use allocation, excessive use of cars, unnecessary exploitation of resources, shifting the economic structure from a production-based economy to a consumer-dependent economy, weakening of village cultural customs and collapse of longstanding traditions of rural cooperation and participation, that pose many problems in achieving sustainable development of rural settlements. The growth of suburban settlements in the metropolitan area of Tehran, rather than being the result of new rural migrants or natural population growth, is the result of redistribution and relocation of the urban population within the metropolitan area of Tehran. One of the forces driving such developments is the uncontrolled policies of urban growth. The existence of such a trend demonstrates the need to plan and formulate a proper pattern for the villages in the suburbs in order to avoid sporadic and unstable growth concequences and to achieve a quality of life. However, smart growth strategy is being considered as a solution to environmental, social, economic and physical problems.
Methodology
The purpose of this study is to identify ten indices of smart growth based on the typology of rural areas of the country and to evaluate the villages around Tehran metropolis based on these indices. The general approach of this study is quantitative and data collection based on library-documentary data and field survey. Indicators of smart growth pattern matching the characteristics of rural areas of the country were identified by experts in the field of rural studies and the basis of questionnaire design was used as the main research tool in field studies. 74 indicators were finally accepted by experts in the form of ten smart growth criteria. Based on distance variables, population between 1000-1000, population growth rate above 3% and having a physical development plan, 15 villages were identified. Cronbach's alpha technique was used to measure the reliability of the research instrument and the value of 0.805 was obtained, which indicates appropriate reliability of the research instrument. To determine sample size, Cochran formula was used. Considering the size of the statistical population of the villages in the study area which is 41845 people, 378 heads of households were selected as sample population.
Results and discussion
Radar test was used to assess the intelligence level of suburban villages of Tehran metropolis.
Radar test results based on Prescott Allen's five spectrum show that the villages are in two situations; 7 villages in non-intelligent growth potential and 8 villages in potential non-intelligent growth status, and none of the villages are in medium status or smart growth. The results of one-way analysis of variance showed that there was a significant difference between all villages in terms of smart growth pattern at alpha level of 0.05. Based on the Tukey test, it was found that the villages were divided into 4 floors. The villages of Zaman Abad, Ibrahim Abad and Sarbandan are on the first floor and tend to be sparse. Chehelghaz, Rye and Nouchman ghale villages are on the second floor; Abdul Abad Ghale, Qeshlagh Mallard and Mehrabad villages are on the third floor; Bagh Kamesh, Noamlak Ghale, Kordzar, Emameh Balah and Lalan are on the fourth floor; and in trendy condition, they are on the path to smart growth.
Conclusion
Although the suburban rural areas are heavily influenced by the growth and expansion of cities and their relationships with their development path, this impact is more pronounced in terms of population growth and physical expansion of rural settlements around the cities, and less as a sign of economic and socioeconomic development. Within the framework of sustainable development, they have their own village. In this study, we tried to evaluate the suburban villages of Tehran metropolis based on the smart growth model principles. To this end, based on existing research literature on the evaluation and analysis of smart growth components with special emphasis on rural areas, 74 items in the form of 10 principles including hybrid land use, intensive development, quality housing, attractive housing, pedestrian, environmental quality, optimized transportation, internal development, social participation and economic investment were designed and analyzed.
It can be deduced from the results of radar test and Alcan Prescott intelligence levels segmentation, that the villages under study are in no way in the position of a smart growth and potential smart growth (good) model and the process of rural development is more sprawl and potential dispersed growth (weak). Therefore, it can be said that the smart growth paradigm in the study areas has not returned to its position as a spatial strategy in regional and local planning policies, and is more susceptible to change, unintended and dispersed growth due to Tehran metropolitan policies and programs