Search published articles


Showing 3 results for Sensitivity

Ali Jahani,
Volume 6, Issue 2 (9-2019)
Abstract

Risks assessment of forest project implementation in spatial density changes of forest under canopy vegetation using artificial neural network modeling approach
 
Nowadays, environmental risk assessment has been defined as one of the effective in environmental planning and policy making. Considering the position and structure of vegetation on the forest floor, the main role of forest under canopy vegetation cover can be noted in attracting and preventing runoff in the forest floor and reducing subsequent environmental risks. The purpose of this article is forest under canopy vegetation density changes modeling considering forest ecosystem structure and forest management activities as an environmental risk. The main objectives of this study were to: (1) model forest under canopy vegetation density in forest ecosystem to elucidate the ecological and management factors affecting on under canopy vegetation density; (2) prioritize the impacts of model inputs (ecological and management factors) on under canopy vegetation density using model sensitivity analysis and (3) determining the trend model output changes in respond to model variables changes.
In this study, Land Management Units (LMUs) were formed in the region considering ecological characteristics of land. LMUs were mapped out based on Ian McHarg’s overlay technique by ARC GIS 9.3 software. Ecological factor classes of an LMU differ from ecological factor classes of adjacent LMUs (at least in one ecological factor class). The following types of data were solicited for each LMU:
(1) Ecological variables: Altitude or elevation (El), Slope (Sl), Aspect (As), soil depth (SD), Soil Drainage (SDr),Soil Erosion (SE), Precitipation (Pr), Temprature (Te), trees Diameter at Breast Height (DBH), Canopy Cover (CC), and forest Regeneration Cover (RC).
(2) Management variables: Cattle Density (CD), Animal husbandry Dsitance (AD), Road Dsitance (RD), Trail Dsitance (TD), logs Depot Dsitance (DD), Soil Compaction (SC), Torist impacts (To), Skidding impacts (Sk), Logging impacts (Lo), Harvested trees volume (Ha), artificial Regeneration (Re) and Seed Planting (SP).
(3) Forest under canopy vegetation density: The percentage of under canopy vegetation density in each LMU was estimated by systematic random sampling method. In each LMU, a one square meter sample was taken. The average percentage of under canopy vegetation density in sample units of each LMU was calculated and used in the modeling process.
ANN learns by examples and it can combine a large number of variables. In this study, an ANN is considered as a computer program capable of learning from samples, without requiring a prior knowledge of the relationships between parameters. To objectively evaluate the performance of the network, four different statistical indicators were used. These indicators are Mean-Squared Error (MSE), Root Mean-Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2).
Various MLFNs were designed and trained as one and two layers to find an optimal model prediction for the under canopy vegetation density and variables. Training procedure of the networks was as follows: different hidden layer neurons and arrangements were adapted to select the best production results. Altogether, many configurations with different number of hidden layers (varied between one and two), different number of neurons for each of the hidden layers, and different inter-unit connection mechanisms were designed and tested.
In this research, 129 LMUs were totally selected, then ecological and management variables were recorded in them. In the structure of artificial neural network, ecological and management variables were tagged as inputs of artificial neural network and the percentage of under canopy vegetation density was tagged as output layer. Considering trained networks (the structure of optimum artificial neural network has been summarized in Table1), Multilayer Perceptron network with one hidden layer and 4 neurons in each hidden layer created the best function of topology optimization with higher coefficient of determination of test data (which equals 0.857) and the lowest MSE and MAE (which are 0.866 and 0.736 respectively). Considering the results of sensitivity analysis, ecological and management variables like the forest canopy density, cattle density in forest, soil erosion and soil compaction respectively show the highest impact on forest under canopy vegetation density changes (Fig1).
 
Table1. The structure of optimum artificial neural network in forest under canopy vegetation density

Output Layer First Hidden Layer Network features
Linear Hyperbolic tangent Transmission Layer
Gradient descent Gradient descent Optimization Algorithm
0.7 0.7 Momentum
1 4 Number of Neurons
-0.9 up to 0.9 -0.9 up to 0.9 Normalization
 
Table2. The structure of optimum artificial neural network in test data
MSE MAE RMSE R2 Data The structure of network( the number of neurons)-epoch
0.716 0.678 0.846 0.931 Trainning Tanh(4)-160
0.793 0.703 0.891 0.894 Validation
0.866 0.736 0.931 0.857 Test

 

 
Fig1. The results of sensitivity analysis of artificial neural network model
 
Nowadays, artificial neural network modeling in natural environments has been applied successfully in many researches such as water resources management, forest sciences and environment assessment. The results of research declared that designed neural network shows high capability in forest under canopy vegetation density modeling which is applicable in forest management of studied area. Sensitivity analysis identified the most effective variables which are influencing under canopy vegetation density.
So, to identify hazardous LMUs in study area, we should pay attention to the canopy density of LMUs as the variable with high priority in determination of under canopy vegetation density. We believe that, in hazardous LMUs in forests, we should pay attention to some modifiable factors of LMU, which is cattle density in forest, by timely plan for livestock elimination. The forest under canopy vegetation density assessment model, in forest projects impact assessment, could be a solution in decision making about forest plan structure and implementation of similar projects in similar locations. 
 
Keywords: Forest plan, Environmental impact assessment, Multilayer perceptron, under canopy vegetation, artificial neural network
 


Narges Kefayati, Khalil Ghorbani, Gholam Hossein Abdollahzade,
Volume 8, Issue 2 (9-2021)
Abstract

Regional leveling of drought vulnerability in Golestan province
Narges Kefayati*1-  Khalil Ghorbani2- Gholamhossein Abdollahzadeh 3-
 
1- PhD student of irrigation and drainage, Department of Water Engineering, College  Of Water   Engineering, Gorgan University of Agricultural Sciences and Natural Resources,Gorgan,Iran. (Corresponding Author)*
2- Associated Professor, Department of Water Engineering, College  Of Water   Engineering, Gorgan University of Agricultural Sciences and Natural Resourcesm, Gorgan, Iran.
3- Associated Professor, Department of Agricultural Promotion and Training, Faculty of Agricultural Management, Gorgan University of Agricultural Sciences and Natural Resources
 
Abstract
Drought is one of the natural phenomena that causes a lot of damage to human life and natural ecosystems. In general, drought is a lack of rainfall compared to normal or what is expected, when it is longer than a season or a period of time and is insufficient to meet the needs. Drought causes damage to the agricultural sector. The vulnerability of the agricultural sector in each region depends on three factors: the degree of drought exposure, the degree of sensitivity to drought and the capacity to adapt to drought. A review of previous studies indicates the diversity of indicators and methods used to assess vulnerability, which indicates the importance of the issue. Institutions responsible for agricultural management can only manage drought properly if they have the appropriate tools to measure the vulnerability of the agricultural sector to drought. Therefore, the first step in drought studies is to identify vulnerable areas and assess the vulnerability of areas. Vulnerability measurement in geographical dimensions and measurement of indicators by main vulnerability components have received less attention. Based on this, the present study has investigated drought vulnerability in Golestan by scientific method and by combining the three mentioned components and has compared the exposure situation, sensitivity level and level of drought adaptation capacity among the cities of Golestan province. Golestan province as one of the important agricultural hubs is highly dependent on the amount of annual rainfall. Due to fluctuations in rainfall and drought in some parts of the province, there have been 4 outbreaks and as a result, 7-12 and 10 days of drought have occurred, which has caused severe damage to the livelihood of farming families. Therefore, the aim of the present study was to compare drought vulnerability among cities in Golestan province by three components (exposure, sensitivity and adaptation). First, by reviewing the sources, the effective indicators on drought vulnerability are identified separately by the three components and judged by experts (faculty members of water engineering, agriculture and plant breeding, agricultural extension and education, and agricultural economics and experts of water engineers). 55 appropriate indicators in three main dimensions of vulnerability, namely: a) exposure (14 indicators), b) sensitivity (26 indicators) and c) compatibility (17 indicators) were developed and data related to the indicators were collected. The weights of the indices were extracted by Shannon entropy model and by the TOPSIS method the combined index was compiled separately into three vulnerability components. The final result of the combined index was combined with the GIS layers of the cities of Golestan province, and the level of vulnerability of the cities was determined separately for the desired components. The results showed that in terms of exposure to Bandar-e-Gaz, Bandar-e-Turkmen and Aq Qala are in the first to third ranks, respectively, and are exposed to drought. Azadshahr, Galikesh and Bandar-e-Turkmen counties are in the first to third ranks with the highest sensitivity to drought, respectively. The cities of Gomishan, Galikesh and Maravah Tappeh are the most adapted to drought, respectively. Finally, the results of calculating the total vulnerability index showed that the cities of Marwah Tappeh and Bandar-e-Turkmen are the most vulnerable areas to drought in Golestan province. The findings of this study showed that rainy areas can be more exposed to drought at the same time than other areas and there is no direct relationship between rainfall and drought exposure. This confirms the findings of other studies such as Kramker et al. And O'Brien et al. On the other hand, the findings of this study showed that there is no direct relationship between rainfall and vulnerability to drought and the most  rainy areas of a region at the same time can be the most vulnerable to drought. This is in line with the findings of Tanzler et al. And Salvati et al. On the relationship between rainfall and drought vulnerability. Due to the fact that the rainy areas of this province are more exposed to drought than other areas and farmers in these areas have shown a higher degree of sensitivity to drought and are more vulnerable to drought than other areas, it is recommended Measures should be taken to reduce the sensitivity and increase the adaptation capacity of farmers in these areas.
 
Keywords: Drought, Vulnerability, Exposure, Sensitivity, Compatibility, Regional Leveling
Changiz Seravani, Gholamhossein Abdollahzadeh, Mohammad Sharif Sharifzadeh, Khalil Ghorbani,
Volume 8, Issue 2 (9-2021)
Abstract

Zoning map Vulnerability of Flood Spreading areas
(Case study: Musian Flood spreading station in Ilam province)
 
 
 
Introduction
One of the flood plain hazards is a change in the pattern of surface flows due to natural factors or human activities. Changes in the stream pattern are the changes that occur due to the surface stream patterns in terms of the shape of the drains, drainage form and quantitative morphological indices of the basin. These changes ,by formation of flood, submersibility, erosion, longitudinal and transverse displacements of rivers and streams, environmental degradation, etc., have a great deal of risk and harm to residents of the land adjacent to the watersheds, including the demolition of residential buildings,  valuable agriculture lands, facilities, river structures, buildings and relation routes, etc. There are several watersheds in the Musian Plain Basin that regularly change the direction of surface streams and, while displacing large volumes of sediments of erosion-sensitive structures, degrades crops, rural dwellings, connection paths, facilities, Irrigation canals obstruction, water supply and a lot of financial and physical damage to the residents of the region. Therefore, in order to solve these problems, in 1997, the Dehloran flood spreading plan was carried out at a level of 5000 hectares from the Basin of Musian Plain. Although some of the changes in the dynamics of the region, such as stream pattern, flood control, supllying groundwater aquifers, etc., have been caused by the implementation of this plan, but the problem of the concentration of watersheds behind the embankments composed of sensitive formations ,and the release of these areas will have many financial and even physical losses. Therefore, with the implementation of this research, it is attempted to identify the domain and risks that threaten the lowlands and to identify the appropriate measures to prevent them from happening with the zoning and inspection of the vulnerable areas of the Musain Plain.
 
 
Methodology
This study was conducted in five stages to prepare a vulnerability map of the flood spreading area of ​​Mosian plain. First, the implementation phases of the flood distribution plan were separated. In the second stage, information layers of effective factors in changing the flow pattern and concentration of surface currents behind the flood spreading structures were prepared. These layers included elevation, slope, and direction classes, which were prepared based on the Digital Elevation Model (DEM) extracted from the 1: 50,000 topographic maps of the Armed Forces Geographical Organization, as well as the layers of geological formations and land use changes. The lands were prepared based on the maps of the Geological Survey of Iran and the processing of Landsat satellite images of eight OLI sensors in 2013, respectively, by the method of determining educational samples. In the third stage, each class of effective factors in changing the flow pattern (mentioned layers) was given a score based on the range of zero to 10. The basis of the scores of the classes of each factor was according to the number of classes and the average of the total classes of that factor. The fourth stage in the GIS environment was created by combining the weight layers created, the vulnerability layer of the study area (quantitative map of vulnerability areas) of the basin. Then, by analyzing the vulnerability layer (filtering), the pixels and small units were removed or merged into larger units. The last (fifth) step was to classify the quantitative layer and then extract the qualitative map of the vulnerability zoning according to the range of scores based on the five very low, low, medium, severe and very severe classes. A summary of the research steps is shown in the form of a diagram.
 
Results and Discussion
The results showed that the most important threat and danger factor is the concentration of waterways behind erosion-sensitive embankments. Also, the study area in terms of vulnerability includes three classes with medium risk, high and very high and covers 16, 62 and 22% of the area, respectively. Flood and upland Spreading areas, risk areas and lowland lands are the most vulnerable parts of the basin in terms of floods and sedimentary deposits.
 
Conclusion
Based on the results obtained by combining the information layersof the factors influencing the stream pattern change, the zoning map of vulnerable areas of the region was created in 5 classes. Except for very few and very small classes that are not present in the region, there are other cases at the basin level:
Medium class:Includes about 16% of the basin. The existing watersheds in this part are ranked 1th class, and some of them are entering the rivers of Dojraj and Chiqab in the eastern and western parts. The formations of this part are often Bakhtyari and limitedly Aghajari. The floors have a height of 100 to 400 meters and the gradient is from 0-2 percent to 20 percent.
Medium class: About 62% of the basin level. The watersheds that flow in this section are in 1to 5 class. The formations of this part are often alluvial and bakhtiari of lahbori sections. It has a height of less than 100 meters to 300 meters and a gradient of 2-0 percent to 20 percent.
very intense: it covers about 22% of the basin's surface. The existing watersheds are of of class 2 and 3. The formations of this part are often alluvial and bakhtiari of lahbori sections. They have height classes of 100 to 300 meters and the gradient is 5-2 percent and is limited to 5 to 10 percent in the slopes.
 
Keywords: Vulnerability, Aquifer, zoning, Satellite imagery, Environmental hazards, Musian

Page 1 from 1     

© 2024 CC BY-NC 4.0 | Journal of Spatial Analysis Environmental hazarts

Designed & Developed by : Yektaweb