Using algorithmic game theory to improve supervised machine learning: A novel applicability approach in flood susceptibility mapping.

This study was carried out with the aim of applying Condorcet and Borda scoring algorithms based on Game Theory (GT) to determine flood points and Flood Susceptibility Mapping (FSM) based on Machine Learning Algorithms (MLA) including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) in the Cheshmeh-Kileh watershed, Iran. Therefore, first, FS conditioning factors including Aspect (As), Elevation (El), Euclidean distance (Euc), Forest (F), NDVI, Precipitation (P), Plan Curvature (PlC), Profile Curvature (PrC), Residential (Re), Rangeland (Rl), Slope (Sl), Stream Power Index (SPI), Topographic Position Index (TPI), and Topographic Wetness Index (TWI) were quantified in each Sub-Watershed (SW). Based on this, flood and non-flood points were identified based on both GT algorithms. In the following, MLAs including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) were used for the distributional mapping of FS. Finally, based on optimal conjunct approaches, FS maps were presented in the study watershed. Based on the results, among the conjunct algorithms in FS classification, RF-Condorcet and RF-Borda models were selected as the most optimal MLA-GT hybrid models. The upstream SWs were highly susceptible. Also, the effectiveness of NDVI and forest conditioning factors in each classification approach was high. The similarity of SW prioritization based on Condorcet algorithm with RF-Condorcet algorithm was about 86.70%. Meanwhile, the degree of similarity in RF-Borda conjunct algorithm was around 73.33%. These results showed that Condorcet algorithm had an optimal classification compared to Borda scoring algorithm.

Predicting the effect of hydro-climatic and land-use dynamic variables on watershed health status.

This study aimed to predict the impact of changing hydro-climatic variables and land use changes on the future health status of the Safaroud Watershed, northern Iran. It also sought to explore the significance of hydro-climatic and land use variables in prioritizing sub-watersheds based on the watershed health index. The study involved extracting key characteristics related to anthropogenetic, climatic, and hydrological factors for pressure, state, and response indicators. The current watershed health index was calculated, followed by predictions of watershed health based on dynamic hydro-climatic and land-use variables for the next 10 and 20 years. The Safaroud Watershed health assessment and zoning showed that the average value and standard deviation of the current pressure index were equal to 0.573 and 0.185, respectively. The lowest value of this index was around 0.290 and related to sub-watershed 5, and the highest value was around 0.840 and related to sub-watershed 11. The initial evaluation of the classification indicated the prevalence of moderate and high-pressure conditions with a range of about 79%. Finally, the physical factors of sub-watersheds (time of concentration with 15.72%) had the lowest role. In general, among the criteria used to calculate the pressure index in the current period, anthropogenetic and climatic factors showed the highest percentage of participation in determining the pressure index. The quantification of the current watershed health status and the 10- and 20-year-forecast periods showed that the values of the watershed health index were similar. However, the changes in the health index in the sub-watersheds at the beginning of the study period ranged from relatively unhealthy favorable conditions to moderately positive and moderately negative conditions.

Efficiency evaluation of low impact development practices on urban flood risk.

Urban flood risk assessment delivers invaluable information regarding flood management as well as preventing the associated risks in urban areas. The present study prepares a flood risk map and evaluate the practices of low-impact development (LID) intended to decrease the flood risk in Shiraz Municipal District 4, Fars province, Iran. So, this study investigate flood vulnerability using MCDM models and some indices, including population density, building age, socio-economic conditions, floor area ratio, literacy, the elderly population, and the number of building floors to. Then, the map of thematic layers affecting the urban flood hazard, including annual mean rainfall, land use, elevation, slope percentage, curve number, distance from channel, depth of groundwater, and channel density, was prepared in GIS. After conducting a multicollinearity test, data mining models were used to create the urban flood hazard map, and the urban flood risk map was produced using ArcGIS 10.8. The evaluation of vulnerability models was shown through the use of Boolean logic that TOPSIS and VIKOR models were effective in identifying urban flooding vulnerable areas. Data mining models were also evaluated using ROC and precision-recall curves, indicating the accuracy of the RF model. The importance of input variables was measured using Shapley value, which showed that curve number, land use, and elevation were more important in flood hazard modeling. According to the results, 37.8 percent of the area falls into high and very high categories in terms of flooding risk. The study used a stormwater management model (SWMM) to simulate node flooding and provide management scenarios for rainfall events with a return period ranging from 2 to 50 years and five rainstorm events. The use of LID practices in flood management was found to be effective for rainfall events with a return period of less than 10 years, particularly for two-year events. However, the effectiveness of LID practices decreases with an increase in the return period. By applying a combined approach to a region covering approximately 10 percent of the total area of Shiraz Municipal District 4, a reduction of 2-22.8 percent in node flooding was achieved. The analysis of data mining and MCDM models with a physical model revealed that more than 60% of flooded nodes were classified as "high" and "very high" risk categories in the RF-VIKOR and RF-TOPSIS risk models.

Watershed health and ecological security zoning throughout Iran.

Today, land degradation and the decrease in the expected services of watersheds have been mainly influenced by human-induced activities. Hence, it requires more attention to adaptively manage and provide feasible solutions to watershed disruptions. However, appropriate management of precious commodities such as water, soil, air, and vegetation cover needs insight planning on a proper scale. Nonetheless, such an integrated approach to comprehensive health assessment of watershed resources is yet to be indoctrinated by scholars, implemental agencies, managers, and policymakers. Accordingly, the present endeavor has tried to evaluate the health status of Iran's 30 second-order large watersheds with the pressure-state-response (PSR) approach. In this regard, 44 problem-oriented, influential, and, at the same time, accessible variables with compatible scales at the national level were primarily determined in climatic, hydrologic, anthropogenic, and natural sectors. The collinearity-free and independent variables were then finalized using the variance inflation factor (VIF) test. Ultimately, P, S, and R indices were calculated using the arithmetic mean of 25 normalized variables based on which PSR-based health and security indices were also mapped countrywide. The results indicated that P, S, and R indices varied from 0.49 to 0.69, 0.42 to 0.82, and 0.40 to 0.94, respectively. Health and security indices ranged from 0.46 to 0.69 and 0.30 to 0.89, respectively. The weighted mean of P, S, and R was 0.59, 0.62, and 0.67, respectively, wholly placing them in the intermediate class. The weighted health and security indices were also 0.58 and 0.59, representing the intermediate class. The results showed that study watersheds had different health and security conditions from interplaying watershed-specific factors. The results revealed the necessity of watershed-unique managerial strategies to cope with the existing unfavorable conditions at the country level. However, further insight with high resolution is recommended for the high-priority watersheds to plan implementation and executive projects.

The monetary facilities payment for ecosystem services as an approach to restore the Degraded Urmia Lake in Iran.

This study analyzed the potential use of Payment for Ecosystem Services (PES) as a strategy for improving water supply management. This study focused on the Siminehroud Sub-basin due to its high importance to the Basin of Urmia Lake (UL). Siminehroud is the second provider of water (by volume) to Urmia Lake. To evaluate the technical and economic feasibility of a PES scheme, the current land use map was extracted using satellite imagery. In addition, the two algorithms of Support Vector Machines (SVMs) and Maximum Likelihood (ML) are used for Landsat images classification, rather than analyzing the relationship between land use and ecosystem services. Then, the most relevant ecosystem services provided in the region were evaluated using the Benefit Transfer Method. In the last step, by designing and implementing a survey, on the one hand, the local farmers' Willingness to Accept (WTA) cash payments for reducing the area they cultivate, and on the other hand, the farmers' Willingness to Pay (WTP) for managing the water consumption were determined. The results illustrated that the WTA program is more acceptable among the beneficiaries. It is also notable that this program needs very high governmental funding. Furthermore, the results of the program indicate that the land area out of the cultivation cycle will gradually increase while the price of agricultural water will also increase.

'Impact of Urbanization on Temporal Distribution Pattern of Storm Runoff Coefficient.

Runoff coefficient (RC) is one of the important parameters, which is often considered in surface runoff and peak flood discharge estimation methods in various projects of watershed management and flood control. However, the effect of variability of RC due to human-induced activities on hydrologic behavior of the watershed has not been adequately considered globally. Therefore, the present research was carried out using 18 hyetographs and their corresponding hydrographs during 1984 to 2012 after considering the existence of suitable Landsat 7 (ETM+ and TM) satellite images with corresponding storm events for the Amameh Watershed located in Tehran Province, Iran. The object-oriented classification method was used to derive land use maps from satellite images. Afterward, four time periods were determined based on mean and standard deviation of residential area variations. The temporal distribution pattern of RC was then derived using a ranking method. The one- and two-way analyses of variance were also used to investigate the effect of residential area and rainfall variables on RC. Relationships among residential area as well as rainfall variables as independent variables and mean RC storm-wise as dependent variable were then modeled using two and multiple linear regressions. The results showed that RCs reduced in order of third, second, fourth, and first quartiles with respective values of 42.4, 38.2, 15.8, and 3.6%. The results also showed that RCs in the second and first quartiles and in the third and fourth quartiles were non-significantly decreased and increased by increasing of residential area, respectively. So that the highest variations occurred in first quartile with slope of - 144%. The results further proved that rainfall amount, φ index, and residential area with respective standardized regression coefficients (ß) of 0.629, - 0.465, and - 0.108 had the highest controlling effects on RCs. The finding of the current research proved the temporal variability of RCs at storm scale with more determinant effectiveness of rainfall properties than urbanized interferences. It helps hydrologists and watershed mangers designate appropriate strategies leading to proper implementations of developmental projects.

Spatial and temporal variability of soil moisture in relation with topographic and meteorological factors in south of Ardabil Province, Iran.

This research has been tried to evaluate the spatial and temporal variability of surface soil moisture (SM) in a semi-arid and cold region of Ardabil Province in Iran with an area of about 10,000 km2. The used SM data is the SMAP Enhanced L2 Radiometer Half-Orbit 9 km Soil Moisture, provided by NASA. The study area was subdivided into 120 locations consisting 10 × 12 grids, matching with the pixels of the SMAP images. In order to evaluate the spatial variations of SM, the relation of mean SM with coefficient of variation and standard deviation has been evaluated and, then, the representative location for mean SM of the area has been identified using the index of temporal stability. Moreover, the effect of topographic factors (elevation, slope, and aspect) on spatial variations of SM, and the effect of meteorological factors (rainfall, sunshine hours, temperature, relative humidity, wind speed, and number of dry days) on temporal variations of SM have been investigated. The relation of mean SM with the coefficient of variation and standard deviation represented an exponentially negative and upper convex shape, respectively. The SM content of the representative location had a correlation with the mean SM of the area with the coefficient of determination value of 0.91. Of the three topographic factors, only the slope factor, and of the meteorological factors all of them except the wind speed have showed a significant relationship with SM spatial and temporal variations respectively.