Search

Floods are among the natural hazards that have seen a rapid increase in frequency in recent decades. The damage caused by floods, including human and financial losses, poses a serious threat to human life. This study evaluates two machine learning (ML) techniques for flood susceptibility mapping (FSM) in the Gamasyab watershed in Iran. We utilized random forest (RF), support vector machine (SVM), ensemble models, and a geographic information system (GIS) to predict FSM. The application of these models involved 10 effective factors in flooding, as well as 82 flood locations integrated into the GIS. The SVM and RF models were trained and tested, followed by the implementation of resampling techniques (RT) using bootstrap and subsampling methods in three repetitions. The results highlighted the importance of elevation, slope, and precipitation as primary factors influencing flood occurrence. Additionally, the ensemble model outperformed both the RF and SVM models, achieving an area under the curve (AUC) of 0.9, a correlation coefficient (COR) of 0.79, a true skill statistic (TSS) of 0.83, and a standard deviation (SD) of 0.71 in the test phase. The tested models were adapted to available input data to map the FSM across the study watershed. These findings underscore the potential of integrating an ensemble model with GIS as an effective tool for flood susceptibility mapping., (© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

Water quality experiments are difficult, costly, and time-consuming. Therefore, different modeling methods can be used as an alternative for these experiments. To achieve the research objective, geospatial artificial intelligence approaches such as the self-organizing map (SOM), artificial neural network (ANN), and co-active neuro-fuzzy inference system (CANFIS) were used to simulate groundwater quality in the Mazandaran plain in the north of Iran. Geographical information system (GIS) techniques were used as a pre-processer and post-processer. Data from 85 drinking water wells was used as secondary data and were separated into two splits of (a) 70 percent for training (60% for training and 10% for cross-validation), and (b) 30 percent for the test stage. The groundwater quality index (GWQI) and the effective water quality factors (distance from industries, groundwater depth, and transmissivity of aquifer formations) were implemented as output and input variables, respectively. Statistical indices (i.e., R squared (R-sqr) and the mean squared error (MSE)) were utilized to compare the performance of three methods. The results demonstrate the high performance of the three methods in groundwater quality simulation. However, in the test stage, CANFIS (R-sqr = 0.89) had a higher performance than the SOM (R-sqr = 0.8) and ANN (R-sqr = 0.73) methods. The tested CANFIS model was used to estimate GWQI values on the area of the plain. Finally, the groundwater quality was mapped in a GIS environment associated with CANFIS simulation. The results can be used to manage groundwater quality as well as support and contribute to the sustainable development goal (SDG)-6, SDG-11, and SDG-13. [ABSTRACT FROM AUTHOR]

Precipitation forecasting plays a key role in natural resource management, agriculture management, and water requirement provision. Hence, dendroclimatology methods and artificial neural network (ANN) are used to estimate precipitation values in the past times. Moreover, a geographic information system (GIS) can be applied as a tool to demonstrate the spatial variation of precipitation. In this study, earlywood vessel features and tree-rings of Siberian elm species were used to simulate precipitation. The vessel features, the tree-ring extent, and the secondary data of climatologic station from the different sites were studied. At first, cross-dating and standardization of the tree-rings and vessels were performed. Then, time series analysis was done. In the next step, the relations between vessel chronologies and tree-rings with the precipitation were defined. The input parameters were selected tree-ring width and vessel features for the modeling, whereas precipitation of the growing season was selected as the output. The model or network was trained and verified by taking a case study of Fomanat plain (northern part of Iran). The results showed that the combinatory usage of vessel features and tree-rings extent in precipitation simulating can increase simulation capability. Further, different isohyets were generated using the simulated precipitation values, an interpolation technique in a GIS system. The results showed that the highest precipitation and the lowest precipitation have occurred in 1926 and 1986 during the last century. [ABSTRACT FROM AUTHOR]

Soil erosion and sediment transport measurement is a time-consuming and difficult step yet important part of hydrological studies. Hence, use of models has become commonplace in estimating soil erosion and sediment transport. In this study, we used an artificial neural network (ANN) to simulate soil erosion rates. A geographic information system (GIS) was used as a pre-processor and post-processor tool to present the spatial variation of the soil erosion rate. The ANN was trained, optimized and verified using data from the Kasilian watershed located in the northern part of Iran. Field plots were used to estimate soil erosion values on the hillslopes. A Multi Layer Perceptron (MLP) network was adopted, where the soil erosion rate was the output variable and the rainfall intensity and amount, air and soil temperature, soil moisture, vegetation cover and slope were the inputs. After the training process, the network was tested. According to the test results, the ANN can estimate soil erosion with an acceptable level (coefficient of determination = 0.94, mean squared error = 0.04). The verified network and its inputs were used to estimate soil erosion rates on the hillslopes. Finally, a soil erosion rate map was generated based on the results of the verified network and GIS capabilities. The results confirm the high potential when coupling an ANN and a GIS in soil erosion estimation and mapping on the hillslopes. [ABSTRACT FROM AUTHOR]

The process of water quality testing is money/time-consuming, quite important and difficult stage for routine measurements. Therefore, use of models has become commonplace in simulating water quality. In this study, the coactive neuro-fuzzy inference system (CANFIS) was used to simulate groundwater quality. Further, geographic information system (GIS) was used as the pre-processor and post-processor tool to demonstrate spatial variation of groundwater quality. All important factors were quantified and groundwater quality index (GWQI) was developed. The proposed model was trained and validated by taking a case study of Mazandaran Plain located in northern part of Iran. The factors affecting groundwater quality were the input variables for the simulation, whereas GWQI index was the output. The developed model was validated to simulate groundwater quality. Network validation was performed via comparison between the estimated and actual GWQI values. In GIS, the study area was separated to raster format in the pixel dimensions of 1 km and also by incorporation of input data layers of the Fuzzy Network-CANFIS model; the geo-referenced layers of the effective factors in groundwater quality were earned. Therefore, numeric values of each pixel with geographical coordinates were entered to the Fuzzy Network-CANFIS model and thus simulation of groundwater quality was accessed in the study area. Finally, the simulated GWQI indices using the Fuzzy Network-CANFIS model were entered into GIS, and hence groundwater quality map (raster layer) based on the results of the network simulation was earned. The study's results confirm the high efficiency of incorporation of neuro-fuzzy techniques and GIS. It is also worth noting that the general quality of the groundwater in the most studied plain is fairly low. [ABSTRACT FROM AUTHOR]

Forest roads network is one of the main sources of sediment generation in the forest watersheds. It is difficult to estimate the sediment rate using direct methods, because of more time consuming and costs. Therefore, it is vital to use erosion and sediment models that require less time and cost. To start with, the study area (northern Iran) was selected by homogeneous units based on different digital layers such as soil texture, geology, precipitation, and topography in geographic information system and supported by extensive field surveys. Afterward, the sediment trapping wooden dams were constructed on the output culverts in homogeneous units. Next, the trapped sediments were measured in 45 wooden dams and compared with the values of estimated sediments using SEDMODL 2.0. After that, thirty wooden dam samples were used for modeling/calibration aims and the remaining 15 wooden dams were used for model validation. As a result, comparing the observed sediments with the estimated sediments by SEDMODL, it has been revealed that the mean estimated sediment rate by SEDMODL was about 8% less than the actual observation values by the direct method. Moreover, the results showed that average trapping coefficient of the sediment was about 0.25 (sediments traps on the road edges). Finally, validation results for 15 wooden dams were used to investigate the accuracy of the model. Accordingly, the results exposed an increase in model efficiency after calibration for the given forest area. To enclose, the overall results showed that SEDMODL model can contribute as a tool for a quick, accurate, and acceptable generation of estimations accommodating sediment yields. [ABSTRACT FROM AUTHOR]

Drinking water wells need to have clearly defined sanitary boundaries to ensure proper water quality. This study has been done to define these boundaries for drinking water wells in the Mazandaran plain using statistical and geographic information system (GIS) techniques. Here, an index known as the groundwater quality index (GWQI) was used to investigate the water quality. In the study area, 83 drinking water wells were selected, and for each drinking water well, the GWQI values were then estimated. Statistical analysis revealed that transmissivity of aquifer formations, groundwater depth, and distance from residential and industrial areas were significant factors on the groundwater quality. In the next step, we applied a multiple regression method using SPSS software in order to model the sanitary boundaries. Consequently, a linear model was presented to model the sanitary boundary as well as to provide the corresponding maps of these boundaries using the GIS techniques. The linear model, for each well, estimates the minimum distance from the contaminant centers that guarantees the normal GWQI values. Then, the validated model was applied in the GIS environment for zonation of the sanitary boundaries of the drinking water wells. Coupling statistical analysis with GIS technique capabilities could provide practitioners with easily interpretable water quality boundary maps in the management of these resources. [ABSTRACT FROM AUTHOR]