Journal of Watershed Management Research

  Flood is one of the natural hazards that causes numerous financial and life damages each year. Therefore, flood potential prioritizing is crucial to reduce the damages caused by it. The aim of this study was to evaluate the efficiency of the Analytic Hierarchy Process (AHP) in flood potential prioritizing of Barajin sub-catchments. So, flood potential of sub-catchments was determined using AHP and the results are compared with the outputs of the HEC-HMS model as observed data. The results showed that in addition to full compliance of the two maps, there is a significant correlation (0.9299 and 0.934) between flooding potential ranks and peak flood discharge ranks with the return periods of 25 and 50 years of sub-catchments. The weights of AHP were also showed that in the flood of sub-catchments, generally, hydro-climatic criteria (weight = 0.65) is more important than morphometric criteria (weight = 0.35); and the rainfall intensity is the most important sub-criteria (weight = 0.373). Based on the final ranking, sub-catchments of 5, 3, and 4 that are located in upland and mountainous areas, have high flood potential due to the high weight of tow sub-criteria, one rainfall intensity, and the other 25-years rainfall. The results of this study could be a good guide for controlling floods of the study area in addition to understanding the processes governing the watershed.

   The prediction and modeling of land use changes is important for understanding the quantity and quality of possible future changes. The purpose of this research is to monitor land use changes in the past and to investigate the possibility of predicting them in the future using the LCM model in the Beheshabad watershed of Chaharmahal va Bakhtiari province. In this study, Landsat 5 TM sensors images of 1991 and 2008 and Landsat 8 OLI sensors images in 2016 were used and analyzed. Images of all three periods were classified into five categories of range lands, urban-construction areas, agricultural lands, garden lands and Bare lands. The prediction of land use status for 2016 was carried out using user maps of 1370 and 1387 using the LCM model based on artificial neural networks and Markov chain analysis. For this purpose, the spatial variables of the distance from the pastures, the distance from the residential and urban areas, the distance from the agricultural land, the distance from the garden, the distance from the Bare Lands, distance from the river, distance from the road, elevation or digital elevation model, slope and direction of the slope, are used as factors affecting changes in artificial neural network. The results of modeling the transmission force using artificial neural network in most. of the sub-models showed high accuracy (62 to 94 percent). The total error in modeling for the year 2016 obtained approximetly 23%, which reflects the large mismatch of the predicted image of the model with the image of the Earth reality and the acceptability of the model. The prediction results for the years of 1420 and 1429 showed that the area of range land and bare lands would be reduced and the area of urbanconstruction areas, garden lands and agricultural lands would becincrease.

Extended Abstract
Introduction and Objective: Todays, considering climate change and its impact on the state of sea waves and the dangers caused by its severity, assessing and estimating the height of the significant wave in the seas is of great importance. Predicting the height of the significant wave in Amirabad port by using a combination of variables representing the characteristics of waves and meteorology, developing artificial intelligence models and de-noising the data using wavelet theory, and finally extracting the mathematical relationships governing the principles of marine-meteorological engineering to estimate altitude Wave is one of the unique goals and innovations in this study.
Material and Methods: In this study, wave height in the Caspian Sea port of Amirabad, using single and hybrid-wavelet artificial intelligence methods, including Artificial Neural Network (ANN, WANN), multilayer perceptron with the Levenberg-Margaret training algorithm, Adaptive Fuzzy-neural Inference System (ANFIS, WANFIS), and Gene Expression Programming (GEP, WGEP) in different short time lags including no time lag, 3 and 6 hour time lags is estimated. For this purpose, hourly waves and meteorological data were used in 2018.
Results: The results indicate that noise removed by wavelet analysis can improve performance in all models. Also, in this study, hybrid-wavelet models have presented better results than single models. Among all the models, the WGEP model was the best model and the ANN model was the weakest model for all time steps. The highest values of correlation coefficient and Nash-Sutcliffe efficiency coefficient are related to no time lags and WGEP model and its values are 0.960 and 0.980 and root of the mean squared error and the mean absolute value of the error values are 0.037 and 0.078 meters, respectively. The lowest values of correlation coefficient and Nash-Sutcliffe efficiency coefficient and the highest values of RMSE and MAE are related to the single ANN model for 6 hours lags with the values 0.509, 0.607, 0.181, and 0.286.
Conclusion: The results of their three single and hybrid-wavelet methods can be acceptable for estimating the significant wave height in Amirabad port. Also, disruption of observational data reduces many measurement errors and increases the performance of artificial intelligence models. This study has a significant impact on crisis and coastline management and can be a strategic model for managers, policymakers, and researchers for future research.