RS
Abstract
Changes in land cover and land use due to human activities have left adverse effects on the environment. The eastern regions of Ardabil province are a clear example of this phenomenon. The purpose of this research is to analyze spatial and temporal changes in land cover and land use and its effects on ...
Read More
Changes in land cover and land use due to human activities have left adverse effects on the environment. The eastern regions of Ardabil province are a clear example of this phenomenon. The purpose of this research is to analyze spatial and temporal changes in land cover and land use and its effects on the temperature of the surface of the earth in Lake Neor. To estimate land use and land cover, random forest models (RTC), maximum likelihood model (MLC) and support vector machine (SVM) were used and the efficiency of each was estimated by the Kappa coefficient and it was observed that the SVM model has the highest Kappa coefficient (0.87) Bands 6, 5 and 10 of Landsat 8 were also used to extract the LST index, and it was observed that the western part of the lake faced an increase in the temperature of the earth's surface. During the time period of 2002, 2013 and 2022, significant changes were observed in the water area of Neor Lake and its nearby vegetation. Barren lands had the largest extent in all studied periods. Vegetation has increased by 1.04 square kilometers based on SVM model. The surface area of the lake was estimated as 3.19 square kilometers based on the MLC model in 2002. The area of the water zone in the MLC model has decreased by 1.56 square kilometers between 2002 and 2022, and this decrease is 0.67 and 0.69 square kilometers for the RTC and SVM models, respectively.
reza dehghani; hassan torabi; hojatolah younesi; babak shahinejad
Abstract
River flow prediction is one of the most important key issues in the management and planning of water resources, in particular the adoption of proper decisions in the event of floods and the occurrence of droughts. In order to predict the flow rate of rivers, various approaches have been introduced in ...
Read More
River flow prediction is one of the most important key issues in the management and planning of water resources, in particular the adoption of proper decisions in the event of floods and the occurrence of droughts. In order to predict the flow rate of rivers, various approaches have been introduced in hydrology, in which intelligent models are the most important ones. In this study the application of hybrid wavelet vector hybrid model to estimate the discharge of Kharkhe basin rivers on daily discharge statistics of hydrometric stations located upstream of dam during the statistical period (2008-2018) has been evaluated and its performance with vector machine model The backup was compared. The correlation coefficients, root mean square error, mean absolute error was used for evaluation and also comparison of the performance of models in this research. The results showed that the hybrid structures presented acceptable results in the modeling of river discharge. Comparison of models also showed that the hybrid model of support-wavelet vector machine has better performance in flow forecasting. .Overall, the results showed that using a hybrid backup vector machine model can be useful in predicting daily discharge.
Maryam Asadi; Ali Fathzadeh; Roohollah Taghizadeh Mehrjerdi
Volume 4, Issue 10 , June 2017, , Pages 121-143
Abstract
The main purpose of this study is an inquiry into the functions of daily, monthly, and annual scales of sediment data in their estimations using machine learning models. For this purpose, suspended sediment load data for three temporal, daily, monthly, and annual, scales at Ohio station, located in the ...
Read More
The main purpose of this study is an inquiry into the functions of daily, monthly, and annual scales of sediment data in their estimations using machine learning models. For this purpose, suspended sediment load data for three temporal, daily, monthly, and annual, scales at Ohio station, located in the USA, between the years of 1992 and 2014 were selected. In order to choose the best model, some machine learning base models such as artificial neural networks, error back propagation as well as radial basis function, k-nearest neighbor, M5 decision tree, Gaussian process, support vector machine (SVR), evolutionary support vector machine (ESVM), and linear regression (LR) models were run and evaluated. The results of this study showed that the k-nearest neighbor with RMSE=5.28, the data Gaussian process model with RMSE=8.7, and the Gaussian process model with a RMSE=7.2 were respectively the best models for the daily, monthly, and annual data. The comparison of the models' assessment also suggested that the predicted annual data were more accurate than the monthly and daily data.
