Saeed Farzaneh; Mohammad Ali Sharifi; Amir Abdolmaleki; Masood Dehvari
Abstract
Extended AbstractIntroductionSatellites in geodesy receive and transport important information. Among those, satellites with Low Earth Orbit (LEO), which are at altitudes less than 1000 km, have a significant role in the advancement of geophysical sciences such as earth’s potential field. ...
Read More
Extended AbstractIntroductionSatellites in geodesy receive and transport important information. Among those, satellites with Low Earth Orbit (LEO), which are at altitudes less than 1000 km, have a significant role in the advancement of geophysical sciences such as earth’s potential field. Many parameters have an impact on the precision and accuracy of their information. Atmospheric friction is one of the most principal forces on satellites, which may cause deviation and falling of satellite on a short period. From the beginning of aerospace missions, many efforts have been done to determine atmospheric friction by geodesists, e.g., empirical models of atmosphere neutral density. Because of the complex nature of atmosphere behavior and also data limitations, these models may have low accuracy. So, there is a need for methods to improve the accuracy of empirical models by means of combining observations of atmospheric density to predict its future state. Materials & MethodsAlong with the extension of computer science, new reliable algorithms have been introduced which are able to predict a time series; Artificial Intelligent (AI) and Neural Networks (NN) are the best of these methods. These simple algorithms are inspirations of the human brain and its ability to learn and have been used in many different scientific fields. In these techniques without any requirement for constructing complex modeling, the relation between input and output will be provided only using weight and bias vectors during the training procedure. Simple Neural Networks are memoryless meaning that the value of time-series in previous can’t be used for predicting the future value of time series and therefore some important dependency of signal values with time will be lost. A Recurrent Neural Network (RNN) has been implemented to overcome this issue. RNN’s can store some important information of the values of the time series in the previous steps in a chain-like structure and using this information for predicting the next value of time series that will improve the accuracy of prediction. In this study, the Long Short-Term Memory (LSTM) Neural Network which is a kind of Recurrent Neural Network’s has been implemented to predict the scale for correcting atmospheric density of numerical models. The data of Grace Accelerometer observation in the 6 first month of the year 2014 have been used for training the LSTM for univariate training. Also, the LSTM has been trained in multi-variants mode once with using the coefficient of atmospheric correction expansion up to degree 2 and once with using sun geomagnetic information along with information of k_p index. Results & DiscussionAfter training the LSTM network, by using the estimated parameters of the model, the zero degrees coefficient of harmonic expansion for a scale factor of correcting atmospheric density has been predicted in periods of 7, 14, 30, 60, and 90 days. The results of the univariate model show that the lower RMSE (Root Mean Square Error) is obtained about 0.054 in the period of prediction of about 14 days. Also, the results show that the multi-variants model with input data of sun geomagnetic information and k_p index has lower RMSE values in considered prediction periods compared to the other modes and the lowest RMSE is about 0.03 and belongs to the prediction of about 7 days. For evaluation of LSTM parameters in the obtained results, the predictions have been implemented with various Window sizes. The results show that by increasing windows size, the RMSE of the prediction will be reduced and the lowest RMSE was for prediction of 7 days with a window size of about 90 days. For the purpose of more evaluation, with the predicted atmospheric densities correction coefficient, the orbit of GRACE satellites has been propagated and the calculated position and velocity of satellites have been compared with the real orbit data. The results show that the lower RMSE will be provided with the prediction of 7 days with an RMSE for position and velocity of about 50 meters and 0.15 m/s respectively. ConclusionIn this study, due to the complex nature of the atmosphere, the LSTM Neural Network has been used for modeling and predict the zero-order scale for correcting atmospheric densities harmonic expansion. For training the network, the data of Grace Satellites Accelerometer in the 180 days of the year 2014 have been used. The LSTM has been in univariate and multi-variant models. In the multi-variants model, once with using the coefficient of atmospheric correction expansion up to degree two and once with using sun geomagnetic information along with information of k_p index the network have been trained. The period of prediction was considered of about 7, 14, 30, 60, and 90 days.The results show that the LSTM is capable to predict the correction coefficient in considered periods with a mean RMSE of about 0.05 for zero-order degree. Also, the results show that the lowest RMSE was for the 7 and 14 days of prediction and by increasing the window size of LSTM the RMSE will be decreased. The results of calculating the position of GRACE satellites position and velocity using predicted correction coefficients with real data show that the lowest RMSE was for prediction of 7 days for implemented method.
Ali Asghar Alesheikh; Saeed Mehri
Abstract
Extended Abstract
Introduction
Oak is a common species in Iran and the most important one in Zagros forests. Zagros forests play a crucial and effective role in water supply, soil conservation and climate modification in Iran. Unfortunately, a significant part of those forests suffer from oak decline. ...
Read More
Extended Abstract
Introduction
Oak is a common species in Iran and the most important one in Zagros forests. Zagros forests play a crucial and effective role in water supply, soil conservation and climate modification in Iran. Unfortunately, a significant part of those forests suffer from oak decline. Oak decline (or oak mortality) is a widespread phenomenon in oak forests around the world, which has gained the attention of many researchers in forestry over the past decade. In Iran, this phenomenon was first observed in Zagros forests in 2013. Factors affecting oak decline and their mutual interactions are not clearly identified, which makes understanding and modeling of these processes challenging. Only a few studies have been performed in relation to this phenomenon in Iran. Thus, we chose to determine the most effective parameters and find the best modeling method for oak decline in Iran and especially in Lorestan province.
Materials & Methods
In order to find effective environmental variables, related literature review was thoroughly investigated. Environmental parameters including temperature, precipitation, elevation, slope, direction, soil type, and amount of aerosols were selected as basic influencing parameters. All parameters were then interpolated to produce raster data with 30-meter cell resolution. To find the optimal combination of the parameters, four operators including multiplication, logarithm, hyperbolic transformations, and principal component analysis (PCA) were used. A total 385 different combinations of the influencing parameters were produced using the above mentioned operators. The relation and weight of each parameter are unknown, thus Artificial Neural Networks were used to model oak decline process. Three feed forward artificial neural network, including Back-propagation Neural Network (BP), Probabilistic neural network (PNN) and Support Vector Neural Network (SVNN) were selected as modeling methods. Then, 385 different combinations of the influencing parameters were used in the above mentioned models. To train and evaluate each neural network, a total number of 10000 samples were randomly selected from the study area. 70 percent of these random samples were used to train, 15 percent to evaluate and 15 percent to validate the models. Also, cross-validation method was used to avoid over fitting of neural networks. Finally, 1155 created NN models were compared using R parameter to find the best configuration for modeling oak decline and identifying the most influential environmental parameters in oak decline.
Results & Discussion
Evaluating 1155 different networks indicated that Probabilistic neural network (R=0.87) with 6 inputs, including 1) elevation, 2) slope, 3) direction, 4) aerosols, 5) soil type and 6) principal component of temperature and precipitation, performed better than SVNN and BP in modeling oak decline. Moreover, using different combinations of influencing factors improved the results and increased correlation coefficient (R) of optimal inputs by 0.05 as compared to initial inputs. Thus, it can be concluded that increased number of inputs does not necessarily guarantee a better performance. Furthermore, two principle parameters of temperature and perception have a more significant role in modelling drought stress as compared to other parameters.
Conclusion
Oak decline is a complicated phenomenon and different factors contribute to its occurrence. The present study investigates all environmental parameters affecting oak decline through a comprehensive literature review. Results indicate appropriate performance of probabilistic neural networks in modeling oak decline. Moreover, principal component analysis is considered to be a useful tool for modeling of drought stress in oak trees. Due to different accuracy and precision of these neural networks, it is necessary to evaluate different configurations. For further researches, it is suggested to use other parameters, such as distance from population centers, water table, age of oak trees, oak tree height and characteristics of other nearby trees.
seyyede samira jafari pour; Nazila Mohammadi
Abstract
Extended Abstract
Introduction
Ionosphere is a region of ionized plasma that extends at an altitude of 80 to 1,200 km above the earth's surface. The ionosphere consists of free electrons and ions formed during the ionization process. Total electron content (TEC) in the ionosphere is reported in TECU ...
Read More
Extended Abstract
Introduction
Ionosphere is a region of ionized plasma that extends at an altitude of 80 to 1,200 km above the earth's surface. The ionosphere consists of free electrons and ions formed during the ionization process. Total electron content (TEC) in the ionosphere is reported in TECU units. Each TECU is equivalent to 1016 electron units per square meter. Ionosphere is highly sensitive to any atmospheric turbulence, and thus is considered to be an atmospheric event sensor. The present study seeks to investigate the effect of space and temperature on the amount of total ionospheric electron content in order to accurately estimate TEC value. To reach this aim, variations in latitude and longitude are decomposed for a given period of time using the process of transforming wavelet to frequency component and modeled using a variety of artificial neural networks.
Materials and Methods
Here, after separating the location and temperature parameters in each region, ionospheric electron density is estimated for each spatial and temperature parameter separately and also as a combination using the capabilities of artificial neural networks and wavelet transform. TEC value for each location and temperature parameter is extracted from the ionospheric maps and then used as input data in the suggested method. These maps show ionospheric electron content. The standard format of ionospheric maps, which contains TEC values is called IONEX. These files are received from the website of Iranian National Mapping Agency.
Results and discussion
In general, IONEX is divided into three different parts: description, TEC maps, and standard deviations of maps. TEC values are presented in a regular network. Each IONEX file includes 25 maps, the last of which is the first map of the next day. As mentioned before, TEC value gives us a better understanding of ionospheric behavior. Availability of enough data and time coverage are two important factors in understanding a phenomenon and proper evaluation of its behavior.
Conclusion
As results of artificial neural networks indicate, MLP generally has lower RMSE values. Therefore, it gives a more accurate estimation of TEC, compared to other artificial neural networks. Also compared to artificial neural networks, a combination of artificial neural networks and wavelet shows better results. The best condition of all three methods shows that compared to other methods, temperature variations give us a better estimation of TEC in ionosphere.
Yaser Amini; Abbas Alipour; Seyyed Mostafa Hashemi; Sajjad Bagheri SeyeedShokri
Abstract
Introduction
Snow cover represents the amount of stored water, and the water from melting snow plays an important role in the formation of surface water and groundwater in the country's watersheds. Detection and determination of snow and ice different characteristics by using remote sensing data, ...
Read More
Introduction
Snow cover represents the amount of stored water, and the water from melting snow plays an important role in the formation of surface water and groundwater in the country's watersheds. Detection and determination of snow and ice different characteristics by using remote sensing data, which is widely used in hydrology, created new approaches in acquiring needed parameters in Hydrology.Results of the research show that the observations of the guesser have high potentials for detection of snowcover and the use of its data is suggested for calculating water of the equivalent snow in the areas such as Kerman Province which is facedwith the limitation of ground stations.
Materials & Methods
Since this area is able to have snow in winter, therefore the data about water equivalent to the snow in this area is necessary for many applications such as hydrology, meteorology, climatology and also producing hydroelectric and flood estimation. In this study, using brightness temperature from the Advanced Microwave Sounding Unit-A (AMSU-A), on board the NOAA satellites and the artificial neural networks as well as multiple regression techniques, the snow water equivalent forthe catchment basins of Tehran in the winter during a 10-year period (2015-2006) has been calculated and verified. In total, data from 5 monitoring stations of snow for 104 days during the study period was used for the estimation and verification.
Results & Discussion
Based on the results we obtained, the best estimate is related to the artificial neural networks with an RMSE=0/05, MSE=0/11, Bias= 0/0006 and r=0/14.The results indicate the superiority of the artificial neural networks over the regression method.
Conclusion
This results also show that, the observations of this sounding has the high potential for indicating the coverage of snow which are useful information and it is suggested to calculate snow water equivalent in the regions like Kerman where has a limited ground stations of snow measurement.
Gholamreza Latifi; Mohammad Hosein Kazemi Andaryian
Volume 21, Issue 82 , September 2012, , Pages 22-26
Abstract
The present article proposes land transformation model which consists of Geographic Information System (GIS) and Artificial Neural Networks (ANNs). This model applies varied political, social and environmental models as predictive variables. The study introduces a version of LTM model for Grand Traverse ...
Read More
The present article proposes land transformation model which consists of Geographic Information System (GIS) and Artificial Neural Networks (ANNs). This model applies varied political, social and environmental models as predictive variables. The study introduces a version of LTM model for Grand Traverse basin in Michigan gulf and shows how factors like roads, highways, and local streets, and rivers, coastlines in large lakes, entertainment facilities, inland lakes, agriculture density and landscape quality can affect urbanization pattern in coastal basin. GIS is used for understanding local patterns of development, estimating predicting capacity of the model from artificial neural network, spatial expansion of predicting stimulators, and spatial analysis. Finally, the contribution of each predicting variable is estimated and presented on a spatial scale. Landscape quality was the strongest predicting variable on the smallest scale. Multi-scale impacts of land use changes are analyzed using the relational impacts of the site (like landscape quality, local streets) and position (like highways and roads between different regions) on different scales.