Showing 11 results for Linear Regression
J. Abdollahi, N. Baghestani, M.h. Saveqebi, M.h. Rahimian,
Volume 12, Issue 44 (7-2008)
Abstract
The present study discusses a method used to produce updated information about vegetation cover in arid and semi-arid zones, using RS data and GIS technique. In this method, Landsat ETM+ data in 2002 was collected in an area of about 60000 ha in Nodoushan basin, Yazd, Iran. To collect the necessary ground data, 50 sites of different vegetation types were selected and the percentage of vegetation cover in each one was determined. Also, different vegetation and soil indices were derived and crossed with located sampling points using ILWIS software capabilities. To get the best fitted curve, the relationship between vegetation cover, as a dependent variable, and satellite data bands, vegetation indices and environmental factors, as independent variables were assessed. Therefore, a multiple linear regression model was established for the prediction of vegetation cover percentage in the studied area. Finally, a vegetation cover map with high a precision was produced. As a conclusion, it can be said that mapping of vegetation cover via remote sensing is possible even if its vegetation cover is sparse.
M Noruzi, A Jalalian, Sh Ayoubi, H Khademi,
Volume 12, Issue 46 (1-2009)
Abstract
Crop yield, soil properties and erosion are strongly affected by terrain parameters. Therefore, knowledge about the effects of terrain parameters on strategic crops such as wheat production will help us with sustainable management of landscape. This study was conducted in 900ha, of Ardal district, Charmahal and Bakhtiari Province to develop regression models on wheat yield components vs. terrain parameters. Wheat yield and its components were measured in 100 points. Points were distributed randomly in stratified geomorphic surfaces. Yield components were measured by harvesting of 1 m2 plots. Terrain parameters were calculated by a 3×3 m spacing from digital elevation model. The result of descriptive statistics showed that all variables followed a normal distribution. The highest and lowest coefficient of variance (CV) was related to grain yield (0.36) and thousand seeds weight (0.13), respectively. Multiple regression models were established between yield components and terrain parameters attributes. The predictive models were validated using validation data set (20% of all data). The regression analysis revealed that wetness index and curvature were the most important attributes which explained about 45-78% of total yield components variability within the study area. The overall results indicated that topographic attributes may control a significant variability of rain-fed wheat yield. The result of validation analysis confirmed the above-stated conclusion with low RMSE and ME measures.
H Tabari, S Marofi, H Zare Abiane, R Amiri Chayjan, M Sharifi, A.m Akhondali,
Volume 13, Issue 50 (1-2010)
Abstract
In mountainous basins, snow water equivalent is usually used to evaluate water resources related to snow. In this research, based on the observed data, the snow depth and its water equivalent was studied through application of non-linear regression, artificial neural network as well as optimization of network's parameters with genetic algorithm. To this end, the estimated values by artificial neural network, neural network-genetic algorithm combined method and regression method were compared with the observed data. The field measurement were carried out in the Samsami basin in February 2006. Correlation coefficient (r) mean square error (MSE) and mean absolute error (MAE) were used to evaluate efficiency of the various models of artificial neural networks and nonlinear regression models. The results showed that artificial neural network and genetic algorithm combined methods were suitable to estimate snow water equivalent. In general, among the methods used, neural network-genetic algorithm combined method presented the best result (r= 0.84, MSE= 0.041 and MAE= 0.051). Of the parameters considered, elevation from sea level is the most important and effective to estimate snow water equivalent.
A.a Sabziparvar, H Tabari, A Aeini,
Volume 14, Issue 52 (7-2010)
Abstract
Soil temperature is one of the important variables in hydrology, agriculture, meteorology and climatology studies. Owing to the fact that soil temperature is only measured at synoptic stations, reconstruction of this variable in other places is of great importance for many relevant agricultural surveys. Using 10-year (1996-2005) daily meteorological observations, including: air temperature, global solar radiation, precipitation, relative humidity, vapor pressure, wind speed and air pressure data, different empirical relationships are suggested. At statistically significant level (P<0.05), the suggested regressions are reliable for estimating soil temperature in various depths (5, 10, 20, 30, 50 and 100 cm) and different climate types. Using soil temperature as the dependent variable and the other meteorological parameters as the independent variables, the multivariable relationships are classified accordingly. The results indicate that the impact of meteorological parameters on soil temperature is not the same. At statistically significant level (P<0.05), the mean daily air temperature presented the highest correlation coefficients with soil temperature for all climate types (on average, from R2>0.91 for warm semi-arid, to R2>0.85 for humid climates). Other results highlighted that the correlation coefficients decreased as the soil depth increased. The behavior of statistical validation criteria of the suggested relations are also discussed for all the mentioned climates.
M. Shadmani, S. Marofi,
Volume 15, Issue 55 (4-2011)
Abstract
In this research, based on the observed data of Class A pan evaporation and application of non-linear regression (NLR), artificial neural network (ANN), neuro-fuzzy (NF) as well as Stephens-Stewart (SS) methods daily evaporation of Kerman region was evaluated. In the cases of NLR, ANN and NF methods, the input variables were air temperature (T), air pressure, relative humidity (RH), solar radiation (SR) and wind speed (U2) which were used in various combinations to estimate daily pan evaporation (Ep) defined as output variable. Performance of the methods was evaluated by comparing the observed and estimated data, using determination coefficient (R2), root mean square error (RMSE) and mean absolute error (MAE). Based on the observed data at Kerman meteorological station, the monthly and annual average evaporation values of the region were 272 and 3263 mm, respectively. The results of this study indicated that NF method is the most suitable method to estimate daily Class A pan evaporation. The statistics criteria of this model which is constituted based on the 5 input parameters were R2 = 0.85, RMSE=1.61 and MAE= 1.24 mm day-1. The sensitivity analysis of NF model revealed that the estimated EP is more sensitive to T and U2 (as the input variables), respectively. Due to weak accuracy of SS method, a new modification step of the model was also developed based on the SR and T in order to have a more exact daily evaporation estimation of the region. However, the result of the modified model was not acceptable
A. Rahimikhoob, P. Saberi, S. M. Behbahani, M. H. Nazarifar,
Volume 15, Issue 56 (7-2011)
Abstract
In this study, the remote sensing statistical approach was used to determine the global solar radiation from NOAA-AVHRR satellite data in southeast of Tehran. This approach is based on the linear correlation between a satellite derived cloud index and the atmospheric transmission measured by the clearness index on the ground. A multiple linear regression model was also used to convert the five AVHRR data channels and extraterrestrial radiation to global solar radiation. The results of this study showed that multiple linear regression model estimated the solar radiation with an R2 of 0.93 and a root mean square error (RMSE) of 5.8 percent, which was better than the statistical approach.
F. Mahmoodi, R. Jafari, H. R. Karimzadeh, N. Ramezani,
Volume 19, Issue 71 (6-2015)
Abstract
This study aimed to evaluate the performance of TM satellite data acquired in June 2009 to map soil salinity in southeast of Isfahan province. Ground salinity data (EC) was collected within 9 pixels, covering an area of approximately 8100 m2 using stratified random sampling technique at 53 sample sites. Spectral indices including TM bands, BI, SI1, SI2 and SI3, PC1, PC2, PC3 and also multiple linear regression modeling and maximum likelihood classification techniques were applied to the geometrically corrected image. Results of regression analysis showed that the TM band 4 had the strongest relationship with EC data (R2=0.48) and also the relationship of the modeling image using TM 3, TM 4, TM5 and PC3 was significant at the 99% confidence level. The accuracy assessment of the stratified TM4 and modeling image into five classes including 0-4, 4-20, 20-60, 60-100 and EC>100 ds/m indicated that there was more than 86% agreement with the field measurements of EC data. Therefore, it can be concluded that the discretely classified salinity maps have higher accuracy than regression methods for identifying broad areas of saline soils, and can be used as appropriate tools to manage and combat soil salinization.
M. Isazadeh, P. Mohammadi, Y. Dinpazhoh,
Volume 21, Issue 4 (2-2018)
Abstract
Statistical analysis and forecast discharge data play an important role in management and development of water systems. The most fundamental issues of statistical analysis and forecast discharge in Iran are lack of data in long term period and lack of stream flow data in gauging stations. Considering the issues mentioned in this study, we tried to estimate the daily data flow (runoff) of Santeh gauging station in Kordestan province using the nearby hydrometric and meteorological stations data. This estimation occurred based on the sixteen different input combinations, including data of daily flow of hydrometric stations Safakhaneh and Polanian and daily runoff in Santeh precipitation gauging station. In this research, the daily flow estimation of the Santeh station in each of the months of the year was evaluated for sixteen different combinations and artificial neural network models and multiple linear regressions. The performance of each model was evaluated with the indicators RMSE, CC, NS and t-student statistic. The results showed good performance of both models but the performance of the artificial neural network model was better than the regression model in estimation of the daily runoff in the most months of the year. Mean error of artificial neural network and multiple linear regression models was respectively estimated as 6.31 and 8.07 m3/s in the months of the year. It should be noted that the artificial neural network, for each sixteen combination used, had better result than the regression model.
S. Zandifar, Z. Ebrahimikhusfi, M. Khosroshahi, M. Naeimi,
Volume 24, Issue 3 (11-2020)
Abstract
The occurrence of wind erosion and the spread of dust particles can be regarded as one of the most important and threatening environmental factors. Climate change and the frequency of droughts have played an important role in exacerbating or weakening these events. The primary objective of the present study was to investigate the trend of changes in four important climatic elements (precipitation, temperature, wind speed and relative humidity) and dust storm index (DSI) in Qazvin city using the Mann-Kendall pre-whitened test and to determine the relationship between them based on the multiple linear regression method. Assessment of the meteorological drought status based on two standardized precipitation index and standardized precipitation, as well as the evapotranspiration index and analysis of their effect on activity level of dust events, was the other objective of this study in the study area. For this purpose, after preparing and processing the climatic data and calculating the dust storm index, the trend of changes and the relationship between climatic parameters and dust events were investigated. The results showed that the changes of trend in the annual precipitation and relative humidity in Qazvin city were increasing, while the trend of annual changes in the wind speed and the mean air temperature was a decreasing one. Investigation of the monthly changes in the dust events also showed that there was a sharp decrease in the occurrence of wind erosion and the spread of domestic dust particles only in July. On a seasonal scale, with the exception of winter that has been reported without trends, in other seasons, the intensity of these events was significantly reduced. The effect of the meteorological drought on wind erosion was estimated to be 11% at the confidence level of 99%. In general, these findings indicate a decreasing trend of land degradation and desertification caused by wind erosion in Qazvin.
M. Alinezhadi, S. F. Mousavi, Kh. Hosseini,
Volume 25, Issue 1 (5-2021)
Abstract
Nowadays, the prediction of river discharge is one of the important issues in hydrology and water resources; the results of daily river discharge pattern could be used in the management of water resources and hydraulic structures and flood prediction. In this research, Gene Expression Programming (GEP), parametric Linear Regression (LR), parametric Nonlinear Regression (NLR) and non-parametric K- Nearest Neighbor (K-NN) were used to predict the average daily discharge of Karun River in Mollasani hydrometric station for the statistical period of 1967-2017. Different combinations of the recorded data were used as the input pattern to predict the mean daily river discharge. The obtained esults indicated that GEP, with R2= 0.827, RMSE= 59.45 and MAE= 26.64, had a better performance, as compared to LR, NLR and K-NN methods, at the validation stage for daily Karun River discharge prediction with 5-day lag, at the Mollasani station. Also, the performance of the models in the maximum discharge prediction showed that all models underestimated the flow discharge in most cases.
A. Ghorbani, M. Moameri, F. Dadjou, L. Andalibi,
Volume 25, Issue 2 (9-2021)
Abstract
The purpose of this study was to model biomass with soil parameters in Hir-Neur rangelands of Ardabil Province. Initially, considering the vegetation types and different classes of environmental factors, at the maximum vegetative growth stage, using one square meter plot, biomass was estimated by clipping and weighing method. For each transect, a soil sample was taken and transferred to the soil laboratory and the various parameters were measured by conventional methods. The relationship between soil factors and the rangeland biomass was analyzed and simulated using linear multiple regression. Among the measured soil factors, the Silt, EC, Ca, Ksoluble, OC, POC, pH, Mg, TNV, clay, P, and volumetric moisture had the highest effect and percentage of biomass forecast (p<0.01). The accuracy of the simulated maps was analyzed using RMSE criteria and for grasses, forbs, shrubs, and total biomass were equal to 0.81, 0.65, 0.34, and 0.46, respectively. The results of this study, not only point out the importance of soil factors on the biomass but also as a baseline data for managing rangelands, supply-demand, and carbon balance can be used in the current section.
