Serveh Darvand; Hassan Khosravi; Hamidreza Keshtkar; Gholamreza Zehtabian; Omid Rahmati
Abstract
The purpose of this study was to compare machine learning models including Support Vector Machine, Classification and Regression Tree, Random Forest, and Multivariate Discriminate Analysis to prioritize susceptible areas to dust production. To determine the dust days, hourly meteorological data of Alborz ...
Read More
The purpose of this study was to compare machine learning models including Support Vector Machine, Classification and Regression Tree, Random Forest, and Multivariate Discriminate Analysis to prioritize susceptible areas to dust production. To determine the dust days, hourly meteorological data of Alborz and Qazvin provinces and satellite images of the same days for the period 2000 to 2019 were used. 420 dust collection points were identified and the map of their distribution was prepared. The maps of factors affecting the occurrence of dust, including landuse map, soil orders map, slope map, slope aspect map, elevation map, vegetation map, topographic surface moisture, topographic surface ratio, and geology mam were prepared. Using the mentioned models, the impact of each of the effective factors of dust was determined and prioritization maps of dust harvesting areas were prepared. Models were evaluated using the ROC curve. According to the results, the elevation factor is more important in all models than the other parameters used in the model. The modeling results also showed that the Random Forest )RF( and Multivariate Discriminate Analysis (MDA) models had the highest values of accuracy (0.96), precision (0.94), Probability of Detection (POD) (0.98), and False Alarm Ratio (FAR) (0.051) compared to the others. The performance of the RF and MDA models is better than the other models, followed by the Support Vector Machine (SVM) and Classification and Regression Tree (CART) models, respectively. Also, in evaluating the models using Receiver Operating Characteristic (ROC), the RF model was selected as the best model.
Seyyed Erfan Khamoshi; Fereydoon Sarmadian; Ali Keshavarzi
Abstract
Soil is known as a dynamic media so it easily degrade with inapplicable usage so with increasing in degradation of this limited source, the world’s food safety would be in danger. Thus, applicable and sustainable usage of agricultural lands are become an essential and inevitable agenda. Therefore, ...
Read More
Soil is known as a dynamic media so it easily degrade with inapplicable usage so with increasing in degradation of this limited source, the world’s food safety would be in danger. Thus, applicable and sustainable usage of agricultural lands are become an essential and inevitable agenda. Therefore, the aim of this study is to Digital soil mapping using decision tree for agricultural land suitability, In order to constitute management programs for sustainable use of agricultural lands. For this aim, samples were collected based on cLHS and after some laboratory experiments, modeling and digital soil mapping were created by Random Forest Model. Also, agricultural land suitability for dominant crops were investigated by parametric method. The results showed that the land evaluation for irrigated wheat with surface irrigation 75.27% of the total area S2 class and 24.73% of the land in the class S3, respectively. In assessing the suitability of land for Maize irrigation, 14.78% of the land in classes S1, S2 84.82 of class and 0.39% of the land in the class S3, respectively. Results for alfalfa irrigation land evaluation showed that 11.10 percent of the land in classes S1, 88.49% in the S2 class and 0.4% of the class S3, respectively
M. Navidi; F. Sarmadian; Sh. Mahmoudi
Volume 62, Issue 2 , October 2009, , Pages 299-309
Abstract
Sustainable exploitation of land resources is directly affected by considering soil quality which finally will also conclude environmental protection. Therefore, assessing different soil quality aspects which are sensitive to various land management practices seems too important. In this study, some ...
Read More
Sustainable exploitation of land resources is directly affected by considering soil quality which finally will also conclude environmental protection. Therefore, assessing different soil quality aspects which are sensitive to various land management practices seems too important. In this study, some selected soil quality indicators have been compared in five land use systems including untouched rangelands, semi degraded rangelands due to grazing, rangelands that converted to rainfed agriculture, abandoned rainfed agriculture and an irrigated wheat farm in eastern Qazvin province, Iran. Samples were taken from the surface layer (A horizon) of soils in a completely randomized design with four replications. Statistical comparisons of the results revealed highest decrease in soil organic matter and total nitrogen owing to abandoned rainfed agriculture that showed 74% and 70% decline, respectively. Eventually the abandoned rainfed agriculture meets the sharpest slump in some soil properties such as cation exchange capacity (CEC), available phosphorous, total porosity and thickness of A horizon. Meantime the most increase in bulk density was also in recent land use. According to the results, the negative effects of inappropriate land use changes were led to soil productivity decline and will cause undesirable consequences in soil quality. So maintenance of soil quality is critical to environmental sustainability and this should be done on the basis of recognition all features that reduce its quality.