GIS&RS
sayyad asghari; hamid Soleimani Youzband; Aboozar Sadeghi
Abstract
Cereals are considered one of the most important sources of dietary protein, and wheat is a significant cereal crop with high protein content. Currently, the rapid and excessive population growth and the perceived shortage of available resources to meet essential human needs are among the biggest challenges ...
Read More
Cereals are considered one of the most important sources of dietary protein, and wheat is a significant cereal crop with high protein content. Currently, the rapid and excessive population growth and the perceived shortage of available resources to meet essential human needs are among the biggest challenges facing the world. Accurate and up-to-date statistics and information on agricultural capacities form the foundation of proper planning and management in agricultural affairs.
Methods: In this study, Sentinel2-L2A satellite images were initially downloaded, and the Normalized Difference Vegetation Index (NDVI) was extracted using the set of images containing ground reflectance data. Then, the Support Vector Machine (SVM) and Random Forest classification algorithms were applied to the images using the R programming language in the Jupyter Notebook environment.
Results: Finally, it was observed that the Random Forest algorithm performed better and more appropriately, with an overall accuracy of 93% and a kappa coefficient of 87%, compared to the Support Vector Machine algorithm, which had an overall accuracy of 90% and a kappa coefficient of 82%. This preference is due to its higher accuracy and kappa coefficient, indicating a greater agreement with reality and higher prediction accuracy.
Conclusions: The results of these algorithms showed that each algorithm has its own strengths and weaknesses. The Support Vector Machine algorithm is used in many classification problems due to its simple structure and adequate performance. However, in this study, it performed weaker compared to the other algorithm, the Random Forest. The Random Forest algorithm usually provides accurate results due to its ability to combine different models and reduce the effect of overfitting. Nevertheless, its high computational complexity can be problematic in larger applications.
Geomorphology
elhame ebady; Fariba Esfandayari Darabad; sayyad Asghari; Raoof Mostafazadeh; Elham mollanuri
Abstract
One of the important conditions for optimal use of land is obtaining information about landuse patterns and their changes over time. Landuse is usually defined based on human use of land, emphasizing the role of land in economic activities. Today, remote sensing technology is considered as the main element ...
Read More
One of the important conditions for optimal use of land is obtaining information about landuse patterns and their changes over time. Landuse is usually defined based on human use of land, emphasizing the role of land in economic activities. Today, remote sensing technology is considered as the main element in landuse monitoring. The aim of the current research is to extract landuse maps for the years 2000 and 2021 in FirozabadKhalkhal region and to investigate the changes made in the studied time period in the region using the images of ETM and OLI sensors of Landsat. Also, checking the capability of basic pixel and object-oriented methods for landuse classification is another purpose of this study. In the current research, the object-oriented technique nearest neighbor algorithm and the vector machine method supporting the pixel-based algorithm have been used for landuse classification. Then, to verify the accuracy of these two methods, the overall accuracy and Kappa were extracted. The results of this evaluation show the high accuracy of the object-oriented method in extracting land use classes. Based on the results of the detection of landuse changes in the studied time period, the highest amount of changes occurred is related to the use of good pasture to poor pasture with a value of 51.72 square kilometers, followed by forest to good pasture with a value of 30.11 and the lowest changes It is related to the use of pasture and water with the amount of 0.03 square kilometers. The reasons for these changes are the increase in population, indiscriminate grazing of livestock, incorrect and illegal use of different lands. The use of more parameters such as scale, shape, compactness, color, texture, smoothness criterion and pattern for landuse classification in the object oriented technique can be considered as an innovation of the present study.
