Image Processing
A. Mesri; F. Rahimi-Ajdadi; I. Bagheri
Abstract
IntroductionRice is the fourth most consumed grain worldwide. In recent years, monitoring the area under rice cultivation; as a strategic crop in Gilan province has become more important because of the uncontrolled migration of residents of the southern provinces to it. Remote sensing is one of the practical ...
Read More
IntroductionRice is the fourth most consumed grain worldwide. In recent years, monitoring the area under rice cultivation; as a strategic crop in Gilan province has become more important because of the uncontrolled migration of residents of the southern provinces to it. Remote sensing is one of the practical tools to study the trend of changes in the area under cultivation of agricultural and horticultural products on a large scale and in a short time. This technique can help policymakers to make true and timely decisions. The aim of this study is to estimate the area under rice cultivation in Kiashahr county of Gilan province.Materials and MethodsThe images of the TM sensor of Landsat 5 satellite and the OLI sensor of Landsat 8 satellite were used to prepare land use maps. First, geometric and atmospheric corrections were made to the images. Then, supervised classification using the maximum likelihood algorithm was used to prepare land use maps for each year. Seven main classes/land covers, based on the available data of the area were determined: rice-land, semi-dense forest, sparse forest, built-up area (towns and other urbanized areas), waterbody, sandy area and other areas. Then, the area of each land use was calculated by GIS, and their changes were compared.Results and DiscussionOverall accuracy and kappa coefficient of classification were 98.45% and 0.98 for 2000, 97.59% and 0.97 for 2010, and 98.72% and 0.98 for 2020, respectively. According to the results, rice land area decreased by 4.42% from 2000 to 2010. It also had a decrease of 2.64% between 2010 and 2020. In total, rice lands decreased by 6.94% between 2000 and 2020, so its area has decreased to 10311.69 hectares. This downward trend can be due to the conversion of rice land to the built-up area. The area of semi-dense forest decreased by 47.48% between 2000 and 2010, but its downward trend decreased to 26.36% between 2010 and 2020. In total, semi-dense forest area decreases by 61.32%, equal to 682.25 hectares over a period of 20 years. This is due to the uncontrolled cutting of trees and the change of land use from semi-dense forests to sparse forests and built-up areas. Also, during this period, built-up areas and sparse forests have grown by 67.94% and 18.73%, respectively. But, semi-dense forests, water bodies and sandy areas have decreased by 61.32%, 4.91% and 61.48%, respectively.ConclusionThe reduction rate in the area of rice land and semi-dense forest classes between 2010 and 2020 was lower than the ten-year period before, which can be attributed to the adoption of restrictive laws and more inspections by relevant organizations. However, the downward trends in these land uses have continued over the past decade. Meanwhile, the increase of 67.94% of built-up lands indicates that the lost lands in the forest and rice land classes have been converted into the built-up area. The rate of land-use change in the built-up class has the highest rate among the studied classes. This result indicates the need for serious attention to land-use change in the rural area more than before. Another point is that there was a growth in sparse forests between 2000 and 2010, and then a reverse trend was observed between 2010 and 2020, which shows that in a period of 10 years, deforestation has taken place, and in 10 years later, the lands from these destructions have been converted to the built-up area. As a result, serious attention to natural resource organizations is necessary. It is considered that there was a deliberate destruction of forests over time with the aim of personal profit.
F. Alipour; M. H. Aghkhani; M. H. Abbaspour-Fard; A. Sepehr
Abstract
Application of satellite imagery and remote sensing techniques in agriculture and other natural resources has been approved by many studies. In this study two ETM+ imagery data for May and September 2012 of Astan Ghods Razavi Great Farm were acquired to identify the boundaries of lands cultivated with ...
Read More
Application of satellite imagery and remote sensing techniques in agriculture and other natural resources has been approved by many studies. In this study two ETM+ imagery data for May and September 2012 of Astan Ghods Razavi Great Farm were acquired to identify the boundaries of lands cultivated with different crops coverage and to create crops maps of that farm. . To classify the images, the supervised classification methods including Maximum Likelihood and artificial neural network were used. In order to compare the results of two applied classification methods, the same training and testing samples were used. To evaluate the accuracy of classification results, the produced map was compared with the ground control points extracted by GPS and local observations. Kappa coefficient and overall accuracy were estimated to be 82% and 85%, respectively by maximum likelihood method and these outputs were estimated to be 84% and 87%, respectively by neural network approach. The difference of cultivated area estimated by maximum likelihood and by neural network methods with actual measured area was 16.8% and 14.2%, respectively. The results of this study showed that satellite imagery has high capabilities to classify and estimate agricultural and cultivated areas. These data can be useful for strategic management to develop mechanization and cultivation plans.
