Document Type : Original Research Paper
Authors
1 Department of Soil Sciences, Faculty of Agriculture, University of Zanjan, Zanjan. Iran
2 Department of Surveying Engineering, Faculty of Civil, Water and Environmental Engineering, Shahid Beheshti University, Tehran, Iran
3 Department of Range and Watershed Management, Faculty of Natural Resources, University of Kurdistan, Kurdistan, Iran
Abstract
Background and Objectives: Human activities and natural processes drive land use changes, resulting in pressing issues such as deforestation, biodiversity loss, and heightened vulnerability to natural disasters like floods. Population growth and increasing socio-economic demands exert substantial pressure on land use and cover, often leading to unregulated alterations primarily attributed to mismanagement in agriculture, urban development, pasturelands, and forests. Integrating remote sensing and geographic information systems (GIS) offers a potent approach to accurately assess and monitor land use changes across vast areas. Satellite data, particularly from sources like Landsat's Multispectral Scanner (MSS), Thematic Mapper (TM), and Advanced Thematic Mapper (ETM+), have been extensively utilized to analyze land use changes, especially in forested and agricultural regions. This study aims to analyze land use changes in paddy rice soil texture in Gilan, North Iran, from 1391 to 1401. Leveraging Landsat MSS and ETM+ data and GIS software, the study endeavors to identify and characterize significant land use and cover changes, providing valuable insights into regional landscape dynamics.
Methods: In this research conducted in Gilan province, Landsat-8 satellite images from 2012 and 2022, featuring minimal cloud cover, were utilized. Geometric and radiometric corrections were made on Landsat-8 satellite images to reduce errors. Employing the maximum likelihood method, supervised classification of land use classes was determined. This method calculates the probability of a pixel belonging to each predefined class and assigns the pixel to the class with the highest probability. This comprehensive approach enabled the analysis of land use dynamics in the study area, offering valuable insights into environmental changes over time.
Findings: The evaluation of land use classification maps revealed an overall accuracy of 80% and a kappa coefficient exceeding 0.8, indicating substantial agreement with ground truth classes. Forest area exploitation decreased from 46% in 2011 to 33% in 2011, signaling ecosystem degradation. Similarly, pasture land decreased from 51% in 1391 to 42% in 1401. Conversely, agricultural land witnessed significant growth, increasing by 7% from 2013 to 1401 (34% to 41%). Residential land area experienced a notable increase, rising by 34%. These findings underscore significant land use changes, including forest decline and increased residential expansion, highlighting the pressing need for sustainable land management practices in the study area.
Conclusion: Forest cover in the study area declined by 13%, whereas residential land witnessed a significant expansion of 34%. Data analysis indicated that the primary alterations in land area were linked to changes in residential use. Remote sensing technology proved instrumental in precisely, effectively, and economically estimating these changes, highlighting its crucial role in environmental studies.
Keywords
- Boosted Regression Trees Landsat-9
- Random Forest
- Sentinel-1
- Support Vector Machine
- Total Soil Nitrogen
Main Subjects
COPYRIGHTS
© 2025 The Author(s). This is an open-access article distributed under the terms and conditions of the Creative Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
)