Document Type : Research Paper
Authors
1
Department of Soil Science, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
2
soil science department< faculty of agricultural engineering and technology, university of Tehran
3
Department of Agricultural Machinery Engineering, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
Abstract
Introduction:
Various factors such as rising food prices, economic factors, and climate change have led to crises in different parts of the world. To address these challenges, the world needs to create organizations and develop various programs to ensure food security and reduce food waste. One important program is increasing food production without increasing the cultivated area, which requires evaluating land suitability and identifying the main obstacles to achieving maximum crop performance in each region. Land suitability assessment is an essential step in optimizing and sustainable land use planning, especially in crop rotation planning. Traditional methods of soil mapping have limitations in representing the continuous nature of soil changes. Therefore, it is necessary to use different methods to better understand the variability of land suitability classes for sustainable land management. Machine learning techniques can be used to improve land suitability analysis. Data mining methods and digital mapping attempt to identify the environmental variables that are easily accessible, the features of the soil, and the land suitability classes. Therefore, this study aimed to evaluate land suitability for sustainable agricultural production in the Abiek region of Qazvin province in northwest Iran, covering an area of 60,000 hectares.
Methods:
The study collected data from 300 soil profiles and determined land suitability classes for wheat cultivation with surface irrigation using the FAO classification system. Digital elevation models, Landsat-8 and Sentinel-2 satellite images, and environmental variables extracted from the digital elevation model were used to create digital maps using both traditional and machine learning methods. The traditional method used the FAO classification system, while the machine learning method used a classification algorithm based on environmental variables. The accuracy of both methods was evaluated using a Kappa index and overall accuracy.
Results and Discussion:
The study found that the machine learning method had a higher accuracy rate of 74% and a Kappa index of 68 compared to the traditional method with an accuracy rate of 62% and a Kappa index of 53. The most important environmental variables used in the machine learning model were those extracted from the digital elevation model and Landsat-8 satellite images. The study identified the most suitable class (S2) for wheat cultivation with surface irrigation and the least suitable class (N) in terms of land suitability. The results of this study can be used to optimize land use, promote sustainable land use, protect the environment, and ensure optimal use of natural resources in the study area. The study identified the most suitable and least suitable classes for wheat cultivation with surface irrigation, which can be used to guide land use planning and agricultural production in the region. The use of machine learning methods for land suitability analysis can be further explored in future studies.
Keywords
Main Subjects
)