Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models
Land suitability assessment is essential for increasing production and planning a sustainable agricultural system, but such information is commonly scarce in the semi-arid regions of Iran. Therefore, our aim is to assess land suitability for two main crops (i.e., rain-fed wheat and barley) based on...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/10/4/573 |
| _version_ | 1797570413861011456 |
|---|---|
| author | Ruhollah Taghizadeh-Mehrjardi Kamal Nabiollahi Leila Rasoli Ruth Kerry Thomas Scholten |
| author_facet | Ruhollah Taghizadeh-Mehrjardi Kamal Nabiollahi Leila Rasoli Ruth Kerry Thomas Scholten |
| author_sort | Ruhollah Taghizadeh-Mehrjardi |
| collection | DOAJ |
| description | Land suitability assessment is essential for increasing production and planning a sustainable agricultural system, but such information is commonly scarce in the semi-arid regions of Iran. Therefore, our aim is to assess land suitability for two main crops (i.e., rain-fed wheat and barley) based on the Food and Agriculture Organization (FAO) “land suitability assessment framework” for 65 km<sup>2</sup> of agricultural land in Kurdistan province, Iran. Soil samples were collected from genetic layers of 100 soil profiles and the physical-chemical properties of the soil samples were analyzed. Topography and climate data were also recorded. After calculating the land suitability classes for the two crops, they were mapped using machine learning (ML) and traditional approaches. The maps predicted by the two approaches revealed notable differences. For example, in the case of rain-fed wheat, results showed the higher accuracy of ML-based land suitability maps compared to the maps obtained by traditional approach. Furthermore, the findings indicated that the areas with classes of N2 (≈18%↑) and S3 (≈28%↑) were higher and area with the class N1 (≈24%↓) was less predicted in the traditional approach compared to the ML-based approach. The major limitations of the study area were rainfall at the flowering stage, severe slopes, shallow soil depth, high pH, and large gravel content. Therefore, to increase production and create a sustainable agricultural system, land improvement operations are suggested. |
| first_indexed | 2024-03-10T20:25:15Z |
| format | Article |
| id | doaj.art-84f719cf0a2549d0a85bdce76ed12a97 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T20:25:15Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-84f719cf0a2549d0a85bdce76ed12a972023-11-19T21:53:24ZengMDPI AGAgronomy2073-43952020-04-0110457310.3390/agronomy10040573Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning ModelsRuhollah Taghizadeh-Mehrjardi0Kamal Nabiollahi1Leila Rasoli2Ruth Kerry3Thomas Scholten4Department of Geosciences, Soil Science and Geomorphology, University of Tübingen, 72070 Tübingen, GermanyDepartment of Soil Science and Engineering, Faculty of Agriculture, University of Kurdistan, Sanandaj 6617715175, IranDepartment of Soil Science and Engineering, Faculty of Agriculture, University of Kurdistan, Sanandaj 6617715175, IranDepartment of Geography, Brigham Young University, Provo, UT 84602, USADepartment of Geosciences, Soil Science and Geomorphology, University of Tübingen, 72070 Tübingen, GermanyLand suitability assessment is essential for increasing production and planning a sustainable agricultural system, but such information is commonly scarce in the semi-arid regions of Iran. Therefore, our aim is to assess land suitability for two main crops (i.e., rain-fed wheat and barley) based on the Food and Agriculture Organization (FAO) “land suitability assessment framework” for 65 km<sup>2</sup> of agricultural land in Kurdistan province, Iran. Soil samples were collected from genetic layers of 100 soil profiles and the physical-chemical properties of the soil samples were analyzed. Topography and climate data were also recorded. After calculating the land suitability classes for the two crops, they were mapped using machine learning (ML) and traditional approaches. The maps predicted by the two approaches revealed notable differences. For example, in the case of rain-fed wheat, results showed the higher accuracy of ML-based land suitability maps compared to the maps obtained by traditional approach. Furthermore, the findings indicated that the areas with classes of N2 (≈18%↑) and S3 (≈28%↑) were higher and area with the class N1 (≈24%↓) was less predicted in the traditional approach compared to the ML-based approach. The major limitations of the study area were rainfall at the flowering stage, severe slopes, shallow soil depth, high pH, and large gravel content. Therefore, to increase production and create a sustainable agricultural system, land improvement operations are suggested.https://www.mdpi.com/2073-4395/10/4/573random forestssupport vector machineparametric methodrain-fed wheatbarley |
| spellingShingle | Ruhollah Taghizadeh-Mehrjardi Kamal Nabiollahi Leila Rasoli Ruth Kerry Thomas Scholten Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models Agronomy random forests support vector machine parametric method rain-fed wheat barley |
| title | Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models |
| title_full | Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models |
| title_fullStr | Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models |
| title_full_unstemmed | Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models |
| title_short | Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models |
| title_sort | land suitability assessment and agricultural production sustainability using machine learning models |
| topic | random forests support vector machine parametric method rain-fed wheat barley |
| url | https://www.mdpi.com/2073-4395/10/4/573 |
| work_keys_str_mv | AT ruhollahtaghizadehmehrjardi landsuitabilityassessmentandagriculturalproductionsustainabilityusingmachinelearningmodels AT kamalnabiollahi landsuitabilityassessmentandagriculturalproductionsustainabilityusingmachinelearningmodels AT leilarasoli landsuitabilityassessmentandagriculturalproductionsustainabilityusingmachinelearningmodels AT ruthkerry landsuitabilityassessmentandagriculturalproductionsustainabilityusingmachinelearningmodels AT thomasscholten landsuitabilityassessmentandagriculturalproductionsustainabilityusingmachinelearningmodels |