Land Suitability Assessment and Agricultural Production Sustainability Using Machine Learning Models

• Published in: Agronomy (Basel) Vol. 10; no. 4; p. 573
• Main Authors: Taghizadeh-Mehrjardi, Ruhollah, Nabiollahi, Kamal, Rasoli, Leila, Kerry, Ruth, Scholten, Thomas
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 17.04.2020
• Subjects: Agricultural land; Agricultural management; Agricultural production; Arid regions; Arid zones; artificial intelligence; Barley; Chemical properties; Climatic data; Crops; Farming systems; Flowering; Food and Agriculture Organization; Gene mapping; Gravel; Information systems; Iran; Land improvement; land suitability; Land use; Learning algorithms; Machine learning; meteorological data; Methods; parametric method; planning; Precipitation; Rain; rain-fed wheat; Rainfall; random forests; Semi arid areas; Semiarid zones; Soil analysis; Soil depth; Soil layers; Soil profiles; Soil properties; soil sampling; Soils; support vector machine; Support vector machines; Sustainability; Sustainable agriculture; Topography; Wheat; Iran; Kurdistan
• DOI: 10.3390/agronomy10040573
• ISSN: 2073-4395

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 km2 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.