Mapping climate suitability index for rainfed cultivation of medicinal plants by developing an AI-based probabilistic...

Area of Science:

• Agricultural Science
• Environmental Science
• Data Science

Background:

• Climate suitability assessments are crucial for agricultural efficiency.
• Existing frameworks often rely on subjective expert judgments.
• Rainfed cultivation of medicinal plants requires precise climate suitability analysis.

Purpose of the Study:

• To develop a probabilistic framework for calculating the Climate Suitability Index (CSI).
• To identify high-potential cultivation areas for 12 medicinal plants based on climate data.
• To reduce subjectivity in suitability assessments using advanced computational methods.

Main Methods:

• Utilized frequency analysis to calculate precipitation and temperature occurrence probabilities for each plant.
• Employed Particle Swarm Optimization (PSO) for unsupervised clustering and CSI quantification.
• Integrated geographical information system (GIS) processes for spatial interpolation of climate data.

Main Results:

• Developed a novel, less subjective CSI calculation framework.
• Identified specific clusters with higher CSI values for medicinal plant cultivation in the Lake Urmia basin.
• Demonstrated the framework's applicability in an area facing water resource management challenges.

Conclusions:

• The probabilistic CSI framework enhances the identification of suitable cultivation areas.
• Optimized cultivation patterns can be achieved by leveraging CSI insights.
• This approach supports increased agricultural yields, reduced costs, and improved profitability for farmers and managers.