Publications

Mapping of soil suitability for medicinal plants using machine learning methods

Scientific Reports, 14 Feb 2024

The study aims to revive 150 vulnerable medicinal herbs by leveraging machine learning (ML) and geographic information systems (GIS). Integrating United Nations’ FAO soil datasets with geospatial data, the study employed a decision tree based model to accurately delineate 28 subregions, achieving remarkable accuracy rates of 99.01% for soil classification and 98.76% for subregion classification.

An Early Recommendation Tool to Enhance Medicinal Plant Growth based on GIS and Soil Data

IEEE Xplore, 29 Sep 2023

The research introduces a novel method using machine learning, particularly the random forest algorithm, to pinpoint ideal soil types and locations for medicinal plants in Karnataka, India. This system proposes real-time recommendations for cultivation and conservation efforts, promoting the preservation of traditional medicinal knowledge and the cultivation of herbs aligned with Ayurveda.