Abstract
Farmers often struggle to interpret soil test results and make optimal crop selection decisions. We developed an intel- ligent crop recommendation system that uses machine learning to analyze soil parameters and predict crops best suited to the field. The system processes measurements of nitrogen, phosphorus, potassium, pH, and organic carbon, along with environmental factors. Random Forest emerged as the best-performing model with an accuracy of 94.2%. The system bridges scientific soil analysis and practical farming decisions, helping farmers improve yield outcomes with minimal effort.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 0
Judged adjacent: soil study without a plant endpoint — claims were not extracted. This is a scope decision by the model, not a statement about the paper’s findings.