Crop Recommendation

Practical decision support in farming often requires two complementary capabilities: identifying crops that match local soil–weather conditions and estimating how strongly irrigation may be needed under the same conditions. This paper presents a compact machine-learning workflow that addresses both tasks using a public crop-recommendation dataset. First, a Random Forest classifier maps soil nutrients (N, P, K) and environmental measurements (temperature, humidity, pH, rainfall) to one of 22 crop classes. Second, because public data typically lacks ground-truth irrigation volumes, we define a transparent Irrigation Demand Score (IDS) that increases with thermal stress and decreases with rainfall and humidity, while mildly accounting for pH deviation and nutrient imbalance. Multiple Linear Regression is then trained to predict IDS for interpretability and low-cost deployment. On the held-out test split, the classifier achieves 98.5% accuracy, and the regression attains R2 =0.87 against the engineered score. The overall system is reproducible, lightweight, and suitable for low-instrumentation contexts, while remaining extensible to real sensor-based water measurements in future work.