Abstract: A large portion of India's population depends on agriculture as their main occupation. However, improper use of fertilizers often results in poor crop production. This paper presents a system that combines Internet of Things (IoT) and Machine Learning (ML) technologies for soil testing and intelligent crop recommendation. Sensors are used to measure parameters such as soil temperature, moisture, pH, and nutrient levels (NPK). The data collected is processed using ML algorithms, particularly Random Forest, to recommend suitable crops. Additionally, Convolutional Neural Networks (CNNs) are applied to detect plant diseases. This system minimizes soil degradation and supports farmers in making data-driven agricultural decisions.

Keywords: Soil nutrient identification, Crop suggestion, Plant pathology, NPK, IoT, Machine Learning, CNN, K-Nearest Neighbour (KNN).

| DOI: 10.17148/IARJSET.2025.12703