ML Based Agriculture Crop Recommendation System by Monitoring Soil Condition

Agricultural yield generally depends on the level of soil fertility. Nitrogen (N), Phosphorus (P), Potassium (K), pH, the temperature of the soil, and moisture as soil chemical constituents are fundamental parameters for determining soil fertility. Good yield can easily be ensured by measuring their presence and applying the right amount of fertilizer in the right season. Most farmers do not produce good crops due to insufficient knowledge and the inability to use the proper amount of fertilizers. Current methods of measuring soil nutrients involve collecting soil from the field and transporting it to a laboratory for testing, which is often subjective and very expensive. This paper suggests an efficient IoT-based soil nutrient monitoring and machine learning-based crop recommendation system that helps farmers by offering crop- related details and recommendations for crops based on different soil and weather attributes. The proposed system deploys various types of sensors to determine soil nutrients, these sensors continuously collect the required data from the farm field and transmit it via a wireless sensor network (WSN) to a cloud database. By monitoring (N, P, K, temperature, pH, humidity, rainfall) values and analyzing the permanent and temporary behavior of the soil, the machine learning approach will recommend what types of crops have the best production potential for this land. Agriculture’s use of machine-learning technology makes it easier to select the best-yielding crops by reducing the cost of unnecessary fertilizer use, which reduces manual labor in crop and crop management and increases productivity. The most appropriate crops for that cropland are suggested using machine learning algorithms in IoT-based soil nutrient monitoring, which stores data from various soil nutrients in a database. As a result, agricultural production will contribute more to national growth.