Light GBM Algorithm based Crop Recommendation by Weather Detection and Acquired Soil Nutrients
R Jaichandran, T. Murali Krishna, Sri Harsha Arigela, Ramakrishnan Raman, N. P. Dharani, Ashok Kumar
Abstract
A significant part of sedentary human civilization is agriculture. The crop yield will grow with the correct kind of crop planted. Systems for making recommendations can be made using a variety of machine learning techniques. According to the agricultural criteria, crop recommendations are made. With the aid of data science, a suggestion system can be given to the farmer to help him plant crops. Numerous resources might be lost in the event of quality prediction. We have applied the Light GBM Machine Learning Algorithm to address this flaw in the current system and enhance its accuracy and dependability. Based on the analysis of data sets and consideration of environmental elements and soil nutrient concentration, crop recommendations were developed. The recommendation system trustworthy. Certain measurable data, including temperature, humidity, rainfall, pH level, and soil nutrient content (N, P, and K), are taken into account in this particular kind of recommendation system. Using a third-party API, the environmental variables temperature, humidity, and air pressure are discovered. By offering solutions to crop disease predictions and offering appropriate fertilizer recommendations, this data assists in providing an accurate prediction about suitable crop growth.