Treffer: CROP YIELD PREDICTION USING HYBRID MACHINE LEARNING MODEL

Crop yield prediction is a crucial task forfarmers to optimize their resources and maximizeproductivity. This paper proposes a hybrid machinelearning and Internet of Things (IoT) approach for cropyield prediction that utilizes Ph, rainfall, temperature,humidity, and NPK sensors. The system combines datafrom these sensors to provide accurate predictions forcrop yield. The IoT-based data collection and processingplatform ensures real-time and accurate data collection.The proposed system utilizes machine learning modelssuch as Random Forest, Decision Tree, and ArtificialNeural Network to predict the crop yield based on thecollected sensor data. The accuracy of the proposedapproach is evaluated through experiments, which showthat it can achieve high accuracy in crop yield prediction.The results demonstrate the effectiveness of the proposedapproach in enhancing the agricultural industry'sproductivity. The proposed system can help farmers makeinformed decisions about irrigation, fertilization, andother farming practices. By using the Ph, rainfall,temperature, humidity, and NPK sensors, the system canassist in reducing the use of resources and minimizingwaste. The study concludes that the hybrid machinelearning and IoT approach with these sensors can providean efficient and effective solution for crop yieldprediction, helping farmers to optimize their resourcesand maximize their productivity. Overall, the proposedsystem has the potential to revolutionize the agricultureindustry, leading to sustainable and efficient farmingpractices. The use of the Ph, rainfall, temperature,humidity, and NPK sensors can provide more accurateand relevant data for crop yield prediction, leading tobetter decision-making and higher yields for farmers.