Enhancing Oyster Mushroom Cultivation with Solar-Powered IoT and Machine Learning: Predicting Harvest Readiness

Abstract

The cultivation of oyster mushrooms demands skillful control over environmental conditions and timely harvesting to optimize yield as well as quality. By using the IoT system, key growth parameters — temperature, humidity, air quality, and light intensity — are monitored. Simultaneously, a machine learning framework that uses Convolutional Neural Networks (CNNs) and object detection models analyze and capture patterns related to environmental factors that influence mushroom growth stages. This offers system integration with solar power to enhance sustainability and automates the environmental monitoring and control solutions thus reducing operation costs while keeping the quality of yield at a higher level. This novel study not only speeds up the growing process but also helps predict exactly when the crop is ready to harvest. Harvesting oyster mushrooms at the right time ensures they reach the best size and weight, leading to larger yields while preserving their taste, texture, and nutritional value for customer satisfaction. Accurate predictions of harvest readiness help farmers plan better to meet market demand and increase their profits. The result of this study used a machine learning model to predict if oyster mushrooms can be harvested. The trained model achieved 85% accuracy, with 97% precision and 82% recall, resulting in an F1 score of 89%. Cohen's Kappa analysis showed a strong match between the model's predictions and the farmer's judgment, with a Kappa value of 0.654 and a p-value of 0.000, meaning the model is reliable.