The Air/Ground cooperation for optimal rice harvesting model is established to provide a visual harvesting decision service on a cloud platform. Drones and mobile devices are employing to estimate grain moisture and forecast the variation of harvest moisture content (HMC) in the coming days by huge amounts of imagery data, deep learning algorithms, and weather forecasts. This model can benefit in several aspects, such as setting an accurate and comprehensive optimal harvest schedule, reducing the cost of agricultural apparatus and barn ovens, ensuring the rice quality, and maximizing farmers' benefits. The potential value of the model practice could be more than a billion in Taiwan.

Through massive images of UAVs and smartphones, AI technologies, such as Deep Neural Networks, Multilayer perceptron, and Random Forest, are applied to establish a water content evaluation model so to reveal HMC by a large-area non-destructive approach. Combining the air (drone) and ground (mobile devices), the HMC assessment model can be implemented on a cloud platform. By integrating weather forecast, the multi-day HMC can be predicted as an assistant reference for decision-making in remote intelligent cultivation. 

With rice paddies of 170,000 hectares in Taiwan, the profit by just reducing 3% HMC can be made up to 1.7 billion. The proposed optimal harvesting model cooperates with a cloud platform of air (UAVs) and ground (smartphones) image analysis technologies. This proposed model can provide multiple-day grain moisture content of the individual rice field, which can be displayed through friendly visualization to assist to arrange the optimized harvesting schedule, and eventually greatly increase rice quality and both farmers’ and purchasers’ profits and significantly reduce the carbon footprint.