Nutrients are important to promote plant growth and nutrient deficiency is the primary factor limiting crop production. However, excess fertilisers can also have a negative impact on crop quality and yield, cause an increase in pollution and decrease producer profit. Hence, determining the suitable quantities of fertiliser for every crop is very useful. Currently, the agricultural systems with internet of things make very large data volumes. Exploiting agricultural Big Data will help to extract valuable information. However, designing and implementing a large scale agricultural data warehouse are very challenging. The data warehouse is a key module to build a smart crop system to make proficient agronomy recommendations. In our paper, an electronic agricultural record (EAR) is proposed to integrate many separate datasets into a unified dataset. Then, to store and manage the agricultural Big Data, we built an agricultural data warehouse based on Hive and Elasticsearch. Finally, we applied some statistical methods based on our data warehouse to extract fertiliser information such as a case study. These statistical methods propose the recommended quantities of fertiliser components across a wide range of environmental and crop management conditions, such as nitrogen (N), phosphorus (P) and potassium (K) for the top ten most popular crops in EU.

The application of digital technologies to facilitate farming activities has been on the rise in recent years. Among different tasks, the classification of weeds is a prerequisite for smart farming, and various techniques have been proposed to automatically detect weeds from images. However, many studies deal with weed images collected in the laboratory settings, and this might not be applicable to real-world scenarios. In this sense, there is still the need for robust classification systems that can be deployed in the field. In this work, we propose a practical solution to recognition of weeds exploiting two versions of EfficientNet as the recommendation engine. More importantly, to make the learning more effective, we also utilize different transfer learning strategies. The final aim is to build an expert system capable of accurately detecting weeds from lively captured images. We evaluate the approach’s performance using DeepWeeds, a real-world dataset with 17,509 images. The experimental results show that the application of EfficientNet and transfer learning on the considered dataset substantially improves the overall prediction accuracy in various settings. Through the evaluation, we also demonstrate that the conceived tool outperforms various state-of-the-art baselines. We expect that the proposed framework can be installed in robots to work on rice fields in Vietnam, allowing farmers to find and eliminate weeds in an automatic manner.