Digitalisation is widely regarded as having the potential to provide productivity and sustainability gains for the agricultural sector. However, there are likely to be broader implications arising from the digitalisation of agricultural innovation systems. Agricultural knowledge and advice networks are important components of agricultural innovation systems that have the potential to be digitally disrupted. In this paper, we review trends within agricultural knowledge and advice networks both internationally and in Australia, to anticipate and prepare for potential transformations in these networks. Through a combined structured and traditional review of relevant literature, we come to three key conclusions regarding the state-of-the-art. First, the connectivity of humans and technologies in agricultural knowledge and advice networks and value chains will likely continue to increase. Second, transparency of agricultural practices and informational interaction between farmers, advisors, agri-businesses, consumers and regulators will drive and be driven by growing connectivity. Finally, there are likely to be challenges balancing the priorities of various agricultural stakeholders as agricultural innovation systems digitalise. These findings have implications for the oversight of international agri-food sectors.
In order to monitor the working states and working environment of agricultural machinery in real time, an intelligent monitoring system based on I.MX6 is developed in this paper. Through USB, CAN and RS485, the environment videos, positions and working states of agricultural machinery are collected. The working environment information and the depth of obstacles are obtained through Intel D4 VPU (vision processing unit). The monitoring datum and videos are transmitted to the cloud server through 3G/4G module. Experimental results show that the system can effectively monitor the working states of agricultural machinery, and can identify the working environment information and obstacles in real time.
[前沿资讯] How can robotics startups respond to the urgent need for automation in the food industry? 进入全文
Another week, another part of the agrifood supply chain that’s struggling from the impact of the Covid-19 pandemic. Last month, the challenge facing the meat industry was top of the headlines, as large processing plants were forced to shut after numerous workers contracted the virus. This month, we’re seeing whole workforces in the produce industry come down with the virus, threatening the summer harvest of fruits and vegetables. Other parts of the world are experiencing similar labor shortages; the #PickforBritain campaign in the UK is a case in point. But labor shortages are nothing new for agriculture — the West Coast of the US has been struggling with this challenge for years; Covid-19 is merely exacerbating this existing problem. Is it sustainable and efficient to import labor from other countries like the US and the UK do? The time for automation in the food and agriculture industry is now. But are the robots ready to be unleashed? If venture capital funding is any indication of progress, the answer is probably no.
[学术文献] Onsite nutritional diagnosis of tea plants using micro near-infrared spectrometer coupled with chemometrics 进入全文
Computers and Electronics in Agriculture
A rapid and accurate diagnosis of nutritional status in field crops is crucial for site-specific fertilizer management. The micro near-infrared spectrometer (Micro-NIRS) is an extremely portable optical device that can be connected to a smartphone through a Bluetooth connection. In this study, a Micro-NIRS was used to evaluate pigment contents, namely chlorophyll a (Chl-a), chlorophyll b (Chl-b), and carotenoid (Car) in two varieties of field tea plants. A variable combination population analysis (VCPA), genetic algorithm (GA), and VCPA-GA hybrid strategy were used to select characteristic wavelengths; a partial least squares regression (PLSR) algorithm was employed for modeling. Results indicated that the simplified VCPA-GA-PLSR models provided the most favorable performance among all models for Chl-a, Chl-b, and Car content prediction; the correlation coefficients in prediction (Rps) were 0.9226, 0.9006, and 0.8313, respectively; the root mean square errors in prediction (RMSEPs) were 0.0952, 0.0771, and 0.0373 mg/g, respectively; the relative prediction deviations (RPDs) were 2.55, 1.92, and 1.79, respectively. Extracted characteristic variables occupied <13.63% of full spectra. The current work provided a useful example for implementing a smartphone-based Micro-NIRS system that can diagnose plant nutrition rapidly, nondestructively, and at low cost.