Agriculture Research and Innovation Hub (AGRIHUB)

Agriculture Research and Innovation Hub (AGRIHUB)

Agriculture Research and Innovation Hub (AgriHub) Logo  
​The Agricultural Research and Innovation Hub (AgriHub), within the Ministry of Agriculture, Fisheries and Animal Rights, serves as a place where researchers, innovators, and farmers, both Maltese and foreign, work together to develop new agricultural practices.

Part-financed by the European Union through the Rural Development Programme (2014-2020), the project saw its commencement in 2020. The leader for this ongoing research is the Agriculture Directorate, in collaboration with a team from the Malta College of Arts, Science and Technology (MCAST) and several scientists from the International Centre for Advanced Mediterranean Agronomic Studies, CIHEAM, Bari. Collaboration between local and international researchers is essential to create an environment of excellence that brings together people with new ideas and new knowledge.

The aim of this project is to draft, finalise, validate, and publish the first local integrated pest management (IPM) programmes for five major crops grown locally, namely tomatoes for processing, potatoes, strawberries, olives and vines. A total of 29 IPM guidelines for different crops will be finalised until the project finish date. This will provide all the necessary strategies to control pest populations and safeguard these crops. For the monitoring phase, the government has sought to invest in some of the latest technological traps available on the market.

The main principle of these traps is to facilitate the monitoring of pests. For this reason, these traps are equipped with the required technology and artificial intelligence. The traps, which are powered up by solar energy, catch pests through the use of pheromones and can determine the total count of pests caught every day and assess the severity of pest populations. Other data parameters, such as weather and soil conditions, are also fed to the system which can be accessed from the office or elsewhere via a connection. 




AgriHub Trap
AgriHub Press Launch


















As part of this project, 400 farmers took part in a technical questionnaire where they were asked numerous questions. This was done by officials from the Directorate in which they met the farmers personally and were able to ask them questions on how they manage their crops, from the day they seed until the day they harvest. Some of the questions also included which pests and pathogens the farmers face during the crop growth cycle. The purpose of this study was that through the results that came out, the experts within CIHEAM, analyzed this data and wrote the mentioned IPM guidelines to give farmers more help on how they can look after their crops more sustainably. When these 29 documents will be finalised, they will be accessible to the public and all those who wish to work in agriculture.

The Directorate is also in the process of developing computerised models (Pest Prediction Models) which will allow us to predict how certain pest populations will develop during the growing season of the crop. The five pests that are being studied for now are Tuta absoluta (susa tat-tadam), Lobesia botrana (susa tad-dwieli), Bactrocera oleae (dubbiena taż-żebbuġ), Phthorimaea operculella (susa tal-patata) and Tetranychus urticae (red spider).

Through the generation of the prediction models, the Directorate will be in a position to guide farmers on the ideal timing to take the necessary action to control the pest populations effectively and in a more sustainable manner.

Another part of the project aims to study and determine ways and methods to improve local fodder production, such as identifying the ideal crop, including its subspecies, and possibilities of silage production.

To this day, 40 farmers and entities have already participated in the monitoring phase of this project. Currently, the aim is to continue perform additional monitoring on all the mentioned pests and engage more farmers and entities to help the Directorate obtain more data, which will fine-tune the models being developed.







 
 
​​​