Through IRRIGOPTIMAL® we intend to reach the following goals:

• Creation of a new integrated model driven by data and based on a Decision Support module for crop analysis.
• Optimization of product yield, improvement in quality and damage minimization (minor probability of disease, less fertilizer, less pesticides).
• Economic Savings - By optimizing the use of water, farmers can now realize the savings based on the reduced water and energy bills, fertilizers and pesticides. This allows farmers to maximise profits and can create a useful pathway for operational and capital reinvestment.

• IRRIGOPTIMAL Suite: it is a centralised Web Application hosted at WES TRADE servers where it deploys the core software solution implementing several modules including the Water Plan Prediction, Crop Monitoring, Decision Support and Disease Modules. This is the Artificial Intelligence core engine where all information incoming from a network of sensors and external services are merged, analysed and used for prediction purposes. This suite provides an extensive variety of graphs and reports to fully monitor the farms.
• Network of Sensors: there are several sensors used to collect in-situ data useful for the prediction model. The sensors include grounded data loggers, meteorological stations and other sensors which are connected to the IRRIGOPTIMAL suite through sim cards.
• Mobile App: it is a user-friendly app for the farmers containing only limited and useful information for operating irrigation with the saving plan. The online desktop version can be used by agronomists to conduct more detailed and extensive research. The IRRIGOPTIMAL suite has been designed and implemented in a way to easily operate through web-services to external applications if needed.

IRRIGOPTIMAL works for several categories of crops:

leafy crops (lettuce, spinach, cabbage, water cress, kale, etc.)

fruiting crops (cucumber, eggplant, watermelon, melon, strawberries, beans, bell peppers, tomato, etc.)

fruiting trees (citrus, grapes, apples, peach, almond, apricot, plum, banana, kiwi, mango, pistachio, walnut, cherry, etc.)

tuberous and bulbous crops (potato, sweet potato, cassava, yam, carrot, artichoke, onions, garlic, kohlrabi, etc.)

grains (wheat, barley, oat, rye, triticale, corn, etc.)

Explore the website

SOLEATECH has been funded under the PRIMA MCST-TUBITAK Program last October and will focus its research on the optimization of olive trees cultivations; in fact, in the previous years both fruitification and quality of the olive oil have dropped by far, causing great damage to the local agricultural economy.

SOLEATECH aims to achieve the following objectives:

• Integration of already consolidated studies, research, and tools to create an innovative Predictive Model based on Artificial Intelligence techniques to improve olive tree cultivation.
• Identify correlations between environmental factors (soil, climate change impacts, irrigation) with crop productivity and quality.
• Introduce Early Alerts to farmers to intervene on environmental factors to improve yield productivity while reducing the usage of pesticides, optimizing natural resources available (green approach), and reducing poorly calibrated economic practices that could induce pathogenesis in the plants themselves.
• Implement and strengthen a Knowledge Transfer between research entities that have already developed complimentary studies and collaborated to improve precision agriculture in the Mediterranean area.
• Involve respective Ministry of Agriculture (as both entities have collaborations in place with their correspondent national one) in the results disseminating achievements and solutions.
• Create a model which could be fast developed and integrated in already available respective platforms to quickly reach final users with a concrete solution.

MARINA Research will focus on the design and implementation of a Machine Learning algorithm able to predict conditions where tuna fish productivity may be impacted by factors that are cause of stress for fish using in-situ data collected by IoT sensors covering water quality, presence of microplastics and observation of fish behaviour including symptoms of fish stress.

The research shall identify correlations that may alert farmers about risks in their tuna fish productivity. The research will be carried on a live lab on open sea for the measurements of data and observations when tuna cultivations is active.

Project started last August from TRL 1 and MARINA research will target it to TRL 4 and will provide an excellent basis for the realization of an integrated system to be tested on a real scenario for higher TRLs.

Blue Drop to analyse Apparent Water Losses and Water Balance Confirmations

Apparent Water Losses (AWL) are a major source of revenue loss by water utilities and the governments that fund these utilities, with the water consumer ultimately paying the price due to resulting tariff hikes that are implemented to recuperate these losses.

The research in question shall carry out a very detailed study of Apparent Water Losses in both physical mode and in complementary simulated mode, with an aim of closely studying some three pilot zones with highly accurate instrumentation and data resolution, and then repeating and studying these values in a simulated environment. The project shall be implemented over a three-year period to allow for adequate longitudinal depth.

The main objective of the Blue Drop application is to simulate, predict and give results of water distribution network, based on algorithm deigned by Kore which is able to include presence of water tanks and transient pressure variability. One of the project challenges is develops a specific model able to identify possible apparent water losses and investigate on the effect of flow and pressure fluctuations on AWL.

Project deliverable is complete water distribution network simulation, presented in a graphical and numerical way, for each network component, providing better understanding of flow and pressure variability. User will have clear visualization in context of time and pressure oscillation, that causes water meter to lose their accuracy over time. Also, high pressure can indicate for potential burst or leakage in network. Such events can cause mass water loss and even more financial damage.

DIEM focuses on 12 research areas, each hosting individual PhD projects, all interlinked and complimentary. The ultimate goal is to build an international network of interdisciplinary scholars, organizations and institutions across sectors, all driven by a common goal: Pushing the boundaries of DLT innovation.

DIEM Consortium consists of:

• Vrije Universiteit Amsterdam (VU)
• Durham University
• Norwegian University of Science and Technology (NTNU)
• IE University
• Accenture
• Hellenic Ministry of Digital Governance
• WES Trade Ltd
• CRH Nederland BV
• Helixconnect Europe
• Kielce Technology Park
• YET