Enhancing Mediterranean olive farming resilience: The SOLEATECH project

SOLEATECH project utilises AI to enhance Mediterranean olive farming, addressing climate challenges and fostering sustainability

SOLEATECH represents a significant step forward in addressing the complex challenges facing Mediterranean olive farming.
SOLEATECH represents a significant step forward in addressing the complex challenges facing Mediterranean olive farming.

The SOLEATECH project aims to advance technological research in Mediterranean olive farming to bolster productivity, efficiency, and sustainability amid challenges posed by climate change. This article outlines the project’s objectives, methodology, and unique contributions, highlighting its significance in improving soil management, predicting crop yields, and mitigating environmental impacts through AI-driven decision support systems.

SOLEATECH has been awarded under the PRIMA MCST-TUBITAK 2023 Joint Call For R&I Proposals, and, starting last December, will be carried on for two years by the Turkish Bahçeşehir University, Faculty of Engineering and Natural Sciences, and the Maltese company WES TRADE, in continuity with the already existing collaboration agreement among the parties and the current activities already in place in the application of Artificial Intelligence to Agriculture.

The cultivation of olive trees is a cornerstone of agriculture in the Mediterranean region. However, escalating climate change impacts, including water scarcity, soil degradation, and energy constraints, threaten the livelihoods of olive farmers. The SOLEATECH project responds to these challenges by harnessing technology to develop innovative solutions for sustainable olive farming.

In machine learning, statistical and mathematical methods are used to learn from datasets to make data-driven predictions/ decisions. The unsupervised learning algorithms such as Artificial Neural Network (ANNs), clustering, genetic algorithm, and deep learning and use unlabeled datasets enable the use of the input and output variables without previous knowledge about them.

Machine learning algorithms are significant as they enable us to anticipate efficient solutions, by helping the farmers and stakeholders to enhance their decisions by adopting sustainable agricultural practices. These comprise crucial choices, especially the use of digital technologies including Internet of things (IoT), Artificial Intelligence (AI), and cloud computing. This study focuses on the specific application of olive trees.

The dynamics of olive ripening will be investigated by combining the climate data in addition to the real-time sensor information coming from IRRIGOPTIMAL system - developed by WES TRADE team - which considers a set of predefined data provided by agronomists and weather forecasts.

The data gathered from the sensors will be used as the input for the Decision Support System based on decision making, to overcome the negative effects of the Climate Change and protect the olive trees and their products, while the qualitative characteristics of the olives and olive oil will be examined through the ANN Preventive Model – developed by the Bahçeşehir University experts.

SOLEATECH represents a significant step forward in addressing the complex challenges facing Mediterranean olive farming, by enhancing resilience through technology-driven solutions, the project offers practical tools for farmers to adapt to changing environmental conditions. The comparative analysis underscores the project’s unique contributions and potential for broader adoption across Mediterranean regions.

Collaboration with stakeholders and expansion into additional Mediterranean regions will further validate the project’s effectiveness and foster broader adoption.

SOLEATECH is part-financed by the Malta Council for Science and Technology and the Scientific Technological Research Council of Türkiye (TÜBİTAK) through the MCST- TÜBİTAK 2023 Joint Call for R&I projects. This initiative is part of the PRIMA Programme supported by the European Union