Greece: Intelligent system to monitor health of olive groves
Verticillium wilt is a major problem for olive growth and very difficult to detect at early stages of infestation. The project MyOliveGroveCoach has been launched to develop an intelligent system that will monitor olive groves and support farmers in the detection and treatment of Verticillium. The system employs multispectral imaging from unmanned aerial vehicles and automatic image processing using computer vision and machine learning techniques. The goal is to assess the health of olive groves and provide novel solutions for the early detection of Verticillium wilt and its spread.
Olives and olive oil are important for the European Union, in particular those Member States with Mediterranean coastlines. Spain alone produces 36% of the world’s olive oil, and the sector is a major contributor to the economies of Greece, Italy, and Portugal, and is also important to Cyprus, France, and Slovenia. Additionally, Italy and Spain are the largest consumers of olive oil in the EU, with an annual consumption of around 500,000 tons each, while Greece has the biggest EU consumption per capita, with around 12 kg per person per year. In total, the EU accounts for around 53% of world consumption. In terms of trade, the EU represents roughly 65% of world exports of olive oil. But the economic benefits of olive oil production, and of the production of table olives, come at a cost. Olive growing has become more intensive over the last three decades and is using an increasing amount of agricultural land. This intensification and expansion in the cultivation of olives have contributed to the significant spread and amplified the consequences of many diseases affecting olive trees. Among those, the most important fungal problem is verticillium wilt. The solutions available to tackle Verticillium’s effects require the accurate classification of trees in the early stages of infestation—a task that is impractical with traditional means but also very difficult, as early stages are almost impossible to distinguish by visual inspection.
All the above constitute the underlying context of MyOliveGroveCoach project, which utilizes multispectral imaging from unmanned aerial vehicles to develop an olive grove monitoring system based on the autonomous and automatic processing of the multispectral images using computer vision and machine learning techniques. The goal of the system is to monitor and assess the health of olive groves andprovide novel solutions for the early detection of Verticillium wilt and its spread. Olive cultivation in Greece represents a large percentage of the total agricultural land and a very large percentage of agricultural land that would be, considering territorial characteristics such as low fertility and sloping, difficult or economically impractical to exploit with other crops. Therefore, the effects of Verticillium are quite severe also from an economic point of view since it contributes to a serious reduction in olive
productivity, plant capital destruction and subsequently leads to derivative unwanted effects such as increased soil degradation. Verticillium wilt causes a gradual malfunction and eventually a complete blockage of the vessels of the tree, in part or in whole, interrupting the movement of water from the roots to the leaves, resulting in interruption of the water supply in the affected part of the tree. This reduction in water supply leads to nutritional deficiencies and even starvation of the branches. Before the complete blockage and total necrosis of the affected tissue associated with the part of the root that has been infected, there precedes a stage of temporary water stress, a reversible stress, which can be mainly attributed to the closure of the stomata of the affected plant tissue [2], stunting, chlorosis or yellowing of the leaves, necrosis or tissue death, and defoliation. Internal vascular tissue discoloration might be visible when the stem is cut.[1] In Verticillium, the signs and effects will often only be on the lower or outer parts of plants or will be localized to only a few branches of a tree. The severity of the infection plays a large role in how severe the signs are and how quickly they develop.
In the preliminary stage of early wilt infection, the natural process of photosynthesis is impaired, since the leaf pigments that are responsible for the canopy photosynthetic activity (mainly chlorophyll) are unable to function properly [3]. This impediment of the photosynthetic activity leads to a subsequent degradation of the canopy pigment percentage which results in a reduction of plant canopy reflectance in the Near Infrared wavelengths. As the infection progresses and because of the slow degradation of chlorophyll in the canopy the reflectance in the Green wavelengths (640nm) is also affected leading to light-green discoloration of the leaves; a discoloration that even in this stage of verticillium infection is very subtle and very difficult to detect with the naked eye, especially in there where photosynthetic activity has been hampered but the percentage of chlorophyll pigments in the canopy is still adequate for a functional photosynthetic activity.
Thermal and multispectral surveying has shown high correlations of leaves’ spectral characteristics with the degree of infestation, as measured in the 11 point [4]. On this basis, using Remote Sensing technologies enabled by the advent of small format high resolution multispectral sensors carried by unmanned aerial vehicles with autonomous mission capabilities. The team comprised of Kostas Blekos, Anastasios Tsakas, Aris Lalos, Ioannis Evdokidis, Dimitris Alexandropoulos, Christos Alexakos, Athanasios Kalogeras (Industrial Systems Institute, Athena Research Center, Patras, Greece), Sofoklis Katakis, Andreas Makedonas, Christos Theoharatos (Irida Labs S.A., Patras, Greece), Christos Xouris (Gaia Robotics S.A., Patras, Greece) created the platform “My Olive Grove Coach” (MyOGC). The main goal of MyOGC is the development of an intelligent system that will monitor olive groves and support farmers in the detection and treatment of Verticillium, using multispectral sensors and spectrophotometers. All raw data collected by the dedicated multispectral sensors are algorithmically processed and augmented by machine learning techniques. Finally, the end-results are visualized in a user friendly way so that producers and agronomists have access to reliable, actionable and customizable data, according to the principles of human-centered design.
With MyOGC it will be possible to (a) collect actionable data on the progress and spread of tree infestation; (b) quickly detect the problem using innovative signal processing methods and multispectral imaging and computer vision, in combination with machine learning techniques, thereby providing accurate spatial identification of affected trees; (c) guide the producers/agronomists when required, with a user-friendly communication and decision-making support system, with maps of quantitative and qualitative characteristics of the grove, that will help them optimize their olive management practices thus leading to (d) better yield quantity and quality while achieving a lesser environmental footprint of agricultural practices.
References
[1] Herder, M.D.; Moreno, G.; Mosquera-Losada, R.; Palma, J.; Sidopoulou, A.; Santiago Freijanes, J.J.; Crous-Duran, J.; Paulo, J.A.; Tomé, M.; Pantera, A.; et al. Current Extent and Trends of Agroforestry in the EU27. Available online: www.agforward. eu/index.php/en/current-extent-and-trends-of-agroforestry-in-the-eu27.html (accessed on 30 November 2020).
[2] Calderón, R.; Navas-Cortés, J.A.; Lucena, C.; Zarco-Tejada, P.J. High-resolution airborne hyperspectral and thermal imagery for early detection of Verticillium wilt of olive using fluorescence, temperature and narrow-band spectral indices. Remote Sens. Environ. 2013, 139, 231–245. [CrossRef]
[3] Fradin, E.F.; Thomma, B.P. Physiology and molecular aspects of Verticillium wilt diseases caused by V. dahliae and V. albo-atrum. Mol. Plant Pathol. 2006, 7, 71–86. [CrossRef] [PubMed]
[4] Zartaloudis, Z.; Iatrou, M.; Savvidis, G.; Savvidis, K.; Glavenas, D.; Theodoridou, S.; Kalogeropoulos, K.; Kyparissi, S. A new 11-point calibration scale of Verticillium wilt of olive verified by thermal remote sensing and plant analysis. In Proceedings of the 17th PanHellenic Plant Pathology Conference, Volos, Greece, 13–18 October 2014