Search

The Mediterranean is characterised by high biodiversity and numerous endemic species. These species are not only present in natural habitats, but also inhabit areas under human influence, such as agricultural lands. In the biodiversity assessment of Mediterranean vineyards and olive orchards within Zadar County, in Croatia, we identified eight endemic species with Mediterranean distribution, six with a Balkan Peninsula distribution, four with Dinaric Alps distribution and three species rare and endangered in Europe. Alongside these species, we have recorded five new species for Croatian fauna, many of those identified by combining morphological characteristics and the DNA barcoding tool. Araneae and Coleoptera contributed the highest number of endemic species and groups with new record were the following: Coleoptera, Diptera and Araneae. Compared to other sites, an olive orchard with ecological pest management (EPM), surrounded by natural ecosystems, had the highest ratio of endemic and rare species. Our findings emphasise that agricultural lands in the Mediterranean can be habitats for endemic and rare species and that future biodiversity research of these habitats is highly important, to monitor potential biodiversity changes and motivate future species and ecosystem conservation.

Cherry (Prunus avium L.) is an economically highly profitable fruit crop, due to the market, technological and commercial value of the fruit. The aim of this paper was to determine how treatment with different physiologically active substances affects individual morphological properties of the cherry fruit, Regina variety. Research of the effect physiologically active substances had on 75 trees in the cherry orchard was conducted in 2022, during the phenophase of fruit growth and development, in two locations in Zadar County: Ninski stanovi and Murvica. The treatment was carried out three times, with knapsack sprayers on five variants in 3 repetitions: K - no treatment, only water, T1 - CaO 15%, T2 - biostimulator (based on Ascophyllum nodosum L. extract), T3 - prolin, T4 - salicylic acid. The first treatment was carried out at a certain time interval after full flowering, depending on the microclimate of the particular location, while the other treatments were conducted with intervals of 10 days. The fruit samples on which morphological measurements were performed contained twenty random fruits per repetition. Data processing with one-way analysis of variance (ANOVA) and regression test (Tukey) determined the effect of physiologically active substances on the length, width, weight, as well as on the percentage of dry matter and fruit toughness, by treatments and locations. The highest values of fruit length, width and mass were achieved by treatments T2 and T4, while the least cracked fruits were obtained with treatment T1.

Mycotoxins are low-molecular-weight secondary metabolites synthesized by some filamentous fungi, toxic to animals and humans. As a contaminant, they can be found on different feed and foodstuffs, especially on cereal grains. Therefore, they pose a major problem worldwide. Within the project “Food production of biocomposites and cereals in a circular economy”, monitoring the occurrence of ochratoxigenic and aflatoxigenic fungi was carried out during a two-year survey in the experimental field in Osijek. Air sampling in the field was conducted during May, July and October of 2021 and 2022. Sampling was performed using an Air Sampler, which was adjusted so that the airflow through the Petri dishes for sampling was 100 L min-1. Two nutrient media ; Potatoe Dextrose Agar and Sabouraud Dextrose Agar, were used to isolate conidia from as many species of fungi present in the air as possible. Mycotoxigenic airborne molds in maize, wheat, and barley plantations, as well as in maize cobs were isolated and morphologically determined. Moreover, an assay of the ability of potential mycotoxigenic fungi to synthesize ochratoxin A and aflatoxin was performed. The results of the research are in accordance with the preliminary results of the first-year study, which showed the presence of both aflatoxigenic and ochratoxigenic fungi in the field with a percentage of occurrence of less than 10%. Analysis of the presence of aflatoxins and ochratoxin A in the harvested cereals is in the progress. Since the risk of contamination is present, it is necessary to continue monitoring in order to implement preventive control measures for aflatoxin and ochratoxin A contamination.

The wild olives (Olea europaea ssp. europaea var. sylvestris) emerge from seeds of either cultivated or wild populations. Preservation of biological diversity and the source of raw materials for industry (leaf) are the basis for their wider research. There is a large presence of wild olives in extensive olive groves on the island of Ugljan in Zadar County. Some individuals differ in fruit size, fertility, and resistance to drought and harmful organisms. The aim of this preliminary research is to morphologically describe six isolated individuals (trees) of wild olives located on the island of Ugljan. In the period from January to November 2017, their morphometric examination was carried out. It included measurements of five morphological characteristics of the leaf, four of the inflorescence, thirteen of the fruit, and twelve of the stone. The measurements were carried out according to the international method for the description of olive cultivars used by the International Olive Council (IOC). The comparison of characteristics was performed by one-way analysis of variance, and the reverse Tukey test was used to compare mean values. By comparing the morphological characteristics of leaves, inflorescences, fruits, and stones, significant differences were found among the studied individuals. According to the characteristics of the leaf and the number of flowers per inflorescence, one individual was singled out, for which the largest average leaf area and the largest average number of flowers per inflorescence were determined. The highest average mass of fruit and stone was found only in one of all the research individuals. Morphological characteristics of leaves and fruits at harvest are influenced by the cultivar, but also by a number of other agroecological factors. The obtained preliminary results are useful for mass selection when selecting individuals of interest for further vegetative reproduction, which would be a preparation for genetic identification research.

Food production is increasingly preoccupied with precision agriculture. One of its solutions are visual data processing technologies - object detection (OD), combined with the development and application of artificial intelligence (AI) models. These technologies as a tool are much more precise than looking with the “naked eye”. The olive fly Bactrocera oleae (Rossi 1790) is an economic pest of the olive fruit that appears regularly in the Mediterranean climate, but the capture is not the same every year. Measuring the capture on the yellow plates, creating the flight curve is an extremely time-consuming job for olive growers. OD technologies, with the application of AI, speed up the process of measuring captures. The developed AI model bridges the spatial distance and travel time of the yellow plates. The aim of the paper is to show the development of the OD model for B. oleae and its reliability. The AI model was developed in Zadar County on visual samples of images of yellow plates from 6 localities collected from 2020 to 2022. The research was carried out as part of the project: SAN-KK.01.2.1.01.0100 (Smart agriculture network), financed by IRI- ERDF fund. AI model development was carried out using TensorFlow software. The concept used to determine the level of precision bio efficientdet lite4. This is an AI algorithm, and it works by having a separate set of images determine the quality of the model. With it, reliability of up to 95% was achieved. OD technologies, along with the development of AI models, have proven to be applicable in measuring the captures of adults and setting the flight curve of the olive fly. Technology further bridges distance and time to measure adult captures.

The aim of this work was to investigate the influence of the silicon foliar application on the intensity of olive damage caused by the settlement of jasmine moth (Margaronia (Palpita) unionalis Hubner) larvae, and the phenolic response of olive leaves. The field trail on two years old Leccino cv. olives was conducted, as a completely randomized design with two treatments (untreated control (Si-) and silicon treated plants (Si+)), during September and October of 2022. During the trial Si+ plants were foliarly treated five times at intervals of one week. After second treatment the larvae of four jasmine moth were settled on the apical buds of Si- and Si+ olives. Seven days after the last treatment, samples of young and old leaves for phenolic analyses were taken. Damaged leaves, apical buds and the number of pupae per plant were also counted. The results showed significant differences in the oleuropein concentration between Si- and Si+ leaves (6121 mg/100 g DW and 6914 mg/100 g DW, respectively). Comparing the percentage of damaged leaves and the percentage of damaged apical buds, there was no significant difference between Si- and Si+ olives. A significant difference was shown in the number of pupae per plant, namely, no pupae were found on Si+ plants, while an average of 0.3 pupae per olive was found on Si- plants. Due to our preliminary results further investigation of the silicon foliar application in protecting olives from the jasmine moth as well as other insects is needed.

The effectiveness of pest control depends on monitoring methods, most of which are outdated and irrelevant. For example, the pear leaf blister moth (Leucoptera malifoliella (O. Costa, 1836)) is an important apple pest whose larvae damage leaves. Its monitoring is done with pheromone traps, which are time-consuming to inspect and may result in delayed pest control. The most effective time for its control is an early stage of damage occurrence (mines), which is difficult to detect with classical monitoring techniques. Artificial neural networks (ANN) have recently been used for pest monitoring. Therefore, the aim of this study was to develop automatic systems for monitoring pear leaf blister moth and its damage using ANNs. The two ANNs were trained to detect the pear leaf blister moth and its damage using photographs collected in three apple orchards in Zagreb County. The model was developed for use in two prototype smart monitoring devices (pest monitoring device and vegetation monitoring device). The model was tested and the results were processed using a confusion matrix. The developed models showed high accuracy and precision in detecting pear leaf blister moth and its damage, while the monitoring devices showed good functionality in apple orchards. The developed system is effective for automatic monitoring of pear leaf blister moth and its damage, and therefore can significantly improve pest control and apple production in general.

Cultivation of sweet cherry (Prunus avium L.) is spread across the Republic of Croatia, but its importance is greater in the Mediterranean region, especially for early ripening cultivars. Extreme weather conditions during flowering and ripening negatively affect the commercial of fruits. Aim of this work was to determine the occurrence of sweet cherry fruit cracking and fruit firmness and to examine it with the amount of precipitation during fruit development. Research was conducted during 2019 and 2020 at the sweet cherry orchard in Ninski Stanovi, Zadar County. Fruits were harvested at commercial maturity. Fruit cracking index (CI) and fruit firmness (FF) of fifteen sweet cherry cultivars ('Burlat', 'Cristalina', 'Early Burlat', 'Ferrovia', 'Germersdorf', 'Giorgia', 'Grace Star', 'Lapins', 'Regina', 'Samba', 'Summit', 'Sunburst', 'Sweet Early', 'Sweet Valina' and 'Volovsko srce') were evaluated. Statistical comparison of fruits was made by one way analysis of variance and Tukey post hoc test. Person correlation between CI and FF of all cultivars and both years was also carried out. Significant differences were found for CI and FF between the cultivars. Furthermore, the influence of the year on the measured parameters is also visible. 'Grace Star' has shown the lowest CI value in 2019 (2.80), while ‘Sweet Early’ in 2020 has shown the highest CI (52.4). FF ranged from 1.09 kg/cm2 in 'Early Burlat' in 2019 to 2.82 kg/cm2 in 'Volovsko srce' in same year. There is a moderate negative correlation between the CI and FF. Obtained results are useful for the selection and valorization of sweet cherry cultivars for the Mediterranean growing area in the Republic of Croatia. Conducted research contributes to the assessment of extreme weather conditions risk, mostly precipitation, which could affect the cracking and firmness of sweet cherry fruits.

The influence of the rhizobacterium Azospirillum brasilense on the vegetative activity of MaxMa 14 (Prunus mahaleb x Prunus avium) rootstocks, a widely used sweet cherry rootstock in semi- intensive orchards, was determined. The field experiment was conducted on one-year-old micropropagated rootstocks in 3L pots, arranged to randomized block design in 3 repetitions, and 15 pots in row per each repetition. Vegetative growth promoter AZOS® that contains single rhizobacterium A. brasilense was added by watering to plants in concentration of 0 g/l (T0 control), 0.8g/l once a month (T1) and 0.8g/l every two months (T2) in controlled time intervals. Plant height, trunk cross-section area (TCSA), shoot number and chlorophyll content index (CCI) were observed as factors of vegetative activity. Also, vegetative growth of 3 individual shoots and number of their internodes was measured three times during vegetation. Based on the obtained research results, it was determined that the use of A. brasilense by watering rootstock seedlings affected vegetative activity. Plant height, TCSA, CCI, shoot length and internode number were influenced by A. brasilense while shoot number wasn’t influenced by rhizobacteria. In conclusion, watering MaxMa 14 rootstocks with A. brasilense could be useful for obtaining quality grafting material.

Najdestruktivnija bolest na maslini (Olea europaea L.) je paunovo oko koju izaziva gljiva Spilocaea oleagina, (Castage). Prvi simptomi se pojavljuju na listu. Patogen je prisutan u masliniku tokom cijele godine. Tijek inkubacije od 15 dana pa do nekoliko mjeseci otežava nadzor bolesti zbog pojave latentne zaraze. Uzgoj stabla masline u mediteranskom podneblju je na plitkom skeletnom tlu koje ima niski kapacitet za vodu. Za postizanje zadovoljavajućeg prinosa i kvalitete ploda maslinu je potrebno navodnjavati. Cilj rada je odrediti intenzitet i jačinu zaraze paunovim okom na sorti Coratina u sklopu projekta „SAN – Smart Agriculture Network“ na 24 stabla po slučajnom bloknom rasporedu. Navodnjavanje je provedeno sustavom kap na kap. Varijante su: K (0%) - bez navodnjavanja, T1 (PP) - proizvođačka praksa, T2 (SAN) – 80 % od izračunate evapotranspiracije i T3 (100%) – od izračunate evapotranspiracije. Za određivanje latentne zaraze po pojedinim varijantama pokusa ubrani listovi tretirani su natrijevom lužinom. Ocjenjivan je postotak zaražene površine lista razvrstane u pet kategorija. Statističkom obradom podataka jednosmjernom analizom varijance (ANOVA) i povratnim testom (Duncan) određen je postotak zaraženih listova i postotak pokrivenosti lisne površine lezijama. Dobiveni rezultati ukazuju da bez obzira na obrok navodnjavanja sve varijante u istraživanju imaju jednak broj zaraženih listova. S druge strane sve istraživane varijante imaju jednak prosječni postotak zaražene površine lezijama, osim varijante T3 gdje je on značajno veći.

Mycotoxins are toxic secondary metabolites produced by fungi toxic for humans and animals. They are generally considered to be unavoidable contaminants of food for humans and animals and pose a major problem worldwide. Environmental conditions conducive to mycotoxin production are humidity and temperature, oxygen concentration, physical damage, and the presence of mold spores. It is assumed that the increase in the average temperature on Earth could lead to the migration of mycotoxigenic fungi from tropical and subtropical areas where high temperatures and humid conditions prevail towards more northern areas with temperate climates. In the project “Food production of biocomposites and cereals in a circular economy”, the occurrence of conidia of afla and ochratoxigenic fungi during three year in the experimental field in Osijek will be monitored. The occurrence of mycotoxigenic airborne molds in maize, wheat, and barley plantations, as well as in maize cobs will be analyzed. Preliminary results showed the presence of both aflatoxigenic and ochratoxigenic fungi in the field. About 10% of conidia isolated from the air belong to afla or ochratoxigenic species. The presence of these species was confirmed on swabs taken from damaged and contaminated maize cobs in the pre-harvest period. Analysis of the presence of aflatoxins and ochratoxin A in the harvested cereals is in the progress. The risk of contamination is present and the measures for prevention and control of aflatoxins and ochratoxin A should be applied.

Ground beetles (Coleoptera, Carabidae) provide valuable ecosystem services including biocontrol on pest species and weed seeds in the agroecosystems. These services are connected to species traits such as feeding preferences, body size, and wing development. The aim of this study was to analyse the functional diversity of carabids in Mediterranean vineyards and olive orchards based on the selected traits. Previous studies confirmed that the composition of the traits within carabid species assemblages is affected by habitat structure. Here we tested if agricultural practice like integrated pest management (IPM) and organic management (OM), have an effect on the proportion of the traits within the carabids species assemblages, and if they differ from the natural surrounding habitats. To analyse this effect, we compared data collected from five sites in the Zadar County in Croatia with the published data from vineyards and olive orchards from Mediterranean countries where similar management practices and beetle sampling methods were applied. Unmanaged habitats supported significantly more carnivorous species compared to OM sites, while there were no significant differences for ground beetles feeding preferences between OM and IPM sites. Large, brachypterous species had the highest proportion at unmanaged sites and lowest at IPM sites. Contrary, unmanaged sites displayed significantly lower functional diversities in feeding preferences and size ranges. We hope these findings could help in the development of the management that promotes sustainability of predatory carabids, and prevent biodiversity losses in the susceptible Mediterranean region.

Smeđa mramorasta stjenica (Halyomorpha halys Stål, 1855) je invazivna vrsta porijeklom iz Azije. U Hrvatskoj je zabilježena 2017. godine, a posljednjih godina bilježi se porast populacije i širenje štetnika u ratarskim usjevima i višegodišnjim nasadima. H. halys je izuzetno polifagna vrsta, a ekonomske štete u proizvodnji poljoprivrednih kultura iz porodica Rosaceae i Fabaceae već su zabilježene u nama susjednim državama (Sloveniji i Mađarskoj, te Italiji). Stoga, pouzdano praćenje štetnika u realnom vremenu korištenjem automatskih sustava za praćenje može pridonijeti ranoj detekciji i sprečavanju širenja vrste na nova područja. Zahvaljujući ključnim tehnološkim konceptima računalnog vida i umjetne inteligencije, ovakvi sustavi uz brzu detekciju pridonose pravovremenom suzbijanju štetnika, te smanjenoj upotrebi pesticida. Monitoring vrste H. halys korištenjem automatskih sustava za praćenje je u začetcima, a na tržištu se može pronaći samo jedan tip tzv. pametne lovke. Stoga se u sklopu ‘’AgriART‘’ projekta razvija model za automatsko praćenje smeđe mramoraste stjenice. Model se razvija stvaranjem ulazne baza podataka s fotografijama snimljenih pomoću RGB (red-green-blue) kamere u poljskim uvjetima, a metodom prepoznavanja Convolutional neural network (CNN), sustav detektira štetnika. Takav sustav trebao bi uvelike olakšati ranu detekciju i suzbijanje ove invazivne vrste, te na taj način spriječiti njezino brzo širenje i pridonijeti održivoj poljoprivrednoj proizvodnji u Hrvatskoj.

Jabukov savijač (Cydia pomonella L.) ekonomski je štetnik koji uzrokuje velike gubitke u proizvodnji jabuke. Zbog ekonomske važnosti jabuke (Malus domestica Borkh.) širom svijeta, tržište zahtjeva proizvodnju visokokvalitetnog voća bez prisutnih šteta od jabukovog savijača. Jabukov savijač razvija jednu do četiri generacije godišnje ali zbog klimatskih promjena zabilježen je neočekivani porast populacije i broja generacija štetnika. U suzbijanju štetnika, proizvođači obično učestalo primjenjuju insekticidne tretmane koji uzrokuju razvoj rezistentnosti štetnika i opterećuju finalni proizvod, okoliš i druge ne ciljane organizme agrokemikalijama. S obzirom na navedeno, mnogo je razloga za korištenje sofisticiranijih tehnika praćenja štetnika koje bi poboljšale njegovo suzbijanje. Cilj ovog istraživanja je razviti sustav za automatsko praćenje i ranu detekciju jabukovog savijača korištenjem RGB kamere. Tijekom razdoblja leta jabukova savijača u 2022. godini prikupljeno je 140 fotografija štetnika, na kojima je kasnije anotirano 4000 jedinki vrste. Na temelju 90% anotiranih fotografija trenirana je konvolucijska neuronska mreža. Rezultati su pokazali da analitički model detektirao jabukovog savijača s 80% točnosti, što je potvrđeno korištenjem preostalih 10% anotiranih fotografija. Razvojem ovog pametnog sustava, proizvođači će moći učinkovitije pratiti te pravovremeno detektirati jabukovog savijača što će poboljšati suzbijanje štetnika, a time i proizvodnju jabuke.

Even though the satellites in orbits of different heights are tracked from Earth, for many applications there is a need for precise satellite positioning or timing and therefore, such satellites carry Global Navigation Satellite Systems (GNSS) receivers. Many of those are single-frequency receivers. Signals from the main and side lobes of GNSS satellites, arriving to a satellite-borne receiver from different directions, are used to calculate the position and time. To compensate for the ionospheric error, ionospheric models integrated within GNSS, intended for use on Earth, cannot be applied without modifications. For each GNSS signal arriving to the space-borne receiver, the cross-section of the path within the ionosphere must be determined, and the resulting ionospheric error compensated.

Kukuruzna zlatica (Diabrotica virgifera virgifera LeConte, 1858) i kukuruzni moljac (Ostrinia nubilalis Hübner, 1796) gospodarski su značajni štetnici kukuruza. Odrasli oblici zlatice i moljca stvaraju mnogobrojne populacije čije jedinke stalno posjećuju sve nadzemne dijelove biljaka: list, metlicu, stabljiku, svilu i klipove. Odrasli oblici kukuruzne zlatice i kukuruznog moljca mogu biti vektori spora mikotoksigenih gljivica i tako doprinositi kontaminaciji kukuruza mikotoksinima. Značajniji mikotoksini su aflatoksin B1 i okratoksin A. Aflatoksine proizvode mikotoksigene gljivice vrste Aspergillus flavus, a okratoksin vrste rodova Aspergillus i Penicillium. U sklopu projekta „Proizvodnja hrane, biokompozita i biogoriva iz žitarica u kružnom gospodarstvu“ (EFRR: KK.05.1.1.02.0016) provedeno je istraživanje potencijala prijenosa spora mikotoksigenih gljiva odraslim kukcima. Istraživanje je provedeno u poljskim uvjetima u Osijeku tijekom 2021. Prikupljene su 103 odrasle jedinke kukuruzne zlatice i 87 jedinki kukuruznog moljca. Postupak dokazivanja kukaca kao prijenosnika mikotoksigenih gljivica proveden je ispiranjem kukaca u sterilnoj vodi, inokulacijom i inkubacijom na hranjivoj podlozi Potatoe Dextrose Agar. Kulture gljivica razvijenih na hranjivim podlogama morfološki su determinirane prema dostupnim ključevima. Potencijalno mikotoksigene gljivice su izdvojene i inokulirane na hranjive podloge Potatoe Dextrose Broth koje induciraju proizvodnju aflatoksina B1 i okratoksina A. Aflatoksin B1 i okratoksin A su ekstrahirani i potvrđeni HPLC metodom. Preliminarni rezultati prikazuju pojavnost mikotoksigenih proizvođača aflatoksina B1 i okratoksina A.

Apple (Malus domestica Borkh.) is one of the world's highest-yielding fruit crops. In addition to codling moth (Cydia pomonella L.), which is considered the most important apple pest, other lepidopterans, fruit flies, and true bug species also threaten production, affecting fruit quality and preventing its commercialization. Early detection and monitoring of pests is critical to preventing damage from pests. Due to new climatic conditions, the phenology of pests changes frequently and it is very difficult to predict their occurrence. Therefore, there is an increasing need to develop and use new smart technologies for pest monitoring (smart traps, sensors, etc.). Such methods can greatly facilitate site-specific management and consequently reduce the use of pesticides and their residues. The aim of this work is to provide an overview of methods for automatic monitoring of economically important apple pests in order to improve sustainable pest management in apple production.

Codling moth is a cosmopolitan pest that causes economically significant damage in apple production. The damage is visible on the fruits, which lose their organoleptic properties and market value. Therefore, the use of artificial intelligence offers a good perspective for the early detection of the pest and its damage in the field. Information and communication technology has contributed to the use of intelligent devices throughout the agricultural chain. In the context of precision agriculture, the artificial intelligence system is a comprehensive solution for the digitalization of agriculture. In practice, this system involves the creation of an information database, and in the case of pest monitoring, red-green-blue (RGB) and hyperspectral imaging cameras (HSI) can be used. These cameras record the occurrence of pests and damage in orchards. Later, these photos are processed using machine learning methods. Based on all the data, accurate models are developed to identify the target pest and facilitate monitoring and management. Inhibiting factors for the use of cameras can be the high market price, the lack of certain electronic components, and the required expertise. Nonetheless, high-precision classification models for pest monitoring represent the future of agriculture and offer a new opportunity to reduce economic losses caused by codling moth.

Trčci (Carabidae, Coleoptera) često se proučavaju kao agensi biološkog suzbijanja štetnih organizama. Maslinina muha (Bactrocera (Daculus) oleae (Gmelin, 1790) i puževi (Gastropoda) prisutni su u maslinicima i vinogradima mediteranskih agro-ekosustava gdje čine štetu na nasadima. Cilj rada je identificirati vrste trčaka korisnih u biološkom suzbijanju, prateći sezonsku dinamiku odabranih organizama na istraživanim plohama. Istraživanje je provedeno na pet ploha u Zadarskoj županiji. Istraživana su dva vinograda i dva maslinika po jedan u ekološkom, odnosno integriranom sustavu uzgoja. Peta ploha bila je kontrola bez uzgoja, s tipičnom mediteranskom makijom i garigom. Trčci su uzorkovani od travnja do srpnja te od rujna do studenog 2018. u plastične posude volumena 300 mL, po 12 u liniji postavljenih u zemlju kao zamke. Nemetrička višedimenzionalna analiza skaliranja (NMDS) korištena je za provjeru grupiranja skupina trčaka na temelju sličnosti vrsta između ploha. Sezonske promjene u brojnosti B. oleae i puževa te trčaka modelirane su generaliziranim linearnim modelom mješovitih učinaka (GLMM). Mesojedi poput Poecilus (Macropoecilus) koyi (Germar, 1824) i Pterostichus (Morphnosoma) melanarius (Illiger, 1798) bili su najzastupljeniji. Brojnost trčaka pokazala je značajan utjecaj na brojnost puževa. Na osnovi dobivenih rezultata mogu se izdvojiti vrste s potencijalom u suzbijanju promatranih štetnih organizama kroz vegetacijsku sezonu.

One of the most important apple pests are insects from the order of butterflies (Lepidoptera) - the codling moth (Cydia pomonella (Linnaeus, 1758), whose larvae feed on apple fruit, making it unusable for the market, and the pear leaf blister moth (Leucoptera maifoliella (O. Costa, 1836), whose larvae develop in apple leaves. Classical pest monitoring methods are unreliable and time- consuming, resulting in greater damage to apple production. The use of artificial neural networks (ANN) has recently shown great potential for pest monitoring. Therefore, the aim of this paper is to present ANNs as a pest detection tool that can be used for automatic monitoring of Lepidoptera apple pests (Figure 1). Looking at the examples from the literature where ANNs are used for apple pest monitoring and comparing their accuracy, it can be seen that all effective models for codling moth detection have an accuracy of over 90% in most cases compared to manual counts by human experts. The model for pear leaf blister moth is still pending, but since it belongs to the same order as codling moth (Lepidoptera), the model accuracy should also be high. In addition, ANNs have been used to detect damage to leaves caused by the pear leaf blister moth and also achieved high accuracy. Further development of ANNs for detection and monitoring of important apple pests is certain. Thus, this study reveals an unexplored potential for the use of ANNs in monitoring apple pests from the order Lepidoptera. Therefore, this work advocates more efficient and rapid monitoring that allows for targeted and effective pest control without unnecessary insecticide treatments and thus without negative agricultural impacts on the environment and human health.