Andrzej Wójtowicz

Septoria leaf blotch (SLB), caused by Zymoseptoria tritici, is one of the most destructive foliar diseases of wheat and requires accurate methods for early detection and disease severity assessment. This study evaluated the potential of hyperspectral ASD measurements and UAV multispectral imagery combined with machine learning for the detection and quantification of SLB in winter wheat. Six spectral datasets derived from hyperspectral reflectance, UAV multispectral imagery, and vegetation indices were analyzed using CatBoost, Random Forest, and XGBoost algorithms. Random Forest achieved the highest classification performance, reaching an accuracy of 0.9583 and a balanced accuracy of 0.9483. For disease severity prediction, the best performance was obtained using ASD-derived vegetation indices with Random Forest (R² = 0.9199), while CatBoost consistently provided high regression accuracy across hyperspectral datasets. A reduced set of green, red, red-edge, and near-infrared bands produced classification results comparable to those obtained with the full hyperspectral spectrum, indicating that most diagnostic information is concentrated within these spectral regions. Although UAV multispectral data showed lower accuracy than hyperspectral measurements, particularly for disease severity prediction, they enabled effective field-scale disease monitoring. These findings demonstrate that hyperspectral sensing provides a valuable reference for developing accurate disease detection models, whereas UAV multispectral imagery represents a practical and scalable solution for operational precision agriculture.

Accurate and timely assessment of crop disease severity is crucial for effective management strategies and ensuring sustainable agricultural production. Traditional visual disease scoring methods are subjective and labor-intensive, highlighting the need for automated, objective alternatives. This study evaluates the effectiveness of a model for field-based identification and quantification of stripe rust severity in wheat using red, green, blue RGB imaging. Based on crop reflectance hyperspectra (CRHS) acquired using a FieldSpec ASD spectroradiometer, two complementary approaches were developed. In the first approach, we estimate single leaf disease severity (LDS) under laboratory conditions, while in the second approach, we assess crop disease severity (CDS) from field-based RGB images. The high accuracy of both methods enabled the development of a predictive model for estimating LDS from CDS, offering a scalable solution for precision disease monitoring in wheat cultivation. The experiment was conducted on four winter wheat plots subjected to varying fungicide treatments to induce different levels of stripe rust severity for model calibration, with treatment regimes ranging from no application to three applications during the growing season. RGB images were acquired in both laboratory conditions (individual leaves) and field conditions (nadir and oblique perspectives), complemented by hyperspectral measurements in the 350–2500 nm range. To achieve automated and objective assessment of disease severity, we developed custom image-processing scripts and applied Random Forest classification and regression models. The models demonstrated high predictive performance, with the combined use of nadir and oblique RGB imagery achieving the highest classification accuracy (97.87%), sensitivity (100%), and specificity (95.83%). Oblique images were more sensitive to early-stage infection, while nadir images offered greater specificity. Spectral feature selection revealed that wavelengths in the visible (e.g., 508–563 nm and 621–703 nm) and red-edge/SWIR regions (around 1556–1767 nm) were particularly informative for disease detection. In classification models, shorter wavelengths from the visible range proved to be more useful, while in regression models, longer wavelengths were more effective. The integration of RGB-based image analysis with the Random Forest algorithm provides a robust, scalable, and cost-effective solution for monitoring stripe rust severity under field conditions. This approach holds significant potential for enhancing precision agriculture strategies by enabling early intervention and optimized fungicide application.

High-throughput sequencing (HTS) has revolutionized phytopathology by overcoming many limitations of traditional diagnostic methods, as it permits precise pathogen monitoring, identification, and control, with ribosomal DNA (rDNA) regions serving as reliable markers for fungal classification. In this study, next-generation sequencing (NGS) was used, targeting the ITS1 and ITS2 regions to explore fungal diversity and pathogen presence in winter wheat grain samples and identifying 183 OTU sequences across 115 taxa. The ITS1 analysis yielded 249,743 reads, with Fusarium sp. (61%) as the dominant pathogenic taxon, followed by Sporobolomyces sp. (14%), Cladosporium sp. (3%), and other yeast-like or saprotrophic fungi, such as Cryptoccocus spp., F. wieringae, and B. alba. Sequencing of ITS1 also permitted the detection of F. acuminatum and the quarantine-regulated pathogens T. caries and T. triticoides. The ITS2 analysis produced 179,675 reads, with F. culmorum (47%) as the most abundant taxon, confirming significant grain contamination with this pathogen. Other frequently detected taxa included yeast-like fungi such as C. tephrensis (21%) and V. victoriae (13%), along with saprotrophic species like S. roseus and Davidella sp. ITS2 provided better resolution for the identification of Fusarium species by the detection of more pathogenic taxa associated with cereal diseases, including F. culmorum, as well as F. cerealis, F. poae, and F. tricinctum. The analysis revealed a diverse fungal community, including other pathogens such as A. porri, B. cinerea, and C. herbarum, as well as various non-pathogenic and saprotrophic fungal taxa. These findings underscore the complementary utility of ITS1 and ITS2 in profiling fungal diversity and detecting critical pathogens using HTS, highlighting the potential of these DNA regions for monitoring and managing cereal crop health.

Oilseed rape (Brassica napus L.) is one of the most important oil crops worldwide. Machine learning metchods are gaining increasing im­portance in oilseed rape production, enabling yield prediction, crop condition assessment, and support for agronomic decision-making. This paper presents a review of studies on the use of various algorithms – from classical models such as linear regression, decision trees, random forest, and support vector machine to more advanced ones, including neural networks. Applications of remote sensing data, unnamed aerial vehicles and satellite imagery, as well as ground-based sensors for monitoring diseases, environmental stresses, and nutrient requirements are discussed. The potential of machine learning to enhance efficiency and sustainability in rapeseed production is highlighted, along with challenges related to data quality, model complexity, and interpretability.

Microbiome of winter wheat grain was characterized based on next-generation sequencing (NGS) of ribosomal DNA (rDNA) regions. The obtained results revealed significant differences in microbiome composition across the study years. In 2020 and 2022, the dominant spe­cies were Blumeria graminicola (40% and 70% of identified sequences), Alternaria infectoria (14% and 4%), and Mycosphaerella tassiana (12% and 8%). In contrast, in 2021, the most frequently detected species were M. tassiana (20%), Sporobolomyces roseus (13%), andB. graminicola (11%). The analysis confirmed the presence of Fusarium species in all study years, with their sequence percentage fluc­tuating significantly – from 0.5% in 2020 to 5.5% in 2021. Four species were identified: F. graminearum, F. poae, F. sporotrichioides and F. culmorum. The proportion of yeast-like fungi in the total number of sequences also varied over the years, accounting for 20% in 2020, rising to 50% in 2021, and decreasing to 12% in 2022. Two taxons were dominant: S. roseus and Vishniacozyma spp., including V. victo­riae. Additionally, other yeast-like fungi were identified, including Filobasidium wieringae, Filobasidium stepposum, Dioszegia hungarica, Aureobasidium pullulans, Holtermaniella wattica, Bulleromyces albus, and Bullera crocea. The results highlight the dynamic nature of the wheat microbiome and its sensitivity to changing environmental conditions.

The study aimed to assess the impact of Trichoderma harzianum, Trichoderma atroviride, Sarocladium strictum, Wickerhamomyces anomalus and Bacillus spp. on the growth inhibition of Fusarium spp. colonies, and on the health and development of winter wheat va¬rietas Euforia seedlings. In the laboratory conditions, the presence of T. atroviride and T. harzianum the most strongly limited the growth of the colonies of Fusarium culmorum, Fusarium graminearum and Fusarium avenaceum. Well-developed growth inhibition zones were observed in the bicultures containing strains of Bacillus spp. and W. anomalus. The development of wheat seedlings in the presence of antagonistic and pathogenic fungi was varied, but W. anomalus provided the best protection against damping off caused by F. culmorum and F. graminearum. The influence of individual antagonistic microorganisms in variants with inoculation with pathogenic microorgan¬isms on the green mass of wheat seedlings was variable. The best results were achieved with T. atroviride, S. strictum and Bacillus spp.

Under natural conditions, mixed infections are often observed when two or more species of plant pathogens are present on one host. Thus, the detection and characterization of co-occurring pest species is a challenge of great importance. In this study, we focused on the development of a spectral unmixing method for the discrimination of two fungi species, Plenodomus lingam and Plenodomus biglobosus, the pathogens of oilseed rape. Over 24 days, spectral reflectance measurements from Petri dishes inoculated with fungi were conducted. Four experimental combinations were used: the first two were pure fungal samples, while the other two were co-occurring fungal samples. The results of the study show the possibility of distinguishing, based on spectral characteristics, between P. lingam and P. biglobosus not only in pure but also in co-occurring samples. We observed the changes in the reflectance of electromagnetic radiation from the tested fungi over time and a strong correlation between the reflectance and changes in the areas of the mycelia on the Petri dishes. Moreover, the wavelengths most useful for spectral classification of the tested fungal mycelia were selected. Finally, a spectral unmixing model was proposed, which enables the estimation of the areas of two pathogens in co-occurring samples based on the spectral characteristics of the entire plate with an error smaller than 0.2. To our knowledge, the present study is the first report examining the use of reflectance spectroscopy methods for classifying pathogens on the same Petri dish. The study results indicate the feasibility of reflectance spectroscopy as a nondestructive sampling method for plant pathogen detection and classification.

Sclerotinia stem rot, caused by Sclerotinia sclerotiorum, threatens oilseed rape (Brassica napus) crops internationally. The development of this disease is strongly controlled by the weather, which is why global climate change is likely to influence its spread and impact. Climate change may affect the pathogen directly or indirectly via the host plant. This study investigates the potential impact of climate warming on Sclerotinia stem rot severity in oilseed rape in Poland. The aim of this investigation was to assess the relationship between the direct impact (DI) and indirect impact (II) of climate change on disease severity using the 4.5 and 8.5 representative concentration pathways (RCPs). Under the RCP4.5 scenario, nearly 60% of the simulations performed for 16 regions in four periods (2020–2039, 2040–2059, 2060–2079, 2080–2099) showed reductions in disease severity in comparison to those conducted for 1986–2005, while under RCP 8.5, this reduction was generated for nearly 90% of the cases. The effect of the RCP scenario on clustering the regions according to the value of Sclerotinia stem rot severity was also investigated. The simulations revealed that, for all periods, the lowest disease severities are expected for Zachodniopomorskie and Pomorskie. The results obtained also show the superior effects of the II over the DI on Sclerotinia stem rot severity in the future. Under the RCP4.5 scenario, the rate of IIs was greater than that of DIs for 10 regions, while under RCP8.5, this relationship was registered for 16 regions. These outcomes result from the acceleration of the oilseed rape flowering period triggered by expected temperature increases. The novelty of this study lies in a detailed analysis of the relationships between the DI and II of climate change, expressed numerically, for 16 regions in Poland. The obtained results highlight the role of the indirect impact in shaping disease severity and indicate that it should be incorporated into assessment methods of climate change effects alongside the direct impact.

In this study, three fungi species (Botrytis cinerea, Rhizoctonia solani, Sclerotinia sclerotiorum) were discriminated using hyperspectral and red-green-blue (RGB) data and machine learning methods. The fungi were incubated at 25 °C for 10 days on potato dextrose agar in Petri dishes. The Hyperspectral data were acquired using an ASD spectroradiometer, which measures reflectance with 3 and 10 nm bandwidths over the range 350–1000 nm and the range 1000–2500 nm, respectively. The RGB images were collected using a digital Canon 450D camera equipped with the DIGIC 3 processor. The research showed the possibility of distinguishing the analysed fungi species based on hyperspectral curves and RGB images and assessing this differentiation using machine learning statistical methods (extreme boosting machine with bootstrap simulation). The best results in analysed fungi discrimination based on hyperspectral data were achieved using the Principal Component Analysis method, in which the average values of recognition and accuracy for all three species were 0.96 and 0.93, respectively. The wavelengths of the shortwave infrared (SWIR) wavelength region appeared to be the most effective in distinguishing B. cinerea-R. solani and B. cinerea-S. sclerotiorum, while of the visible range (VIS) of electromagnetic spectrum in discrimination of R. solani-S. sclerotiorum. The hyperspectral reflectance data were strongly correlated with the intensity of the pixels in the visible range (R² = 0.894–0.984). The RGB images proved to be successfully used primarily for the identification of R. solani (recognition = 0.90, accuracy = 0.79) and S. sclerotiorum (recognition = 0.84, accuracy = 0.76). The greatest differences in the intensity of the pixels between B. cinerea and R. solani as well as R. solani and S. sclerotiorum occurred in the blue band and in distinguishing B. cinerea and S. sclerotiorum in the red band.

Hyperspectral remote sensing consists in collecting and processing information about the reflectance of electromagnetic radiation from the examined object in very narrow spectral ranges. The essence of this method in relation to the monitoring of the health of crops is the registration of differences in the reflectance of radiation from healthy and infected plants. This paper presents examples of the use of this technology to monitoring of the occurrence of pathogens on cereal plants (Zymoseptoria tritici, Blumeria graminis, Puccinia striiformis, Puccinia recondita, Puccinia graminis, Fusarium culmorum, Fusarium graminearum, Pyrenophora tritici-repentis), root crops (Phytophthora infestans, Alternaria solani, Cercospora beticlerotinia, Erysiphe betae, Uromyces betae) and industrial plants (Golovinomyces cichoracearum, Septoria helianthi, Verticillium dahliae, Phymatotrichopsis omnivora, Puccinia kuehnii, Puccinia melanocephala, potato virus Y, tomato spotted wilt virus, tobacco mosaic virus).