Soil represents an important pool of biodiversity, hosting about a quarter of the living species on our planet. This soil richness has led to increasing interest in the structural and functional characteristics of its biodiversity. Studies of arthropod responses, in terms of abundance and taxon richness, have increased in relation to their ecological value as bioindicators of environmental change. This research was carried out over the 2014–2018 period with the aim to better understand arthropod taxa responses in vineyard soils in Franciacorta (Lombardy, Italy). To determine the biological composition in terms of arthropod taxa presence, one hundred soil samples were analysed. Environmental characteristics, such as chemical composition, soil moisture and temperature, and soil management were characterized for each soil sample. A total of 19 taxa were identified; the NMDS model analysis and the cluster analysis divided them into five groups according to their co-occurrence patterns. Each group was related to certain abiotic conditions; of these, soil moisture, temperature and organic matter were shown to be significant. A decision tree analysis showed that a longer period since conversion from conventional to organic farming lead to a higher arthropod biodiversity defined as a higher number of taxa.

The carbon footprint is an index used to assess the impact of an activity in terms of greenhouse gas emissions. Viticulture contributes to greenhouse gas emissions due to the use of fuels, fertilizers and pesticides, and the consequent soil erosion. Organic viticulture differs from conventional viticulture, mainly because of the absence of synthetic products, the soil tillage, and the level of organic carbon in the soil. The purpose of the study was to determine the actual differences between conventional and organic vineyard management in terms of greenhouse gas emissions, comparing multiannual data from 25 wineries in northern Italy. No statistically significant differences were found between the overall mean values of conventional and organic management. In organically farmed vineyards, a higher incidence of fuel consumption was observed, while in conventionally farmed vineyards higher emissions were observed, due to the use of such products as pesticides and fertilizers. No differences were found between the two management systems in terms of emissions resulting from direct fertilizing. Further assessment of the potential sequestration of organic fertilizer would be necessary.

The importance of soil biodiversity and soil-based ecosystem services in the context of viticulture has recently been emphasized. Over 85% of soil fauna species richness is represented by edaphic arthropod communities. Edaphic arthropod responses to soil characteristics and management practices can be considered as good bioindicators of soil quality. Here, 168 soil samples that were collected from 2014 to 2019 in several vineyards of different Italian wine-growing areas were analyzed to explore how arthropod communities respond to several factors that are characteristic of vineyard ecosystems. The analysis of the combined effects of the primary abiotic variables (the chemical and physical characteristics of soil) and management practices (organic vs. conventional, soil inter-row management) on soil biological quality (assessed by QBS-ar index) identified soil temperature and soil texture as the abiotic factors exerting the most significant effect on the QBS-ar values. Organic vineyards exhibited higher QBS-ar values compared to those of conventionally managed vineyards, and subsoiling negatively influenced the soil biological quality.

Biodiversity regulates agroecosystem processes, ensuring stability. Preserving and restoring biodiversity is vital for sustainable agricultural production. Species identification and classification in plant communities are key in biodiversity studies. Remote sensing supports species identification. However, accurately identifying plant species in heterogeneous plant areas presents challenges in dataset acquisition, preparation, and model selection for image classification. This study presents a method that combines object-based supervised machine learning for dataset preparation and a pre-trained transfer learning model (EfficientNetV2) for precise plant species classification in heterogeneous areas. The methodology is based on the multi-resolution segmentation of the UAV RGB orthophoto of the plant community into multiple canopy objects, and on the classification of the plants in the orthophoto using the K-nearest neighbor (KNN) supervised machine learning algorithm. Individual plant species canopies are extracted with the ArcGIS training dataset. A pre-trained transfer learning model is then applied for classification. Test results show that the EfficientNetV2 achieves an impressive 99% classification accuracy for seven plant species. A comparative study contrasts the EfficientNetV2 model with other widely used transfer learning models: ResNet50, Xception, DenseNet121, InceptionV3, and MobileNetV2.

The automatic identification of plant species using unmanned aerial vehicles (UAVs) is a valuable tool for ecological research. However, challenges such as reduced spatial resolution due to high-altitude operations, image degradation from camera optics and sensor limitations, and information loss caused by terrain shadows hinder the accurate classification of plant species from UAV imagery. This study addresses these issues by proposing a novel image preprocessing pipeline and evaluating its impact on model performance. Our approach improves image quality through a multi-step pipeline that includes Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) for resolution enhancement, Contrast-Limited Adaptive Histogram Equalization (CLAHE) for contrast improvement, and white balance adjustments for accurate color representation. These preprocessing steps ensure high-quality input data, leading to better model performance. For feature extraction and classification, we employ a pre-trained VGG-16 deep convolutional neural network, followed by machine learning classifiers, including Support Vector Machine (SVM), random forest (RF), and Extreme Gradient Boosting (XGBoost). This hybrid approach, combining deep learning for feature extraction with machine learning for classification, not only enhances classification accuracy but also reduces computational resource requirements compared to relying solely on deep learning models. Notably, the VGG-16 + SVM model achieved an outstanding accuracy of 97.88% on a dataset preprocessed with ESRGAN and white balance adjustments, with a precision of 97.9%, a recall of 97.8%, and an F1 score of 0.978. Through a comprehensive comparative study, we demonstrate that the proposed framework, utilizing VGG-16 for feature extraction, SVM for classification, and preprocessed images with ESRGAN and white balance adjustments, achieves superior performance in plant species identification from UAV imagery.