In this article, we introduce machine learning (ML) techniques developed for the monitoring of the brown marmorated stink bug (BMSB), a significant agricultural pest responsible for considerable crop damage worldwide. The Haly.ID project, initiated in early 2021, aims to enhance BMSB monitoring through the utilization of information and communication technology methods. We employ computer vision techniques on RGB images captured by drones and investigate the performance of deep neural networks to evaluate the impact of this invasive species on crop yields in orchards around Europe. Specifically, we evaluate the single shot multibox detector, detection transformer, YOLOv5 , YOLOv9 , and YOLOv10 architectures for full-level and patch-level image analysis, respectively. To improve detection accuracy, we experiment with shortwave infrared hyperspectral imaging (SWIR-HSI) in laboratory settings. Given that pheromone baited traps are the most accepted tools for pest detection by field operators, we also propose an Internet of Things sticky trap with an integrated camera equipped with lightweight convolutional neural networks models operating “on the edge” in this resource constrained system. In addition, we develop a client–server application for real-time bug detection, integrating the ML models to provide accessible results to farmers. Lastly, we explore effective postharvesting strategies using SWIR-HSI images to detect insect punctures invisible to the naked eye, thereby enhancing the quality of marketable fruit.

Agriculture plays a crucial role in Romania's economy, a fact that accelerates the search for ways to maximize production yield and profit. The aim of the paper is to study the characteristics of the transformation of agriculture in the context of digitization. Research methods include scientific and theoretical approaches to assess the state of agriculture and its potential in the context of digitization, such as system and situation analysis. The current stage of agricultural development is characterized by a significant transformation of management and production processes due to the introduction of digital technologies. The experience has convincingly shown that the traditional forms of development of agricultural production have practically exhausted themselves. In the new conditions of financial and economic activity, the scientific and technological progress becomes decisive. In agriculture, the digital transformation has a significant impact on material and human resources, increases the productivity of crops, improves the quality of agricultural and livestock products. The digitization of agriculture is extremely important, because it is a source of agricultural economic growth and can become a strong incentive for the innovative development of the sector. Investments in the development of digital infrastructure in rural areas can improve the living conditions of the rural population, with local authorities solving more efficiently the problems within their competence. Also, the digitalization of agriculture will promote the development of small farms in rural areas and contribute to the diversification of the rural economy.

The COVID-19 pandemic has led to the introduction of unprecedented safety measures, one of them being physical distancing recommendations. Here, we assessed whether the pandemic has led to long-term effects on two important physical distancing aspects, namely interpersonal distance preferences and interpersonal touch behaviors. We analyzed nearly 14,000 individual cases from two large, cross-cultural surveys – the first conducted 2 years prior to the pandemic and the second during a relatively stable period of a decreased infection rate in May-June 2021. Preferred interpersonal distances increased by 54% globally during the COVID-19 pandemic. This increase was observable across all types of relationships, all countries, and was more pronounced in individuals with higher self-reported vulnerability to diseases. Unexpectedly, participants reported a higher incidence of interpersonal touch behaviors during than before the pandemic. We discuss our results in the context of prosocial and self-protection motivations that potentially promote different social behaviors.

The demand for soybeans in Europe motivates breeders, researchers, and growers to find suitable cultivars to adapt and extend the soybean crop to improper climate areas. Weed control is a crucial aspect of crop technology in organic agriculture, but particularly for soybean crops. In laboratory conditions, the cumulative stress index for seedlings was determined to identify the susceptible cultivars. A field experiment with 14 soybean accessions and 2 sowing dates was conducted under organic farming conditions over the course of three years, from 2020 to 2022. Plant population density was found to be significantly (p < 0.01 and p < 0.1) negatively correlated to the degree of resistance to low temperature as well as infestation degree with weeds (for p < 0.05 and p < 0.1), with the exception of early sowing in 2021. Yield was significantly (p < 0.05, p < 0.01, p < 0.1) correlated with plant population density, with the exception of optimal sowing in 2022. Early sowing variants emerged with vigor in the first two years, breeding lines and registered varieties showed low input, and organic agriculture systems showed low yields in the drought years of 2020 and 2022. Although early sowing even in the first two years proved to be a practice that increased the cultivars’ performance, in 2022, due to the long period of chilling stress in the field, this option had negative effects on yield due to the high weed frequency. Therefore, the early sowing strategy for the soybean crop in this particular case of non-irrigated conditions in a temperate continental area proved to be a risky practice.

The invasive insect brown marmorated stink bug (BMSB) is an emerging pest of global importance, as it is destroying fruits and seeds, having caused estimated damages of € 588 million to crops in 2019 in Northern Italy alone. An open challenge is to improve monitoring of BMSB in order to be able to deploy countermeasures more efficiently and to increase consumer confidence in the end product. The Horizon 2020 Haly.ID project seeks to reduce or eliminate dependence on conventional monitoring tools and practices, such as traps, baits, visual inspections, sweep netting, and tree beating. In their place, the project proposes the use of unmanned aerial vehicle (UAV) and Internet of Things (IoT) solutions for monitoring the insect population and investigates novel methods for enhancing the quality of fruit in the market. In this work, we focus on the novel autonomous IoT insect monitoring system consisting of multiple innovative solutions for BMSB monitoring and trusted data management developed in Haly.ID . In particular, this article describes the challenges faced when integrating and deploying this monitoring system consisting of those different parts and aims at presenting valuable “lessons learned” for the realization of future deployments. We show that massive over-provisioning of power supply and network speed allows to adapt the system at run-time reflecting changing project requirements, and to conduct experiments remotely. At the same time, over-provisioning introduces new weak points impacting the system reliability, such as cables that can be unplugged or damaged.

Grain morphometry is presently among the main targets of modern barley breeding. Three yield trials with winter barley cultivars were performed in the 2018-2020 period at the National Agricultural Research and Development Institute Fundulea in order to analyze the weight of thousand grains and grain morphometry (grain length, grain width, grain area, grain circularity, grain length-width ratio, and factor form density) of six and two-row registered Romanian winter barley cultivars. Acquired image analysis of grains produced by 25 winter barley cultivars in three years with different grain filling conditions, showed that variation of climatic conditions significantly influenced the thousand grain weight (TGW), grain length (Gl), grain width (Gw), grain area (Ga), grain circularity (Gc), grain length-width ratio (L/W ratio) and factor form density (FFD). The barley cultivars were significantly different for all studied traits, which underlined a high level of diversity. All traits were on average different between six-row and two barley cultivars. TGW was highly correlated to Ga, Gw, and FFD. The PCA analysis revealed that PC1, PC2, and PC3 explain 99.1% of the amount of variation. Our paper provides extended information and the newest grain morphometry insight of an old, oldest, and modern barley germplasm released in three different breeding periods.