The expansion of LEAN and small batch manufacturing demands flexible automated workstations capable of switching between sorting various wastes over time. To address this challenge, our study is focused on assessing the ability of the Segment Anything Model (SAM) family of deep learning architectures to separate highly variable objects during robotic waste sorting. The proposed two-step procedure for generic versatile visual waste sorting is based on the SAM architectures (original SAM, FastSAM, MobileSAMv2, and EfficientSAM) for waste object extraction from raw images, and the use of classification architecture (MobileNetV2, VGG19, Dense-Net, Squeeze-Net, ResNet, and Inception-v3) for accurate waste sorting. Such a pipeline brings two key advantages that make it more applicable in industry practice by: 1) eliminating the necessity for developing dedicated waste detection and segmentation algorithms for waste object localization, and 2) significantly reducing the time and costs required for adapting the solution to different use cases. With the proposed procedure, switching to a new waste type sorting is reduced to only two steps: The use of SAM for the automatic object extraction, followed by their separation into corresponding classes used to fine-tune the classifier. Validation on four use cases (floating waste, municipal waste, e-waste, and smart bins) shows robust results, with accuracy ranging from 86 to 97% when using the MobileNetV2 with SAM and FastSAM architectures. The proposed approach has a high potential to facilitate deployment, increase productivity, lower expenses, and minimize errors in robotic waste sorting while enhancing overall recycling and material utilization in the manufacturing industry.

More and more attention in sewage sludge management is being devoted to its environmental utilization. This approach is justified both from economic and environmental points of view. However, as with any method, there are certain possibilities and limitations. The goal of the natural utilization of sewage sludge is to recover the valuable agronomic properties and fertilizing potential of the sludge. The main aspect limiting the possibility of using sludge as a fertilizer is the heavy metal content. In this paper, an analysis of the risk of environmental contamination in the case of application of sewage sludge with different forms of sludge treatment was carried out. Risk indices such as Igeo and PERI, based on the comparison of total metal content in sludge and soil, as well as RAC and ERD indices, which take into account the mobility of metals in soil, were calculated. It was shown that high levels of potential risk and geoaccumulation indicators do not necessarily disqualify the use of sewage sludge, the key aspect is the form of mobility in which the heavy metals are found in the sludge, and this should be the only aspect taken into account for the possibility of their environmental use.

Sewage sludge, a by-product of wastewater treatment, is garnering increasing attention in the pursuit of closed-loop economy practices due to its highly beneficial fertilizing properties. However, like any technique, using sewage sludge as fertilizer has potential and limitations. Heavy metals within sewage sludge are a primary limitation curtailing its application as a fertilizer. This study collected sewage sludge samples from four wastewater treatment plants and soil from potential application sites. The mobility of heavy metals was then examined using a sequential BCR analysis. Furthermore, a comprehensive environmental risk assessment associated with the agricultural use of sewage sludge was conducted, using various risk indicators such as I_geo and Nemerov, to compare the cumulative metal concentrations in the sewage sludge and soil. Additionally, risk assessment codes, ecological risk indices of metal mobility, and environmental risk indices were calculated, specifically focusing on the mobility of metals in the soil environment. This research demonstrates that sewage sludge failing to meet conventional criteria for agricultural use based on total metal content does not necessarily pose a high-risk application. Understanding the mobility forms of metals in sewage sludge is crucial, influencing the analysis of their potential utilization. Importantly, sewage sludge from wastewater treatment plants utilizing biological bed technology tends to exhibit a higher tendency of heavy metals to exist in mobile forms, migrating within the soil environment.

In modern agriculture today, the cultivation of agricultural products cannot be imagined without greenhouses. This paper presents an energy optimization of a solar greenhouse with a photovoltaic system (PV) and a ground-source heat pump (GSHP). The PV system generates electricity, while the GSHP is used for heating and cooling. A greenhouse is designed with an Open Studio plug-in in the Google SketchUp environment, the EnergyPlus software (8.7.1 version) was used for energy simulation, and the GenOpt software (2.0.0 version) was used for optimization of the azimuth angle and PV cell efficiency. Results for different solar greenhouse orientations and different photovoltaic module efficiency are presented in the paper. The obtained optimal azimuth angle of the solar greenhouse was −8°. With the installation of a PV array with higher module efficiency (20–24%), it is possible to achieve annual energy savings of 6.87–101.77%. Also, with the PV module efficiency of 23.94%, a concept of zero-net-energy solar greenhouses (ZNEG) is achieved at optimal azimuth and slope angle. Through the environmental analysis of different greenhouses, CO₂ emissions of PV and GSHP are calculated and compared with electricity usage. Saved CO₂ emission for a zero-net-energy greenhouse is 6626 kg CO₂/year. An economic analysis of installed renewable energy systems was carried out: with the total investment of 19,326 € for ZNEG, the payback period is 8.63 years.

One of the barriers to the rapid transition of societies toward a more sustainable future is a scarcity of field experts. Members of scientific and professional communities believe that this obstacle could be overcome by supplementing the decisions of non-experts with artificial intelligence. To examine this opportunity, this study examines the viability of GPT-3.5 as an expert adviser in the energy management of kindergartens. Thus, field experts investigated the deductive and inductive reasoning potential of GPT-LLM (Large Language Model). The first task was conducted on a sample of kindergartens in the Western Balkans. The LLM was instructed to provide the buildings’ specific heat consumption (SHC) by relatively detailed building descriptions and building occupancy. The second task involved kindergartens in various European locations, and the LLM was tasked with estimating energy savings using limited data about the renovation process. The study found deductive reasoning to be insufficient for estimating SHC from the building envelope details, with average accuracy below the least predictive model (R² = 0.56; MAPE = 48%). Including the factor of occupancy, the SHC estimates were relatively accurate, wherein the first deductive test proved precise (MAPE = 27%), but it was less so in the opposite case (MAPE = 67%). In terms of inductive reasoning, the LLM assumptions were relatively consistent with practice.