CONTEXT Crop sequences are important for sustainable agriculture, yet we know relatively little about how they recur across individual fields or which information best predicts the crop grown each year. Denmark's national field records allow both questions to be examined over time. OBJECTIVE We identified recurrent crop sequences across Denmark and tested how well annual crop-family selection could be predicted from crop history, farm characteristics, management, prices, soil and climate. METHODS Using 10 years (2011−2020) of national field-level crop data (∼600,000 fields yr−1), we developed a heuristic algorithm to detect recurring crop sequence patterns. We then trained machine learning (LightGBM) and deep learning (TabNet) models to predict annual crop choices based on preceding crops and lagged management and farm structure predictors, and pedoclimatic conditions. Models were evaluated through forward-chaining validation and temporal holdout tests, and SHAP values were used to examine how LightGBM used each predictor. RESULTS AND DISCUSSION Crop sequences were largely dominated by cereals, with little diversification even in longer sequences. Crop selection patterns were strongly associated with the previous crops and farm typology, but pedoclimatic conditions and previous management played a minor role. The DL model achieved a slightly higher overall accuracy, particularly for dominant crops, while the ML model provided a more balanced performance across different crops and enabled interpretation through SHAP. SIGNIFICANCE The analysis separates two distinct tasks: identifying multi-year crop sequences and predicting the crop family grown each year. The sequence analysis shows why diversification cannot be assessed from sequence length or crop counts alone. The predictive models could help generate locally plausible sequences for agri-environmental simulations, reducing reliance on standard rotations that poorly reflect observed field histories.
European pork production pursues traceability and authenticity to ensure animal welfare, food safety, and support products with geographical indications. This study reports a European survey integrating stable isotope ratios (δ13C, δ15N, δ34S, δ18O, δ2H) and multi-element profiling using IRMS and ICP-MS, on 612 samples collected across Denmark, Poland, Italy, and Spain, with diverse production systems, breeds, feeding, and slaughter ages. Geographical and climatic gradients influenced δ2H and δ18O, which ranged from −111‰ to −89‰ in samples from Denmark and Spain and from 13.3‰ to 16.0‰ in samples from Italy and Spain, respectively. In selected farms, δ13C ranged from −22.7‰ to −17.0‰ depending on diet composition based on C3 and C4 plants. The wide variability in pig management practices suggested that δ15N (2.50 ÷ 4.96‰) increased with slaughter age and was positively correlated with Fe (3.38 ÷ 8.39 mg/kg) and Zn (9.39 ÷ 23.6 mg/kg). Most mineral components were mainly driven by feed formulation and supplementation. Principal component analysis (PCA) showed that samples were grouped based on their origin and husbandry system, confirming the key role of isotopic and elemental markers for the development of a database supporting the pork supply chains across Europe.
Self-adaptive robots adjust their behaviors in response to unpredictable environmental changes. These robots often incorporate deep learning (DL) components into their software to support functionality such as perception, decision-making, and control, enhancing autonomy and self-adaptability. However, the inherent uncertainty of DL-enabled software makes it challenging to ensure its dependability in dynamic environments. Consequently, test generation techniques have been developed to test robot software, and classical mutation analysis injects faults into the software to assess the test suite's effectiveness in detecting the resulting failures. However, there is a lack of mutation analysis techniques to assess the effectiveness under the uncertainty inherent to DL-enabled software. To this end, we propose UAMTERS, an uncertainty-aware mutation analysis framework that introduces uncertainty-aware mutation operators to explicitly inject stochastic uncertainty into DL-enabled robotic software, simulating uncertainty in its behavior. We further propose mutation score metrics to quantify a test suite's ability to detect failures under varying levels of uncertainty. We evaluate UAMTERS across three robotic case studies, demonstrating that UAMTERS more effectively distinguishes test suite quality and captures uncertainty-induced failures in DL-enabled software.
This work presents a systematic methodology for the electrification of industrial breweries through Pinch Analysis. A generalized brewery layout is defined, with a total heat demand of 21.4 kWh/hl, based on literature and case studies. This is used as the basis for Pinch Analysis to quantify energy demands and identify heat recovery opportunities. Three electrification solutions are proposed: a centralized high-temperature heat pump replacing the boiler, a two-heat pump system with a CO2 heat pump supporting the warm water heat recovery tank and a High Temperature Heat Pump for wort boiling, and a fully integrated system combining a CO2 heat pump, a High Temperature Heat Pump booster, and mechanical vapor recompression for wort boiling. Results highlight the trade-offs between solution complexity, energy performance, and investment costs, with electricity consumption ranging from 5 to 3.6 kWh/hl. Economic assessment using both payback period and net present value at year 10 reveals that long-term decision-making favors more efficient but capital-intensive configurations.
Since reconfigurable battery systems (RBS) can set a desired voltage by engaging/bypassing individual cells, they can fast-charge electric vehicles without battery-to-battery DC-DC converters. However, as individual cell voltages limit the control accuracy, current ripples exceed charging standard (IEC61851-23) tolerances. To eliminate the DC-DC converters without increasing losses, this work investigates the feasibility of using a minor subset of cells with pulse-width modulated (PWM) discharging. The analysis is twofold. Laboratory experiments are designed and demonstrate that switching more frequently than 2μs can interfere with switching dynamics. This allows us to choose a PWM frequency, which does not interfere with switching, accelerate degradation or increase impedance, and to choose coils for the battery string to suppress PWM current ripples. The current ripples are validated with laboratory tests. Finally, closed-loop simulations prove the concept. A fast-dynamics simulation is used to prove fast current tracking and to validate a computationally inexpensive theoretical model for current ripples, then a slow-dynamics simulation uses this model to demonstrate that the designed circuit sufficiently reduces the undesired current ripples. The proposed system has similar efficiency to a system with a DC-DC converter, and it is ready for deployment.
