Objectives: Food quality assessment is critical for indicating the shelf-life and ensuring food safety or value. Due to high environmental sensitivity, the post-harvest quality of fresh fruit will undergo complex changes in the supply chain, with various dynamic quality-related features. It is difficult to efficiently and accurately extract comprehensive quality feature of post-harvest fruits from high-dimensional monitoring data with heterogeneous characteristics (numerical and categorical). Therefore, we proposed a dynamic comprehensive quality assessment method based on self-adaptive analytic hierarchy process (SAHP) integrated with the CatBoost model. Materials and Methods: By adaptive weight optimization, the SAHP was utilized to analyze the multi-source quality information and obtain the quantized fusion value, as an output sample of CatBoost machine learning. Then, using heterogeneous monitoring data as input, the CatBoost model was directly trained through unbiased boosting with categorical features for dynamic assessment of overall quality status. Results: Three quality index monitoring data sets for ‘Jufeng’ grape in different transportation chains (normal temperature, cold insulation, and cold chain) were individually constructed as the research samples. Furthermore, compared to other machine learning methods, the SAHP–CatBoost had more accurate results in comprehensive quality feature extraction. In actual transportation chains, the mean absolute error, mean absolute percentage error, and root mean squared error of dynamic comprehensive assessment were limited to 0.0044, 1.012%, and 0.0078, respectively. Conclusions: The proposed method is efficient in handling heterogeneous monitoring data and extracting comprehensive quality information of post-harvest grape as a robust shelf-life indicator. It can reasonably guide post-harvest quality management to reduce food loss and improve economic benefits.

Water retention is an important hydrological ecosystem service of active floodplain soils. The aim of the study was to evaluate the soil chemical, physical, and hydrological properties in Fluvisols in three different ecosystems that have an impact on water retention hydrological ecosystem services (WRHESs). We selected 16 localities along the Štiavnica River in Central Slovakia, 8 located in riparian zones (RZ), 5 in arable lands (AL), and 3 in grasslands (GL). Soil samples were collected from two layers (0–10 and 20–30 cm). In the laboratory, the soil physical (soil texture) and soil chemical properties (pH, soil organic carbon content, humic and fulvic acid ratio) were determined. Using undisturbed soil samples, the soil physical characteristics (particle density, bulk density, porosity, and actual soil moisture–SMa) were measured. With the help of pedotransfer functions, hydrological soil properties (field water capacity–FWC, wilting point–WP, available water capacity–AWC) were estimated. The recorded properties differed between the localities, ecosystems, and two layers. The SMa values showed a higher soil water retention potential of extensively used ecosystems, such as GL and RZ. However, the hydrological properties estimated by pedotransfer functions (FWC, WP, AWC) showed a higher soil water retention potential in AL localities. This indicated that for calculations, selected pedotransfer functions (particle size fractions, organic matter, and bulk density) and other soil or ecosystem properties (e.g., vegetation cover, meteorological conditions) have an impact on WRHESs. One such soil factor can be the quality of organic matter. On the basis of the results of the ANOVA, significant differences emerged between the different ecosystems for selected basic chemical, physical, and hydrological properties. The effect of the soil layer on the soil properties was revealed only in the case of SOC. The results indicated the effect of different ecosystems on soil WRHES and the importance of extensively managed ecosystems, such as RZ and GL. From this point of view, the reduction in the RZ and GL areas during a period of the last 70 years is negative. The findings should be taken into account in future sustainable floodplain management and landscape architecture.

This paper compares the difference in energy consumption in different sub-patterns and features of energy consumption structures used in protected grape production systems using statistical data. Then, spatial characteristics between different production modes based on geographic information systems are also analyzed. The results reveal that the types of energy consumption include steel, iron wire, water, chemical fertilizer, pesticides, electric power, organic fertilizer, plastic films, and labor. The total energy consumption for protected grape production was 210,534.3 MJ ha⁻¹ in 2011, 211,504.6 MJ ha⁻¹ in 2012, and 222,571.8 MJ ha⁻¹ in 2013. From the perspective of cultivation modes, early ripening production and late ripening production consumed more energy than rain-shelter production; in terms of facility types, the total energy input of both vinyl tunnels and solar greenhouses were always higher than rain-shelter greenhouses. Indirect and non-renewable energy consumption were higher than that of direct and renewable energy, which accounted for 90% of energy consumption. Spatial analysis showed that the values of Moran’s I were all positive for the three years, which means protected grape input had a positive spatial autocorrelation. Therefore, we should adjust the energy input structure and choose more sustainable production modes to improve the sustainability of the production of protected grapes.