Giuseppina Pennisi

Hyperspectral imaging adoption is hindered by high investment costs, and multicollinearity among contiguous bands requires dimensionality-reduction (DR) algorithms, raising concerns about cost-effectiveness for farmers. In this study, we propose a direct comparison between feature extraction and feature selection methods as DR strategies for monitoring the nitrogen (N) status of processing tomato. The hyperspectral reflectance (399–1001 nm) was monitored in a processing tomato experiment with four N levels alongside crop traits (aboveground biomass, AGB; N uptake; N nutrition index, NNI). Gaussian process regression (GPR) was trained in two DR scenarios, (i) feature extraction using principal component analysis (GPR-PCA) and (ii) feature selection, with a sequential backward band removal (band analysis tool, BAT, in ARTMO software (v3.30); GPR-BAT), to identify the most informative key bands. The GPR-PCA achieved the highest mean accuracy for AGB, whereas for N uptake and NNI GPR-BAT yielded comparable estimation performance. Selected bands were located in the NIR for all variables, in the red-edge for N uptake and NNI, and in the blue region for NNI, and were interpreted as candidate spectral regions. Based on the identified bands, two candidate multispectral sensor configurations were proposed for N monitoring: an AGB–NNI scenario (6 bands) and an AGB–N uptake scenario (5 bands). These findings suggest the potential of task-specific multispectral sensors for crop N monitoring, although NNI accuracy (RMSE ≈ 0.11 NNI units) remains insufficient for decisions close to the fertilization threshold.

Automated cucumber harvesting requires a perception system that can detect fruit, assess ripeness and localize the peduncle for cutting under real commercial greenhouse conditions. This study proposes an RGB-D perception framework combining YOLOv8n object detection with depth-based geometric estimation. The framework was evaluated on data collected in commercial greenhouses with dense, continuously varying occlusion, variable illumination and multiple co-visible fruits at different maturity stages. Detections were assigned to five operational classes: ripe, unripe, flagged (non-marketable due to overripeness or deformity), obstructed and peduncle. The detector achieved an overall mAP50 of 0.568, but appearance-based ripeness classification proved unreliable. Confusion concentrated along two boundaries: a continuous, judgment-based occlusion criterion and an absolute length threshold that RGB appearance cannot directly resolve. Depth-based length estimation, by contrast, achieved an MAE of 0.72 cm (RMSE = 1.15 cm, MAPE = 4.04%) directly in the greenhouse. Applying the ripeness length threshold to the estimated lengths misclassified 6.4% of fruits at the RIPE/UNRIPE boundary on the dimensional validation set, indicating that length-based ripeness assignment is feasible. Diameter estimation was markedly less accurate (R² = 0.49) and is not proposed as a validated measurement for grading or yield estimation. The framework also estimated candidate 3D cutting points that remained spatially consistent across frames; cutting accuracy requires future robotic validation. These results suggest that, in complex greenhouse environments, ripeness decisions of cucumber should rely on depth-based geometric measurement, with object detection used primarily for fruit and peduncle localization. Combining visual detection with quantitative measurement therefore appears to be a promising basis for robotic cucumber harvesting.

While vertical farming may offer high productivity per unit land area and has received increasing attention for urban food production, research has primarily focused on leafy greens and herbs. Although recent studies have also introduced fruiting vegetables and cereal crops, comparative evaluations under standardized environmental conditions remain limited because crop morphology, duration, harvestable organs, and biomass allocation differ substantially among crop types. This study, conducted in AlmaVFarm, the experimental vertical farm of the University of Bologna, evaluated the productivity and resource use efficiency of five representative crops grown under identical environmental conditions. Crops included dwarf corn as a staple crop, dwarf tomato as a fruit crop, basil as an herb, and lettuce and arugula as leafy greens. To enable meaningful cross-crop evaluations, performance was assessed using normalized indicators of land-surface, cultivation volume, light, energy, and cost use efficiencies. Lettuce achieved the highest annual marketable yield (73.2 kg FW m⁻² y⁻¹), producing 46% more than arugula and 35% more than basil. It also exhibited the greatest land-surface use efficiency (65 kg m⁻² y⁻¹), volume use efficiency (24.5 kg m⁻³ y⁻¹), and energy use efficiency (46.7 g FW kWh⁻¹), corresponding to 3.5-fold and 58-fold higher energy efficiency than tomato and corn, respectively, and up to 1.8-fold higher than arugula and basil. The normalized resource use efficiency framework enabled robust comparisons among contrasting crop categories despite their distinct biological characteristics, revealing substantial differences in adaptation to indoor cultivation. These findings provide a quantitative basis for crop selection and diversification strategies in vertical farming while highlighting the need for crop-specific optimization to improve the resource use efficiency and commercial viability of fruit and staple crops in CEA.

Urban gardens are increasingly framed as multifunctional components of urban green infrastructure, yet limited evidence exists on how ordinary, municipally managed gardens are experienced through everyday and long-term use. This study examined perceived environmental restorativeness, self-reported well-being, and patterns of social and motivational engagement among users of municipally managed urban gardens in Padua, Italy. A mixed-methods design combined a qualitative phase, including document analysis, site observations, and interviews with municipal stakeholders and garden representatives, with a quantitative survey completed by 210 gardeners across ten sites (response rate ≈62%). The questionnaire collected data on sociodemographic characteristics, garden use, social interactions, motivations, and self-reported well-being, and assessed perceived restorativeness using the validated Italian 11-item Perceived Restorativeness Scale (PRS-11). Results showed that gardens were widely perceived as restorative environments, with a mean total PRS-11 score of 7.0 and high internal consistency (Cronbach’s alpha = 0.91). Cluster analyses identified distinct user profiles based on seasonal attendance, social interactions, motivations, and perceived restorativeness. In an exploratory Ordinary Least Squares (OLS) regression, motivations related to being in nature and cultivating the land were significantly associated with higher PRS-11 scores, while meeting friends showed a borderline positive association. Self-reported well-being was highly positive across the sample and showed a descriptive gradient across PRS-11 groups. Overall, the findings suggest that municipally managed urban gardens can function as everyday, socially embedded green infrastructures whose perceived restorative value depends on patterns of access, engagement, motivation, and governance, with implications for inclusive urban green infrastructure planning and municipal policy.

In plant factories with artificial lighting (PFAL), light-emitting diodes (LEDs) are the sole light source, essential for photosynthesis. Changing light features (e.g. spectrum, photoperiod and intensity) can optimize crop quality and yield, reduce energy consumption and production costs and increase energy use efficiency (EUE). Individually inspecting light features has been extensively explored, whereas comprehensive analyses of varying light features while maintaining a similar daily light integral (DLI, the total daily amount of mol received by plants) have been limited. This study aimed to investigate the influence of different combinations of photoperiod and light intensity on the yield, growth and lighting-energy use efficiency (L-EUE) while maintaining a constant DLI on four leafy vegetable crops, namely crispy lettuce ( Lactuca sativa L.), green kale ( Brassica oleracea L.), pak choi ( Brassica rapa L.) and lettuce var. canasta ( L. sativa L.). The experiment took place in a commercial vertical farm equipped with full white spectrum LED light fixtures. Three different light regimes with a DLI (9.75 ± 0.15 mol m ⁻² day ⁻¹ ) were used for the experiment, obtained by simultaneously varying photoperiod and light intensity, as follows: 14 h day ⁻¹ and 190 μmol m ⁻² s ⁻¹ (14/190), 18 h day ⁻¹ and 150 μmol m ⁻² s ⁻¹ (18/150), and 24 h day ⁻¹ and 115 μmol m ⁻² s ⁻¹ (24/115). Continuous light exposure (24/115) yielded the best morphological results for both lettuce cultivars, whereas pak choi showed higher leaf width at higher light intensity and a shorter photoperiod. L-EUE was not affected by light treatments in crispy lettuce, whereas differences were evident in the other three crops in which the shortest photoperiod with the highest intensity was associated with the lowest L-EUE values. Conversely, differences in light use efficiency (LUE) were observed only in pak choi with the shorter photoperiod (14/190), resulting in higher LUE values than in the continuous day (24/115) treatment. The use of 24/115 and 18/150 is a valid strategy to increase L-EUE for the crops used in this study, but additional research with higher DLI is needed to further investigate the effects of different combinations of light intensity and photoperiod in commercial settings. Significance of the study: What is already known on this subject? Light intensity and photoperiod independently affect crop growth and energy-use efficiency in vertical farms. However, their combined effects at constant daily light integral (DLI) need to be deeply investigated, especially in commercial settings. What are the new findings? Reducing light intensity while extending the photoperiod at constant DLI improved lighting-energy use efficiency (L-EUE) by approximately two-fold in canasta lettuce, pak choi and green kale, without compromising yield. Species-specific morphological responses were observed, with lettuce showing increased plant height under continuous light. Additionally, pak choi exhibited higher light use efficiency (LUE) under shorter, more intense exposure. What are the expected impacts on horticulture? These results demonstrate that extending photoperiods at lower light intensities can reduce energy consumption in vertical farms without affecting productivity. The species-specific responses highlight the importance of developing crop-specific light recipes to optimize both yield and energy efficiency in indoor commercial production systems.

Vertical farming (VF) is increasingly regarded as a promising solution for year-round, local leafy-green production; however, its substantial electricity demand remains a key environmental concern, and evidence from commercial multi-crop facilities is still limited. We conducted a cradle-to-grave life-cycle assessment (LCA) of a commercial hydroponic VF in Stockholm producing lettuce, pak choi, and kale; the functional unit (FU) was 1 kg of marketed edible product. Impacts were assessed with Environmental Footprint (EF) 3.1 midpoint indicators and sensitivity analyses for electricity sourcing and allocation. Under the baseline electricity mix, climate change reached 2.89 kg CO₂-eq per kg. Energy use dominated most impact categories, while infrastructure was the second contributor and main driver of abiotic depletion of elements. Shifting the electricity supply altered climate-change results from 2.03 to 3.26 kg CO₂-eq per kg, introducing trade-offs across other indicators, notably water use and mineral depletion. Under identical conditions, higher yields resulted in lower impacts for pak choi than lettuce and kale. Allocation sensitivity was limited: economic and mass allocation matched due to uniform prices, and retail-price allocation did not alter crop ranking or hotspot identification. Overall, environmental performance is governed by electricity demand, electricity-mix assumptions, and dilution of fixed burdens through crop productivity.

The starch and moisture content of saffron corms are critical indicators of their flowering potential and yield. This study investigated the use of rapid, minimally invasive VNIR reflectance spectroscopy measurement to assess these parameters. The measurements were used to develop predictive models through four machine learning algorithms (PLSR, RF, SVR, and GPR). Spectral data were obtained from 130 fresh corm samples. Wavelength analysis identified key starch-sensitive intervals (~930–1000 nm and ~1150–1220 nm) and a broad moisture-sensitive region (~900–1350 nm). Among the evaluated models, the combination of the multiplicative scatter correction pre-processing method and Gaussian process regression (MSC-GPR) demonstrated the optimal predictive performance for water content (R² = 0.92, RMSE = 0.71%, RPD = 4.56, RPIQ = 5.37), and the combination of the MSC method and partial least squares regression (PLSR-MSC) demonstrated moderate performance for starch content (R² = 0.73, RMSE = 28.7 mg g⁻¹, RPD = 2.14, RPIQ = 2.81, dry weight). These results demonstrate the viability of VNIR spectroscopy as a minimally invasive tool for the pre-planting assessment of saffron corm quality under laboratory conditions. The method provides a laboratory-based framework for corm screening and selection, with potential for future adaptation to field settings using portable spectrometers following expanded calibrations and advanced modeling techniques.

Light quality plays a decisive role in controlled-environment agriculture, shaping plant morphology, physiology, and productivity. This study investigated the impact of far-red (FR) light on Cannabis sativa L. by comparing two different application strategies: continuous FR supplementation throughout 12 h of the photoperiod and end-of-day (EOD) FR exposure applied only at the end of the light period. In both treatments, FR was added to a background spectrum of red and blue (RB) light, while a control group grown under RB light alone was included to assess the specific effects of FR on plant growth, physiological responses, and flowering. Continuous FR exposure induced pronounced shade-avoidance traits, increasing plant height by 9% and petiole length by 17% relative to the control, and raised leaf dry weight to 12.9 g, 9% higher than under EOD (11.7 g) and 16.3% higher than under RB alone (10.8 g). Besides plant height and petiole length, both FR and EOD treatment induced limited morphological adjustments but increased chlorophyll content by 9%, resulting in greater canopy expansion and photosynthetic potential. However, flowering time was unaffected by spectral treatment, confirming that Cannabis floral induction is tightly regulated by photoperiod rather than light quality. Energy-use analysis revealed that EOD supplementation achieved many of the benefits of continuous FR while reducing overall consumption, but energy-use efficiency analysis proved FR as the more efficient treatment. These findings highlight the potential of FR light, particularly when applied continuously, to optimize vegetative growth and canopy physiology in controlled-environment Cannabis cultivation, while EOD strategies offer a practical compromise between cost savings and physiological benefits.

The starch and moisture content of saffron corms are critical indicators of their flowering potential and yield. This study investigated the use of rapid, non-destructive vis-NIR reflectance spectroscopy measurement to assess these parameters. The measurements were used to develop predictive models through four machine learning algorithms (PLSR, RF, SVR, and GPR). Spectral data were obtained from 130 fresh corm samples. Wavelength analysis identified key starch-sensitive intervals (~930–1000 nm and ~1150–1220 nm) and a broad moisture-sensitive region (~900–1350 nm). Among the evaluated models, the partial least squares regression (PLSR) model demonstrated the optimal predictive performance for moisture (R² = 0.89, RMSE = 0.91%, RPD = 3.67, RPIQ = 4.91) and moderate performance for starch (R² = 0.68, RMSE = 26.29 mg g⁻¹, RPD = 1.87, RPIQ = 2.37, dry weight). These results demonstrated the viability of VIS-NIR spectroscopy as a viable, non-destructive tool for the pre-planting assessment of saffron corm quality. The method provides a practical foundation for corm screening and selection, with potential for further improvement in starch prediction through expanded calibrations and advanced modeling techniques.