This article investigates the relationship between meteorological factors and the weight dynamics of honey bee ( Apis mellifera ) colonies. Beekeeping, a crucial component of agriculture, is directly influenced by environmental conditions. The study employs a comprehensive approach, integrating meteorological data and hive weight measurements to assess the impact of temperature, humidity, wind speed and precipitation on honey bee colony productivity. Through bee colony weight measurements in four different geographical locations and available meteorological data, the research aims to identify patterns and correlations between meteorological variations and the fluctuations in hive weight, shedding light on the potential implications for beekeeping practices and the overall wellbeing of honey bees. Weight Delta is a negative or positive increase in the average weight of the hive in the current hour in relation to the hive’s average weight in the preceding hour of day. The developed correlation matrix revealed that the bee colony weight Delta value most depends on the air relative humidity, temperature and hour of the day. Random Forest was selected as the regression model because it showed the most promising performance comparing to other regression models. The developed prediction model showed that the highest Delta value is obtained when the outdoor temperature is in the range of 19 °C to 27 °C and the relative humidity is from 20% to 40%. The findings contribute valuable insights to the fields of apiculture and environmental science, facilitating informed decision-making for beekeepers and policymakers alike in efforts to mitigate the challenges faced by honey bee colonies in an ever-changing climate.

The study is part of a larger project aimed at developing an integrated disease risk warning and early detection system for greenhouse-grown tomatoes, particularly for medium- and small-scale growers. Tomato plants (Solanum lycopersicum L. ‘Encore’ F1) were cultivated under controlled greenhouse conditions and artificially inoculated with Alternaria sp., the causal agent of early blight. Disease progression was monitored using a hyperspectral (HS) camera operating at 400–1000 nm, alongside visual disease assessments. Five experimental replicates were conducted, differing slightly in plant developmental stage at inoculation and post-inoculation temperature and relative humidity. A total of 1000 HS images were acquired, comprising 155 control and 845 inoculated leaves, although visible symptoms did not develop on all inoculated leaves. Mean visually assessed disease severity across replicates ranged from 0.1% to 17.7%. Principal component analysis (PCA) effectively discriminated between diseased and non-diseased tissues. The most informative spectral regions were associated with pigment absorption (beyond 550 nm), red-edge, and near-infrared domains, supporting their relevance for early detection of Alternaria-induced stress. As proof of concept, logistic regression-based leaf image segmentation achieved a mean cross-validation accuracy equal to 93.8%.