Discrete time series forecasting in non-invasive monitoring of managed honey bee colonies: Part II: are hive weight and in-hive temperature seasonal and colony-specific?

Authors: KULYUKIN, VLADIMIR - Utah State University; KULYUKIN, ALEKSEY - Utah State University; Meikle, William

Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/8/2025
Publication Date: 7/10/2025
Citation: Kulyukin, V.A., Kulyukin, A.V., Meikle, W.G. 2025. Discrete time series forecasting in non-invasive monitoring of managed honey bee colonies: Part II: are hive weight and in-hive temperature seasonal and colony-specific?. Sensors. 25(14): Article 4319. https://doi.org/10.3390/s25144319.
DOI: https://doi.org/10.3390/s25144319

Interpretive Summary: Monitoring honey bee colonies using sensors, such as hive scales and temperature sensors is becoming more widespread. In this study we examined datasets of continuous hive weight and temperature to see whether the past performance of the bee colonies could be used to forecast future performance, at least in the short term. We applied different models to the hive weight and temperature data to see if future data can be anticipated, and to see if differences among bee colonies were smaller than or bigger than differences we observed over time. We found that time does matter - that bee colonies change in weight and temperature over the course of the season - and that differences among hives were signficant. Hive weight was easier to forecast over the season than hive temperature. These results will help us build better models to apply to longer-term datasets, and to datasets in different locations and with different kinds of bees.

Technical Abstract: We explored the stationarity, trend, and seasonality of the hive weight and in-hive temperature of ten managed honey bee (Apis mellifera) colonies at a research apiary of the Carl Hayden Bee Research Center in Tucson, Arizona, USA. The hives were monitored with electronic scales and in-hive temperature sensors from June to October 2022. The weight and temperature were recorded every five minutes around the clock. The collected data were curated into 2160 timestamped weight and 2160 timestamped temperature observations. We performed a systematic autoregressive integrated moving average (ARIMA) time series analysis to answer three fundamental questions: (a) Does seasonality matter in the ARIMA forecasting of hive weight and in-hive temperature? (b) To what extent do the best forecasters of one hive generalize to other hives? and (c) Which time series type (i.e., hive weight or in-hive temperature) is better predictable? Our principal findings were as follows: (1) The hive weight and in-hive temperature series were not white noise, were not normally distributed, and, for most hives, were not difference- or trend-stationary; (2) Seasonality matters, in that seasonal ARIMA (SARIMA) forecasters outperformed their ARIMA counterparts on the curated dataset; (3) The best hive weight and in-hive temperature forecasters of the ten monitored colonies appeared to be colony-specific; (4) The accuracy of the hive weight forecasts was consistently higher than that of the in-hive temperature forecasts; (5) The weight and temperature forecasts exhibited common qualitative patterns