Makine Öğrenmesi ile Hava Durumu ve Arıcılık Verilerini Kullanarak Bal Arısı Koloni Sağlığının Tahmini

Year 2025, Volume: 4 Issue: 2, 140 - 160, 30.11.2025

Ümit Yılmaz

Abstract

Bal arısı kolonileri, küresel gıda güvenliği için hayati öneme sahiptir; ancak biyolojik ve çevresel stres faktörlerinin etkileşimi nedeniyle yüksek kayıplar yaşamaya devam etmektedir. Bu nedenle koloni sağlığının tahmin edilmesi, sürdürülebilir arıcılık yönetimi açısından öncelikli bir konudur. Bu çalışma, hava durumu ve mevsimsel değişkenlerle birlikte Sağlıklı Koloni Kontrol Listesi saha değerlendirmelerinden yararlanarak bal arısı koloni sağlığının öngörülebilirliğini incelemektedir. Kuzey Carolina ve Utah’taki arılıklardan 1.277 denetim ve yakın meteoroloji istasyonu kayıtları kullanılmıştır. Türetilen özellikler arasında buhar basıncı açığı, sıcaklık–nem etkileşimleri, rüzgâr enerjisi tahminleri ve mevsimsel kodlamalar bulunmaktadır. Tahmin görevi, ikili sınıflandırma (sağlıklı vs. sağlıksız) olarak kurgulanmıştır. Birçok makine öğrenmesi modeli test edilmiş, özellikle Rastgele Orman, Aşırı Rastgele Ağaçlar, Hafif Gradyan Artırma Makinesi, Kategorik Artırma, Gradyan Artırma, Histogram Tabanlı Gradyan Artırma ve Aşırı Gradyan Artırma gibi ağaç tabanlı topluluk yöntemleri üzerinde durulmuştur. Optimize edilmiş yumuşak oylama ve yığınlama gibi topluluk stratejileri de uygulanmıştır. Sonuçlar, doğruluk oranlarının %75–76 aralığında, ROC AUC değerlerinin ise 0,80’e yakın olduğunu göstermiştir. Hassasiyet %0,70’in üzerinde gerçekleşirken, duyarlılık düşük kalmıştır (~0,55). Mevsimsellik en baskın belirleyici olurken, yağış ve nem gibi hava durumu göstergeleri ek katkı sağlamıştır. Bulgular, tarımsal meteorolojik verilerin karar destek sistemlerinde yararlı olduğunu, ancak biyolojik ve yönetimsel değişkenlerin gelişmiş yöntemlerle bütünleştirilmesinin gerektiğini ortaya koymaktadır.

Keywords

Bal arısı sağlığı , sağlıklı koloni kontrol listesi , makine öğrenmesi , topluluk yöntemleri

Predicting Honeybee Colony Health Using Weather and Apiary Data with Machine Learning

Abstract

Honey bee colonies are essential for global food security but continue to suffer heavy losses from interacting biological and environmental stressors. Predicting colony health is therefore a priority for sustainable apicultural management. This study examines the feasibility of forecasting honey bee colony health using weather and seasonal variables together with field assessments from the Healthy Colony Checklist. A dataset of 1,277 inspections from apiaries in North Carolina and Utah, integrated with meteorological records from nearby stations, was analyzed. Engineered features included vapor pressure deficit, temperature–humidity interactions, wind energy estimates, and seasonal encodings. The prediction was structured as a binary classification task (healthy vs. unhealthy). Several machine learning models were tested, emphasizing tree-based ensembles such as Random Forest, Extra Trees, Light Gradient Boosting Machine, Categorical Boosting, Gradient Boosting, Histogram-based Gradient Boosting, and Extreme Gradient Boosting. Ensemble strategies, including optimized soft voting and stacking, were also applied. Results showed accuracies of 75–76% with ROC AUC values near 0.80. Precision exceeded 0.70, while recall remained modest (~0.55). Seasonality was the dominant predictor, with weather indicators providing complementary value. Findings confirm the usefulness of agrometeorological data for decision-support in apiculture but also highlight the limits of weather-only models. Incorporating hive-level biological and management factors with advanced learning methods is recommended.

Keywords

Honey bee health , healthy colony checklist , machine learning , ensemble methods

References

• J. Marcelino et al., “The movement of western honey bees (Apis mellifera L.) among U.S. states and territories: history, benefits, risks, and mitigation strategies,” Front. Ecol. Evol., 10, 850600, 2022.
• E. J. García-Vicente et al., "Main causes of producing honey bee colony losses in southwestern Spain: a novel machine learning-based approach," Apidologie, 55(5), 67, 2024.
• J. Tang et al., "Survey results of honey bee colony losses in winter in China (2009–2021)," Insects, 14(6), 554, 2023.
• B. Branchiccela et al., "Impact of nutritional stress on the honeybee colony health," Sci. Rep., 9(1), 10156, 2019.
• Z. Şengül, B. Yücel, G. Saner, and Ç. Takma, "Investigating the impact of climate parameters on honey yield under migratory beekeeping conditions through decision tree analysis: the case of İzmir province," ANADOLU Ege Tarımsal Araştırma Enstitüsü Dergisi, 33(2), 268-280, 2023.
• M. Güneşdoğdu and A. Şekeroğlu, "Honey bee (Apis mellifera L.) nutrients and nutritional physiology: A review," in Current Studies on Agriculture, Forest and Aquatic Products, M. N. İzgi ed. Türkiye: Iksad Publishing House, 2024, 3-46.
• K. A. Overturf et al., "Winter weather predicts honey bee colony loss at the national scale," Ecol. Indic., 145, 109709, 2022.
• Z. N. Ulgezen, C. van Dooremalen, and F. van Langevelde, "Why does resource availability matter for honeybee colonies in spring?," Insectes Soc., 72, 405-411, 2025.
• J. A. Cazier, R. Rogers, E. E. Hassler, and J. T. Wilkes, "The healthy colony checklist (HCC) Part I: A framework for aggregating hive inspection data," Bee Culture, 29-32, 2018.
• D. B. Carlini et al., "Quantitative microbiome profiling of honey bee (Apis mellifera) guts is predictive of winter colony loss in northern Virginia (USA)," Sci. Rep., 14(1), 11021, 2024.
• H. Hammami and N. Abdulaziz, "BeeBetter: A multi-modal beehive system for honeybee health monitoring and hazard detection," in Proc. 7th Int. Conf. Signal Process. Inf. Secur. (ICSPIS), Nov. 12–14, 2024, 1-5.
• A. Liang, “Developing an AI-based integrated system for bee health evaluation,” IEEE Access, 158703-158713, 2024.
• C. van Dooremalen et al., "Bridging the gap between field experiments and machine learning: The EC H2020 B-GOOD project as a case study towards automated predictive health monitoring of honey bee colonies," Insects, 15(1), 76, 2024.
• M. Torky, A. A. Nasr, and A. E. Hassanien, "Recognizing beehives’ health abnormalities based on MobileNet deep learning model," Int. J. Comput. Intell. Syst., 16(1), 135, 2023.
• Y. Zhu et al., "Early prediction of honeybee hive winter survivability using multi-modal sensor data," in Proc. IEEE Int. Workshop Metrol. Agric. Forestry (MetroAgriFor), Nov. 6–8, 2023, 657-662.
• A. R. Braga et al., "A method for mining combined data from in-hive sensors, weather and apiary inspections to forecast the health status of honey bee colonies," Comput. Electron. Agric., 169, 105161, 2020.
• E. Lower, S. P. Kollaparthi, R. Rogers, E. Hassler, and J. Cazier, "Predicting honeybee health: the healthy colony checklist, hive scale and weather data," Data Anal. Good, 2, 1-25, 2024.
• E. Lower, S. Kollaparthi, R. Rogers, E. Hassler, and J. Cazier, Predicting Honeybee Health: The Healthy Colony Checklist, Hive Scale and Weather Data. Mendeley Data, 2025.
• T. Luo, J. Qu, and S. Cheng, "Technological opportunity discovery based on VERGM and random forest model," Expert Syst. Appl., 293, 128712, 2025.
• J. Luo, L. Wang, W. Gao, and H. Jiang, "Prediction of ventilation air methane explosion in regenerative thermal oxidation based on hyperparameter-optimized random forest algorithm," J. Loss Prev. Process Ind., 98, 105757, 2025.
• K. F. Chin et al., "Predicting unmeasured asymmetry time spectra in μSR experiments using random forest," J. Magn. Magn. Mater., 629, 173320, 2025.
• M. Badrakh, N. Tserendash, E. Choindonjamts, and G. Albert, "Potential of random forest machine learning algorithm for geological mapping using PALSAR and Sentinel-2A remote sensing data: A case study of Tsagaan-uul area, southern Mongolia," J. Asian Earth Sci.: X, 14, 100204, 2025.
• Z. Guo, T. Huang, Z. Wu, T. Lin, and H. Huang, "A study on dynamic cleaning of charging pile electric energy metering data based on improved random forest algorithm," Measurement, 256, 118114, 2025.
• M. Matboli et al., "Machine learning-based stratification of prediabetes and type 2 diabetes progression," Diabetol. Metab. Syndr., 17(1), 227, 2025.
• M. R. C. Acosta, S. Ahmed, C. E. Garcia, and I. Koo, "Extremely randomized trees-based scheme for stealthy cyber-attack detection in smart grid networks," IEEE Access, 8, 19921-19933, 2020.
• S. Zhang, "Drug usage classification based on personality and demographic features using a combination of sampling and machine learning algorithms," Comput. Methods Biomech. Biomed. Eng., 1-22, 2025.
• M. Seyyedattar, S. Zendehboudi, and S. Butt, "Relative permeability modeling using extra trees, ANFIS, and hybrid LSSVM–CSA methods," Nat. Resour. Res., 31(1), 571-600, 2022.
• W. Kong, P. Hou, X. Liang, F. Gao, and Q. Liu, "An interpretable rockburst prediction model based on SSA-CatBoost," Tunn. Undergr. Space Technol., 164, 106820, 2025.
• M. Rahimi et al., "Meticulous estimation of maize actual evapotranspiration: A comprehensive explainable CatBoost algorithm reinforced with Jackknife uncertainty paradigm," Comput. Electron. Agric., 237, 110599, 2025.
• Y. Hu et al., "Predictive optimization of educational buildings' environmental performance under future climate scenarios using Catboost and SHAP," Sol. Energy, 300, 113746, 2025.
• Z. Fan, J. Gou, and S. Weng, "Complementary CatBoost based on residual error for student performance prediction," Pattern Recognit., 161, 111265, 2025.
• M. H. Sulaiman, Z. Mustaffa, A. S. Samsudin, A. I. Mohamed, and M. M. Saari, "Electric vehicle battery state of charge estimation using metaheuristic-optimized CatBoost algorithms," Franklin Open, 11, 100293, 2025.
• [X. Zhang, H. Wang, G. Yu, and W. Zhang, "Machine learning-driven prediction of hospital admissions using gradient boosting and GPT-2," Digit. Health, 11, 20552076251331319, 2025.
• M. K. Hossen and M. S. Uddin, "From data to insights: Using gradient boosting classifier to optimize student engagement in online classes with explainable AI," Educ. Inf. Technol., 30(13), 18089-18130, 2025.
• E. Ismail, W. Gad, and M. Hashem, "HEC-ASD: A hybrid ensemble-based classification model for predicting autism spectrum disorder disease genes," BMC Bioinformatics, 23(1), 554, 2022.
• L. W. Rizkallah, "Enhancing the performance of gradient boosting trees on regression problems," J. Big Data, 12(1), 35, 2025.
• S. Rahman, M. Irfan, M. Raza, K. Moyeezullah Ghori, S. Yaqoob, and M. Awais, "Performance analysis of boosting classifiers in recognizing activities of daily living," Int. J. Environ. Res. Public Health, 17(3), 1082, 2020.
• A. Fatty, A.-J. Li, and Z.-G. Qian, "An interpretable evolutionary extreme gradient boosting algorithm for rock slope stability assessment," Multimed. Tools Appl., 83(16), 46851–46874, 2024.
• I. B. Mustapha et al., "Comparative analysis of gradient-boosting ensembles for estimation of compressive strength of quaternary blend concrete," Int. J. Concr. Struct. Mater., 18(1), 20, 2024.
• H. Emami, S. Emami, and V. Rezaverdinejad, "A backtracking search-based extreme gradient boosting algorithm for soil moisture prediction using meteorological variables," Earth Sci. Inf., 18(2), 181, 2025.
• M. Achite, H. Nasiri, O. M. Katipoğlu, M. Abdallah, R. Moazenzadeh, and B. Mohammadi, "A coupled extreme gradient boosting-MPA approach for estimating daily reference evapotranspiration," Theor. Appl. Climatol., 156(2), 113, 2025.
• T. Kavzoglu and A. Teke, "Advanced hyperparameter optimization for improved spatial prediction of shallow landslides using extreme gradient boosting (XGBoost)," Bull. Eng. Geol. Environ., 81(5), 201, 2022.
• Q. Guo, H. Wang, and Y. Tian, "Automated algorithm selection for black-box optimization using light gradient boosting machine," Swarm Evol. Comput., 98, 102071, 2025.
• T. O. Omotehinwa, D. O. Oyewola, and E. G. Moung, "Optimizing the light gradient-boosting machine algorithm for an efficient early detection of coronary heart disease," Inf. Health, 1(2), 70–81, 2024.
• S. Zhang, Z. Wang, and X. Su, "A study on the interpretability of network attack prediction models based on light gradient boosting machine (LGBM) and SHapley additive explanations (SHAP)," Comput. Mater. Continua, 83(3), 5781–5809, 2025.
• S. Radhika, A. Prasanth, and K. K. D. Sowndarya, "A reliable speech emotion recognition framework for multi-regional languages using optimized light gradient boosting machine classifier," Biomed. Signal Process. Control, 105, 107636, 2025.
• M. Elattar, A. Younes, I. Gad, and I. Elkabani, "Explainable AI model for PDFMal detection based on gradient boosting model," Neural Comput. Appl., 36(34), 21607–21622, 2024.
• M. Tamim Kashifi and I. Ahmad, "Efficient histogram-based gradient boosting approach for accident severity prediction with multisource data," Transp. Res. Rec., 2676(6), 236–258, 2022.
• M. Saied, S. Guirguis, and M. Madbouly, "A comparative study of using boosting-based machine learning algorithms for IoT network intrusion detection," Int. J. Comput. Intell. Syst., 16(1), 177, 2023.
• S. Seth, G. Singh, and K. Kaur Chahal, "A novel time-efficient learning-based approach for smart intrusion detection system," J. Big Data, 8(1), 111, 2021.
• A. Habib, B. Alibrahim, M. Z. Alnunu, H. Moussa, and M. Habib, "Comprehensive assessment on estimating the thermodynamic and mechanical properties of multicomponent Fe–Cr-based alloys using machine learning techniques," Discover Mater., 5(1), 76, 2025.
• I. Chhillar and A. Singh, "An improved soft voting-based machine learning technique to detect breast cancer utilizing effective feature selection and SMOTE-ENN class balancing," Discover Artif. Intell., 5(1), 4, 2025.
• R. Dey and R. Mathur, "Ensemble learning method using stacking with base learner, a comparison," in Proc. Int. Conf. Data Analytics Insights (ICDAI), Singapore: Springer, 2023, 159–169.
• B. A. Ture, A. Akbulut, A. H. Zaim, and C. Catal, "Stacking-based ensemble learning for remaining useful life estimation," Soft Comput., 28(2), 1337–1349, Jan. 2024.
• H. Ye, H. Qin, Y. Tang, N. Ungvijanpunya, and Y. Gou, "Mapping an intelligent algorithm for predicting female adolescents’ cervical vertebrae maturation stage with high recall and accuracy," Prog. Orthod., 25(1), 20, 2024.
• P. Singh et al., "An ensemble-driven machine learning framework for enhanced water quality classification," Discover Sustain., 6(1), 552, 2025.
• D. K. Dake, E. Nwiah, G. S. Klogo, and W. X. Ativi, "Instructor-assisted question classification system using machine learning algorithms with N-gram and weighting schemes," Discover Artif. Intell., 3(1), 29, 2023.
• A. Cisneros Eufracio, R. S. Perez Alvarado, J. A. Rosales Huamani, U. R. Villanueva, J. L. Castillo Sequera, and J. M. Gomez Pulido, "Rock block fall prediction prototype by structural control applied to slopes using Quantum Machine Learning (QML)," J. Supercomput., 81(2), 422, 2025.
• M. Abdelsattar, A. AbdelMoety, and A. Emad-Eldeen, "Advanced machine learning techniques for predicting power generation and fault detection in solar photovoltaic systems," Neural Comput. Appl., 37(15), 8825–8844, 2025.
• H. GhorbanTanhaei, P. Boozary, S. Sheykhan, M. Rabiee, F. Rahmani, and I. Hosseini, "Predictive analytics in customer behavior: Anticipating trends and preferences," Results Control Optim., 17, 100462, 2024.