Proactive early invisible spoilage-risk prediction through uncertainty-quantified temporal microbial growth intelligence
4 affiliations
- 1College of Computer and Information Sciences, Jouf University, Sakaka, Saudi Arabia
- 2Department of ECE, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi/Chennai, Tamil Nadu, India
- 3Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia
- 4Department of Mathematics, College of Science and Humanities in Al-Kharj, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia
Abstract
The study addresses the need for proactive food safety monitoring because microbial growth can increase before visible spoilage becomes apparent. Existing microbial prediction methods mainly provide deterministic forecasts and often lack temporal interpretability, predictive uncertainty, and decision-oriented risk estimation. This study proposes the Bayesian Attention Temporal Microbial Growth Network (BAT-MG Net) to forecast microbial concentration and estimate early spoilage risk. The model is implemented using Python with GPU-accelerated deep-learning tools, using ComBase microbial growth time-series data. Missing values are handled using training-derived imputation, features are Min-Max normalized, and group-stratified 80:20 partitioning prevents experimental leakage. A 6-h temporal window and a 6-h-ahead forecasting horizon are used with LSTM and attention mechanisms, while Monte Carlo Dropout quantifies predictive uncertainty. The resulting D-PSRI combines microbial concentration and uncertainty to classify risk as low, moderate, or high. BAT-MG Net achieved 97.8% accuracy, 0.198 RMSE, 0.154 MAE, and 0.97 R2, with 94.6% PICP and 0.021 calibration error. These results indicate effective microbial concentration forecasting and uncertainty-aware spoilage-risk estimation within the evaluated ComBase analytical subset. Previously reported studies are included as contextual references because differences in datasets, prediction endpoints, experimental conditions, and modeling tasks prevent direct head-to-head comparisons of performance.
Related
- HOW ARE INVISIBLE RELIGIOUS LONGINGS AND HOPES TRIGGERED BY SOCIAL MEDIA AND ARTIFICIAL INTELLIGENCE?
- Mapping the prediction-invisible fraction of an engineered immunopeptidome: a pilot analysis of immunoproteasome-reprogrammed mesenchymal stromal cells
- Neural representation of the subjective uncertainty of prediction in the human brain
- Representation-aware conformal prediction for reliable uncertainty quantification in drug-target affinity
- Quantifying Uncertainty in Brain Age Predictions via Conformal Prediction
BibTeX
@article{alsmarah2026proactive,
title = {{Proactive early invisible spoilage-risk prediction through uncertainty-quantified temporal microbial growth intelligence}},
author = {Mansi Alsmarah and D. David Neels Ponkumar and Refga Abdallah Eltieb Elebeed and Fuad S. Al-Duais},
journal = {Frontiers in Sustainable Food Systems},
year = {2026},
month = nov,
doi = {10.3389/fsufs.2026.1957987},
url = {https://doi.org/10.3389/fsufs.2026.1957987},
note = {CC BY},
}
RIS
TY - JOUR
TI - Proactive early invisible spoilage-risk prediction through uncertainty-quantified temporal microbial growth intelligence
AU - Mansi Alsmarah
AU - D. David Neels Ponkumar
AU - Refga Abdallah Eltieb Elebeed
AU - Fuad S. Al-Duais
PY - 2026
DA - 2026/11/04
JO - Frontiers in Sustainable Food Systems
DO - 10.3389/fsufs.2026.1957987
UR - https://doi.org/10.3389/fsufs.2026.1957987
AB - The study addresses the need for proactive food safety monitoring because microbial growth can increase before visible spoilage becomes apparent. Existing microbial prediction methods mainly provide deterministic forecasts and often lack temporal interpretability, predictive uncertainty, and decision-oriented risk estimation. This study proposes the Bayesian Attention Temporal Microbial Growth Network (BAT-MG Net) to forecast microbial concentration and estimate early spoilage risk. The model is implemented using Python with GPU-accelerated deep-learning tools, using ComBase microbial growth time-series data. Missing values are handled using training-derived imputation, features are Min-Max normalized, and group-stratified 80:20 partitioning prevents experimental leakage. A 6-h temporal window and a 6-h-ahead forecasting horizon are used with LSTM and attention mechanisms, while Monte Carlo Dropout quantifies predictive uncertainty. The resulting D-PSRI combines microbial concentration and uncertainty to classify risk as low, moderate, or high. BAT-MG Net achieved 97.8% accuracy, 0.198 RMSE, 0.154 MAE, and 0.97 R2, with 94.6% PICP and 0.021 calibration error. These results indicate effective microbial concentration forecasting and uncertainty-aware spoilage-risk estimation within the evaluated ComBase analytical subset. Previously reported studies are included as contextual references because differences in datasets, prediction endpoints, experimental conditions, and modeling tasks prevent direct head-to-head comparisons of performance.
SN - 2571-581X
ER -