Skip to Content
AgriEngineeringAgriEngineering
  • Article
  • Open Access

20 November 2026

37 Pages

Bi-PINN: Encouraging Biological Monotonicity in Multi-Task Tomato Ripeness Classification and Horizon-Based Progression Forecasting

and
1
Department of Information Science and Engineering, B.M.S. College of Engineering, Bull Temple Road, P.O. Box 1908, Bengaluru 560019, Karnataka, India
2
Visvesvaraya Technological University, Jnana Sangama, Belagavi 590018, Karnataka, India
3
Department of Machine Learning (AI and ML), B.M.S. College of Engineering, Bull Temple Road, P.O. Box 1908, Bengaluru 560019, Karnataka, India
*
Author to whom correspondence should be addressed.
AgriEngineering2026, 8(11), 504;https://doi.org/10.3390/agriengineering8110504 
(registering DOI)

Abstract

Tomato ripening is an irreversible, non-linear biological process that is difficult to track. Conventional ripeness classifiers are static and single-observation, failing to capture time-dependent progression and limiting data-driven post-harvest decision-making. This study presents a dual-head physics-inspired neural network (Bi-PINN) built on a ResNet50 backbone that classifies tomatoes into eight ripeness stages and forecasts four temporal horizons (red, peak ripeness, overripe, and senescence), representing the expected, class-conditioned progression interval for each stage. The main novelty of Bi-PINN is the combination, within a single network, of joint stage classification and multi-horizon regression through a shared backbone (multi-task learning), with a monotonicity penalty that keeps the four predicted horizons in biological order. The violations are quantified by a physical violation rate (PVR). Under 5-fold tomato-wise GroupKFold cross-validation, Bi-PINN achieved 71.06 ± 6.29% accuracy, MAE = 0.672 ± 0.197 days, R2 = 0.927 ± 0.038 and PVR = 0.55 ± 0.61%. Its accuracy was statistically indistinguishable from that of the strongest baseline, ResNet18 (71.31 ± 6.67%), and its main advantage was a lower PVR than the baselines (1.76–3.82%). This proof of concept provides the predictive component that a future post-harvest digital twin could build on; broader deployment requires larger, multi-cultivar datasets.

Article Metrics

Citations

Article Access Statistics

Article metric data becomes available approximately 24 hours after publication online.