An Uncertainty-Aware Hybrid Mathematical-Machine-Learning Model for Smart Irrigation Decision Support
Abstract
Agriculture accounts for roughly 70% of global freshwater withdrawals, yet irrigation is still commonly scheduled reactively, with no forecast of where soil moisture is heading and no statement of confidence in that forecast. Data-driven models are accurate but opaque and point-valued; water-balance models are transparent but carry large structural error. Neither alone supports a defensible irrigation decision under uncertainty. This study coupled the two and carried uncertainty through to the decision: a four-parameter water-balance core, calibrated on training data only, was corrected by a Random Forest that learned nothing but the physical residual, conformal prediction attached 90%-nominal intervals, and a risk-aware rule converted the interval lower bound into an irrigation trigger. It was evaluated on three years of hourly in-situ measurements from a rainfed Mediterranean cropland station under a strict chronological split, scored against persistence, from one hour to one week. At the 24 h horizon the hybrid reached RMSE 0.00925 m^3 m^-3 and +9.4% skill, roughly double the best of nine baselines, of which only the Random Forest beat persistence. Skill did not grow with lead time: it peaked at +27.4% at three hours and fell to +1.2% at one week. Conformalised quantile regression was better calibrated and 11% sharper than constant-width conformal prediction. The risk-aware rule raised management-threshold crossings detected in advance from 0.905 to 1.000, at a precision cost of 0.975 to 0.950 and 3.7% more notional water, and beyond 72 h the point forecast fell below the no-forecast rule while the interval-based rule did not. Uncertainty quantification therefore governs the lead time over which forecast-driven irrigation advice remains trustworthy, and here transparency in the physical layer cost no measurable accuracy.
Related
- Integrating Machine Learning and Uncertainty Quantification for Real-Time Decision-Making in Digital Twins: A System-Centric Review and Perspective
- Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications
- The Role of Uncertainty in Assessing the Fairness of Machine Learning Models
- Constructive Probability, Foundations and Numerical Analysis for mathematical finance and machine learning
- Machine learning-based thermoelectric materials screening with physical consistency and uncertainty propagation
BibTeX
@misc{scariolo2026uncertaintyaware,
title = {{An Uncertainty-Aware Hybrid Mathematical-Machine-Learning Model for Smart Irrigation Decision Support}},
author = {Andrea Scariolo},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.13864},
eprint = {2609.13864},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.13864},
}
RIS
TY - UNPB
TI - An Uncertainty-Aware Hybrid Mathematical-Machine-Learning Model for Smart Irrigation Decision Support
AU - Andrea Scariolo
PY - 2026
DA - 2026/09/12
PB - arXiv
DO - 10.48550/arxiv.2609.13864
UR - https://arxiv.org/abs/2609.13864
AB - Agriculture accounts for roughly 70% of global freshwater withdrawals, yet irrigation is still commonly scheduled reactively, with no forecast of where soil moisture is heading and no statement of confidence in that forecast. Data-driven models are accurate but opaque and point-valued; water-balance models are transparent but carry large structural error. Neither alone supports a defensible irrigation decision under uncertainty. This study coupled the two and carried uncertainty through to the decision: a four-parameter water-balance core, calibrated on training data only, was corrected by a Random Forest that learned nothing but the physical residual, conformal prediction attached 90%-nominal intervals, and a risk-aware rule converted the interval lower bound into an irrigation trigger. It was evaluated on three years of hourly in-situ measurements from a rainfed Mediterranean cropland station under a strict chronological split, scored against persistence, from one hour to one week. At the 24 h horizon the hybrid reached RMSE 0.00925 m^3 m^-3 and +9.4% skill, roughly double the best of nine baselines, of which only the Random Forest beat persistence. Skill did not grow with lead time: it peaked at +27.4% at three hours and fell to +1.2% at one week. Conformalised quantile regression was better calibrated and 11% sharper than constant-width conformal prediction. The risk-aware rule raised management-threshold crossings detected in advance from 0.905 to 1.000, at a precision cost of 0.975 to 0.950 and 3.7% more notional water, and beyond 72 h the point forecast fell below the no-forecast rule while the interval-based rule did not. Uncertainty quantification therefore governs the lead time over which forecast-driven irrigation advice remains trustworthy, and here transparency in the physical layer cost no measurable accuracy.
ER -